In the post-layout simulation for large-scale integrated circuits, Transient Analysis (TA), determining the time-domain response over a specified time interval, is essential and time-consuming. Especially, a mass of backward steppings and low simulation efficiency occur without proper settings of Newton-Raphson (NR) initial solution and accurate Local Truncation Error (LTE) estimation. In this work, a novel multi-step irregular sequence prediction model (MISP-Net) is proposed to predict multiple NR initial solutions and precise LTE estimations by just one inference step. This model is constructed by an Irregular Multiple Timesteps Prediction Module (IMTP) and a Irregular Multi-step Solution Prediction Module (IMSP). In IMSP, to improve the irregular prediction performance, a Dual-branch Irregular Feature Pyramid (DIFP) equipped with lightweight Multi-Channel Irregular Time Attention (MITA) are designed. We assess the proposed MISP-Net in the real large-scale industrial circuits on a commercial SPICE simulator. Compared with the commercial SPICE and the SOTA ISPT-Net model, significant backward stepping reductions are achieved: up to 78.57% for NR nonconvergence case and 76.62% for LTE overlimit case, respectively. And the prediction time for NR initial solution in our model is remarkably reduced by up to 5.58× compared to the SOTA ISPT-Net model.

DC analysis holds critical importance in nonlinear circuit simulation, providing the essential precondition for transient and AC analyses. While Pseudo-Transient Analysis (PTA) and its variants excel in DC analysis, selecting the optimal PTA method for specific circuits remains challenging. To address this, we propose GE-LLM, a novel framework for optimal PTA method selection, which integrates Graph Neural Networks (GNNs) with Large Language Models (LLMs). The framework first converts circuit netlists into graph representations and employs a GNN-based graph encoder to capture essential circuit topologies. Subsequently, a novel text-graph alignment strategy bridges circuit topologies and textual descriptions, enabling the LLM to effectively comprehend multimodal information. Finally, we introduce a multi-perspective few-shot prompt that mitigates data scarcity by enabling effective in-context learning from limited circuit examples. Experimental results demonstrate that GE-LLM achieves a high selection accuracy of 0.9714 and improves the efficiency of DC analysis, yielding an average speedup of 2.89× in PTA steps (up to 12.14×) and 3.45× in Newton-Raphson iterations (up to 30.39×) compared to a commercial SPICE-like simulator.

Visual navigation is a fundamental capability for autonomous home-assistance robots, enabling the execution of long-horizon tasks such as object search. While recent methods have leveraged Large Language Models (LLMs) to incorporate commonsense reasoning and improve exploration efficiency, their planning processes remain constrained by textual representations, which cannot adequately capture spatial occupancy or scene geometry-critical factors for informed navigation decisions. In this work, we explore whether Vision-Language Models (VLMs) can achieve mapless visual navigation using only onboard RGB/RGB-D streams, unlocking their potential for spatial perception and planning. We achieve this by developing the imagination-powered navigation framework ImagineNav++, which imagines the future observation images at valuable robot views and translates the complex navigation planning process into a rather simple best-view image selection problem for VLMs. Specifically, we first introduce a future-view imagination module, which distills human navigation preferences to generate semantically meaningful candidate viewpoints with high exploration potential. These imagined future views then serve as visual prompts for the VLM to identify the most informative viewpoint. To maintain spatial consistency, we develop a selective foveation memory mechanism, which hierarchically integrates keyframe observations through a sparse-to-dense framework, thereby constructing a compact yet comprehensive memory for long-term spatial reasoning. This integrated approach effectively transforms the challenging goal-oriented navigation problem into a series of tractable point-goal navigation tasks. Extensive experiments on open-vocabulary object and instance navigation benchmarks demonstrate that our ImagineNav++ achieves SOTA performance in mapless setting, even surpassing most cumbersome map-based methods, revealing the importance of scene imagination and scene memory in VLM-based spatial reasoning.

Despite the recent advancements in artificial intelligence (AI) technologies showing great potential in improving transport efficiency and safety, autonomous vehicles (AVs) still face great challenges when driving in time-varying traffic flow, especially in dense and interactive situations. Meanwhile, humans have free will and usually do not make the same decisions even situated in exactly the same scenarios, leading to data-driven methods suffering from poor migratability and high search cost problems, decreasing the efficiency and effectiveness of the behavior policy. In this article, we propose a safety-first human-like decision-making (SF-HLDM) framework for AVs to drive safely, comfortably, and with social compatibility and efficiency. The framework integrates a hierarchical progressive architecture, which combines a spatial–temporal attention (STA) mechanism for other road users’ intention inference, a social compliance estimation (SCE) module for behavior regulation, and a deep evolutionary reinforcement learning (DERL) model for expanding the search space efficiently and effectively to make avoidance of falling into the local optimal trap and reduce the risk of overfitting, thus make human-like decisions with interpretability and flexibility. The SF-HLDM framework enables autonomous driving AI agents to dynamically adjust decision parameters to maintain safety margins while adhering to contextually appropriate driving behaviors at the same time. Extensive experiments in car learning to act, an open-source autonomous-driving simulator (CARLA) validate the framework’s superior performance, which enlarges the minimum time to worst-case hazards (TWHs) by 41.8% to keep a safer distance away from others, while improving the average velocity by 2.5%, reducing the average acceleration and yaw rate by 23.5% and 60.5%, respectively. The results highlight the potential of SF-HLDM to bridge the gap between machine-driven precision and human-like flexibility in AV systems, paving the way for more interpretable and socially acceptable autonomous driving solutions.

Object counting is the core of perception components in the industry system. Nevertheless, real-world occlusion and dense clustering pose significant challenges to fruit harvesting. Existing methods closely rely on physics-agnostic 2D clustering with rigid thresholds, neglecting critical 3D geometric cues in complex scenes. Thus, they suffer from the multi-view double-counting issue. In this paper, we propose a 3D object counting framework that integrates semantic Neural Radiance Fields (NeRF) with a physics-guided adaptive clustering algorithm. In particular, we employ a semantic NeRF to achieve implicit 3D scene reconstruction, which effectively isolates target objects from the background. Based on the semantic NeRF, we introduce a physics-guided adaptive clustering algorithm that exploits physically interpretable features, including surface normals and elevation gradients, for accurate unsupervised point cloud segmentation. Subsequently, an energy function optimization mechanism is utilized to autonomously aggregate multi-dimensional features for dynamically adjusting clustering thresholds, which enables the 3D counting to adapt to diverse fruit morphologies without manual parameter tuning. Extensive experiments on both synthetic and real-world datasets demonstrate the superiority of the proposed framework, which improves counting accuracy by an average of 9.0 percentage points (6.9 pp on synthetic, 7.2 pp on real-world, and 12.9 pp on Fuji) over the state-of-the-art 3-D baseline.

This paper presents a novel dual event-driven hierarchical control architecture to achieve fully distributed practical prescribed-time consensus (Pd-TC) tracking for uncertain multi-agent systems (MASs). Firstly, a distributed estimate layer is established to reconstruct the leader’s states, guaranteeing practical prescribed-time convergence of estimation errors independent of global information. The proposed communication-triggered event-triggered mechanism (ETM) eliminates continuous communication among neighboring followers, effectively reducing communication resource consumption. Then, utilizing the estimated information, a local control layer is designed to realize practical Pd-TC tracking for uncertain MASs, where the control-update ETM reduces unnecessary control updates to conserve limited control resources, and adaptive gains eliminate the dependence on the bounds of disturbances and uncertain inherent parameters. Furthermore, a rigorous analysis confirms the exclusion of Zeno behavior in both communication-triggered and control-update ETMs. Finally, the proposed control architecture is applied to multiple ground vehicles, validating the theoretical findings.

This article proposes an interpretable deep reinforcement learning (DRL) method for energy management of low-carbon community energy systems (LCCES), which effectively addresses the transparency limitations caused by the black-box nature of traditional DRL neural network structures, thereby overcoming a key constraint in energy system applications. First, we develop a hybrid integer dynamic decision DRL algorithm to solve the low-carbon scheduling problem in community energy systems with continuous-discrete hybrid action spaces. Second, we construct an interpretable artificial intelligence framework, where the temporal attention mechanism is used to process and extract features to provide macro-level decision contribution analysis. These features are input into the decision tree for extracting device-level rules. Building upon this, we design an ensemble decision tree architecture with temporal attention mechanism to effectively identify critical time periods influenced by system inertia and energy fluctuations, thereby achieving interpretable optimization strategies while enhancing decision robustness under state fluctuations. Simulation results based on the independent test set demonstrate that, in comparison with alternative methods, the proposed approach yields a 22.1% cost reduction and a 32.4% carbon emission reduction rate relative to twin delayed deep deterministic policy gradient (TD3), and a 14.7% improvement in explanation accuracy compared with static decision trees.

Predicting human future trajectories is crucial for various intelligent systems and applications. Previous approaches typically adopt a direct prediction strategy, which decodes trajectory features directly into future coordinates. However, they overlook different hierarchical high-order velocities, which have stronger representational abilities in dynamics. In this paper, we introduce HDDNet, a novel trajectory prediction framework that follows dynamical principles and employs a hierarchical dynamics decomposition strategy. Specifically, HDDNet models future trajectories by progressively transferring trajectory coordinates into velocity, acceleration, and jerk, up to the highest-order velocity, which sequentially represent a broader receptive field and a more compact representation of motion dynamics. Furthermore, we design a hierarchical dynamics decomposition decoder with a corresponding dynamics loss, which predicts future trajectories by sequentially refining human motions from the highest-order velocity down to the final coordinates. Compared to the traditional direct prediction strategy, our approach makes better use of dynamic information at different levels. Extensive experiments and ablation studies on the ETH-UCY, SDD and GigaTraj datasets demonstrate that our method outperforms existing state-of-the-art approaches.

This article is concerned with the asynchronous $H_{\infty }$ control design based on model-free policy iteration (PI) algorithm for a class of discrete-time hidden Markov jump system, where a hidden Markov model is developed to characterize the asynchronous phenomenon between the controller modes and the system modes. A pair of zero-sum asynchronous control and disturbance strategies are constructed to achieve a tradeoff between value function and control performance. The presented approach shows two pivotal aspects: 1) the asynchronous PI algorithm is not dependent on strict temporal alignment between the controller and the system's dynamics, enhancing flexibility of the control scheme and 2) it relies on the collected data to solve the algebraic Reccati equation iteratively, which avoids the need for system-internal and transfer probability information, and circumvents the interference of coupled terms. Subsequently, it is verified that the designed PI algorithm monotonically converges to an optimal solution and the system based on this optimal solution is stochastically stable in the mean-square sense. Finally, the effectiveness of this approach is validated by conducting a simulation experiment on a DC motor device system.

In this article, the problem of practical prescribed-time (PT) cooperative path following (CPF) is investigated for underactuated autonomous surface vehicles (ASVs), which are not equipped with velocity sensors and subject to unmodeled dynamics and actuator saturation. First, a practical PT velocity observer (PTVO) is designed to estimate unmeasurable velocity information, which is then employed in the design of the guidance law and controller. At the kinematic level, a cooperative guidance law based on aperiodic intermittent communication is developed for synchronized path following, effectively saving communication resources. At the dynamic level, an aperiodic intermittent controller incorporating neural networks (NNs) is designed to approximate unmodeled dynamics and effectively avoid continuous operation of actuators with input saturation. Meanwhile, the intermittent adaptive law is constructed to estimate the optimal weights of the NNs, thereby reducing their complexity. The closed-loop system is verified to converge to a residual set within a PT interval. Finally, we conduct numerical simulations to demonstrate the effectiveness of the proposed algorithms.

With growing renewable integration, optimizing bidding strategies is critical for efficient capacity allocation and generator revenue. However, using real operational data poses significant privacy risks. Thus, this article proposes a novel electricity market bidding strategy optimization framework based on reward learning and enhanced by conditional tabular generative adversarial networks (CTGAN). Initially, a CTGAN is employed to synthesize market data, effectively implementing data augmentation and mitigating privacy leakage risks. Subsequently, a reward learning algorithm grounded in the maximum entropy principle is developed to infer the implicit reward functions. Finally, leveraging the identified reward functions, a deep$Q$-network algorithm generates enhanced bidding strategies. Experimental results indicate that the CTGAN method more accurately replicates real-data distributions than conventional methods. In bidding simulations, the strategy derived from the identified reward function demonstrates enhanced flexibility and strategic behavior compared to predefined reward approaches, ultimately increasing generator profits and improving market efficiency.

This article presents an accelerated distributed optimization algorithm for online optimization problems over large-scale networks. The proposed algorithm's iteration only relies on local computation and communication. To effectively adapt to dynamic changes and achieve a fast convergence rate while maintaining good convergence performance, we design a new algorithm called NGTAdam. This algorithm combines the Nesterov acceleration technique with an adaptive moment estimation method. The convergence of NGTAdam is evaluated by evaluating its dynamic regret through the use of linear system inequality. For online convex optimization problems, we provide an upper bound on the dynamic regret of NGTAdam, which depends on the initial conditions and the time-varying nature of the optimization problem. Moreover, we show that if the time-varying part of this upper bound is sublinear with time, the dynamic regret is also sublinear. Through a variety of numerical experiments, we demonstrate that NGTAdam outperforms state-of-the-art distributed online optimization algorithms.

Event cameras with high dynamic range and temporal resolution, which are bio-inspired vision sensors, have shown great potential in event-based tracking tasks, particularly in scenarios involving rapid motion and low levels of illumination. Nonetheless, the efficient extraction of sparse information from event camera remains a persistent challenge. Meanwhile, the event camera works asynchronously, generating a continuous stream of events, rendering it highly compatible with Spiking Neural Networks (SNNs) due to their event-driven nature and low power consumption. Motivated by the issues mentioned above, we propose an Efficient Hybrid Cascade Tracker ( EHCT ) with SNN for object tracking in the event domain. We combine the transformer, convolutional network, and SNN structure skillfully to form the basic Hybrid CNN-SNN-Transformer (HCST) block structure, which is also the central component part of our EHCT network. The HCST block is primarily utilized to process the incoming event data and extract information from both local and global contexts. After several cascade HCST blocks, these two types of information will be efficiently integrated with the preprocessed raw data, which are then fed into the Classifier and Regressor head to produce the bounding box (bbox) of the tracked target. Extensive experiments on various event and RGB frame-based datasets demonstrated that our proposed EHCT algorithm outperforms most of the existing state-of-the-art trackers by a significant margin and also achieves a great advantage in terms of energy consumption. Our source code will be available at https://github.com/masac11/EHCT .

This article focuses on the vibration issue of flexible two-link manipulators (FTLMs) with input saturation. An efficient system model is represented by a set of ordinary differential equations (ODEs) based on the assumed mode method (AMM). Subsequently, a reinforcement learning (RL)-based adaptive vibration control strategy, which is a model-free control approach, is proposed by employing the actor–critic algorithm structure. Additionally, an auxiliary system is constructed to tackle the influence of input saturation, ensuring trajectory tracking while achieving vibration suppression. Furthermore, the stability of the closed-loop system under RL control is examined using the Lyapunov direct method, which demonstrates the semi-global uniform ultimate boundedness (SGUUB) of tracking and vibration errors. Finally, to verify the effectiveness and superiority of the proposed RL strategy, the comparative simulations and experimental studies are conducted on the Quanser experimental platform. The experimental results demonstrate that RL control reduces steady-state errors by 40% and 96.6% against PSF control and by 50% and 97.2% against neural network (NN) control, respectively.

Recent learning-based methods for event-based optical flow estimation utilize cost volumes for pixel matching but suffer from redundant computations and limited scalability to higher resolutions for flow refinement. In this work, we take advantage of the complementarity between temporally dense feature differences of adjacent event frames and cost volume and present a lightweight event-based optical flow network (EDCFlow) to achieve high-quality flow estimation at a higher resolution. Specifically, an attention-based multi-scale temporal feature difference layer is developed to capture diverse motion patterns at high resolution in a computation-efficient manner. An adaptive fusion of high-resolution difference motion features and low-resolution correlation motion features is performed to enhance motion representation and model generalization. Notably, EDCFlow can serve as a plug-and-play refinement module for RAFT-like event-based methods to enhance flow details. Extensive experiments demonstrate that EDCFlow achieves better performance with lower complexity compared to existing methods, offering superior generalization. Codes and models will be available at here.

IR drop analysis is crucial for ensuring the reliability and performance of integrated circuits (ICs) but poses computational challenges as the IC designs grow larger, especially for ultra deep-submicron VLSI designs. Deep learnings (DL) as the efficiency-promising solutions, mainly employ various CNN-based networks to achieve image-to-image IR drop predictions. However, they neglect and lose the power delivery network (PDN) global spatial features and cell instance topological information. This paper proposes a novel image-graph heterogeneous fusion framework (IGHF), which integrates the effectiveness and complementarity of dual branches (CNN and GNN) for higher prediction performance. In the CNN-based Power ScaleFusion Unet branch, the proposed long-range and local-detail encoder (LLE) integrates seamlessly with the hierarchical and adjacent compensation group (HACG) module. This design facilitates effective multi-scale global-to-local spatial power feature extraction within the PDN and enables adaptive high-to-low-level feature fusion and compensation in the decoder. Moreover, a cell voltage aware (CVA) module in the GNN branch is designed to adaptively aggregate PDN topological features of heterogeneous neighbors of different orders. Comparative experiments demonstrate that the proposed IGHF achieves significant accuracy improvements, outperforming the state-of-the-art MAUNet and widely-used IREDGe methods by considerable margins of 24.6% and 55.0% reduction in prediction error, while the prediction maps possess higher structural fidelity. Transfer experiments indicate that IGHF with transfer learning can improve the accuracy in real circuits with the few-shot real circuit test cases.

In the post-Moore era, 2.5D chiplet-based ICs present significant challenges in thermal management due to increased power density and thermal hotspots. Neural network-based thermal prediction models can perform real-time predictions for many unseen new designs. However, existing CNN-based and GCN-based methods cannot effectively capture the global thermal features, especially for high-frequency components, hindering pre-diction accuracy enhancement. In this paper, we propose a novel frequency-spatial dual domain aware prediction network (FSA-Heat) for fast and high-accuracy thermal prediction in 2.5D ICs. It integrates high-to-low frequency and spatial domain encoder (FSTE) module with frequency domain cross-scale interaction module (FCIFormer) to achieve high-to-low frequency and global-to-local thermal dissipation feature extraction. Additionally, a frequency-spatial hybrid loss (FSL) is designed to effectively attenuate high-frequency thermal gradient noise and spatial mis-alignments. The experimental results show that the performance enhancements offered by our proposed method are substantial, outperforming the newly-proposed 2.5D method, GCN+PNA, by considerable margins (over 99% RMSE reduction, 4.23X inference time speedup). Moreover, extensive experiments demonstrate that FSA-Heat also exhibits robust generalization capabilities.

ABSTRACT Automated detection of gastric polyps has been proven crucial for improving diagnostic accuracy. However, when there is a domain shift in the data, deep learning‐based detection methods may not perform well. Unsupervised domain adaptation has been demonstrated as a good approach to address this issue. However, existing unsupervised domain adaptation detection methods struggle to handle the problem of foreground–background similarity and the diverse appearances of polyps at different scales in gastric polyp images. In this paper, we propose a boundary‐guided transferable attention module and a transferable prototype alignment module to address the foreground–background similarity issue, and a multi‐scale enhanced alignment method to tackle the problem of information loss when aligning polyps at multiple scales. The boundary‐guided transferable attention module fully explores spatial information of the image with a boundary‐guided multi‐field attention mechanism while considering the transferability of features to mine the easily transferable foreground regions. The transferable prototype alignment module adopts a prototype‐based method to facilitate the transfer of difficult‐to‐align regions. The multi‐scale enhanced alignment method prevents information loss across feature maps and scales with an attention filtering module, enhancing features at each scale. In experiments, this work outperforms advanced domain adaptation detection methods like SIGMA and CAT in polyp detection.

The article focuses on the event-based predetermined performance formation tracking control for uncertain nonlinear multi-agent systems. Each agent is subject to actuator saturation constraint and full-state constraints. To meet the full-state constraints, a barrier function-based nonlinear mapping method is employed instead of the barrier Lyapunov function, such that the undesirable “feasibility conditions” are eradicated. To overcome actuator saturation, the auxiliary systems are utilized to let the controller be designed under the framework of backstepping . The approximation capacity of RBF NNs and adaptive methods are adopted, which can solve unknown uncertainties. An event-triggered predetermined performance formation tracking control strategy is designed, which can guarantee that the agents form the prescribed formation shape in a predetermined settling time and have a fine transient and steady-state tracking performance, while reducing the communication burden from the controller to the actuator. At last, an example of unmanned aerial vehicles is given to test the availability of the results.

Multiagent systems (MASs) can be exploited for malicious activities, which pose significant threats to public safety and national security. While current literature has explored countermeasures for individual or several agents, these approaches are inadequate for large-scale malicious MASs due to the lack of a systematic, global perspective. Additionally, the heterogeneity of MASs, wherein agents exhibit varying system weights, necessitates a strategy that prioritizes agents with high system weight to maximize disruption. To address these challenges, a consensus breakdown algorithm based on critical node identification and network topology decomposition is proposed. The proposed algorithm decomposes the network topology of both large-scale homogeneous and heterogeneous MASs by disabling critical nodes, thereby splitting MASs into multiple smaller agent clusters and preventing MASs from achieving global consensus. In scenarios involving both homogeneous and heterogeneous MASs, this approach transforms the critical node identification problem into a node regression problem. The algorithm leverages GraphSAGE, a highly efficient graph neural network (GNN) with a sampling mechanism, making it well-suited for feature extraction in large-scale networks while addressing potential computational constraints common in real-world applications. Relying on the sampling mechanism, GraphSAGE enhances computational efficiency when processing large-scale network topologies. To better fit the need for consensus breakdown, the information dissemination capabilities of nodes are considered when defining node importance. Furthermore, to extend the algorithm to the scenarios of heterogeneous MASs where agents have different system weights, the node importance is combined with the system weight of each agent to determine the final node criticality. Extensive simulation results validate the superior performance of the proposed algorithm across various aspects. Comparative experiments further demonstrate the accuracy and efficiency of the algorithm.

Pedestrian trajectory prediction plays a crucial and fundamental role in many computer vision tasks. Most existing works utilize recurrent neural networks to extract temporal features from trajectories because their recursive structure is inherently well-suited for time series data. However, previous methods overlook the forgetting characteristics of pedestrians when modeling historical trajectories, which may cause the model to focus on the wrong positions of historical information. In this paper, we propose a simple yet effective Adaptive Forgetting-Controlled Recurrent Neural Network (AFC-RNN) for pedestrian trajectory prediction. The core idea of AFC-RNN is a novel Adaptive Forgetting Controller (AFC), which controls the forgetting degree of the historical information at each time step explicitly and adaptively. Specifically, AFC first learns memory factors for each time step based on the temporal correlation of observed trajectories using the self-attention mechanism. Then, AFC-RNN applies these memory factors to regulate the forgetting degree of observed features at each time step from RNN. Extensive experiments and ablation studies on ETH, UCY, SDD, and NBA datasets demonstrate that our method outperforms existing state-of-the-art approaches. Additionally, we provide a mathematical analysis to demonstrate the superiority of our adaptive forgetting strategy in the AFC-RNN over traditional RNNs for trajectory forgetting modeling.

Privacy issues in remote state estimation for Cyber-Physical System (CPS) against eavesdropping attack pose significant challenges in ensuring both system performance and data security. Existing studies often overlook the challenges posed by the acknowledgment signal's potential risks and the asymptotic convergence properties of stable systems. To address these challenges, this paper proposes a privacy-preserving optimal transmission scheduling method based on a pre-arranged indicator. The method determines whether to transmit real state estimates or artificial noise by solving an optimization problem that balances estimation performance and privacy preservation. The privacy is ensured by keeping the eavesdropper's estimation error covariance higher than the legitimate estimator's. A threshold structure is proved with theoretical derivations. Simulation results are given to support the theoretical analysis.

This letter addresses distributed nonconvex constrained optimization problems, where both the local cost function and the inequality constraint function are nonconvex. Firstly, the global nonlinear equality constraint is added to the global cost function via a penalty-like function method. Then, based on the consensus technique of multiagent systems, the global nonlinear equality constraint is estimated through a distributed nonlinear consensus scheme within a finite time. Secondly, the local inequality constraint is managed with an adaptive penalty factor. Thirdly, the optimal outcome is attained by employing the gradient of the augmented Lagrangian function. The stability analysis is performed using the Lyapunov theory. Lastly, a simulation case on the economic dispatch problem in smart grids is presented to clarify the developed theoretical result.

Focused on the scientific issues of collision avoidance and compliant operation of physical human-robot interaction (pHRI) systems, this paper proposes a reinforcement learning (RL) strategy based on admittance control to achieve compliant collision avoidance and accurate trajectory tracking of pHRI. Firstly, a differentiable reference trajectory is generated using a soft saturation function with an admittance model. Subsequently, a reinforcement learning strategy based on an actor-critic structure is implemented to address dynamic uncertainty and enhance tracking performance and compliance. Different from existing studies, a reinforcement learning admittance controller containing an integral barrier Lyapunov function (IBLF) is constructed to attain accurate tracking while ensuring that the end-effector achieves the position constraints. Lyapunov stability theory is employed to proof that all states of the closed-loop system remain semiglobally uniformly ultimately bounded (SGUUB). Finally, a suite of tests on Baxter robot experimental platform have been conducted to validate the superiority of the proposed algorithm compared with adaptive impedance control and conventional admittance control.

This paper investigates the feasibility of robotic grasping of various objects in complex scenarios, with our method aiming to achieve grasping capabilities for any scene and any object. Firstly, a Target Edge Collision-Avoidance Strategy is proposed that systematically incorporates the edge features of grasping objects. This strategy is specifically designed to address two critical challenges: bridging the significant performance gap between offline training data and real-world operating conditions, and effectively preventing collision incidents between the robotic end-effector and target objects during physical grasping operations. Furthermore, the Grasp Detection Network based on Global and Local Information Perception (GLIP-Net) is proposed, featuring two intricately designed components: the Global Information Perception and Local Aggregation Module, and the Multi-dimensional Multi-scale Attention and Adaptive Feature Fusion Module. The GLIP-Net enhances the network’s perceptiveness to global information, strengthening the correlation between features and the spatial parameters of grasping. To validate the effectiveness of the presented method, extensive tests and grasping experiments is conducted on the Cornell Dataset and Jacquard Dataset, as well as in practical scenarios. The empirical outcomes indicate an accuracy level of 99.2% on the Cornell Dataset and 96.8% on the Jacquard Dataset, respectively. Furthermore, by employing the Kinova robot in both single-object and multi-object complex scenarios within real-world environments, the grasping success rates of 97.0% and 95.8% is achieved. Note to Practitioners—This paper was inspired by the problem of robotic object grasping in various scenarios, but it is also applicable to tasks such as object grasping, sorting, and transportation in unstructured environments. Existing robotic grasping methods are typically limited to structured scenarios, where robots can only grasp objects at fixed positions. When the object or its pose changes, the entire grasping task is likely to fail. Additionally, robots often fail to consider the edge information of the object when grasping, leading to collisions between the end effector and the object. In this paper, we propose a novel approach that employs a graping detection network to process an input color image containing depth information. The neural network takes both global and local information into account, fuses useful feature data, and adaptively outputs a set of grasp configurations. To address the issue of collisions between the end effector and the object, we design a target edge collision-avoidance strategy, prioritizing regions adjacent to the gripper side. Preliminary experiments demonstrate the feasibility of our method, which has been tested in several real-life scenarios. In future research, we aim to address the robot vision closed-loop control problem, enabling robots to perform grasping tasks in dynamic environments.

Due to the limited bandwidth and energy of communication channels among agents in practical applications, the communication-efficient distributed optimization method has emerged as a pressing research topic in recent years. The distributed economic dispatch problem with restricted data communication/finite communication bandwidth is investigated in this study, where the communication among agents can be described as a strongly connected directed network. For this purpose, a robust push-pull distributed optimization algorithm with a dynamic scaling quantization mechanism is developed based on the gradient tracking technique. A novel surplus variable is designed to prevent the accumulation of quantization errors, and then, a heavy-ball momentum is introduced to speed up convergence performance. In addition, a linear convergence rate of the developed approach is deduced for the strongly convex and Lipschitz smooth cost function. Finally, we offer two instances for illustration. Note to Practitioners—This paper proposes a robust quantization-based algorithm for the economic dispatch problem, in which the broadcasting information is quantized before sending to its neighboring generators. Therefore, this method reduces duplicate transmission of agents and improves the use of communication resources. Furthermore, the developed method can be extended to similar constrained optimization problems, such as the resource allocation problem in wireless networks, and the network utility maximization problem in the Internet.

In this article, Nash equilibrium seeking in theN-coalition noncooperative game is studied for the second-order disturbed players. In this formulation, players are divided into different coalitions. Each coalition acts as a virtual player in the noncooperative game, but the real decision-maker is the individual player. Players within the same coalition work together to minimize the cost function of the coalition they belong to, while each coalition competitively minimizes its own cost function. A prescribed-time event-triggeredN-coalition Nash equilibrium seeking strategy is proposed based on the gradient descent method and the dynamic average consensus protocol. The proposed algorithm ensures that the players’ actions converge to the Nash equilibrium of theN-coalition game within a prescribed time, which can be assigned in advance, without any knowledge of the initial states and the system parameters. Additionally, information exchanges between players only happen when the designed event-triggering condition is met, thereby reducing the communication burden. The prescribed-time stability of theN-coalition Nash equilibrium is rigorously proven by Lyapunov stability analysis. The Zeno behavior is shown to be prevented until the Nash equilibrium is reached. Finally, the simulation experiments on maneuvering automated ground vehicles demonstrate the effectiveness of the proposed algorithm.

Object detection and tracking is always a challenging issue in UAV (unmanned aerial vehicle) application. Especially, in the scene of UAV-ASV (autonomous surface vehicle) cooperative system, UAV vision based target tracking performance has been suffering from the target rotation and fast motion. Aiming at optimizing the related UAV vision tracking performance, a SDSST tracker(strong discriminative scale space tracking) with automatic initialization and self-adjusting is developed in this paper. Firstly, in the step of initialization, combining the advantages of both fast optimization of BLS (Broad Learning System) and efficient image processing of CNN (convolutional neural networks), a novel DBLS (Deep Broad Learning System) is posed for the target detection. Meanwhile, a Q-learning based DBLS architecture searching is further introduced. Then, in terms of width/height ratio self-adjusting, this article proposed a novel filter state supervisor that helps to find the abnormal estimated state caused by rotation in target scale estimation. Basically, this so called filter state supervisor could take RSV (Rolling Standard Value) as input feature and give out the filter state. Finally, the abnormal filter state would be adjusted by an appropriate alternative by searching in the proposed rotation angles memory, so that an optimized self-adjusting could be realized. Meanwhile, extensive experiments are performed on data set of USV center in Qiandao Lake, yielding a competitive result compared with five other prevalent trackers. Note to Practitioners—This paper was motivated by the problem of target lost caused by sudden change of target motion in the UAV-ASV vision tracking. Usually, the rotation motion of ASV is a major operation when ASV carries out a maritime assignment. However, the poor tracking state supervision and inflexible scale updating method as well as manual initialization in the existing approaches lead to inappropriate scale and target lost when the target undergoes rotational motion. Therefor, this paper proposes a strong vision tracker (SDSST) to enhance the original DSST in the three aspects: automatic initialization, filter state supervisor, and self-adjusting. This can allow the tracker to initialize without human interference, also bad tracker state can be informed by filter state supervisor. When bad state happens that the target scale in the tracker will be updated flexibly based on proposed rotation angles memory. Finally, The proposed method is implemented on the real filed UAV vision data collected by UAV-ASV system in the Qiandao Lake. The results show that SDSST achieves competitive result compared to 7 other prevalent trackers.

This paper addresses the dynamic task assignment problem for multiple unmanned aerial vehicles (UAVs) operating under weak communication. Existing learning-based methods face two primary challenges: limited scene generalization and excessive reliance on communication resources. To address these issues, this paper proposes an event-triggered reinforcement learning algorithm based on graph neural networks. First, heterogeneous UAVs and tasks are embedded into a graph to construct a relationship model, which clearly represents the complex constraints between UAVs and tasks. This graph structure overcomes the limitations of existing methods in capturing constraint relationships. Second, the incorporation of heterogeneous graph neural networks and adaptive attention mechanisms enables effective learning of changes in adjacent node information, allowing the model to capture complex constraint relationships and environmental dynamics. This approach also addresses the lack of sensitivity to environmental changes observed in existing methods. Lastly, a dynamic synchronization mechanism is employed to update task assignment statuses in real time, preventing task conflicts and ensuring efficient allocation. Experimental results demonstrate that this method strikes a better balance between task assignment quality and efficiency. It performs well in untrained scenarios and significantly reduces communication resource consumption. These results highlight its promising potential for application in weak communication environments.

Multi-task multi-agent reinforcement learning aims to control multiple agents to perform well on multiple tasks. It encounters three core challenges: the varying number of agents and entities, the disparities in cooperative behaviors among different tasks, and the training imbalance caused by varying task difficulty levels. To address these issues, we propose a novel framework named Task-Entity Transformer Qmix (TETQmix), which employs pretrained language models for task encoding, utilizes proposed Task-Entity Transformer to handle observations across various tasks, and adjusts task learning weights to achieve balanced multi-task training. Task-Entity Transformer not only enables handling multi-task scenarios with varying numbers of agents and entities, but also leverages cross-attention modules to integrate observation and task embeddings, so that each agent can obtain individual values and decisions for multiple tasks. We then utilize a transformer-based mixer to monotonically combine the individual values, and train the whole network’s parameters using temporal-difference errors. To facilitate multi-task training, we define task regret as the difference between the current-stage return and the candidate best one, and adjust the learning weight of each task based on its task regret. Experiments are conducted on both simulated multi-particle environments and real-world multi-robot systems. Compared with existing baselines, our method not only is superior in multi-task learning efficiency, but also shows promising transfer ability on unseen tasks. Note to Practitioners—The flexibility of multi-agent systems makes them quite fit to multiple tasks. Compared to designing different decision models for different tasks, it is more convenient if one can use just one decision model to resolve multiple tasks. Besides, it can make the maximum utilization of trajectory data coming from similar tasks when the data are integrated for multi-task decision model training. Natural language provides a powerful tool to describe the task context and emphasize the similarities or differences among different tasks. Pretrained language models can encode the task context, based on which the decision model can adjust its output distribution for different tasks and even synthesize the decisions from existing and similar tasks to achieve promising zero-shot and few-shot transfer performance for unseen tasks. With our proposed TETQmix, practitioners are able to realize multi-task capability in multi-agent systems and increase the generalization in a variety of scenarios.

Decentralized secure control faces significant challenges in handling unknown mismatched interconnections and reducing fault-tolerant delays. To address these issues, this paper proposes a synergetic learning-based decentralized secure tracking control scheme for nonlinear interconnected systems with multiple actuator faults. Replacing actual states with desired ones in the coupled system relaxes the assumption of requiring a known upper bound for interconnections, and a neural network observer is designed to estimate the replaced interconnections. To reduce fault-tolerant delays, the secure tracking control problem is reformulated as an adversarial evolution problem between fault signals and control inputs, eliminating the need for fault compensation. To achieve optimal tracking control, an augmented subsystem is constructed by integrating the dynamics of tracking error and the reference trajectory. A modified cost function is designed for the augmented subsystem, and a critic network with two cooperative updating laws is developed to solve the Hamilton–Jacobi–Isaacs equation, providing a synergetic approximate solution for the control input and fault assistance signal. It is proven that the tracking error converges to a small neighborhood of the equilibrium. Simulation results demonstrate the effectiveness of the proposed approach.

This paper investigates the practical prescribed-time consensus (Pd-TC) for nonlinear multi-agent systems (MASs) in the presence of uncertain disturbance, employing intermittent adaptive dynamic event-triggered and self-triggered controllers, respectively. A novel lemma for achieving the practical prescribed-time stability (Pd-TS) is proposed within the framework of intermittent control (IC), where a single parameter exclusively bounds the settling time. To further reduce the triggered instants, a dynamic variable is introduced to construct the dynamic event-triggered mechanism (D-ETM). Utilizing the proposed lemma, an intermittent adaptive dynamic event-triggered controller is developed by incorporating D-ETM with an intermittent adaptive control scheme, which achieves the practical Pd-TC for uncertain nonlinear MASs. Notably, the developed controller is devoid of global information, such as algebraic connectivity and system scale. Following this, an intermittent adaptive self-triggered controller is designed to eliminate the necessity for continuous monitoring. The results presented above are finally applied to Chua’s system, accompanied by a numerical example to demonstrate the efficacy of the designed controllers.

This article adopts the event-triggered control strategy (E-TCS) to achieve the practical predefined-time synchronization (PPTS) for dynamic complex networks (DCNs) with Markov switching topologies under stochastic denial-of-service (SDoS) attacks. We consider the Markov switching topologies, and the coupling weight of the complex networks between nodes is dynamic. For the proposed E-TCS, the minimum inter-event interval can be directly obtained, thereby eliminating the Zeno phenomenon. By employing the time-varying function, all states of the DCNs can achieve PPTS within the predefined time. Concretely, in contrast to finite/fixed-time synchronization, utilizing PPTS enables the arbitrary setting of convergence time, independent of initial values and controller parameters. Notably, the SDoS attacks occur with a certain probability within the attack intervals. Moreover, the intermittent attacks and the average non-attack rate are considered, and this approach leads to less conservative results. Additionally, we prove that a higher average non-attack rate makes it easier for all states of the DCNs to achieve PPTS. Finally, the validity of the proposed E-TCS is verified by the examples of Chua’s circuit and the Kuramoto oscillator network.

Pedestrian trajectory prediction is a crucial component in computer vision and robotics, but remains challenging due to the domain shift problem. Previous studies have tried to tackle this problem by leveraging a portion of trajectory data from the target domain to fine-tune the model. However, such domain adaptation methods are impractical in real-world scenarios, as it is infeasible to collect trajectory data from all potential target domains. In this paper, we study a new task named generalized pedestrian trajectory prediction, with the aim of generalizing the model to unseen domains without accessing their trajectories. To tackle this task, we further introduce a Recurrent Aligned Network (RAN) to minimize the domain gap through domain alignment. Specifically, we devise a recurrent alignment module to effectively align the trajectory feature spaces at both time-state and time-sequence levels by the recurrent alignment strategy. Furthermore, we introduce a pre-aligned representation module to combine social interactions with the recurrent alignment strategy, which aims to consider social interactions during the alignment process instead of just target trajectories. We extensively evaluate our method and compare it with state-of-the-art methods on three widely used benchmarks. The experimental results demonstrate the superior generalization capability of our method. Our work not only fills the gap in the generalization setting for practical pedestrian trajectory prediction, but also sets strong baselines in this field.

This article develops a cooperative-critic learning-based secure tracking control (CLSTC) method for unknown nonlinear systems in the presence of multisensor faults. By introducing a low-pass filter, the sensor faults are transformed into "pseudo" actuator faults, and an augmented system that integrates the system state and the filter output is constructed. To reduce design costs, a joint neural network Luenberger observer (NNLO) structure is established by using neural network and input/output data of the system to identify unknown system dynamics and sensor faults online. To achieve the optimal secure tracking control, an augmented tracking system is formed by integrating the dynamics of tracking error, reference trajectory, and filter output. Then, a novel cost function is designed for the augmented tracking system, which employs the fault estimation and the discount factor. The Hamilton-Jacobi-Bellman equation is solved to obtain the CLSTC strategy through an adaptive critic structure with cooperative tuning laws. Besides, the Lyapunov stability theorem is utilized to prove that all signals of the closed-loop system converge to a small neighborhood of the equilibrium point. Simulation results demonstrate that the proposed control method has good fault tolerance performance and is suitable for solving secure control problems of nonlinear systems with various sensor faults.

Trajectory tracking in bimanual humanoid robots, whose closed-chain kinematic structures inherently amplify the effects of modeling errors, external disturbances, and time-varying parameters, is a challenging task. To address this, we reformulate the dual-arm tracking task as a servo constraint-following problem and derive the system dynamics under approximate constraints using the Udwadia-Kalaba method. The humanoid system is modeled as a constrained mechanical structure subjected to fast-varying, bounded uncertainties with unknown limits. On this basis, we propose a robust control framework that guarantees both uniform boundedness (UB) and uniform ultimate boundedness (UUB) of the tracking error, ensuring stability and performance even under severe parametric and dynamic uncertainties. To reconcile the trade-off between transient dynamics and steady-state accuracy—essential for service-oriented tasks such as door opening or coffee pouring—we integrate a Nash equilibrium-based optimization mechanism into the controller design. By formulating a two-player non-cooperative game over the controller's key tuning parameters, we analytically derive the existence, uniqueness, and closed-form solutions of the game, achieving an optimal balance between competing objectives. Comprehensive simulations on a reduced-order bimanual humanoid model validate the proposed approach, demonstrating superior tracking accuracy, disturbance rejection, and energy efficiency compared to benchmark methods. The proposed strategy offers a theoretically grounded and practically implementable solution for robust, constraint-compliant humanoid manipulation.

In this paper, a distributed T-S fuzzy security control strategy based on memory events is proposed for a class of multi-input-multi-output (MIMO) cyber-physical systems (CPSs) that subjected to replay attacks. This strategy can also address common uncertainties in practical systems, including communication latency, unmodeled dynamics, and external unknown disturbances. It is worth noting that the replay attack model in the paper is highly generalized. And the attack location, target, and frequency are all uncertain. Therefore, a suitable distributed memory event-based strategy (DMEBS) is designed. It can dynamically adjust the usage of historical data to optimize the release of sampled data, thereby determining when to update the control laws of each subsystem, ensuring system performance while greatly saving communication resources. In addition, the stability of the system is demonstrated by establishing a suitable Lyapunov-Krasovskii (L-K) functional, ensuring the elimination of the Zeno phenomenon. Finally, the effectiveness of the proposed method is validated through simulations conducted on two commonly encountered practical systems.

A physics-data-driven economic model predictive control (EMPC) is proposed in this article for effective energy harvesting in wave energy converters (WECs). By combining artificial intelligence techniques, this article develops a new method that applies a data-driven model upon physical WEC models to address the challenges associated with the nonlinearity and uncertainty in WEC physical models. By collecting the error data between the actual system and the physical model, a deep Koopman operator is applied to transform the nonlinear and uncertain parts of the actual system into a linear model, which is then embedded into the physical model to establish a physical-data-driven model. By iteratively optimizing the physical data-driven model, EMPC generates the optimal control sequence for the WEC. Theoretical analysis is conducted to prove that the physical-data-driven EMPC algorithm ensures that the Lyapunov function converges to the neighborhood of the optimal steady state. Simulation results show that the proposed physical-data-driven model achieves faster convergence and higher accuracy during training compared to data-driven models. This improves the system’s control and optimization performance under EMPC, demonstrating the effectiveness of the proposed algorithm.

This article develops a new observer-based practical predefined-time distributed Nash equilibrium seeking (DNES) algorithm for a network of players in noncooperative games under aperiodically intermittent control (AIC). The proposed intermittent controller is designed in an aperiodic manner, offering a broader applicability compared with the existing periodically intermittent controllers. Considering the players with uncertain disturbances, a disturbance observer is established, which facilitates the development of the practical predefined-time DNES algorithm. The proposed predefined-time control algorithm can ensure the convergence of the players’ actions within an adjustable neighborhood around the Nash equilibrium in a prespecified time, regardless of the initial states and control parameters. Moreover, the dynamic event-triggered communication scheme is employed, allowing players to exchange information only when the triggering condition is satisfied, thereby reducing the communication burden. In addition, the Zeno behavior is excluded. Finally, a simulation example of connected automated ground vehicles is provided to demonstrate the theoretical results.

Due to certain technical limitations of autonomous underwater vehicle (AUV), they cannot completely perform complex tasks independently. When performing complex tasks, coordination between the remote operated vehicle (ROV) and AUV is required. Therefore, collision avoidance is a key technology to ensure vehicle safety. During collision avoidance, AUV need to understand human intentions, make decisions, and perform the corresponding actions. To solve the problems of human intention uncertainty and random noise interference, an AUV collision avoidance strategy based on a dynamic Bayesian network and stochastic model predictive control (SMPC) is proposed in this paper. First, a dynamic Bayesian network is used to assess the probability of AUV collisions in the system. Then, using the properties of Gaussian distribution and related theorems, the objective function is simplified and transformed into a deterministic model predictive control problem. Finally, the intention-exploration item is added to the objective function to better understand human intention. Through the simulations and experiments in specific scenarios, it is verified that the proposed collision avoidance control strategy can safely and effectively control a hybrid system with the coexistence of ROV and AUV.

In the field of robot grasping detection, due to uncertain factors such as different shapes, distinct colors, diverse materials, and various poses, robot grasping has become very challenging. This article introduces a integrated robotic system designed to address the challenge of grasping numerous unknown objects within a scene from a set of $\alpha $ -channel images. We propose a lightweight and object-independent pixel-level generative adaptive residual depthwise separable convolutional neural network (GARDSCN) with an inference speed of around 28 ms, which can be applied to real-time grasping detection. It can effectively deal with the grasping detection of unknown objects with different shapes and poses in various scenes and overcome the limitations of current robot grasping technology. The proposed network achieves 98.88% grasp detection accuracy on the Cornell dataset and 95.23% on the Jacquard dataset. To further verify the validity, the grasping experiment is conducted on a physical robot Kinova Gen2, and the grasp success rate is 96.67% in the single-object scene and 94.10% in the multiobject cluttered scene.

To develop a safe and efficient navigation system of robotic vehicles in dynamic scenes, a new collision-avoidance method using deep reinforcement learning (DRL) is presented. First, a novel method of DRL based on multithreaded asynchronous proximal policy optimization (MAPPO) is developed. It can convert expensive online calculation into an offline training process, improving the sample efficiency during policy learning. Then, a multisensor fusion measurement (MSFM) method is presented by the combination of global reference path (GRP), laser scanner measurement (LSM), and motion energy (ME), to observe the state space of environment to maximum extent. By multireward refining at each timestep, the sparsity of rewards is avoided. On this basis, a collision-avoidance neural network (CANN) fused in multiscale and multilevel is devised to generate high-quality obstacle features, which can enable the MAPPO to master collision threat effectively. Besides, a premature collision prediction (PCP) module supervised by GRP is devised as an auxiliary task to learn high-level feature representation to further improve the safety during robot collision avoidance. Finally, a two-stage training strategy from 2-D Stage to 3-D Gazebo is presented to realize sufficient robot-environment interaction. This way, the policy model can maximize its degree of exploration in complex dynamic scenarios. Extensive navigation experiments are conducted on the complex simulation and real-world scenarios with a variety of obstacles, along with multiple comparative experiments to testify the effectiveness and robustness of our approach in robot collision avoidance. Experiment results reveal that our method can make farsighted navigation decisions in complex dynamic environments to dodge collisions successfully while moving toward the goal.

With the gradual application of reinforcement learning (RL), safety has emerged as a paramount concern. This article presents a novel data-model hybrid-driven safe RL (SRL) scheme to address the challenge of avoidance control in the operation domain containing multiple moving unsafe zones. First, the avoidance problem is transformed into the optimal control problem of an augmented system by encoding a barrier function (BF) term into the cost function. Then, using the idea of integral RL (IRL), an adaptive learning algorithm is proposed for generating safe control policies, in which the actor-critic neural network (NN) structure is established with the aid of state-following (StaF) kernel function. The policy iteration process is executed by this structure; specifically, the critic network undergoes gradient-descent adaptation, while the actor network employs gradient projection updating. Particularly, via a state extrapolation technique, both real-time experience and simulated experience are utilized in the learning process. Next, closed-loop stability and weight convergence are theoretically substantiated. Finally, the effectiveness of the proposed scheme is demonstrated on a single integrator system, a nonlinear numerical system, and a unicycle kinematic system; besides, its advantages over the existing control methods are illustrated by comparisons.

Vision-and-language navigation requires an agent to navigate in a photo-realistic environment by following natural language instructions. Mainstream methods employ imitation learning (IL) to let the agent imitate the behavior of the teacher. The trained model will overfit the teacher's biased behavior, resulting in poor model generalization. Recently, researchers have sought to combine IL and reinforcement learning (RL) to overcome overfitting and enhance model generalization. However, these methods still face the problem of expensive trajectory annotation. We propose a hierarchical RL-based method-discovering intrinsic subgoals via hierarchical (DISH) RL-which overcomes the generalization limitations of current methods and gets rid of expensive label annotations. First, the high-level agent (manager) decomposes the complex navigation problem into simple intrinsic subgoals. Then, the low-level agent (worker) uses an intrinsic subgoal-driven attention mechanism for action prediction in a smaller state space. We place no constraints on the semantics that subgoals may convey, allowing the agent to autonomously learn intrinsic, more generalizable subgoals from navigation tasks. Furthermore, we design a novel history-aware discriminator (HAD) for the worker. The discriminator incorporates historical information into subgoal discrimination and provides the worker with additional intrinsic rewards to alleviate the reward sparsity. Without labeled actions, our method provides supervision for the worker in the form of self-supervision by generating subgoals from the manager. The final results of multiple comparison experiments on the Room-to-Room (R2R) dataset show that our DISH can significantly outperform the baseline in accuracy and efficiency.

In this study, the fixed-time synchronization (FTSn) problem is investigated for coupled reaction-diffusion systems (RDSs) with time-varying delay based on an aperiodically intermittent control (AIC) strategy. For the fixed-time control, the convergence time can be estimated in advance, irrespective of initial states. Additionally, unlike the previous studies with the semi-intermittent control strategy, the FTSn is achieved for the coupled RDSs via completely AIC by adopting the average control rate, then the mechanism is more general. Meanwhile, the utilization of average control rate indicates that the results obtained are less conservative. Furthermore, a new auxiliary function is designed to demonstrate that the fixed-time convergence of the coupled RDSs can be guaranteed with or without the presence of time-varying delay. Finally, numerical examples are provided to verify the effectiveness of the theoretical results.

This article investigates distributed adaptive leader-following consensus tracking optimal control problem for nonlinear multiagent systems (MASs) subject to unknown nonlinearities and uncertain external disturbances. In contrast to traditional centralized control, the primary challenge is that only partial subsystems can access the desired reference trajectory. To address this, positive time-varying smooth function compensating terms are introduced to counteract the effects of uncertain external disturbances and unknown desired trajectories. Then, by fusing consensus errors into the backstepping technique, feedforward controllers are given. On this basis, the controlled nonlinear systems are transformed into an equivalent affine form, and feedback optimal controllers are designed using actor and critic neural networks (NNs) to execute control behavior and evaluate control performance. The whole control laws comprise both feedforward and feedback controllers. The proposed distributed adaptive consensus control protocol can simultaneously achieve desired optimal control performance and minimize the cost function, as demonstrated through theoretical analysis and simulation results.

Data augmentation plays a crucial role in improving the data efficiency of reinforcement learning (RL). However, the generation of high-quality augmented data remains a significant challenge. To overcome this, we introduce ACAMDA (Adversarial Causal Modeling for Data Augmentation), a novel framework that integrates two causality-based tasks: causal structure recovery and counterfactual estimation. The unique aspect of ACAMDA lies in its ability to recover temporal causal relationships from limited non-expert datasets. The identification of the sequential cause-and-effect allows the creation of realistic yet unobserved scenarios. We utilize this characteristic to generate guided counterfactual datasets, which, in turn, substantially reduces the need for extensive data collection. By simulating various state-action pairs under hypothetical actions, ACAMDA enriches the training dataset for diverse and heterogeneous conditions. Our experimental evaluation shows that ACAMDA outperforms existing methods, particularly when applied to novel and unseen domains.

Video Person Re-Identification (Re-ID) is a task of retrieving persons from multi-camera surveillance systems. Despite the progress made in leveraging spatio-temporal information in videos, occlusion in dense crowds still hinders further progress. To address this issue, we propose a Temporal Correlation Vision Transformer (TCViT) for video person Re-ID. TCViT consists of a Temporal Correlation Attention (TCA) module and a Learnable Temporal Aggregation (LTA) module. The TCA module is designed to reduce the impact of non-target persons by relative state, while the LTA module is used to aggregate frame-level features based on their completeness. Specifically, TCA is a parameter-free module that first aligns frame-level features to restore semantic coherence in videos and then enhances the features of the target person according to temporal correlation. Additionally, unlike previous methods that treat each frame equally with a pooling layer, LTA introduces a lightweight learnable module to weigh and aggregate frame-level features under the guidance of a classification score. Extensive experiments on four prevalent benchmarks demonstrate that our method achieves state-of-the-art performance in video Re-ID.

Spiking neural networks (SNNs) have revolutionized neural learning and are making remarkable strides in image analysis and robot control tasks with ultra-low power consumption advantages. Inspired by this success, we investigate the application of spiking neural networks to 3D point cloud processing. We present a point-to-spike residual learning network for point cloud classification, which operates on points with binary spikes rather than floating-point numbers. Specifically, we first design a spatial-aware kernel point spiking neuron to relate spiking generation to point position in 3D space. On this basis, we then design a 3D spiking residual block for effective feature learning based on spike sequences. By stacking the 3D spiking residual blocks, we build the point-to-spike residual classification network, which achieves low computation cost and low accuracy loss on two benchmark datasets, ModelNet40 and ScanObjectNN. Moreover, the classifier strikes a good balance between classification accuracy and biological characteristics, allowing us to explore the deployment of 3D processing to neuromorphic chips for developing energy-efficient 3D robotic perception systems.

To enhance the post-simulation efficiency of large-scale integrated circuits, various model order reduction (MOR) methods have been proposed. Among these, TICER (Time-Constant Equilibration Reduction) is a widely-used resistor-capacitor (RC) network reduction algorithm. However, the time constant computation for eliminated-node classification in TICER is quite time-consuming. In this work, a two-stage TICER acceleration framework (TSA-TICER) is proposed. First, an improved graph attention network (named BCTu-GAT) equipped with betweenness centrality metric (BCM) based sample selection strategy and bi-level aggregation-based topology updating scheme (BiTu) is proposed to quickly and accurately determine all the eliminated nodes one time in the TICER. Second, an adaptive merging strategy for the new fill-in capacitors are designed to further accelerate the insertion stage. The proposed TSA - TI CER is tested on RC networks with the size from 2k to 2 million nodes. Experimental results show that the proposed TSA-TICER achieves up to 796.21X order reduction speedup and 10.46X fill-in speedup compared to the TICER with 0.574% maximum relative error.

In the post-layout simulation for large-scale integrated circuits, transient analysis (TA), determining the time-domain response over a specified time interval, is essential and important. However, it tends to be computationally intensive and quite time-consuming without proper settings of NR initial solution and accurate LTE estimation for determining the next transient timestep, which will lead to a mass of backward-steppings. In this paper, an irregular sequential prediction transformer named ISPT-Net is proposed to predict accurately transient solution as NR initial solution and further obtain precise LTE estimation for setting next timestep. The ISPT-Net is strengthened with timestep positional encoding module (TPE), frequency- and timestep-sensitive muti-head self-attention module (FT-MSA) to enhance irregular sequence feature extraction and prediction accuracy. We assess ISPT-Net in the real large-scale industrial circuits on a commercial SPICE simulator, and achieve a remarkable backward stepping reduction: up to 14.43X for NR nonconvergence case and 4.46X for LTE overlimit case while guaranteeing higher solution accuracy.

Sparse LU factorization is a vital technique in solving circuit linear equations, However, irregular data access patterns contribute to unsatisfactory computational efficiency and excessive memory usage. Conventional LU factorization methods generally involve two approaches: either they utilize space-intensive dense matrices for direct index-to-data mapping, or they inefficiently scour through indices to locate the positions of updated data elements. To resolve these challenges, we propose the Indexing-Efficient Sparse LU factorization (ISLU) in this work. A novel indexing-efficient member union is put forwarded to achieve efficient retrieval of indices within compressed formats, thereby significantly enhancing the LU decomposition efficiency. Furthermore, to expedite the establishment of indexing-efficient member union, we design, for the first time, parallel creating member union strategy for GPU platforms, which remarkably reduces the time overhead associated with constructing the proposed structures. Extensive experimental comparisons on 49 benchmark matrices and real SPICE transient simulations demonstrate that the performance enhancements by our proposed ISLU method are substantial, outperforming various excellent GPU and CPU solvers including commercial solvers.

Zero-shot object navigation is a challenging task for home-assistance robots. This task emphasizes visual grounding, commonsense inference and locomotion abilities, where the first two are inherent in foundation models. But for the locomotion part, most works still depend on map-based planning approaches. The gap between RGB space and map space makes it difficult to directly transfer the knowledge from foundation models to navigation tasks. In this work, we propose a Pixel-guided Navigation skill (PixNav), which bridges the gap between the foundation models and the embodied navigation task. It is straightforward for recent foundation models to indicate an object by pixels, and with pixels as the goal specification, our method becomes a versatile navigation policy towards all different kinds of objects. Besides, our PixNav is a pure RGB-based policy that can reduce the cost of homeassistance robots. Experiments demonstrate the robustness of the PixNav which achieves 80+% success rate in the local path-planning task. To perform long-horizon object navigation, we design an LLM-based planner to utilize the commonsense knowledge between objects and rooms to select the best waypoint. Evaluations across both photorealistic indoor simulators and real-world environments validate the effectiveness of our proposed navigation strategy. More details are accessible via our project website https://sites.google.com/view/pixnav/.

In this paper, an aperiodically intermittent event-based control strategy is developed to investigate the practical fixed-time consensus (FTC) tracking problem of nonlinear multi-agent systems (MASs). Different from the traditional event-based scheme, we incorporate the event-based scheme into the intermittent control mechanism, and the aperiodically intermittent event-based mechanism is developed, which can significantly save resources, particularly in terms of reducing the energy consumption of communication. Additionally, our proposed mechanism enables practical intermittent event-based FTC tracking for a directed graph, while eliminating the dependence on initial states for convergence time estimation. Moreover, the measurement error and intermittent event-based controller are constructed based on the hyperbolic tangent function, then the non-differentiable problem and Zeno behavior can be avoided. Furthermore, an improved triggering mechanism of the event-based scheme is designed to avoid continuous monitoring in control intervals. Hence, resource consumption can be further reduced. Finally, the multiple ground vehicles and Chua’s circuit are considered in simulation examples to verify the effectiveness of theoretical results.Note to Practitioners—This paper addresses the FTC tracking problem of MASs via intermittent event-based control for a directed graph, which can be applied to multiple ground vehicles and Chua’s circuit system. Unlike the asymptotic and finite-time stability results, the upper bound of the convergence time can be estimated, which is unrelated to the initial states and can better satisfy the application requirements. Considering the limitation of communication bandwidth and saving resources, we take the event-based scheme into the intermittent control mechanism, and a new aperiodic intermittent event-based controller is designed under the fixed-time convergence. Contrary to the traditional fixed-time control strategies via intermittent control or event-based control, the proposed algorithms in this study can effectively reduce the update frequency of the controller and significantly save energy under intermittent monitoring, which is more friendly for control engineers. The feasibility of the obtained results is demonstrated by examples of multiple ground vehicles and Chua’s circuit. Potential applications of the proposed control algorithms include smart grid, cooperative search and exploration.

In this paper, the formation obstacle avoidance problem of autonomous underwater vehicles (AUVs) under the disturbances of ocean currents is studied. A variable formation reconfiguration and obstacle avoidance control scheme based on affine transform and the improved artificial potential field (AT-IAPF) is designed, which enable AUVs to avoid both static and dynamic obstacles under external interference, and maintain the desired time-varying formation. Because of the robustness and strong effectiveness of the time-varying control of AT and the obstacle avoidance control law of IAPF. The AT-IAPF algorithm improves the multi-AUV systems’ environmental adaptability and obstacle avoidance performance. Using the Lyapunov function’s stability constraint guarantees stability of a multi-AUV system. A series of simulation results based on MATLAB verify that AUVs can effectively avoid obstacles with different formation shapes. Obstacle avoidance experiments on bionic robotic fish demonstrate the proposed method’s feasibility. Note to Practitioners—This paper was motivated by the problem of formation reconfiguration and obstacle avoidance for AUVs. Still, it also applies to unmanned ground vehicles (UGVs) and unmanned aerial vehicles (UAVs). The existing formation control methods usually solve the problems of formation acquisition and time-invariant maneuvering, and rarely consider the problem of formation obstacle avoidance. This paper presents a new formation obstacle avoidance method using affine transformation (AT) and improved artificial potential field (IAPF) techniques. We use the IAPF method to plan a possible path for the formation in the obstacle environment. At the same time, the appropriate formation shape is selected according to the obstacle information to better adapt to the environment. The preliminary experiments of two bionic robot fish in near-surface positions show that this method is feasible. During the experiment, UWB is used for positioning, and a Zigbee module is used to communicate and transmit data. But it still needs to solve the problem of underwater communication, and it has yet to be tested on multiple bionic robot fish. In future studies, we will conduct multiple actual AUV formation obstacle avoidance experiments or do 3D formation control experiments underwater.

Event cameras are bio-inspired dynamic vision sensors that are superior to frame-based cameras in terms of low power consumption, high dynamic range, and high temporal resolution in computer vision tasks. Recent advances in voxel-based representation learning have successfully exploited the sparsity of events with low computational complexity, but face challenges in extracting spatio-temporal features within voxels and representative global dependencies between voxels, thus limiting their representation power. In this work, towards a better trade-off between accuracy and computation overhead, we propose a novel voxel-based multi-scale transformer network (VMST-Net) to process event streams. Specifically, VMST-Net projects events within voxels into multi-channel frames along the time axis, such that 2D convolutions could be leveraged to encode spatio-temporal features in voxels. Then, VMST-Net utilizes a novel multi-scale multi-head self-attention (MSMHSA) mechanism with a multi-scale fusion (MSF) module that allows different heads within each layer to attend different scale 3D neighborhoods to adaptively aggregate the coarse-to-fine voxel features with little computational costs and parameters. Moreover, to model effective global features while saving computations, we aggregate features in a local-to-global manner by enlarging the coverage of 3D neighborhoods as the network gets deeper. Extensive experimental results on benchmark datasets demonstrate that our model advances state-of-the-art accuracy with low model complexity and computational complexity in all three visual tasks, including object classification, action recognition, and human pose estimation.

At present, deep learning has demonstrated outstanding performance in the area of underwater image enhancement. However, these approaches often demand substantial computational resources and extended training time. Knowledge distillation is a widely used technique for model compression, and nowadays it has delivered outstanding results across various fields. However, it has not been utilized in the field of underwater image enhancement. To tackle the aforementioned issues, this paper introduces a knowledge distillation technique for underwater image enhancement for the first time. It is a semi-supervised self-inter feature distillation and unsupervised self-domain adversarial distillation approach. It specifically includes adaptive local self-feature distillation technique, information lossless multi-scale inter-feature distillation technique, and self-domain adversarial distillation approach in LAB-RGB space. Self-feature distillation enhances the performance of the student network by correcting other lossy feature maps with the maximum effective feature map. Inter-feature distillation enables the student network to maximize the potential information learned from the teacher network. Furthermore, an information loss-free pooling approach is suggested to achieve multi-scale loss-free information extraction. Self-domain adversarial distillation boosts the performance of student networks through unsupervised adaptive enhancement in LAB space and unsupervised domain adversarial distillation in RGB space. Finally, a self-inter alternate knowledge distillation training measure is proposed, aiming to maximize the respective benefits of self-inter knowledge distillation. Through extensive comparative experiments, it can be found that student networks with dissimilar structures trained using the knowledge distillation technique designed in this paper achieve outstanding underwater image enhancement results.

Ground-to-aerial (G2A) geo-localization remains extremely challenging due to the drastic appearance and geometry differences between ground and aerial views, especially when their relative orientation is unknown. In this paper, we focus on the challenging problem of unaligned G2A geo-localization, where the query ground-level image is not perfectly orientation-aligned with respect to reference aerial imagery. We cast this problem as a metric embedding task and propose a decoupled hierarchical (DeHi) architecture to progressively learn meaningful multi-grained features. Specifically, DeHi first leverages CNN to extract high-level semantic features, and then introduces a novel orthogonally factorized transformer model consisting of part-level and global transformer encoders to learn part-level and global feature descriptors sequentially. For the purpose of enhancing representation power, cross-level connections are introduced to enrich part-level and global descriptors by CNN features, and the pooled part-level descriptor is combined with the global descriptor to construct the final query representation. Furthermore, such a decoupled hierarchical architecture allows for incorporating multi-level deep supervision. We introduce two part-level losses combined with one cross-level loss to complement the widely used global retrieval loss. Extensive experiments on standard benchmark datasets show significant boosting in recall rates compared with the previous state-of-the-art. Remarkably, DeHi improves the recall rate @top-1 from 78.59% to 82.38% (+3.79%) and from 72.91% to 77.94% (+5.03%) on CVUSA and CVACT datasets, respectively, under random orientation misalignments. Besides, DeHi maintains competitive inference efficiency with less parameters compared to existing transformer-based methods.

In this article, we investigate the optimal control problem for semicar active suspension systems (SCASSs). First, we model the SCASSs by Newtonian dynamics as well as considering the uncertainties and nonlinear dynamics of the actuator. Second, in order to solve the complexity brought by uncertainties, we apply the Takagi–Sugeno (T-S) fuzzy approach to transform the SCASSs as multilinear systems, as well as solving the optimal control problem as a zero-sum problem to find the solution of Nash-equilibrium. Third, we construct a novel self-learning method based on the reinforcement learning framework, and propose two algorithms to solve the fuzzy game algebraic Riccati equation. Especially, in the second algorithm, without using any model information of the SCASSs, we only use the state and input information in control design by a self-learning manner removing the traditional dependence problem, which is more preferable for practical applications. Finally, we give a simulation result of the SCASSs to demonstrate the effectiveness and practicability for the designed self-learning algorithms.

In this article, a new event-based aperiodic intermittent fixed-time consensus control strategy is developed for multiagent systems (MASs) with nonlinear uncertainties and unknown control directions. Concretely, the intermittent control strategy is considered to construct the intermittent event-based control (IEBC) algorithm, which leads to substantial savings in communication resources. In addition, an enhanced triggering algorithm is further designed to eliminate continuous monitoring of neighbors' and its own states. Consequently, different from the existing event-based control strategy, the IEBC algorithms proposed herein can further reduce communication energy consumption. To handle the nonlinear uncertainties in MASs, fuzzy logic systems are utilized, enhancing the algorithm to tackle more general problems. Considering the problem of unknown control directions, a controller employing Nussbaum-type functions is formulated. Moreover, the fixed-time consensus control algorithm is incorporated, and the estimation of the convergence time is not reliant on the initial states. Finally, the feasibility of the proposed algorithm is demonstrated through a numerical example.

In this article, a switching-event-based interval type-2 variable universe fuzzy tracking control strategy is proposed for a class of uncertain nonlinear systems. Remarkably, the nonlinearities and the large unknown uncertainties (including parametric and structural) can be allowed. Therefore, a novel switching-event-based mechanism is proposed. It not only determines when to update the control law, but also when to update the design parameters. At the same time, generous computing resources are saved. In addition, the interval type-2 fuzzy control technology is introduced to resist unknown uncertainties by identifying the controlled model online. Moreover, the Lyapunov function is designed to prove that the Zeno phenomenon does not occur and the closed-loop system is asymptotically stable. Finally, two practical simulations are given to demonstrate the effectiveness of the proposed method.

In this paper, a switching-event-based interval type2 (IT2) T-S variable direction fuzzy tracking control strategy is proposed for time-varying delay systems with unknown control directions. To deal with the time-varying delay problem, the T-S fuzzy logic system (TSFLS) is used to approximate the unknown nonlinear functions. A novel logic-based switching mechanism is proposed to handle the problem of unknown control directions. At the same time, in order to ensure the stability and tracking performance of the system, an auxiliary controller is designed. The proposed controller not only ensures the tracking performance well, but also reduces the communication burden between the controller and the actuator. In addition, through designing appropriate Lyapunov-Krasoviskii (L-K) functional for tracking error, the system is proved to be asymptotically stable and the Zeno phenomenon is excluded. Wherein the main parameters discussed are tracking error and time interval for eventtriggering. Finally, the effectiveness of the proposed method is verified by using both a mathematical model and an actual physical model.

In this article, an event-based hierarchical fuzzy prescribed performance control strategy is proposed for a class of underactuated systems with input dead zones. It is worth noting that the slope of the input dead zone is uncertain (time-varying/fuzzy). Therefore, a suitable hierarchical fuzzy logic system (HFLS) is designed to compensate for uncertain dead zones while significantly reducing the number of fuzzy rules. In addition, a dynamic event-based mechanism (DEBM) is proposed, which not only determines when to update the control law of the upper-level fuzzy system, but also when to update the parameters of the lower-level fuzzy controller. Moreover, this strategy can better tolerate interference while achieving the specified transient and steady-state performance of the system, and greatly save computing/communication resources. Furthermore, a Lyapunov function is designed to prove the stability of the system and eliminate the Zeno phenomenon. Finally, simulations are conducted using a quadcopter under two uncertain dead zone conditions to verify the effectiveness of the method.

Current adversarial attacks are capable of achieving effective evasion against machine learning-based static malware detectors. However, these methods have problems such as long example generation times and lack of functionality validation. To address these issues, we propose an enhanced adversarial example generation framework based on reinforcement learning. This framework improves the example generation efficiency by redesigning the state space and action space employed by the agents. Furthermore, we incorporate the functionality of adversarial example validation for the first time as a component of the example generation process within the framework, significantly enhancing the efficiency of verification. Multiple popular detectors are chosen as victim models to assess the effectiveness of the attack framework. The vulnerabilities of these detectors are elucidated through explanations of the detectors and the analysis of attack results. Finally, a policy distillation approach based on transfer learning is employed to enhance the generalizability of the framework. By learning expert knowledge from agents trained against different detectors, the framework could launch effective attacks against various detectors. The effectiveness of the proposed framework is verified through experiment results.

Pedestrian trajectory prediction in a first-person view has recently attracted much attention due to its importance in autonomous driving. Recent work utilizes pedestrian character information, i.e., action and appearance, to improve the learned trajectory embedding and achieves state-of-the-art performance. However, it neglects the invalid and negative pedestrian character information, which is harmful to trajectory representation and thus leads to performance degradation. To address this issue, we present a two-stream sparse-character-based network (TSNet) for pedestrian trajectory prediction. Specifically, TSNet learns the negative-removed characters in the sparse character representation stream to improve the trajectory embedding obtained in the trajectory representation stream. Moreover, to model the negative-removed characters, we propose a novel sparse character graph, including the sparse category and sparse temporal character graphs, to learn the different effects of various characters in category and temporal dimensions, respectively. Extensive experiments on two first-person view datasets, PIE and JAAD, show that our method outperforms existing state-of-the-art methods. In addition, ablation studies demonstrate different effects of various characters and prove that TSNet outperforms approaches without eliminating negative characters.

In this article, a reinforcement learning (RL)-based strategy for unmanned surface vehicle (USV) path following control is developed. The proposed method learns integrated guidance and heading control policy, which directly maps the USV's navigation states to motor control commands. By introducing a twin-critic design and an integral compensator to the conventional deep deterministic policy gradient (DDPG) algorithm, the tracking accuracy and robustness of the controller can be significantly improved. Moreover, a pretrained neural network-based USV model is built to help the learning algorithm efficiently deal with unknown nonlinear dynamics. The self-learning and path following capabilities of the proposed method were validated in both simulations and real sea experiments. The results show that our control policy can achieve better performance than a traditional cascade control policy and a DDPG-based control policy.

Gls UUV is an intelligent underwater platform that can operate autonomously. However, it is difficult for unmanned underwater vehicle (UUV) to make correct decisions timely and independently in the face of uncertain events. Therefore, it is necessary to assess the threat of uncertain events and guide UUV to make timely and accurate decisions. This article studies the threat assessment strategy of a human-in-the-loop UUV under uncertain events. First, the uncertain events are classified according to their characteristics, and the Bayesian network (BN) is constructed by taking the characteristic variables of uncertain events as neurons. Then, the human experiences are combined with the genetic optimization algorithm to determine the BN parameters. According to the reasoning of the BN, the threat of uncertain events is evaluated. Finally, according to the threat assessment results, the PSO and A/B model are used to replan the task. The proposed algorithm uses BN to represent uncertain events and introduces human experiences to optimize network parameters, eliminating subjective bias and improving the accuracy of threat assessment. At the same time, the task replanning strategy is introduced to ensure the security of UUV. Four typical UUV tasks are designed, and the trigger elements of uncertain events are set in the simulation to verify the performance of the proposed algorithm. The simulation and experiment results show that a UUV can accurately assess the threat level of uncertain events during the task execution process when using the proposed strategy. The safety of the human-in-the-loop UUV operation is guaranteed by task replanning.

In this article, the practical fixed-time synchronization (PFIXTS) problem of multilayer complex networks (CNs) is investigated based on an intermittent event-triggered control (IE-TC) strategy. Under a new framework of intermittent control (IC), a practical fixed-time stability lemma is proposed. In addition, the conservatism of the results is reduced resulting from the use of average control rate (ACR) for IC. Based on the practical fixed-time stability lemma, a new theorem is developed to achieve the PFIXTS for multilayer CNs, which can further reduce the energy consumption of communication and save resources. Moreover, the emergence of Zeno behavior in the IE-TC strategy is excluded. Finally, the effectiveness of the results is verified by numerical simulations.

This article focuses on the performance analysis of distributed controllers for general linear multiagent systems in the sense of convergence time and energy consumption. First, the specified-time optimal controller is obtained using the linear operator theory-based method, and then the optimal topology is deduced. Second, to analyze the impact of communication topology on energy consumption, two distributed, suboptimal specified-time controllers are developed for undirected and directed graphs, respectively. By utilizing the inverse optimality method and Lyapunov function scaling, the performance in terms of the bounds of the gaps between the energy consumption of the suboptimal and optimal control laws is derived, which evaluates the effectiveness of the suboptimal controllers. Finally, as the simulation results show, the performance can specify appropriate settling times for applications with different energy budgets and facilitate optimizing the communication topology to reduce the energy gap.

Recently, learning-based approaches show promising results in navigation tasks. However, the poor generalization capability and the simulation-reality gap prevent a wide range of applications. We consider the problem of improving the generalization of mobile robots and achieving sim-to-real transfer for navigation skills. To that end, we propose a cross-modal fusion method and a knowledge transfer framework for better generalization. This is realized by a teacher-student distillation architecture. The teacher learns a discriminative representation and the near-perfect policy in an ideal environment. By imitating the behavior and representation of the teacher, the student is able to align the features from noisy multi-modal input and reduce the influence of variations on navigation policy. We evaluate our method in simulated and real-world environments. Experiments show that our method outperforms the baselines by a large margin and achieves robust navigation performance with varying working conditions.

The dc analysis is essential and still quite challenging in large-scale nonlinear circuit simulation. Pseudo transient analysis (PTA) is a widely used and has great potential solver in the industry. However, the PTA convergence and simulation efficiency is still seriously affected by its stepping policy. This article proposes an online stochastic stepping policy (OSSP) for PTA based on deep reinforcement learning (DRL). To achieve better policy evaluation and stronger stepping exploration ability, the dual soft Actor–Critic agents work with the proposed valuation splitting and online momental scaling, enabling our OSSP to intelligently encode PTA iteration status and online further adjust forward and backward time-step size for unseen test circuits without human intervention and domain knowledge, trained solely by reinforcement learning from self-search. Our public sample buffer and priority sampling are also introduced to overcome the sparsity and imbalance of sample data. Numerical examples demonstrate that the proposed OSSP achieves a significant efficiency speedup (up to$47.0\times $less Newton–Raphson iterations) and convergence enhancement on unseen test circuits compared with the previous iter-based and switched evolution/relaxation-based stepping methods, in just one stepping iteration.

Light propagates in water with certain attenuation, which causes quality problems, such as color cast, low contrast, and low illumination, in underwater images. Moreover, it is generally difficult to obtain a large number of real-world underwater images and the corresponding ground truth in convoluted underwater environments. To address these two problems, this article recommends an underwater image enhancement scheme based on few-shot learning and multi-color space, called UIE-FSMC. Specifically, for the first time, we propose a lightweight underwater image enhancement network based on few-shot learning. We design a new strategy to train the network. Specific training steps include the following: First, synthetic underwater images are used for large-scale pre-training, which can obtain the initial weight of the network. Then, according to the characteristics of the data, meta-learning based on supervised and unsupervised loss is suggested. It further enhances the feature expression aptitude of the network by learning the external and internal characteristics of the data. Finally, fine-tuning based on supervised and unsupervised loss is designed. It further improves the accuracy, robustness, and generalization of the network through an average strategy. In addition, we design a post-processing method founded on the RGB and LAB color spaces. In the RGB color space, we suggest a local region-based adaptive color correction method for underwater images. In the LAB color space, we design a multi-scale local adaptive contrast enhancement method for the L channel and a local region-based color balance strategy for the AB channels. Quantitative and qualitative experiments on five different underwater image datasets show that the outcomes of UIE-FSMC are superior to those of other techniques. Furthermore, application research further validates the excellent performance of UIE-FSMC.

Underwater dynamic target tracking technology has a wide application prospect in marine resource exploration, underwater engineering operations, naval battlefield monitoring, and underwater precision guidance. Aiming at the underwater dynamic target tracking problem, an autonomous underwater vehicle tracking control method based on trajectory prediction is studied. First, a deep learning-based target detection algorithm is developed. For the image collected by the multibeam forward-looking sonar image, this algorithm uses the YOLO v3 network to determine the target in a sonar image and obtain the position of the target. Then, a time profit Elman neural network (TPENN) is constructed to predict the trajectory information of the dynamic target. Compared with an ordinary Elman neural network, its accuracy of dynamic target prediction is increased. Finally, underwater tracking of the dynamic target is realized using the model predictive controller (MPC), and the tracking result is stable and reliable. Through simulations and experiment, the proposed underwater dynamic target tracking control method is demonstrated to be effective and feasible.

This article studies the detection of discontinuous false data-injection (FDI) attacks on cyber-physical systems (CPSs). Considering the unknown stochastic properties of the process noise and measurement noise, deep reinforcement learning is applied to designing an FDI attack detector. First, the discontinuous attack detection problem is modeled as a partially observable Markov decision process (POMDP) and a neural network is used to explore the POMDP. In the network, sliding observation windows which are composed of the offline fragment historical data are used as the input. An approach to designing the reward in POMDP is provided to ensure the precision of the detection when there are even some state recognition errors. Second, sufficient conditions on attack frequency and duration to guarantee the applicability of the detector and the expected estimation performance are further given. Finally, simulation examples illustrate the effectiveness of the attack detector.

In this article, a data-based feedback relearning (FR) algorithm is developed for the uncertain nonlinear systems with control channel disturbances and actuator faults. Uncertain problems will influence the accuracy of collected data episodes, and in turn affect the convergence and optimality of the data-based reinforcement learning (RL) algorithm. The proposed FR algorithm can update the strategy online by relearning from the empirical data. The strategy can continuously approach the optimal solution, which improves the convergence and optimality of the algorithm. Moreover, based on the experience replay technology, a data processing method is designed to further improve the data utilization efficiency and the algorithm convergence. A neural network (NN)-based fault observer is used to achieve the model-free fault compensation. The polynomial activation function is redesigned by using the sigmoid function/hyperbolic tangent activation function, to reduce the difficulty of NNs design for an unknown nonlinear system and improve the generalization. In the face of disturbances and actuator faults, the control performance, algorithm convergence, and optimality of the proposed strategy can be well guaranteed through comparative simulation.

This article investigates the co-design problem of adaptive event-triggered schemes (AETSs) and asynchronous fault detection filter (AFDF) for nonhomogeneous higher-level Markov jump systems, involving the hidden Markov model (HMM), higher-level Markov chain (MC), and conic-type nonlinearities. The transformation of the system transition probability can be reflected by the designed higher-level MC. An HMM with another conditional transition probability is applied to detect higher-level Markov processes and make the system be more practical. In order to balance the utilization of network resources and system performance, a novel AETS is proposed and used in the construction of the AFDF. By the Lyapunov theory, sufficient conditions are given to ensure the existences of the AETS and AFDF. It is not only an appropriate tradeoff between the utilization of network resources and system performance, but also reduces the conservatism. Finally, a numerical example is given to detect the faults effectively by the co-designed AFDF.

This article proposes a hybrid policy-based reinforcement learning (HPRL) adaptive energy management to realize the optimal operation for the island group energy system with energy transmission-constrained environment. An island energy hub (IEH) model that can realize the energy cascade utilization is proposed. Compared with the traditional model, the IEH can satisfy the special energy demand of island, meanwhile, ensure the energy supply of island. Moreover, an energy management model of islands group (EMIG) based on the IEH is formulated which comprehensively considers the inverse distribution of energy demand and resources, as well as the limited energy transmission. Since the environment model of the island is difficult to construct due to the increase of proportion of renewable energy generation and civilian load, the EMIG is transformed into a reinforcement learning (RL) task which features model-free. Considering the limitations of traditional RL in discrete-continuous hybrid action space, HPRL is proposed to achieve optimal operation without simplifying the model. Numerical simulations demonstrate the effectiveness of the proposed adaptive energy management.

Localization in unknown environments is an essential requirement for vision navigation of robotic vehicles in intelligent transportation systems. However, moving objects in dynamic scenarios usually bring about great difficulty for robot localization, because motion estimation of robotic vehicles is disturbed by increasing feature outliers caused by moving objects. In order to improve the accuracy and robustness of robot localization, a novel saliency-induced moving object detection (SMOD) approach is proposed to filter out feature outliers for RGB-D-based simultaneous localization and mapping (SLAM) in complex dynamic workspaces. Firstly, three complementary motion saliency potentials, including motion energy (ME), spatiotemporal objectness (STO), and dynamic superpixels (DS), are modeled by fully analyzing spatial, temporal, appearance and depth cues in RGB-D inputs. They can be used to identify the dynamic objects effectively from diversely changing backgrounds. Then, a superpixel-level graph-based motion saliency (MS) measure is proposed to generate the MS map for reliable localization of the moving objects. The edge weights and background nodes on the graph are determined reasonably by fusing ME, STO, and DS, which is not vulnerable to background interferences. Furthermore, the SMOD approach is embedded into the front-end of ORB-SLAM3 as a pre-processing stage, in order to filter out feature outliers associated with the moving objects. Finally, the extensive experiments are performed to verify the accuracy and robustness of the proposed approach on the public dynamic datasets. The experimental results show that the SMOD method can detect the moving objects effectively in a variety of challenging dynamic environments, and separate the dynamic regions reliably from the irrelevant background. The data comparison demonstrates that the SMOD-SLAM navigation system can outperform other state-of-the-art dynamic visual SLAM (vSLAM) systems.

Model-based reinforcement learning (RL) is regarded as a promising approach to tackle the challenges that hinder model-free RL. The success of model-based RL hinges critically on the quality of the predicted dynamic models. However, for many real-world tasks involving high-dimensional state spaces, current dynamics prediction models show poor performance in long-term prediction. To that end, we propose a novel two-branch neural network architecture with multi-timescale memory augmentation to handle long-term and short-term memory differently. Specifically, we follow previous works to introduce a recurrent neural network architecture to encode history observation sequences into latent space, characterizing the long-term memory of agents. Different from previous works, we view the most recent observations as the short-term memory of agents and employ them to directly reconstruct the next frame to avoid compounding error. This is achieved by introducing a self-supervised optical flow prediction structure to model the action-conditional feature transformation at pixel level. The reconstructed observation is finally augmented by the long-term memory to ensure semantic consistency. Experimental results show that our approach is able to generate visually-realistic long-term predictions in DeepMind maze navigation games, and outperforms the prevalent state-of-the-art methods in prediction accuracy by a large margin. Furthermore, we also evaluate the usefulness of our world model by using the predicted frames to drive an imagination-augmented exploration strategy to improve the model-free RL controller.

Due to the complexity of the ocean environment, an autonomous underwater vehicle (AUV) is disturbed by obstacles when performing tasks. Therefore, the research on underwater obstacle detection and avoidance is particularly important. Based on the images collected by a forward-looking sonar on an AUV, this article proposes an obstacle detection and avoidance algorithm. First, a deep learning-based obstacle candidate area detection algorithm is developed. This algorithm uses the You Only Look Once (YOLO) v3 network to determine obstacle candidate areas in a sonar image. Then, in the determined obstacle candidate areas, the obstacle detection algorithm based on the improved threshold segmentation algorithm is used to detect obstacles accurately. Finally, using the obstacle detection results obtained from the sonar images, an obstacle avoidance algorithm based on deep reinforcement learning (DRL) is developed to plan a reasonable obstacle avoidance path of an AUV. Experimental results show that the proposed algorithms improve obstacle detection accuracy and processing speed of sonar images. At the same time, the proposed algorithms ensure AUV navigation safety in a complex obstacle environment.

In this article, a novel hybrid multirobot motion planner that can be applied under no explicit communication and local observable conditions is presented. The planner is model-free and can realize the end-to-end mapping of multirobot state and observation information to final smooth and continuous trajectories. The planner is a front-end and back-end separated architecture. The design of the front-end collaborative waypoints searching module is based on the multiagent soft actor-critic (MASAC) algorithm under the centralized training with decentralized execution (CTDE) diagram. The design of the back-end trajectory optimization module is based on the minimal snap method with safety zone constraints. This module can output the final dynamic-feasible and executable trajectories. Finally, multigroup experimental results verify the effectiveness of the proposed motion planner.

Based on the reinforcement learning mechanism, a data-based scheme is proposed to address the optimal control problem of discrete-time non-linear switching systems. In contrast to conventional systems, in the switching systems, the control signal consists of the active mode (discrete) and the control inputs (continuous). First, the Hamilton-Jacobi-Bellman equation of the hybrid action space is derived, and a two-stage value iteration method is proposed to learn the optimal solution. In addition, a neural network structure is designed by decomposing the Q-function into the value function and the normalized advantage value function, which is quadratic with respect to the continuous control of subsystems. In this way, the Q-function and the continuous policy can be simultaneously updated at each iteration step so that the training of hybrid policies is simplified to a one-step manner. Moreover, the convergence analysis of the proposed algorithm with consideration of approximation error is provided. Finally, the algorithm is applied evaluated on three different simulation examples. Compared to the related work, the results demonstrate the potential of our method.

This article presents a nearly optimal solution to the cooperative formation control problem for large-scale multiagent system (MAS). First, multigroup technique is widely used for the decomposition of the large-scale problem, but there is no consensus between different subgroups. Inspired by the hierarchical structure applied in the MAS, a hierarchical leader-following formation control structure with multigroup technique is constructed, where two layers and three types of agents are designed. Second, adaptive dynamic programming technique is conformed to the optimal formation control problem by the establishment of performance index function. Based on the traditional generalized policy iteration (PI) algorithm, the multistep generalized policy iteration (MsGPI) is developed with the modification of policy evaluation. The novel algorithm not only inherits the advantages of high convergence speed and low computational complexity in the generalized PI algorithm but also further accelerates the convergence speed and reduces run time. Besides, the stability analysis, convergence analysis, and optimality analysis are given for the proposed multistep PI algorithm. Afterward, a neural network-based actor-critic structure is built for approximating the iterative control policies and value functions. Finally, a large-scale formation control problem is provided to demonstrate the performance of our developed hierarchical leader-following formation control structure and MsGPI algorithm.

Reinforcement learning (RL) plays an essential role in the field of artificial intelligence but suffers from data inefficiency and model-shift issues. One possible solution to deal with such issues is to exploit transfer learning. However, interpretability problems and negative transfer may occur without explainable models. In this article, we define Relation Transfer as explainable and transferable learning based on graphical model representations, inferring the skeleton and relations among variables in a causal view and generalizing to the target domain. The proposed algorithm consists of the following three steps. First, we leverage a suitable casual discovery method to identify the causal graph based on the augmented source domain data. After that, we make inferences on the target model based on the prior causal knowledge. Finally, offline RL training on the target model is utilized as prior knowledge to improve the policy training in the target domain. The proposed method can answer the question of what to transfer and realize zero-shot transfer across related domains in a principled way. To demonstrate the robustness of the proposed framework, we conduct experiments on four classical control problems as well as one simulation to the real-world application. Experimental results on both continuous and discrete cases demonstrate the efficacy of the proposed method.

Existing approaches to constrained-input optimal control problems mainly focus on systems with input saturation, whereas other constraints, such as combined inequality constraints and state-dependent constraints, are seldom discussed. In this article, a reinforcement learning (RL)-based algorithm is developed for constrained-input optimal control of discrete-time (DT) systems. The deterministic policy gradient (DPG) is introduced to iteratively search the optimal solution to the Hamilton-Jacobi-Bellman (HJB) equation. To deal with input constraints, an action mapping (AM) mechanism is proposed. The objective of this mechanism is to transform the exploration space from the subspace generated by the given inequality constraints to the standard Cartesian product space, which can be searched effectively by existing algorithms. By using the proposed architecture, the learned policy can output control signals satisfying the given constraints, and the original reward function can be kept unchanged. In our study, the convergence analysis is given. It is shown that the iterative algorithm is convergent to the optimal solution of the HJB equation. In addition, the continuity of the iterative estimated Q -function is investigated. Two numerical examples are provided to demonstrate the effectiveness of our approach.

This article focuses on the bounded stabilization issue for stochastic Takagi–Sugeno (T–S) fuzzy systems with external disturbances under fuzzy intermittent event-triggered control. Different from the common intermittent control scheme, the intermittent control proposed is based on an event-triggered mechanism instead of a traditional time-triggered mechanism during the work intervals. As a result, it reduces unnecessary sampling times and resource waste to a great extent. Meanwhile, the minimum interexecution time is obtained for T–S fuzzy systems under the stochastic case. In addition, this article presents a novel Lyapunov function, which simplifies the proof compared to the traditional Lyapunov function for intermittent control. Based on the average control rate adopted and the Lyapunov method, a bounded stability criterion is established, which is less conservative. Then, a corollary is given under the fuzzy event-triggered control. Finally, an example is shown to illustrate the effectiveness of the results obtained.

With the more extensive application of flexible robots, the expectation for flexible manipulators is also increasing rapidly. However, the fast convergence will cause the increase of vibration amplitude to some extent, and it is difficult to obtain vibration suppression and satisfactory transient performance at the same time. In order to deal with the problem, a fixed-time learning control method is proposed to realize the fast convergence. The constraint on system outputs, system uncertainty, and input saturation is addressed under the fixed-time convergence framework. A novel adaptive law for neural networks is integrated into the backstepping method, which enhances the learning rate of neural networks. The imposed constraint on the vibration amplitude is guaranteed by using the barrier Lyapunov function (BLF). Moreover, the chattering problem is addressed by approximating the sign function smoothly. In the end, some simulations have been carried out to show the effectiveness of the proposed method.

In this article, the problem of the asynchronous fault detection (FD) observer design is discussed for 2-D Markov jump systems (MJSs) expressed by a Roesser model. In general, the FD observer cannot work synchronously with the system, that is, the mode of the observer varies with the mode of the system in line with some conditional transitional probabilities. For dealing with this difficult point, a hidden Markov model (HMM) is employed. Then, combining the$H_{\infty }$attenuation index and$H_{\_{}}$increscent index, a multiobjective solution to the FD problem is formed. In terms of linear matrix inequality technology, sufficient conditions are gained to guarantee the existence of the asynchronous FD. Simultaneously, an asynchronous FD algorithm is generated to acquire the optimal performance indices. Finally, a numerical example concerned with the Darboux equation is demonstrated to exhibit the soundness of the developed approach.

This article develops a finite-dimensional dynamic model to describe a stand-alone tall building-like structure with an eccentric load by using the assumed mode method (AMM). To compensate for the dynamic uncertainties, a new neural-network (NN) control strategy is designed to suppress vibrations of the tall buildings. The output constraint on the angle of the pendulum is also considered, and such an angle can be ensured within the safety limit by incorporating a barrier Lyapunov function. The semiglobally uniform ultimate boundness (SGUUB) of the closed-loop system is proved via Lyapunov's stability. The simulation results reveal that the new NN strategy can effectively realize vibration suppression in the flexible beam and pendulum. The effectiveness of the new NN approach is further verified through the experiments on the Quanser smart structure.

The bionic flapping-wing robotic aircraft is inspired by the flight of birds or insects. This article focuses on the flexible wings of the aircraft, which has great advantages, such as being lightweight, having high flexibility, and offering low energy consumption. However, flexible wings might generate the unexpected deformation and vibration during the flying process. The vibration will degrade the flight performance, even shorten the lifespan of the aircraft. Therefore, designing an effective control method for suppressing vibrations of the flexible wings is significant in practice. The main purpose of this article is to develop an adaptive fault-tolerant control scheme for the flexible wings of the aircraft. Dynamic modeling, control design, and stability verification for the aircraft system are conducted. First, the dynamic model of the flexible flapping-wing aircraft is established by an improved rigid finite element (IRFE) method. Second, a novel adaptive fault-tolerant controller based on the fuzzy neural network (FNN) and nonsingular fast terminal sliding-mode (NFTSM) control scheme are proposed for tracking control and vibration suppression of the flexible wings, while successfully addressing the issues of system uncertainties and actuator failures. Third, the stability of the closed-loop system is analyzed through Lyapunov's direct method. Finally, co-simulations through MapleSim and MATLAB/Simulink are carried out to verify the performance of the proposed controller.

This article investigates the adaptive event-triggered finite-time dissipative filtering problems for the interval type-2 (IT2) Takagi–Sugeno (T–S) fuzzy Markov jump systems (MJSs) with asynchronous modes. By designing a generalized performance index, the$H_{\infty }$,$L_{2}-L_{\infty }$, and dissipative fuzzy filtering problems with network transmission delay are addressed. The adaptive event-triggered scheme (ETS) is proposed to guarantee that the IT2 T–S fuzzy MJSs are finite-time boundedness (FTB) and, thus, lower the energy consumption of communication while ensuring the performance of the system with extended dissipativity. Different from the conventional triggering mechanism, in this article, the parameters of the triggering function are based on an adaptive law, which is obtained online rather than as a predefined constant. Besides, the asynchronous phenomenon between the plant and the filter is considered, which is described by a hidden Markov model (HMM). Finally, two examples are presented to show the availability of the proposed algorithms.

In this article, the optimal control problem for robotic manipulators (RMs) with prescribed constraints is addressed. Considering the environmental conditions and requirements of practical applications, prescribed constraints are imposed on the system states to guarantee the control performance and normal operation of the robotic system. Accordingly, an error transformation function is adopted to cope with the prescribed constraints and generate an equivalent unconstrained error for the convenience of the intelligent control design. In order to improve the learning ability and optimize the control performance, critic learning (CL) is introduced to the control design of the constrained RM based on the transformed equivalent unconstrained system. In addition, the stability analysis is given to illustrate the feasibility of the proposed CL-based control. Finally, simulations are conducted on a two-degree-of-freedom (DOF)-constrained RM to further validate the effectiveness of the proposed controller.

This article studies a distributed model-predictive control (DMPC) strategy for a class of discrete-time linear systems subject to globally coupled constraints. To reduce the computational burden, the constraint tightening technique is adopted for enabling the early termination of the distributed optimization algorithm. Using the Lagrangian method, we convert the constrained optimization problem of the proposed DMPC to an unconstrained saddle-point seeking problem. Due to the presence of the global dual variable in the Lagrangian function, we propose a primal-dual algorithm based on the Laplacian consensus to solve such a problem in a distributed manner by introducing the local estimates of the dual variable. We theoretically show the geometric convergence of the primal-dual gradient optimization algorithm by the contraction theory in the context of discrete-time updating dynamics. The exact convergence rate is obtained, leading the stopping number of iterations to be bounded. The recursive feasibility of the proposed DMPC strategy and the stability of the closed-loop system can be established pursuant to the inexact solution. Numerical simulation demonstrates the performance of the proposed strategy.

This article studies the prescribed performance fault-tolerant control problem for a class of uncertain nonlinear multi-input and multioutput systems. A learning-based fault-tolerant controller is proposed to achieve the asymptotic stability, without requiring a priori knowledge of the system dynamics. To deal with the prescribed performance, a new error transformation function is introduced to convert the constrained error dynamics into an equivalent unconstrained one. Under the actor-critic learning structure, a continuous-time long-term performance index is presented to evaluate the current control behavior. Then, a critic network is used to approximate the designed performance index and provide a reinforcement signal to the action network. Based on the robust integral of the sign of error feedback control method, an action network-based controller is developed. It is shown by the Lyapunov approach that the tracking error can converge to zero asymptotically with the prescribed performance guaranteed. Simulation results are provided to validate the feasibility and effectiveness of the proposed control scheme.

The underwater unmanned vehicle (UUV) is widely used in various marine operations, in which path planning and trajectory tracking are the critical technologies to achieve autonomous motion planning. Unlike previous research methods, this article proposes the asynchronous multithreading proximal policy optimization-based path planning (AMPPO-PP) and trajectory tracking (AMPPO-TT) algorithms and applies these two methods to different task scenarios of UUVs. Taking advantage of the AMPPO, the expensive online computational procedure is converted to an offline training process. The proposed algorithms enable the UUV to learn autonomous planning, tracking, and emergency obstacle avoiding. Besides, the algorithm architecture of the AMPPO-PP and the AMPPO-TT is described in detail. By refining the reward in each timestep and utilizing the reward-shaping trick, the reward sparsity is avoided. The goal-distance heuristic reward function is used to make the UUV explore more directionally. Various simulation environments are developed from simple to complex, along with multiple comparative experiments to verify the effectiveness of the proposed algorithms.

This article addresses the fixed-time average consensus problem of nonlinear multiagent systems (MASs) subject to input delay, external disturbances, and switching topologies. Different from the finite-time convergence, the convergence time of the fixed-time convergence is independent of initial conditions. Then, an event-based control strategy is presented to reach the fixed-time average consensus under switching topologies and intermittent communication. Because the nonlinear dynamics, external disturbances, switching topologies, and triggering condition for intermittent communication are considered, the fixed-time consensus problem is more challenging under the event-based control than under the continuous-time control. Besides, a new measurement error is designed based on the hyperbolic tangent function to avoid Zeno behavior. Furthermore, an improved triggering function is designed to avoid continuous monitoring. Hence, resource consumption is reduced significantly. Finally, the effectiveness of the algorithms is validated by three simulation examples.

This article considers the practical fixed-time self-triggered consensus tracking problem of delayed multiagent networks (MANs) subject to external disturbances under undirected topology and directed topology. The fixed-time consensus implies that the consensus is reached in a finite time and the convergence time is independent of initial conditions under the nonlinear consensus protocols. A self-triggered control (STC) strategy is developed based on the event-triggered control (ETC) strategy. For the ETC strategy, the nonlinear controllers and the measurement errors are designed based on the hyperbolic tangent function to avoid a nondifferential problem and Zeno behavior. To avoid continuous monitoring, the STC strategy is presented. Furthermore, the minimal interevent interval is strictly positive, which implies that no Zeno behavior occurs in the STC strategy. Finally, a numerical example is presented to verify the availability of the algorithms.

In this article, quadrotor unmanned aerial vehicles (QUAVs) are organized as a two-layer structure, where the first layer is leader QUAVs and the second layer is follower QUAVs. In this structure, only the leader QUAVs can receive the desired tracking information of position and attitude. Although the followers cannot obtain the given tracking information directly, they can obtain the corresponding information from leaders and other followers through the communication network based on the graph theory. In terms of this case, a distributed formation-containment (FC) control method is proposed to handle the related flight problems. We aim to develop a formation control for the leader QUAVs and a containment control for the follower QUAVs with the graph theory. Furthermore, a neural network (NN) technique is utilized to cope with the uncertainty of each QUAV. In order to guarantee good flight performance when tracking, the finite-time stability theorem is introduced into the control design to make each QUAV achieve satisfactory tacking performance in finite time. Finally, numerical simulations are conducted in the platform of two-layer 16 QUAVs to validate the feasibility and effectiveness of the proposed NN-based finite-time FC control.

In this article, an intelligent attacker is considered, which aims to prevent leader-following multiagent systems from achieving consensus. The attacker randomly injects denial-of-service (DoS) attacks to some communication channels in the network, which make the corresponding attacked edges disconnected. The minimum number of communication channels needed to be jammed by the attacker to guarantee the system fails to achieve the consensus is provided based on the Max-Flow Min-Cut lemma and an algorithm to generate the minimum attacked edges is proposed. Furthermore, a lower bound and an upper bound of the attack probability to destroy the consensusability of the system are provided, respectively. Finally, numerical simulations are given to illustrate the results.

This study investigates the consensus problem of a nonlinear discrete-time multi-agent system (MAS) under bounded additive disturbances. We propose a self-triggered robust distributed model predictive control consensus algorithm. A new cost function is constructed and MAS is coupled through this function. Based on the proposed cost function, a self-triggered mechanism is adopted to reduce the communication load. Furthermore, to overcome additive disturbances, a local minimum-maximum optimization problem under the worst-case scenario is solved iteratively by the model predictive controller of each agent. Sufficient conditions are provided to guarantee the iterative feasibility of the algorithm and the consensus of the closed-loop MAS. For each agent, we provide a concrete form of compatibility constraint and a consensus error terminal region. Numerical examples are provided to illustrate the effectiveness and correctness of the proposed algorithm.

In this paper, an observer-based adaptive prescribed performance tracking control scheme is developed for a class of uncertain multi-input multi-output nonlinear systems with or without input saturation. A novel finite-time neural network disturbance observer is constructed to estimate the system uncertainties and external disturbances. To guarantee the prescribed performance, an error transformation is applied to transfer the time-varying constraints into a constant constraint. Then, by employing a barrier Lyapunov function and the backstepping technique, an observer-based tracking control strategy is presented. It is proven that using the proposed algorithm, all the closed-loop signals are bounded, and the tracking errors satisfy the predefined time-varying performance requirements. Finally, simulation results on a quadrotor system are given to illustrate the effectiveness of the proposed control scheme.

Visual place recognition is one of the essential and challenging problems in the fields of robotics. In this letter, we for the first time explore the use of multi-modal fusion of semantic and visual modalities in dynamics-invariant space to improve place recognition in dynamic environments. We achieve this by first designing a novel deep learning architecture to generate the static semantic segmentation and recover the static image directly from the corresponding dynamic image. We then innovatively leverage the spatial-pyramid-matching model to encode the static semantic segmentation into feature vectors. In parallel, the static image is encoded using the popular Bag-of-words model. On the basis of the above multi-modal features, we finally measure the similarity between the query image and target landmark by the joint similarity of their semantic and visual codes. Extensive experiments demonstrate the effectiveness and robustness of the proposed approach for place recognition in dynamic environments.

This article addresses the team-triggered fixed-time consensus problems for a class of double-integrator agents subject to uncertain disturbance. Compared with the finite-time results, the convergence time of the fixed-time results is independent of the initial conditions. Furthermore, a novel team-triggered control (TTC) strategy is presented. This control strategy incorporates the event-triggered control (ETC) and self-triggered control (STC). The ETC and STC are proposed to achieve the fixed-time consensus of second-order multiagent systems (MASs), and no Zeno behavior occurs. The TTC scheme, derived by combining the ETC scheme and the STC scheme, is able to relax the requirement of continuous communication and thus lowering the energy consumption of communication while ensuring the performance of the system. The effectiveness of the proposed algorithms is validated by numerical simulations.

In this article, we investigate optimal transmission power allocation at a sensor equipped with the energy-harvesting technology for remote state estimation in wireless cyber-physical systems. The sensor has access to an energy harvester, which can collect energy from the external environment and is an everlasting but unreliable energy source compared with conventional batteries. For the wireless dropping communication channel, the packet dropout rates depend on both the signal-to-noise ratio and the transmission power used by the sensor. We formulate the problem of the optimal transmission power allocation to minimize the remote estimation error covariances as a Markov decision processes (MDPs) subject to energy constraint of the sensor. By analyzing the MDP algorithm, we show that an optimal deterministic and stationary transmission power policy exists. Moreover, we show that the optimal policy has a threshold-type structure. A numerical simulation is provided to illustrate the performance of the transmission power allocation algorithm.

In this article, the semiglobal cluster consensus problem is investigated for heterogeneous generic linear systems with input saturation. A general case in a leaderless framework is studied first, and then in order to broaden the scope of application, we consider a special case in which the leader nodes are pinned intermittently. To tackle the above problems, we propose a linear control scheme by using the low-gain feedback technique under the assumptions that each node is asymptotically null controllable and the underlying topology of each cluster (the extended cluster under the intermittent pinning control) has a directed spanning tree. The Lyapunov-based method and the low-gain feedback technique are developed for convergence analysis. It is shown that for both cases, the convergence rate is explicitly specified, which depends on the low-gain parameter and system matrices. Finally, two numerical examples are provided to verify the effectiveness of the theoretical findings.

In this article, we investigate a robust distributed model predictive control (DMPC) scheme for tracking the consensus of linear multiagent systems (MASs) subject to additive disturbances and time-varying communication delays. A terminal constraint set is constructed by the Lyapunov-Razumikhin functional, and a corresponding local controller is designed for each agent. Furthermore, the sufficient conditions ensure that the terminal constraint set is provided in the form of linear matrix inequalities (LMIs). The recursive feasibility of the proposed algorithm is guaranteed based on the designed terminal constraint set, terminal cost, and local controller. Moreover, the closed-loop system is shown to be input-to-state stable (ISS). An illustrative example is given to verify the effectiveness of the presented approach.

In this article, a solver-critic (SC) architecture is developed for optimal control problems of discrete-time (DT)-constrained-input systems. The proposed design consists of three parts: 1) a critic network; 2) an action solver; and 3) a target network. The critic network first approximates the action-value function using the sum-of-squares (SOS) polynomial. Then, the action solver adopts the SOS programming to obtain control inputs within the constraint set. The target network introduces the soft update mechanism into policy evaluation to stabilize the learning process. By using the proposed architecture, the constrained-input control problem can be solved without adding the nonquadratic functionals into the reward function. In this article, the theoretical analysis of the convergence property is presented. Besides, the effects of both different initial Q -functions and different discount factors are investigated. It is proven that the learned policy converges to the optimal solution of the Hamilton-Jacobi-Bellman equation. Four numerical examples are provided to validate the theoretical analysis and also demonstrate the effectiveness of our approach.

For the practical control system, the controller is normally implemented on a digital platform with a time-triggered scheme. This scheme maybe produces redundant control and resources wasting, and hence, an event-triggered scheme is gradually favored. In this article, the robust learning control scheme is proposed aiming at a class of disturbed control systems, in which the system information is processed by a novel dynamic event communication. First, the robust optimal control problem with external disturbances is redescribed as a zero-sum differential game, and with integral reinforcement learning, a model-independent weight tuning law is devised for a critic neural network. Then, in order to further reduce the computational burden, an additional dynamic variable is put forward to incorporate the past triggering information. The application of a single-link joint arm system demonstrates that the proposed scheme can guarantee learning performance and robust control effect, along with larger triggering intervals. Finally, the load frequency control problem of single-area power system is studied. On one hand, the comparative results of five control schemes reveal that the dynamic event scheme can achieve the better frequency response at the lowest information transmission rate. On the other hand, the advantages of the proposed method are illustrated by comparing with other three event-triggered schemes.

In this article, we investigate the privacy issue of the remote state estimation problem in cyber-physical systems. Specifically, in the presence of an eavesdropper, a sensor observes a discrete linear time-invariant process and then sends the measurements to a remote state estimator with arbitrary finite kinds of transmission options through an unreliable wireless channel. The transmission options of the sensor are in silence state or transmitting aided by injection noise with different energy levels. The eavesdropper wiretaps the channel when the sensor transmits packets to the estimator. Aiming at minimizing the remote estimation error and the cost of the sensors transmission energy while maximizing the eavesdropper state estimation error, we theoretically prove that there exist some structural properties for the optimal transmission schedule for both the known and the unknown eavesdropper's estimation errors. Numerical simulation results are provided to validate the theoretical analysis.

We aim at the optimization of the tracking control of a robot to improve the robustness, under the effect of unknown nonlinear perturbations. First, an auxiliary system is introduced, and optimal control of the auxiliary system can be seen as an approximate optimal control of the robot. Then, neural networks (NNs) are employed to approximate the solution of the Hamilton-Jacobi-Isaacs equation under the frame of adaptive dynamic programming. Next, based on the standard gradient attenuation algorithm and adaptive critic design, NNs are trained depending on the designed updating law with relaxing the requirement of initial stabilizing control. In light of the Lyapunov stability theory, all the error signals can be proved to be uniformly ultimately bounded. A series of simulation studies are carried out to show the effectiveness of the proposed control.

In this article, we study cooperative multiagent systems (MASs) with multiple tasks by using reinforcement learning (RL)-based algorithms. The target for a single-agent RL system is represented by its scalar reward signals. However, for an MAS with multiple cooperative tasks, the holistic reward signal consists of multiple parts to represent the tasks, which makes the problem complicated. Existing multiagent RL algorithms search distributed policies with holistic reward signals directly, making it difficult to obtain an optimal policy for each task. This article provides efficient learning-based algorithms such that each agent can learn a joint optimal policy to accomplish these multiple tasks cooperatively with other agents. The main idea of the algorithms is to decompose the holistic reward signal for each agent into multiple parts according to the subtasks, and then the proposed algorithms learn multiple value functions with the decomposed reward signals and update the policy with the sum of distributed value functions. In addition, this article presents a theoretical analysis of the proposed approach. Finally, the simulation results for both discrete decision-making and continuous control problems have demonstrated the effectiveness of the proposed algorithms.

In this article, a model-free online adaptive dynamic programming (ADP) approach is developed for solving the optimal control problem of nonaffine nonlinear systems. Combining the off-policy learning mechanism with the parallel paradigm, multithread agents are employed to collect the transitions by interacting with the environment that significantly augments the number of sampled data. On the other hand, each thread agent explores the environment with different initial states under its own behavior policy that enhances the exploration capability and alleviates the correlation between the sampled data. After the policy evaluation process, only one step update is required for policy improvement based on the policy gradient method. The stability of the system under iterative control laws is guaranteed. Moreover, the convergence analysis is given to prove that the iterative Q-function is monotonically nonincreasing and finally converges to the solution of the Hamilton-Jacobi-Bellman (HJB) equation. For implementing the algorithm, the actor-critic (AC) structure is utilized with two neural networks (NNs) to approximate the Q-function and the control policy. Finally, the effectiveness of the proposed algorithm is verified by two numerical examples.

This article proposes an adaptive neural network (NN) distributed control algorithm for a group of high-order nonlinear agents with nonidentical unknown control directions (UCDs) under signed time-varying topologies. An important lemma on the convergence property is first established for agents with antagonistic time-varying interactions, and then by using Nussbaum-type functions, a new class of NN distributed control algorithms is proposed. If the signed time-varying topologies are cut-balanced and uniformly in time structurally balanced, then convergence is achieved for a group of nonlinear agents. Moreover, the proposed algorithms are adopted to achieve the bipartite consensus of high-order nonlinear agents with nonidentical UCDs under signed graphs, which are uniformly quasi-strongly δ -connected. Finally, simulation examples are given to illustrate the effectiveness of the NN distributed control algorithms.

Matching and registration between aerial images and prestored road landmarks are critical techniques to enhance unmanned aerial system (UAS) navigation in the global positioning system (GPS)-denied urban environments. Current registration processes typically consist of two separate stages of road extraction and road registration. These two-stage registration approaches are time-consuming and less robust to noise. To that end, in this article, we, for the first time, investigate the problem of end-to-end Aerial-Road registration. Using deep learning, we develop a novel attention-based neural network architecture for Aerial-Road registration. In this model, we construct two-branch neural networks with shared weights to map two input images into a common embedding space. Besides, considering that road features are sparsely distributed in images, we incorporate a novel multibranch attention module to filter out false descriptor matches from the indiscriminative background in order to improve registration accuracy. Finally, the results from extensive experiments show that compared with state-of-the-art approaches, the mean absolute errors of our approach in rotation angle and the translations in the x - and y -directions are reduced down by a factor of 1.24, 1.38, and 1.44, respectively. Furthermore, as a byproduct, our experimental results prove the feasibility of a neural network multitask learning approach to simultaneously achieve accurate Aerial-Road matching and registration, thus providing an efficient and accurate UAS geolocalization.

This article presents a full mathematical proof of the characteristic modeling approach for high-order linear dynamical systems. It explores the nature of the characteristic model in rigorous mathematical forms, also showing why and how the high-order dynamics can be compressed into the lower-order characteristic model. The relationships between high-order linear continuous dynamical systems, discrete-time characteristic model coefficients, and sampling-time intervals are investigated.

In this paper, characteristic model-based modeling and control approaches for complex dynamical networks based on sampled data are studied. It shows that the characteristic model, in which underline network topological structures are simplified, can provide a straightforward and implicit description for network dynamics. The induced parameter estimation method can further make the model adaptive and purely data-driven. Moreover, a control law based on this model is also proposed to govern the network dynamics. Finally, the theoretical results are verified through numerical simulations of modeling and stabilizing a dynamical network.

This article proposes an economic model predictive algorithm for optimal load frequency control, in which both the frequency regulation and economic load dispatch (ELD) are considered, in interconnected power systems. Two-layer hierarchical control can be achieved through one level by EMPC. An economic stage cost function, including ELD and frequency regulation, which can be written in general convex form, is optimized by the controller. The distributed way is utilized to realize the control of large-scale power systems. Each subsystem-based controller works cooperatively with neighboring subsystems to achieve system-wide control performance. Asymptotic stability of the system is guaranteed by the proper terminal cost function. The efficiency and advantages of the proposed method are manifested by the simulation.

This article investigates the optimal control problem for nonlinear nonzero-sum differential game in the environment of no initial admissible policies while considering the control constraint. An adaptive learning algorithm is thus developed based on policy iteration technique to approximately obtain the Nash equilibrium using real-time data. A two-player continuous-time system is used to present this approximate mechanism, which is implemented as a critic-actor architecture for every player. The constraint is incorporated into this optimization by introducing the nonquadratic value function, and the associated constrained Hamilton-Jacobi equation is derived. The critic neural network (NN) and actor NN are utilized to learn the value function and the optimal control policy, respectively, in the light of novel weight tuning laws. In order to tackle the stability during the learning phase, two stable operators are designed for two actors. The proposed algorithm is proved to be convergent as a Newton's iteration, and the stability of this closed-loop system is also ensured by Lyapunov analysis. Finally, two simulation examples demonstrate the effectiveness of the proposed learning scheme by considering different constraint scenes.

Existing results for cooperative control of high-order agents mainly employ the Nussbaum-type function to cope with unknown control directions and mostly require an assumption that the control directions are identical and unknown. This paper proposes a class of algorithms with nonlinear PI functions to relax such an assumption and make them suitable for nonidentical unknown control directions. It is proven that if the distributed nonlinear PI functions are suitably selected, the proposed algorithms can achieve consensus for high-order agents under strongly connected topologies and switching topologies with a jointly strongly connected basis (JSCB). Furthermore, we extend the consensus results to the case of time-varying topologies described by δ-connected, continuous graphs. As a special case, the consensus of high-order agents under the directed graph having a spanning tree is also investigated. Finally, illustrative simulations are presented to indicate the efficiency of the proposed algorithms.

By using the terminal sliding-mode control (TSMC) and the pinning control methods, the fully distributed finite-time consensus problems are investigated for second-order multiagent systems (MASs) and multiquadcopter systems (MQSs) with directed topology. For the second-order MASs, a pinning control scheme is designed by analyzing the outdegree and indegree of nodes, and a TSMC protocol with the local information is proposed to achieve the finite-time consensus. Then, as an application of the MASs, the model of MQSs is constructed and its finite-time attitude consensus is discussed. Finally, the effectiveness of the proposed method is validated by two numerical examples.

In recent years, visual question answering (VQA) has become topical. The premise of VQA's significance as a benchmark in AI, is that both the image and textual question need to be well understood and mutually grounded in order to infer the correct answer. However, current VQA models perhaps 'understand' less than initially hoped, and instead master the easier task of exploiting cues given away in the question and biases in the answer distribution [1]. In this paper we propose the inverse problem of VQA (iVQA). The iVQA task is to generate a question that corresponds to a given image and answer pair. We propose a variational iVQA model that can generate diverse, grammatically correct and content correlated questions that match the given answer. Based on this model, we show that iVQA is an interesting benchmark for visuo-linguistic understanding, and a more challenging alternative to VQA because an iVQA model needs to understand the image better to be successful. As a second contribution, we show how to use iVQA in a novel reinforcement learning framework to diagnose any existing VQA model by way of exposing its belief set: the set of question-answer pairs that the VQA model would predict true for a given image. This provides a completely new window into what VQA models 'believe' about images. We show that existing VQA models have more erroneous beliefs than previously thought, revealing their intrinsic weaknesses. Suggestions are then made on how to address these weaknesses going forward.

In this paper, we investigate the adaptive cooperative control problem with guaranteed convergence for a class of nonlinear multiagent systems with unknown control directions and time-varying topologies. A key lemma is first derived which involves dynamically changing interaction topologies, and then a new kind of distributed control algorithms with Nussbaum-type functions are proposed based on this lemma. It is proven that if the topologies are time varying with integral weight uniform upper bound and reciprocity, then convergence is guaranteed with the proposed algorithms for nonlinear multiagent systems with nonidentical unknown control directions. An important feature of this paper is that, under time-varying topologies, the designed algorithms can deal with nonidentical unknown control directions by using classical Nussbaum-type functions. Moreover, with the proposed algorithms, we extend the adaptive cooperative control results to the case of δ -connected graphs. In particular, the adaptive leaderless consensus of high-order nonlinear agents with nonidentical unknown control directions and a directed graph having a spanning tree is also tackled as a special case. Finally, theoretical results are illustrated by a group of Genesio-Tesi systems with distributed control algorithms under time-varying topologies and some special network topologies.

Differential games have been extensively applied to optimal control problems. Nash equilibrium captures the tradeoff among players' policies when every player independently tries to minimize a predefined index. When considering potential cooperation, Pareto equilibrium plays an important role in cooperative differential games. This article studies the cooperative control of multiplayer systems on the quadratic infinite horizon. First, by defining a joint cost function using a parameter set, a cooperative differential game is reformulated as a general optimal control problem, where all players form a grand coalition. Then, the joint cost function is approximated by a critic neural network, and for the first time, a novel adaptive dynamic programming algorithm with two learning stages is proposed to determine the parameter selection and then obtain Pareto optimal solutions. A numerical example demonstrates that this algorithm can achieve optimal policies and Pareto frontier. As for its application, the cooperative control of a two-area interconnected power system is investigated, where the primary frequency control and secondary frequency control are regarded as two players. Simulation results indicate that the proposed scheme can obtain binding cooperation agreements, such that cooperative control scheme can get better overall performance compared to Nash control method and another three control methods.

Conventional multi-view re-ranking methods usually perform asymmetrical matching between the region of interest (ROI) in the query image and the whole target image for similarity computation. Due to the inconsistency in the visual appearance, this practice tends to degrade the retrieval accuracy particularly when the image ROI, which is usually interpreted as the image objectness, accounts for a smaller region in the image. Since Privileged Information (PI), which can be viewed as the image prior, is able to characterize well the image objectness, we are aiming at leveraging PI for further improving the performance of multi-view re-ranking in this paper. Towards this end, we propose a discriminative multi-view re-ranking approach in which both the original global image visual contents and the local auxiliary PI features are simultaneously integrated into a unified training framework for generating the latent subspaces with sufficient discriminating power. For the on-the-fly re-ranking, since the multi-view PI features are unavailable, we only project the original multi-view image representations onto the latent subspace, and thus the re-ranking can be achieved by computing and sorting the distances from the multi-view embeddings to the separating hyperplane. Extensive experimental evaluations on the two public benchmarks, Oxford5k and Paris6k, reveal that our approach provides further performance boost for accurate image re-ranking, whilst the comparative study demonstrates the advantage of our method against other multi-view re-ranking methods.

This brief addresses the fixed-time event/self-triggered leader-follower consensus problems for networked multi-agent systems subject to nonlinear dynamics. First, we present an event-triggered control strategy to achieve the fixed-time consensus, and a new measurement error is designed to avoid Zeno behavior. Then, two new self-triggered control strategies are presented to avoid continuous triggering condition monitoring. Moreover, under the proposed self-triggered control strategies, a strictly positive minimal triggering interval of each follower is given to exclude Zeno behavior. Compared with the existing fixed-time event-triggered results, we propose two new self-triggered control strategies, and the nonlinear term is more general. Finally, the performances of the consensus tracking algorithms are illustrated by a simulation example.

In this paper, an approximately optimal control strategy is developed for the tracking control of a class of continuous-time nonlinear systems with unmatched uncertainties. By transforming the unmatched uncertain term, the auxiliary system associated with the uncertain nonlinear system is established. The auxiliary system is divided into steady and transient parts, and the related controllers are separately solved, meanwhile the transient tracking error system is also obtained by introducing the reference system. A neural network-based adaptive dynamic programming method is used to get the approximately optimal tracking control law of uncertain nonlinear systems with a predefined cost function. Furthermore, the ultimately uniform boundedness of neural network weights and the stability of tracking error systems are both proved through Lyapunov theory. Two cases of nonlinear systems with unmatched uncertainties are investigated to illustrate the effectiveness of the proposed robust tracking control strategy.

This paper solves the adaptive consensus problem for first-order linearly parameterized agents with completely nonidentical unknown high-frequency gain signs under directed graphs. A new class of Nussbaum-type function-based algorithms are proposed to handle the unknown high-frequency gain signs adaptively and cooperatively. It is shown that if the underlying topology is a fixed graph with strongly connected or switching topologies having a jointly strongly connected basis, the first-order linearly parameterized agents with nonidentical unknown high-frequency gain signs can achieve asymptotic consensus. Finally, the effectiveness of proposed algorithms are verified by one simulation example.

In this paper, a deep reinforcement learning-based robust control strategy for quadrotor helicopters is proposed. The quadrotor is controlled by a learned neural network which directly maps the system states to control commands in an end-to-end style. The learning algorithm is developed based on the deterministic policy gradient algorithm. By introducing an integral compensator to the actor-critic structure, the tracking accuracy and robustness have been greatly enhanced. Moreover, a two-phase learning protocol which includes both offline and online learning phase is proposed for practical implementation. An offline policy is first learned based on a simplified quadrotor model. Then, the policy is online optimized in actual flight. The proposed approach is evaluated in the flight simulator. The results demonstrate that the offline learned policy is highly robust to model errors and external disturbances. It also shows that the online learning could significantly improve the control performance.

This work considers the design of online transmission policy in a wireless-powered communication system with a given energy budget. The system design objective is to maximize the long-term throughput of the system exploiting the energy storage capability at the wireless-powered node. We formulate the design problem as a constrained Markov decision process (CMDP) problem and obtain the optimal policy of transmit power and time allocation in each fading block via the Lagrangian approach. To investigate the system performance in different scenarios, numerical simulations are conducted with various system parameters. Our simulation results show that the optimal policy significantly outperforms a myopic policy which only maximizes the throughput in the current fading block. Moreover, the optimal allocation of transmit power and time is shown to be insensitive to the change of modulation and coding schemes, which facilitates its practical implementation.

WirelessHART is one of the most widely used communication standards in industrial wireless networks. In order to meet the stringent real-time requirements in industrial applications, WirelessHART incorporates many designs including the time slotted channel hopping mechanism that enables dynamic time scheduling and channel allocation. In this paper, we study the problem of joint transmission scheduling and channel allocation aiming to minimize the end-to-end delay of multiple flows in multihop WirelessHART networks. We propose a new network model based on a multidimensional scheduling space spanned by flow-link-channel-slot tuples. A multidimensional conflict graph is then established to depict the conflict relationships among the tuples. Based on this, the original delay minimization problem is formulated as an integer program, which however is difficult to solve due to its significantly large scale. To this end, we develop an iterative hop-wise scheduling algorithm by transforming the original problem into a series of maximum weighted independent set problems. We derive theoretical analysis on the schedulability and the performance bound of the proposed algorithm. In addition, we show that our results can be easily extended to accommodate more general scenarios. Finally, extensive simulation results are provided to demonstrate the effectiveness of the algorithm.

This paper presents a functional model predictive control (MPC) approach based on an adaptive dynamic programming (ADP) algorithm with the abilities of handling control constraints and disturbances for the optimal control of nonlinear discrete-time systems. In the proposed ADP-based nonlinear MPC (NMPC) structure, a neural-network-based identification is established first to reconstruct the unknown system dynamics. Then, the actor-critic scheme is adopted with a critic network to estimate the index performance function and an action network to approximate the optimal control input. Meanwhile, as the MPC strategy can effectively determine the current control by solving a finite horizon open-loop optimal control problem, in the proposed algorithm, the infinite horizon is decomposed into a series of finite horizons to obtain the optimal control. In each finite horizon, the finite ADP algorithm solves the optimal control problem subject to the terminal constraint, the control constraint, and the disturbance. The uniform ultimate boundedness of the closed-loop system is verified by the Lyapunov approach. Finally, the ADP-based NMPC is conducted on two different cases and the simulation results demonstrate the quick response and strong robustness of the proposed method.

This paper addresses a flexible micro aerial vehicle (MAV) under spatiotemporally varying disturbances, which is composed of a rigid body and two flexible wings. Based on Hamilton's principle, a distributed parameter system coupling in bending and twisting, is modeled. Two iterative learning control (ILC) schemes are designed to suppress the vibrations in bending and twisting, reject the distributed disturbances and regulate the displacement of the rigid body to track a prescribed constant trajectory. At the basis of composite energy function, the boundedness and the learning convergence are proved for the closed-loop MAV system. Simulation results are provided to illustrate the effectiveness of the proposed ILC laws.

In this paper, we investigate fuzzy neural network (FNN) control using impedance learning for coordinated multiple constrained robots carrying a common object in the presence of the unknown robotic dynamics and the unknown environment with which the robot comes into contact. First, an FNN learning algorithm is developed to identify the unknown plant model. Second, impedance learning is introduced to regulate the control input in order to improve the environment-robot interaction, and the robot can track the desired trajectory generated by impedance learning. Third, in light of the condition requiring the robot to move in a finite space or to move at a limited velocity in a finite space, the algorithm based on the position constraint and the velocity constraint are proposed, respectively. To guarantee the position constraint and the velocity constraint, an integral barrier Lyapunov function is introduced to avoid the violation of the constraint. According to Lyapunov's stability theory, it can be proved that the tracking errors are uniformly bounded ultimately. At last, some simulation examples are carried out to verify the effectiveness of the designed control.

Fuzzy support vector machine (FSVM) has been combined with class imbalance learning (CIL) strategies to address the problem of classifying skewed data. However, the existing approaches hold several inherent drawbacks, causing the inaccurate prior data distribution estimation, further decreasing the quality of the classification model. To solve this problem, we present a more robust prior data distribution information extraction method named relative density, and two novel FSVM-CIL algorithms based on the relative density information in this paper. In our proposed algorithms, a K-nearest neighbors-based probability density estimation (KNN-PDE) alike strategy is utilized to calculate the relative density of each training instance. In particular, the relative density is irrelevant with the dimensionality of data distribution in feature space, but only reflects the significance of each instance within its class; hence, it is more robust than the absolute distance information. In addition, the relative density can better seize the prior data distribution information, no matter the data distribution is easy or complex. Even for the data with small injunctions or a large class overlap, the relative density information can reflect its details well. We evaluated the proposed algorithms on an amount of synthetic and real-world imbalanced datasets. The results show that our proposed algorithms obviously outperform to some previous work, especially on those datasets with sophisticated distributions.

In this paper, the n-dimensional discretized model of the two-link flexible manipulator is developed by the assumed mode method (AMM). Subsequently, based on the discretized dynamic model, both full-state feedback control and output feedback control are investigated to achieve the trajectory tracking and vibration suppression. In order to guarantee the stability strictly, uniform ultimate boundedness (UUB) of the closed-loop system is realized by the Lyapunov's stability. Furthermore, through appropriately choosing control parameters, the states of the system will converge to zero within a small neighborhood. Eventually, extensive simulations and experiments on the Quanser platform for a two-link robotic manipulator are carried out to demonstrate the feasibility of the proposed neural network controller.

In multi-view re-ranking, multiple heterogeneous visual features are usually projected onto a low-dimensional subspace, and thus the resulting latent representation can be used for the subsequent similarity-based ranking. Albeit effective, this standard mechanism underplays the intrinsic structure underlying the latent subspace and does not take into account the substantial noise in the original spaces. In this paper, we propose a robust multi-view image re-ranking strategy. Due to the dramatic variability in image visual appearance, it is necessary to uncover the shared components underlying those query-related instances that are visually unlike for improving the re-ranking accuracy. Consequently, it is reasonable to assume the latent subspace enjoys the low-rank property and thus the subspace recovery can be achieved via the low-rank modeling accordingly. In addition, since the real-world data are usually partially contaminated, we employ `2;1-norm based sparsity constraint to appropriately model the sample-specific mapping noise for enhancing the model robustness. In order to produce discriminative representations, we encode a similarity preserving term in our multi-view embedding framework. As a result, the sample separability is maximally maintained in the latent subspace with sufficient discriminative power. The extensive evaluations on public landmark benchmarks demonstrate the efficacy and superiority of the proposed method.

It is well known that active learning can simultaneously improve the quality of the classification model and decrease the complexity of training instances. However, several previous studies have indicated that the performance of active learning is easily disrupted by an imbalanced data distribution. Some existing imbalanced active learning approaches also suffer from either low performance or high time consumption. To address these problems, this paper describes an efficient solution based on the extreme learning machine (ELM) classification model, called active online-weighted ELM (AOW-ELM). The main contributions of this paper include: 1) the reasons why active learning can be disrupted by an imbalanced instance distribution and its influencing factors are discussed in detail; 2) the hierarchical clustering technique is adopted to select initially labeled instances in order to avoid the missed cluster effect and cold start phenomenon as much as possible; 3) the weighted ELM (WELM) is selected as the base classifier to guarantee the impartiality of instance selection in the procedure of active learning, and an efficient online updated mode of WELM is deduced in theory; and 4) an early stopping criterion that is similar to but more flexible than the margin exhaustion criterion is presented. The experimental results on 32 binary-class data sets with different imbalance ratios demonstrate that the proposed AOW-ELM algorithm is more effective and efficient than several state-of-the-art active learning algorithms that are specifically designed for the class imbalance scenario.

In this paper, we study the fixed-time event-triggered consensus problem of the uncertain nonlinear multiagent systems. Two fixed-time event-triggered consensus controllers are proposed. In contrast to finite-time results, the convergence time of fixed-time results is independent of initial conditions. Furthermore, continuous communications can be avoided both in the update of controllers and in the triggering condition monitoring. It is proved that there is no Zeno behavior under the fixed-time event-triggered consensus control strategies. The availability of the control algorithms is verified by numerical simulations.

In this paper, an adaptive fuzzy neural network (FNN) control scheme is developed for a class of multipleinput and multiple-output (MIMO) nonlinear systems subject to unknown dynamics and state constraints. FNNs are used to approximate the unknown dynamics that comprises the effects of uncertain parameters and functions. Also, integral Lyapunov functions are introduced to address state constraints. A neuralnetwork-based observer is designed to estimate the unmeasurable states. With state-feedback and output feedback tracking control, the stability of closed-loop system is guaranteed via Lyapunov's stability theory. Two cases of simulations for MIMO systems with state constraints are conducted to verify the effectiveness of the proposed control.

In this paper, vibration control and output constraint are considered for a Timoshenko beam system with input backlash and external disturbances. By integrating iterative learning control (ILC) into adaptive control, two dual-loop adaptive ILC schemes are proposed in the presence of the input backlash. Two observers are designed to estimate two bounded terms, which are divided from the backlash inputs. Based on the defined barrier composite energy function, all the signals are proved to be bounded in each iteration. Along the iteration axis: 1) the endpoint transverse displacements and the endpoint angle displacements are restrained; 2) the transverse vibrations and the rotation vibrations are suppressed to zero; and 3) the spatiotemporally varying disturbance and the time-varying disturbances are rejected. Simulations are provided to manifest the effectiveness of the proposed control laws.

In this paper, we consider the design of online transmission policies in a single-user wireless-powered communication system over an infinite horizon, aiming at maximizing the long-term system throughput for the user equipment (UE) subject to a given energy budget. The problem is formulated as a constrained Markov decision process problem, which is subsequently converted into an equivalent Markov decision process (MDP) problem via the Lagrangian approach. The corresponding optimal resource allocation policy is obtained through jointly solving the corresponding MDP problem and updating the Lagrangian multiplier. To reduce the complexity, a sub-optimal policy named “quasi-best-effort” is proposed, where the transmit power of the UE is structurally designed so that in each block the UE either exhausts its entire battery energy for transmission or suspends its transmission. To validate the effectiveness of our proposed policy, extensive numerical simulations are conducted with various system parameters. The results show that the proposed quasi-best-effort policy requires far less computation time but achieves a similar long-term throughput performance as the optimal policy.

We propose the inverse problem of Visual question answering (iVQA), and explore its suitability as a benchmark for visuo-linguistic understanding. The iVQA task is to generate a question that corresponds to a given image and answer pair. Since the answers are less informative than the questions, and the questions have less learnable bias, an iVQA model needs to better understand the image to be successful than a VQA model. We pose question generation as a multi-modal dynamic inference process and propose an iVQA model that can gradually adjust its focus of attention guided by both a partially generated question and the answer. For evaluation, apart from existing linguistic metrics, we propose a new ranking metric. This metric compares the ground truth question's rank among a list of distractors, which allows the drawbacks of different algorithms and sources of error to be studied. Experimental results show that our model can generate diverse, grammatically correct and content correlated questions that match the given answer.

The problem of optimal resource allocation in wireless networks usually involves scheduling of the network independent sets (ISs), of which the number increases exponentially in the network scale. To deal with such large-scale optimization problems, traditional approaches often resort to some heuristics or iterative algorithms for obtaining a relatively small set of ISs to solve the problems, but at the cost of suboptimality or long convergence time. In this paper, we consider wireless network resource allocation in dynamic flow environments, aiming at maximizing the network capacity. We propose a learning-based approach to find ISs based on the dynamic flow demands. Specifically, instead of searching for individual ISs, we propose to learn groups of ISs by using a deep belief network (DBN). We present detailed design of the DBN-based learning method including details in the offline training and online running phases. Simulation results demonstrate that our DBN-based method outperforms existing ones in terms of achieved network capacity and computation time.

This paper deals with the state estimation fusion problem for stochastic continuous-time systems over wireless sensor networks (WSNs) with multi-sensor scheduling. Due to the power limitation and communication constraints in WSNs, a closed-loop stochastic event-triggered mechanism is designed to reduce the redundant data transmission. Since this design preserves the Gaussian property of the conditional distribution of the system state, an exact minimum mean square error (MMSE) estimator could be presented for every sensor subsystem. Then, the distributed event-triggered information fusion estimator is proposed based on maximum a posterior probability criterion by a matrix-weighted combination of all available local estimates from sensor subsystems. The proposed distributed algorithm has advantages on reliability, computation efficiency due to the netted parallel structure. A numerical simulation is conducted to illustrate the effectiveness of the proposed distributed estimator.

The performance of wireless remote state estimation depends on the wireless channel quality, and hence is vulnerable to wireless channel jamming attack. In this paper, we investigate the problem of optimal jamming attack schedule that causes the largest performance degradation to the remote state estimation system. Unlike many previous studies, we consider that the sensor transmit data to the remote estimator through one of multiple independent wireless channels. Due to radio constraint of the attacker, we assume that it can only launch jamming attack on one of the channels at each step. We propose a matrix game approach to model the interactions between the attacker and the sensor and theoretically prove the existence of an optimal attack strategy. We further design an online algorithm based on temporal-difference learning for the attacker to make attack decisions. Numerical examples are provided to demonstrate the effectiveness of the game theoretical method.

Wireless network resource allocation is an important issue for designing Internet of Things systems. In this paper, we consider the problem of wireless network capacity optimization that involves issues such as flow allocation, link scheduling, and power control. We show that it can be decomposed into a linear program and a nonlinear weighted sum-rate maximization problem for power allocation. Unlike most traditional methods that iteratively search the optimal solutions of the nonlinear subproblem, we propose to directly compute approximated solutions based on machine learning techniques. Specifically, the learning systems consist of both support vector machines (SVMs) and deep belief networks (DBNs) that are trained based on offline computed optimal solutions. In the running phase, the SVMs perform classification for each link to decide whether to use maximal transmit power or be turned off. At the same time, the DBNs compute an approximation of the optimal power allocation. The two results are combined to obtain an approximated solution of the nonlinear program. Simulation results demonstrate the effectiveness of the proposed machine learning-based algorithm.

In this paper, we propose an end-to-end modular reinforcement learning architecture for a navigation task in complex dynamic environments with rapidly moving obstacles. In this architecture, the main task is divided into two subtasks: local obstacle avoidance and global navigation. For obstacle avoidance, we develop a two-stream Q-network, which processes spatial and temporal information separately and generates action values. The global navigation subtask is resolved by a conventional Q-network framework. An online learning network and an action scheduler are introduced to first combine two pretrained policies, and then continue exploring and optimizing until a stable policy is obtained. The two-stream Q-network obtains better performance than the conventional deep Q-learning approach in the obstacle avoidance subtask. Experiments on the main task demonstrate that the proposed architecture can efficiently avoid moving obstacles and complete the navigation task at a high success rate. The modular architecture enables parallel training and also demonstrates good generalization capability in different environments.

Crowd counting is an important task in computer vision, which has many applications in video surveillance. Although the regression-based framework has achieved great improvements for crowd counting, how to improve the discriminative power of image representation is still an open problem. Conventional holistic features used in crowd counting often fail to capture semantic attributes and spatial cues of the image. In this paper, we propose integrating semantic information into learning locality-aware feature (LAF) sets for accurate crowd counting. First, with the help of a convolutional neural network, the original pixel space is mapped onto a dense attribute feature map, where each dimension of the pixelwise feature indicates the probabilistic strength of a certain semantic class. Then, LAF built on the idea of spatial pyramids on neighboring patches is proposed to explore more spatial context and local information. Finally, the traditional vector of locally aggregated descriptor (VLAD) encoding method is extended to a more generalized form weighted-VLAD (W-VLAD) in which diverse coefficient weights are taken into consideration. Experimental results validate the effectiveness of our presented method.

In this paper, we study the control problems of distributed parameter systems, and discuss the limitations of traditional control methods. In recent years, social factors have gradually become an essential parameter of system modeling. For complex distributed parameter systems, the accurate modeling becomes difficult. With the rapid development of the network and the technology of big data and cloud computing, based on the advanced control theory of large-scale computing, we introduce the idea of parallel control to the control of distributed parameter systems. Parallel control is a method to accomplish tasks through the interaction of virtual and actual. Its core is to model the complex distributed parameter system on artificial society or artificial system, then analyze and evaluate it by computational experiment, and finally control and manage the distributed parameter system by parallel execution. Data-driven control and computational control are used in this method, which is a control idea that adapts to the rapid development of society.

A six-degrees-of-freedom integrated adaptive fuzzy nonlinear control method is presented in this paper for uncertain spacecraft proximity systems subject to unknown model uncertainties and complex kinematic couplings. Adaptive fuzzy logic systems are developed to approximate the unknown nonlinear functions, and an adaptive fuzzy backstepping relative pose controller is designed. To overcome the drawback of “curse of dimensionality” in adaptive fuzzy systems for multiple variable systems, all of the parameters in membership functions are updated to reduce the amount of fuzzy rules and computational burden. It is proven via Lyapunov theory that the proposed adaptive fuzzy nonlinear controller ensures the boundedness of all signals in overall system, and the relative motion information ultimately converges to adjustable small neighborhoods of zero. A computer experiment with numerical example is carried out to demonstrate the performance of the proposed control approach.

Nowadays, the control technology of the robotic manipulator with flexible joints (RMFJ) is not mature enough. The flexible-joint manipulator dynamic system possesses many uncertainties, which brings a great challenge to the controller design. This paper is motivated by this problem. In order to deal with this and enhance the system robustness, the full-state feedback neural network (NN) control is proposed. Moreover, output constraints of the RMFJ are achieved, which improve the security of the robot. Through the Lyapunov stability analysis, we identify that the proposed controller can guarantee not only the stability of flexible-joint manipulator system but also the boundedness of system state variables by choosing appropriate control gains. Then, we make some necessary simulation experiments to verify the rationality of our controllers. Finally, a series of control experiments are conducted on the Baxter. By comparing with the proportional-derivative control and the NN control with the rigid manipulator model, the feasibility and the effectiveness of NN control based on flexible-joint manipulator model are verified.

In this paper, in order to analyze the single-link flexible structure, the assumed mode method is employed to develop the dynamic model. Based on the discrete dynamic model, fuzzy neural network (NN) control is investigated to track the desired trajectory accurately and to suppress the flexible vibration maximally. To ensure the stability rigorously as the goal, the system is proved to be uniform ultimate boundedness by Lyapunov's stability method. Eventually, simulations verify that the proposed control strategy is effective, and the control performance is compared with the proportion derivative control. The experiments are implemented on the Quanser platform to further demonstrate the feasibility of the proposed fuzzy NN control.

This paper proposes a sampled data-based modeling approach for complex network systems. A compression method, known as characteristic modeling, is used to construct microscopic models from macroscopic observations. Based on this model, a novel control method is also developed to achieve network synchronization. The proposed approach can reduce both the complexity of microscopic dynamics and overall networks. Its application to pinning control design validates the effectiveness of this approach.

This paper mainly regulates a flexible wing of a micro aerial vehicle to track two spatiotemporally varying trajectories. By utilizing Lyapunov's direct method, two boundary control laws are designed to guarantee uniform boundedness of the closed-loop target system along the time axis. Based on Schur complement lemma, nonlinear inequalities derived from the theoretical deduction are rewritten as matrixes, which are solved through the LMI toolbox in MATLAB. In addition, the tracking control problem is formulated as an optimization problem. The simulation examples are conducted to prove the effectiveness of the proposed boundary control laws.

This paper considers a robust optimal control design for a class of nonlinear discrete-time systems with unknown time-varying delays and dynamic uncertainties. An iterative control strategy based on adaptive dynamic programming (ADP) has been proposed. Neural networks are applied to realize the state prediction, the control input estimation and the performance index function approximation. The estimated control input and performance index function are updated iteratively. Furthermore, it has been proven that the approximated performance index function can converge to the optimal solution of the Hamilton-Jacobia-Bellman (HJB) equation. Finally, the proposed algorithm has been conducted to a numerical simulation. The simulation results demonstrate the effectiveness of the new design.

In this paper, we consider the trajectory tracking of a marine surface vessel in the presence of output constraints and uncertainties. An asymmetric barrier Lyapunov function is employed to cope with the output constraints. To handle the system uncertainties, we apply adaptive neural networks to approximate the unknown model parameters of a vessel. Both full state feedback control and output feedback control are proposed in this paper. The state feedback control law is designed by using the Moore-Penrose pseudoinverse in case that all states are known, and the output feedback control is designed using a high-gain observer. Under the proposed method the controller is able to achieve the constrained output. Meanwhile, the signals of the closed loop system are semiglobally uniformly bounded. Finally, numerical simulations are carried out to verify the feasibility of the proposed controller.

The research of this paper works out the attitude and position control of the flapping wing micro aerial vehicle (FWMAV). Neural network control with full state and output feedback are designed to deal with uncertainties in this complex nonlinear FWMAV dynamic system and enhance the system robustness. Meanwhile, we design disturbance observers which are exerted into the FWMAV system via feedforward loops to counteract the bad influence of disturbances. Then, a Lyapunov function is proposed to prove the closed-loop system stability and the semi-global uniform ultimate boundedness of all state variables. Finally, a series of simulation results indicate that proposed controllers can track desired trajectories well via selecting appropriate control gains. And the designed controllers possess potential applications in FWMAVs.

A data-driven adaptive tracking control approach is proposed for a class of continuous-time nonlinear systems using a recent developed goal representation heuristic dynamic programming (GrHDP) architecture. The major focus of this paper is on designing a multivariable tracking scheme, including the filter-based action network (FAN) architecture, and the stability analysis in continuous-time fashion. In this design, the FAN is used to observe the system function, and then generates the corresponding control action together with the reference signals. The goal network will provide an internal reward signal adaptively based on the current system states and the control action. This internal reward signal is assigned as the input for the critic network, which approximates the cost function over time. We demonstrate its improved tracking performance in comparison with the existing heuristic dynamic programming (HDP) approach under the same parameter and environment settings. The simulation results of the multivariable tracking control on two examples have been presented to show that the proposed scheme can achieve better control in terms of learning speed and overall performance.

Given an unreliable visual patterns and insufficient query information, content-based image retrieval is often suboptimal and requires image re-ranking using auxiliary information. In this paper, we propose a discriminative multi-view interactive image re-ranking (DMINTIR), which integrates user relevance feedback capturing users' intentions and multiple features that sufficiently describe the images. In DMINTIR, heterogeneous property features are incorporated in the multi-view learning scheme to exploit their complementarities. In addition, a discriminatively learned weight vector is obtained to reassign updated scores and target images for re-ranking. Compared with other multi-view learning techniques, our scheme not only generates a compact representation in the latent space from the redundant multi-view features but also maximally preserves the discriminative information in feature encoding by the large-margin principle. Furthermore, the generalization error bound of the proposed algorithm is theoretically analyzed and shown to be improved by the interactions between the latent space and discriminant function learning. Experimental results on two benchmark data sets demonstrate that our approach boosts baseline retrieval quality and is competitive with the other state-of-the-art re-ranking strategies.

This paper presents the design of a novel adaptive event-triggered control method based on the heuristic dynamic programming (HDP) technique for nonlinear discrete-time systems with unknown system dynamics. In the proposed method, the control law is only updated when the event-triggered condition is violated. Compared with the periodic updates in the traditional adaptive dynamic programming (ADP) control, the proposed method can reduce the computation and transmission cost. An actor-critic framework is used to learn the optimal event-triggered control law and the value function. Furthermore, a model network is designed to estimate the system state vector. The main contribution of this paper is to design a new trigger threshold for discrete-time systems. A detailed Lyapunov stability analysis shows that our proposed event-triggered controller can asymptotically stabilize the discrete-time systems. Finally, we test our method on two different discrete-time systems, and the simulation results are included.

In this paper, an event-triggered near optimal control structure is developed for nonlinear continuous-time systems with control constraints. Due to the saturating actuators, a nonquadratic cost function is introduced and the Hamilton-Jacobi-Bellman (HJB) equation for constrained nonlinear continuous-time systems is formulated. In order to solve the HJB equation, an actor-critic framework is presented. The critic network is used to approximate the cost function and the action network is used to estimate the optimal control law. In addition, in the proposed method, the control signal is transmitted in an aperiodic manner to reduce the computational and the transmission cost. Both the networks are only updated at the trigger instants decided by the event-triggered condition. Detailed Lyapunov analysis is provided to guarantee that the closed-loop event-triggered system is ultimately bounded. Three case studies are used to demonstrate the effectiveness of the proposed method.

In this paper, we propose a data-driven supplementary control approach with adaptive learning capability for air-breathing hypersonic vehicle tracking control based on action-dependent heuristic dynamic programming (ADHDP). The control action is generated by the combination of sliding mode control (SMC) and the ADHDP controller to track the desired velocity and the desired altitude. In particular, the ADHDP controller observes the differences between the actual velocity/altitude and the desired velocity/altitude, and then provides a supplementary control action accordingly. The ADHDP controller does not rely on the accurate mathematical model function and is data driven. Meanwhile, it is capable to adjust its parameters online over time under various working conditions, which is very suitable for hypersonic vehicle system with parameter uncertainties and disturbances. We verify the adaptive supplementary control approach versus the traditional SMC in the cruising flight, and provide three simulation studies to illustrate the improved performance with the proposed approach.

In this paper, model identification and adaptive control design are performed on Devanit-Hartenberg model of a humanoid robot. We focus on the modeling of the 6 degree-of-freedom upper limb of the robot using recursive Newton-Euler (RNE) formula for the coordinate frame of each joint. To obtain sufficient excitation for modeling of the robot, the particle swarm optimization method has been employed to optimize the trajectory of each joint, such that satisfied parameter estimation can be obtained. In addition, the estimated inertia parameters are taken as the initial values for the RNE-based adaptive control design to achieve improved tracking performance. Simulation studies have been carried out to verify the result of the identification algorithm and to illustrate the effectiveness of the control design.

In this paper, neural network control strategies based on radial basis functions are designed for biped robots, which includes balancing and posture control. To deal with system uncertainties, neural networks are used to approximate the unknown model of the robot. Both full state feedback control and output feedback control are considered in this paper. With the proposed control, the trajectories of the closed-loop system are semiglobally uniformly bounded which can be proved via Lyapunov stability theorem. Simulations are also carried out to illustrate the effectiveness of the proposed control.

Adaptive neural networks (NNs) are employed for control design to suppress vibrations of a flexible robotic manipulator. To improve the accuracy in describing the elastic deflection of the flexible manipulator, the system is modeled via the lumped spring-mass approach. Full-state feedback control as well as output feedback control are proposed separately. Aiming at achieving the control objective, uniform ultimate boundedness of the closed-loop system is ensured. Numerical simulations for the lumped model of the flexible robotic system are carried out to verify the performance of the NN control. Finally, the experiments are given to further validate the feasibility of the proposed NN controllers on the Quanser platform.

A novel event-triggered approach for a class of nonlinear continuous-time system is proposed in this paper to reduce the computation cost of the dual heuristic dynamic programming (DHP) algorithm. Two neural networks are included in our design. A critic network is used to estimate the partial derivatives of the cost function with respect to its inputs, and an action network is used to approximate the optimal control law. Instead of periodical sampling in the traditional DHP approach, under the event-triggered mechanism, both of the neural networks are only updated at the jump instants, and kept constant during the inter-event time. With the designed trigger threshold, the proposed DHP-based event-triggered approach can save computation time significantly while obtaining competitive control performance when comparing with those of the traditional DHP approach. Two simulation tests are presented to verify the theoretical results.

Auto-encoder is a popular representation learning technique which can capture the generative model of data via a encoding and decoding procedure typically driven by reconstruction errors in an unsupervised way. In this paper, we propose a semi-supervised manifold learning based auto-encoder (named semAE). semAE is based on a regularized auto-encoder framework which leverages semi-supervised manifold learning to impose regularization based on the encoded representation. Our proposed approach suits more practical scenarios in which a small number of labeled data are available in addition to a large number of unlabeled data. Experiments are conducted on several well-known benchmarking datasets to validate the efficacy of semAE from the aspects of both representation and classification. The comparisons to state-of-the-art representation learning methods on classification performance in semi-supervised settings demonstrate the superiority of our approach.

This paper presents a novel non-Gaussian stochastic control framework for the problem of disturbance estimation and rejection by combining fuzzy identification technology with disturbance observer design. First, fuzzy logic models are used to approximate the output probability density functions (PDFs) of non-Gaussian processes such that the task of PDF shape control can be reduced to a fuzzy weight dynamics modeling and control problem. Next, Takagi-Sugeno fuzzy models with multiple disturbances are employed to describe the nonlinear relations between fuzzy weight dynamics and the control input, in which a novel disturbance-observer-based PI-type fuzzy feedback controller is designed to ensure the system stability and convergence of the tracking error to zero. Meanwhile, the disturbance estimation and attenuation performance as well as the state constrained requirement can also be guaranteed. Moreover, the novel composite observer is constructed by augmenting the disturbance estimation into the full-state estimation. The satisfactory tracking performance and full-state observation effect can be achieved by the designed optimization algorithm. Finally, simulations for paper-making process are given to show the efficiency of the proposed approach.

In this paper, adaptive impedance control is developed for an n-link robotic manipulator with input saturation by employing neural networks. Both uncertainties and input saturation are considered in the tracking control design. In order to approximate the system uncertainties, we introduce a radial basis function neural network controller, and the input saturation is handled by designing an auxiliary system. By using Lyapunov's method, we design adaptive neural impedance controllers. Both state and output feedbacks are constructed. To verify the proposed control, extensive simulations are conducted.

In this paper, we present adaptive neural network tracking control of a robotic manipulator with input deadzone and output constraint. A barrier Lyapunov function is employed to deal with the output constraints. Adaptive neural networks are used to approximate the deadzone function and the unknown model of the robotic manipulator. Both full state feedback control and output feedback control are considered in this paper. For the output feedback control, the high gain observer is used to estimate unmeasurable states. With the proposed control, the output constraints are not violated, and all the signals of the closed loop system are semi-globally uniformly bounded. The performance of the proposed control is illustrated through simulations.

To increase the performance of a brain-computer interface and brain-machine interface system, we propose some methods and algorithms for electroencephalograph (EEG) signal analysis. The recorded EEG signal is transmitted to the computer and the upper limb robotic arm interface via a bluetooth. To obtain effective commands from brain, the recorded EEG signal is processed by a front filter, denoise filter, feature extraction, and classification, while the personal computer software and upper limb arm are driven by EEG-based commands. Through the encoders and gyroscopes on the upper limb arm, we can acquire some feedback signals in real time, such as joint angle, arm accelerated speed, and angular speed. The theory of wavelet denoising method, common spatial pattern algorithm and linear discriminant analysis algorithm are investigated in this paper. The simulations and experiments demonstrate the effectiveness and accuracy of these algorithms on EEG signal denoising, feature extraction, and classification.

In this paper, a novel predictive event-triggered control method based on heuristic dynamic programming (HDP) algorithm is developed for nonlinear continuous-time systems. A model network is used to estimate the system state vector, so that the event-triggered instant is available to predict one step ahead of time. Furthermore, an actor-critic structure is used to approximate the optimal event-triggered control law and performance index function. Although event-triggered adaptive dynamic programming (ADP) has been investigated in the community before, to our best knowledge, this is the first study of using a “predictive” approach through a model network to design the event-triggered ADP. This is the key contribution of this work. Compared to the existing event-triggered ADP methods, our simulations demonstrate that the predictive event-triggered approach can achieve improved control performance and lower computational cost in comparison with the existing methods.

Recently researches show that significant energy saving can be achieved by introducing mobile relays into wireless sensor networks. However, due to the extra transceiver circuit energy and the mobility energy consumed by the mobile relay, it is not always better to pass data through the relay rather than to send it from source to destination directly. In this study, the authors study a novel link selection problem in a two‐hop relay scenario where the relay has the ability to move. In this scenario, data from source can be passed through three kinds of links: the direct link, the initial relay link and the adjusted relay link. From the energy‐saving perspective, the optimal moving direction, the position adjustment criterion and the optimal position of the mobile relay are firstly studied through mathematical analysis. Based on a comprehensive discussion of the energy performances of these three kinds of links, and energy‐efficient link selection scheme is then presented. Both the amount of data to be sent and the distance between source and destination are shown to be closely related to the link selection scheme. Finally numerical simulations are carried out to verify the theoretical results.

In this paper, we propose a cascade dictionary learning algorithm for action recognition. In the first stage, a dictionary for basic sparse coding is learned based on local descriptors. And then spatial pyramid features are extracted to represent all the images in the same dimensions. Instead of performing dimension reduction, all the features are regrouped and then fed into second dictionary learning. In the second stage, a supervised dictionary for block and group sparse coding is learned to get discriminative representations based on the regrouped features. Without lowering classification performance, the size of the second dictionary is much smaller than other dictionary based on spatial pyramid features. We evaluate our algorithm on two publicly available databases about action recognition: Willows and People Playing Music Instrument. The numerical results show the effectiveness of the proposed algorithm.

The fuzzy feedback control design problem is addressed in this paper by using the distributed proportional-spatial integral (P-sI) control approach for a class of nonlinear distributed parameter systems represented by semi-linear parabolic partial differential-integral equations (PDIEs). The objective of this paper is to develop a fuzzy distributed P-sI controller for the semi-linear parabolic PDIE system such that the resulting closed-loop system is exponentially stable. To do this, the semi-linear parabolic PDIE system is first assumed to be exactly represented by a Takagi-Sugeno (T-S) fuzzy parabolic PDIE model. A new vector-valued integral inequality is established via the vector-valued Wirtinger's inequality. Then, based on the T-S fuzzy PDIE model and this new integral inequality, a distributed fuzzy P-sI state feedback controller is proposed such that the closed-loop PDIE system is exponentially stable. The sufficient condition on the existence of this fuzzy controller is given in terms of a set of standard linear matrix inequalities (LMIs), which can be effectively solved by using the existing convex optimization techniques. Finally, the developed design methodology is successfully applied to solve the feedback control design of a semi-linear reaction-diffusion system with a spatial integral term.

This paper mainly studies the speed control for a permanent magnet synchronous motor system. The relationship between the reference quadrature axis current and the speed output is approximately considered as a second-order model. Based on this second-order model, a composite control strategy is adopted, where a continuous sliding mode controller is designed for the speed regulation without chattering and a disturbance observer is introduced as a compensator to resist disturbances and to reduce control gains. Simulation results have been presented to illustrate that the proposed method has good responses to reference speed signals with torque load disturbances.

This paper addresses the problem of exponential synchronization via boundary control for a class of networked linear spatiotemporal dynamical networks consisting of N identical nodes, in which the spatiotemporal behavior of the each node is described by parabolic partial differential equations (PDEs). The purpose of this paper is to design boundary controllers ensuring the exponential synchronization of the networked parabolic PDE system. To do this, Lyapunov's direct method, the vector-valued Wirtinger's inequality, and the technique of integration by parts are employed. A sufficient condition on the existence of the boundary controllers is developed in term of standard of linear matrix inequality (LMI). Finally, numerical simulation results on a numerical example are presented to illustrate the effectiveness of the proposed design method.

In this paper, we propose using high-level action units to represent human actions in videos and, based on such units, a novel sparse model is developed for human action recognition. There are three interconnected components in our approach. First, we propose a new context-aware spatial-temporal descriptor, named locally weighted word context, to improve the discriminability of the traditionally used local spatial-temporal descriptors. Second, from the statistics of the context-aware descriptors, we learn action units using the graph regularized nonnegative matrix factorization, which leads to a part-based representation and encodes the geometrical information. These units effectively bridge the semantic gap in action recognition. Third, we propose a sparse model based on a joint l2,1-norm to preserve the representative items and suppress noise in the action units. Intuitively, when learning the dictionary for action representation, the sparse model captures the fact that actions from the same class share similar units. The proposed approach is evaluated on several publicly available data sets. The experimental results and analysis clearly demonstrate the effectiveness of the proposed approach.

In this brief, an optimal control scheme based on adaptive dynamic programming (ADP) is developed to solve infinite-horizon optimal control problems of continuous-time complex-valued nonlinear systems. A new performance index function is established on the basis of complex-valued state and control. Using system transformations, the complex-valued system is transformed into a real-valued one, which overcomes Cauchy-Riemann conditions effectively. With the transformed system and the performance index function, a new ADP method is developed to obtain the optimal control law by using neural networks. A compensation controller is developed to compensate the approximation errors of neural networks. Stability properties of the nonlinear system are analyzed and convergence properties of the weights for neural networks are presented. Finally, simulation results demonstrate the performance of the developed optimal control scheme for complex-valued nonlinear systems.

There is growing interest in solving linear L1 estimation problems for sparsity of the solution and robustness against non-Gaussian noise. This paper proposes a discrete-time neural network which can calculate large linear L1 estimation problems fast. The proposed neural network has a fixed computational step length and is proved to be globally convergent to an optimal solution. Then, the proposed neural network is efficiently applied to image restoration. Numerical results show that the proposed neural network is not only efficient in solving degenerate problems resulting from the nonunique solutions of the linear L1 estimation problems but also needs much less computational time than the related algorithms in solving both linear L1 estimation and image restoration problems.

This article presents a comparative analysis of particle swarm optimisation (PSO), self-organising hierarchical particle swarm optimiser (HPSO) and self-organising hierarchical particle swarm optimiser with time-varying acceleration coefficients (HPSO-TVAC) for data clustering. Through experiments on six well-known benchmarks, we find that the HPSO and the HPSO-TVAC algorithms have better performance than the PSO algorithm in most cases, and all the clustering algorithms using PSO have good performance for large-scale data and high-dimensional data, especially the two algorithms proposed in this article. Furthermore, we have also observed that the convergence of the HPSO and the HPSO-TVAC algorithms are better when using a suitable fitness function.

In this paper, a novel feature named adaptive projection LBP (APLBP) is proposed for face detection. To promote discriminative power, the distribution information of training samples is embedded into the proposed feature. APLBP is generated by LDA which maximizes the margin between positive and negative samples adaptively, utilizing characteristics of similarity to Gaussian distribution of the training samples. Asymmetric Gentle Adaboost is utilized to train strong classifier and nested cascade is applied to construct the final detector. Experimental results based on MIT+CMU database demonstrate that APLBP feature outperforms several well-existing features due to its excellent discriminative power with less feature number.

In this paper, we propose a Multi-Manifold Discriminant Analysis (MMDA) method for face feature extraction and face recognition, which is based on graph embedded learning and under the Fisher discriminant analysis framework. In MMDA, the within-class graph and between-class graph are designed to characterize the within-class compactness and the between-class separability, respectively, seeking for the discriminant matrix that simultaneously maximizing the between-class scatter and minimizing the within-class scatter. In addition, the within-class graph can also represent the sub-manifold information and the between-class graph can also represent the multi-manifold information. The proposed MMDA is examined by using the FERET face database, and the experimental results demonstrate that MMDA works well in feature extraction and lead to good recognition performance.

Recurrent neural networks for solving constrained least absolute deviation (LAD) problems or L(1)-norm optimization problems have attracted much interest in recent years. But so far most neural networks can only deal with some special linear constraints efficiently. In this paper, two neural networks are proposed for solving LAD problems with various linear constraints including equality, two-sided inequality and bound constraints. When tailored to solve some special cases of LAD problems in which not all types of constraints are present, the two networks can yield simpler architectures than most existing ones in the literature. In particular, for solving problems with both equality and one-sided inequality constraints, another network is invented. All of the networks proposed in this paper are rigorously shown to be capable of solving the corresponding problems. The different networks designed for solving the same types of problems possess the same structural complexity, which is due to the fact these architectures share the same computing blocks and only differ in connections between some blocks. By this means, some flexibility for circuits realization is provided. Numerical simulations are carried out to illustrate the theoretical results and compare the convergence rates of the networks.

Affinity propagation exhibits fast execution speed and finds clusters with low error rate when clustering sparsely related data but its values of parameters are fixed. This paper proposes a modified method named partition adaptive affinity propagation, which can automatically eliminate oscillations and adjust the values of parameters when rerunning affinity propagation procedure to yield optimal clustering results, with high execution speed and precision. Experiments are carried on UCI datasets and Caltech101 dataset, and ORL faces dataset. The results verify that this adaptive method is effective and feasible.

The algorithm of least square support vector machine (LSSVM) based on fuzzy c-means (FCM) clustering is presented in this paper, which can select the number of clusters automatically depending on different parameters and samples. We adopt the method to identify the inverse system with crucial spanless process variables and the inenarrable nonlinear character. In the course of identification, we construct the allied inverse system by the left inverse soft-sensing function and the right inverse system, then utilize the proposed method to approach the nonlinear allied inverse system via offline training. Simulation experiments are performed and indicate that the proposed method is effective and provides satisfactory performance with excellent accuracy and low computational cost comparing with the conventional method using LSSVM.

The problem of the global asymptotic stability for a class of neural networks with time-varying delays is investigated in this paper, where the activation functions are assumed to be neither monotonic, nor differentiable, nor bounded. By constructing suitable Lyapunov functionals and combining with linear matrix inequality (LMI) technique, new global asymptotic stability criteria about different types of time-varying delays are obtained. It is shown that the criteria can provide less conservative result than some existing ones. Numerical examples are given to demonstrate the applicability of the proposed approach.

In this brief paper, an augmented Lyapunov functional, which takes an integral term of state vector into account, is introduced. Owing to the functional, an improved delay-dependent asymptotic stability criterion for delayed neural networks (NNs) is derived in term of linear matrix inequalities (LMIs). It is shown that the obtained criterion can provide less conservative result than some existing ones. When linear fractional uncertainties appear in NNs, a new robust delay-dependent stability condition is also given. Numerical examples are given to demonstrate the applicability of the proposed approach.

We study the robust exponential periodicity of a class of interval-delayed neural networks. A new condition ensuring the existence, uniqueness and global robust exponential stability of the periodic solution of interval-delayed neural networks with periodic input is established.

Exponential periodicity of continuous-time neural networks with delays is investigated. Without assuming the boundedness and differentiability of the activation functions, some new sufficient conditions ensuring existence and uniqueness of periodic solution for a general class of neural systems are obtained. Discrete-time analogue of the continuous-time system with periodic input is formulated and we study their dynamical characteristics. The exponential periodicity of the continuous-time system is preserved by the discrete-time analogue without any restriction imposed on the uniform discretization step-size.

For successful monitoring and controlling chemical process, an accurate on-line measurement of important quality variables is essential. However, these variables usually are difficult to measure on-line due to the limitations such as the time delay, high cost and reliability, so they cannot be directly close-loop controlled. In view of the problem above existing in an industry distillation column, a new design methodology is proposed. At first, an adaptive soft sensor instrument based on neural network technology was constructed as an alternative for the physical sensors. Then, the soft-instrument is correctly applied to an advanced control system and run successfully on DCS equipment. The data measured online show the control system has realized the quality close-loop control very well.

In this paper, exponential periodicity of neural networks with delays is investigated. Without assuming the boundedness and differentiability of the activation functions, some new sufficient conditions ensuring existence and uniqueness of periodic solution for a general class of neural networks with delays are obtained. This work gives some improvements to previous ones.