Cooperative rendezvous between the autonomous surface vehicle (ASV) and uncrewed underwater vehicle (UUV) constitutes a core support for the marine Internet of Things (MIoT). However, the communication between two vehicles is vulnerable to denial-of-service (DoS) attacks, which may lead to rendezvous failure. To address this challenge, this study develops a safe resilient rendezvous control method with dynamic event-triggered mechanism. An adaptive neural parameter compression algorithm is incorporated to approximate heterogeneous system uncertainties and external disturbances with fewer adaptive parameters, effectively alleviating computational burdens. To further ensure a safe rendezvous, a prescribed performance control (PPC)-based scheme is proposed to regulate the UUV’s ascending trajectory, thereby facilitating a smooth ascent. Considering that communication between the ASV and UUV may be disrupted by DoS attacks, a second-order resilient filter is proposed to estimate the unavailable virtual leader states in real time. To optimize onboard communication usage, a dynamic event-triggered mechanism is embedded within the control design, enabling a more flexible control for cooperative rendezvous. The closed-loop stability is provided under DoS attacks, with simulation results and comparisons demonstrating the effectiveness of the proposed rendezvous approach.

Motion planning (MP) is one of fundamental issues in robot manipulators. Various MP schemes at joint velocity and acceleration levels are reported, but the noise impact is usually neglected. This paper presents an enhanced version of the acceleration-level MP (ALMP) method, incorporating additive noise considerations, specifically designed for robotic manipulators. Then, such an improved method, which is based on the pseudoinverse of robots’ Jacobian matrix, is theoretically proven to be robust against different types of noise. As case studies of the improved method, the noise-tolerance repetitive motion planning (NT-RMP) and the noise-tolerance minimum acceleration norm (NT-MAN) scheme are established for robot manipulators. Simulation and experiment results under the UR5 and Panda robot manipulators corrupted by different noises further validate the effectiveness and practicality of such two schemes and the improved ALMP method.

The Internet of Everything (IoE) is accelerating the demand for intelligent, low-latency, and highly reliable communication systems to support automation and real-time decision-making. In dense urban and industrial environments, unmanned aerial vehicles (UAVs) are increasingly utilized to extend network coverage, improve connectivity, and enable dynamic data collection. However, managing RIS-assisted UAV-enabled IoE networks poses significant challenges, including accurate signal prediction, high computational complexity, and decentralized task assignment. To address these issues, we propose a novel RIS-empowered UAV-based Dynamic Area of Coverage (DAC) architecture. In this framework, UAVs equipped with reconfigurable intelligent surfaces (RIS) adaptively adjust the phase of reflected signals to optimize wireless channel conditions, suppress interference, and enhance signal quality.We formulate the Dynamic Area of Coverage with Location, Resource Allocation, and Trajectory Optimization (DAC-LRT) problem as a mixed-integer nonlinear programming (MINLP) model, aiming to jointly optimize UAV positioning, power distribution, and trajectory control to maximize real-time downlink capacity and ensure energy efficiency. To solve the DAC-LRT problem in dynamic and large-scale IoE environments, we design a Multi-Agent Distributed Deep Deterministic Policy Gradient (MAD3PG) algorithm. MAD3PG enables decentralized and adaptive policy learning by allowing UAVs to derive optimal actions directly from environmental observations. Simulation results demonstrate that our proposed approach significantly outperforms state-of-the-art methods, achieving improvements of 82.92%, 78.02%, and 71.9% in downlink capacity, coverage ratio, average throughput, and spectral efficiency over Deep Deterministic Policy Gradient (DDPG), Asynchronous Advantage Actor-Critic (A3C), and Greedy algorithms, respectively.

This study presents an adaptive quantized control algorithm designed to address actuator faults and achieve obstacle avoidance for heterogeneous ships. Within this algorithm, a hysteresis quantizer is employed to minimize communication resource utilization. Novel adaptive compensation mechanism is introduced to counteract actuator faults. Additionally, the radial basis function neural networks (RBF-NNs) are utilized to approximate the uncertainties inherent in the ship model. Further adaptive parameters are incorporated to mitigate perturbation errors arising from mismatches between the quantizer and the ships’ unknown parameters. Stability is rigorously established through the construction of a direct Lyapunov function, demonstrating that all signals within the closed-loop system satisfy Semi-Globally Uniformly Ultimately Bounded (SGUUB). To validate the superiority of the proposed algorithm, simulation experiments are conducted for obstacle avoidance mission of marine heterogeneous system.

This article studies the 3-D dynamic rendezvous control problem for coordinated heterogeneous marine vehicles, including an uncrewed underwater vehicle (UUV) and an autonomous surface vehicle (ASV). An observer-based safety-preserving rendezvous control approach is proposed to robustly stabilize the rendezvous errors under the port-Hamiltonian (PH) framework. First, an interconnection and damping assignment passivity-based control (IDA-PBC) method is adopted to provide a basic stabilizing control framework. In this problem, both vehicles are faced with hydrodynamic model uncertainties and unknown external disturbances. Then, to preserve the rendezvous safety under uncertain dynamics, the prescribed performance control (PPC) transformation is implemented for the ascending motion to get the equivalent approaching-constrained PH system. The intuitive design procedure provided by the IDA-PBC method, along with the collision-free rendezvous safety guaranteed by the auxiliary PPC technique, reduces the controller design complexity while providing a smooth rendezvous trajectory. Besides, a structure-keeping uncertainty observer algorithm is designed and incorporated to simultaneously handle model uncertainties and environmental disturbances without destroying the interconnection structure. Under the proposed approach, the UUV-ASV rendezvous errors can be effectively stabilized with rigorous closed-loop stability analysis. Finally, both simulations and comparative experiments are conducted to demonstrate the effectiveness and advantages of the proposed approach.

This article proposes a trajectory tracking strategy for nonuniform quay cranes to suppress flexible cable vibration and attenuate payload swing and rotation, thereby improving tracking accuracy and transport efficiency. To address the challenges posed by time-varying and spatially distributed partial differential equation models, we propose a Bayesian physics-informed neural network (BPINN) framework that integrates tension constraints into the loss function to suppress flexible cable vibrations. In the Bayesian setting, the BPINN acts as a prior model, and Hamiltonian Monte Carlo (HMC) sampling is employed to infer the posterior distribution of the system states. To handle the underactuated nature of the quay crane, differential flatness is exploited to map BPINN-predicted states into a flat output space, where an adaptive backstepping controller is designed to guarantee global uniform ultimate boundedness. Moreover, a multistrategy improved quantum-behaved particle swarm optimization (MIQPSO) scheme is introduced for online tuning of control parameters, achieving a favorable tradeoff between global exploration and fast convergence. Lyapunov analysis establishes closed-loop stability, and simulations and experiments demonstrate fast and accurate tracking as well as robust vibration suppression under external disturbances.

This paper presents a fuzzy sampled-data tracking control framework for a class of general nonlinear systems subject to unmatched disturbances, developed through a composite nonrecursive synthesis approach. First, focusing on unmatched disturbance rejection, an Euler discretization is applied to a continuous-time nonsmooth disturbance observer, resulting in a homogeneous sampled-data observer. Subsequently, by incorporating the estimated disturbances to modify the original system, a homogeneous nonrecursive sampled-data controller is directly derived via a simple coordinate transformation. In the semiglobal stability analysis, a relationship between the sampling period and the system bandwidth factor is established. Furthermore, to address the well-recognized influence of sampling period variations on system performance, a fuzzy logic criterion describing the performance-sampling period relationship is introduced. By this criterion, a fuzzy self-tuning mechanism is employed to more flexibly determine the most appropriate sampling period for the system under real-time operating conditions. Finally, the effectiveness of the proposed strategy is validated through numerical simulations and experimental studies on robot manipulators, demonstrating its practical application potential.

Tracking-by-Detection paradigms shine in generic multi-object tracking (MOT), while their compact construction hinders the real-time applications. In this work, we attribute the substantial computational burden to two expensive components, i.e. detection and re-identification. Building upon the principle of adaptively maintaining acceptable inference efficiency, we present Adaptively Sparse Detection with attention-guided refinement (ASDTracker) for efficient tracking. In specific, our ASDTracker rapidly assess the short-term and long-term occlusion, dynamically determining the usage of the expensive detector. For non-key frames, we efficiently refine small-size crops out of Kalman Filter predictions and introduce the noisy shadow labels to robustly train this refinement network. Additionally, we substitute the lightweight appearance representation for the heavy ReID network, which efficiently extracts sufficient appearance cues in the coarsely quantized color spaces. Extensive experiments on four benchmarks demonstrate that ASDTracker achieves competitive performance in generalization and robustness under favorable inference speed. Moreover, the efficient tracking deployment is further implemented to an unmanned surface vehicle with high accuracy and low latency in real-world scenarios.

This paper addresses the problem of safety-critical path-guided herding control for multiple-input multiple-output multi-agent systems under incomplete state measurement, safety constraints, and limited communication resources. Specifically, an output-feedback finite-time neural predictor is proposed to identify both model uncertainties and unknown state information. Subsequently, a distributed path-guided herding control strategy is designed, including patrolling, gathering, enclosing, and expelling. Control barrier functions are formulated as safety constraints, and a quadratic optimization problem is established. By using the neurodynamic optimization to solve the optimization problem, the optimal control law satisfying both safety constraints and state constraints is generated. Furthermore, a dynamic event-triggered communication method is proposed to reduce unnecessary communication, especially during the transient phase. By using the proposed herding control approach, the collision-free herding is guaranteed for input-to-state stability, and simulation results are provided to demonstrate the effectiveness of the approach.

Load transportation using unmanned aerial vehicles (UAVs) presents both intriguing possibilities and significant challenges in research and practical applications. This study aims to present a comprehensive literature review of recent progress in the development of multirotor UAVs transporting cable-suspended loads. A secondary objective is to assist researchers and engineers in the design and development of flight control systems for UAV-slung-load applications. To this end, the survey begins by providing a historical overview of flight control hardware platforms and load swing measurement systems used in UAV-slung-load systems. Subsequently, representative modeling approaches for UAV-slung-load systems are introduced. The survey then reviews a range of existing flight control strategies, highlighting their key characteristics and advantages. Finally, general challenges and potential future research directions for UAV-slung-load systems are discussed.

This paper proposes a three-dimensional (3D) safety-critical cooperative guidance and control strategy for a group of vehicles aiming at simultaneous formation around a target. First, a reference relative trajectory is constructed using piecewise B$\acute {e}$zier curves to define a time-independent spatial path, along which a space-and-time synchronization strategy is employed to ensure that all vehicles reach their designated relative positions simultaneously. Next, the dimensionless residual path and velocity in reference relative motion are taken as coordination variables in the space-and-time-synchronized cooperative guidance, and a distributed coordination strategy with upper and lower bound constraints on path velocity is designed. Finally, fixed-time controllers with integrated extended state observers (ESOs) are designed for kinematic and kinetic systems to track the reference trajectory under control saturation, while safety constraints are enforced via control barrier function (CBF)-based compensation. Numerical simulations demonstrate the effectiveness of the proposed cooperative guidance law.

This article investigates the problem of disturbance attenuation for autonomous surface vehicles (ASVs) subject to asymmetric time-varying saturation. To address this challenge, we propose a novel event-triggered (ET) zero-sum (ZS) differential game framework that integrates a barrier function and a nonquadratic value function, enabling simultaneous achievement of safety control and disturbance attenuation. Initially, by designing a barrier function, the control problem of the asymmetric time-varying saturated ASV system is transformed into an unsaturated form. Afterward, a nonquadratic value function is designed, and ZS games are employed to obtain the saturated-optimal control policy and the worst-case disturbance policy. Then, the ET method is introduced into policy execution and critic neural network learning. The scheme in this article ensures the safety and stability of the ASV while reducing computational burden and meeting the needs of disturbance attenuation. Finally, theoretical analysis and simulation experiments verify the feasibility of the ET ZS differential game approach.

This article investigates the pursuit–evasion problem of multiple underactuated autonomous surface vehicles (ASVs) under velocity and collision avoidance constraints. A safety–critical pursuit–evasion game (PEG) method based on min–max optimization and neural network dynamic control is proposed. Specifically, an allocation strategy is designed at first based on the position information of the pursuing and evading ASVs to achieve a rational and efficient allocation of pursuit targets by minimizing pursuit distances. Next, a nominal PEG guidance law is proposed by combining model predictive control (MPC) with min–max optimization methods. Then, the nominal guidance law is optimized based on a heading-constrained control barrier function (CBF) such that a safety–critical guidance law for collision avoidance can be achieved. Finally, a predicator-based neural network is developed to estimate the uncertainty and external disturbance, and a dynamic control law is proposed to track the guidance signals without using any model parameters. It is proven that the closed-loop system is input–to–state stable (ISS), and the ASV system is safe. A robot-operating-system (ROS)-based simulation results demonstrate the effectiveness of the proposed safety–critical PEG method based on min–max optimization and neural network dynamic control.

This article investigates the leader-following bipartite time-varying formation (BTVF) control problem for switched multiagent systems (MASs) under the changeable directed signed topologies. The communication topology switches to obey an average dwell-time condition, capturing realistic network dynamics. Two critical challenges are addressed in the controller design, one of which is that the real states are inaccessible and the other is that we know nothing about the active leader input. These constraints significantly increase the design complexity. Against this backdrop, we develop a novel control protocol that is capable of achieving the BTVF tracking even given the uncertain leader input without using the real states. The designed control protocol can perform well to deliver reliable commands to realize the BTVF under switched topologies. Through Lyapunov stability analysis and recursive algorithms, we rigorously prove convergence to the desired BTVF. Notably, the protocol is also shown to guarantee bipartite consensus as a special case. In the end, the effectiveness of the proposed control scheme is validated through simulations involving the clusters of the wheeled mobile robot and autonomous aerial vehicle models in different working scenarios.

Graph neural networks (GNNs) have emerged as a powerful tool for fault diagnosis in industrial processes, where components and their relationships can be modeled as nodes and edges in a graph. However, most GNN models are based on the I.I.D. hypothesis and learn both causal and spurious correlations. In real-world applications, test data distributions often differ from training data, leading to changes in spurious correlations and inaccurate diagnosis results. To address this issue, this paper proposes a causal regularization graph attention network (CR-GAT) that decouples causal and confounding variables and eliminates spurious correlations. The method involves extracting high-level graph variables using differentiable pooling, measuring nonlinear dependence between variables with the Hilbert-Schmidt Independence Criterion (HSIC), and iteratively optimizing GAT loss and variable weights to learn true causal relationships. Comparative experiments on three-phase flow and power system datasets demonstrate the effectiveness of the proposed method.

Pedestrian trajectory prediction ensures safe navigation in autonomous driving and intelligent robots. Existing methods have shown promising results but still face challenges in handling dynamic environments, social interactions, and high-dimensional data. In this paper, we propose a novel PhysGCN-DL within the itransformer framework to address these challenges. Our model incorporates physically-inspired dynamic interaction modeling by representing physical interactions between pedestrians as edge weights in graph convolution. This approach captures the heterogeneity of pedestrian movement and improves the interpretability of social interactions. Moreover, we design a novel loss function to jointly enhance prediction diversity and accuracy, thereby improving the model’s robustness across both dense and sparse scenarios. Empirical evaluations confirm that our approach outperforms existing methods in generating accurate and diverse pedestrian trajectories.

Vision-and-Language Navigation in Continuous Environments (VLN-CE) presents challenges due to environmental variations and domain shifts, making it difficult for agents to generalize beyond seen environments. Most existing methods rely on learning correlations between observations and actions from training data, which leads to spurious dependencies on environmental biases. To address this, we propose CVLN-Think (CVT), a novel navigation model that incorporates causal inference to enhance robustness and adaptability. Specifically, Style Causal Adjuster (SCA) generates counterfactual style observations, enabling agents to learn invariant spatial structures rather than overfitting to dataset-specific visual patterns. Furthermore, Thinking Cause Navigation Engine (TCNE) applies causal intervention to adjust navigation decisions by identifying and mitigating biases from prior experience. Unlike conventional approaches that passively learn from data distributions, our model actively thinks along the "observation-action" chain to make more reliable navigation predictions. Experimental results demonstrate that our approach achieves satisfactory performance on VLN-CE tasks. Further analysis indicates that our method possesses stronger generalization capabilities, highlighting the superiority of our proposed approach.

Achieving repetitive motion planning (RMP) is essential in the study of mobile robot manipulators. This paper presents an acceleration-level RMP (ALRMP) scheme for omnidirectional mobile robotic manipulators (OMRMs). Specifically, a new acceleration-level performance index is designed to realize RMP using the gradient-dynamics and neurodynamics methods. Leveraging this index and incorporating physical constraints (i.e., position-level, velocity-level, and acceleration-level limits), a novel ALRMP scheme is proposed and analyzed. The scheme is formulated as a quadratic program (QP) and solved using a neural network solver. Comparative simulations conducted on an OMRM demonstrate the effectiveness and superiority of the proposed ALRMP scheme over the velocity-level RMP scheme. The applicable potential of the proposed ALRMP scheme is further indicated via the real-world experiment on a practical OMRM system.

This paper investigates the application of deep reinforcement learning (RL) in the reactive collision avoidance control of an autonomous underwater vehicle (AUV) using multi-beam forward-looking sonar. Firstly, an efficient encoding method based on prior knowledge is proposed, which can extract low dimensional representations of obstacles from massive MBFLS detection data, thereby reducing the inference time of the reactive collision avoidance control policy represented by a neural network and improving their collision avoidance effect. On this basis, a state space, action space, and multi-objective reward function are customized for the reactive collision avoidance task of the AUV, and a simulation training environment is constructed. Considering that the contradiction between policy training and deployment is caused by unknown total disturbances, disturbance estimators based on the extended state observer is constructed, and a deployment scheme is designed to compensate for disturbances through both feedforward and feedback channels, ensuring that the policy learned in simulation can be applied to an actual AUV. Finally, combining the above components, a novel reactive collision avoidance method based on deep RL is proposed, and the effectiveness of the proposed method for obstacles of various shapes (both static and dynamic) is fully verified in three different unknown environments.

Infrared maritime object detection is a crucial technology for sea surface monitoring in low-light conditions within maritime Internet of Things (IoT) systems. In practical applications, this task faces significant challenges, including diverse target sizes and stringent real-time processing requirements. To address these challenges, a DEtection TRansformer with Global-Local Adaptive Fusion attention for infrared maritime object detection (GLAF-DETR) is proposed. The Global-Local Adaptive Fusion (GLAF) attention mechanism is designed to capture both global contextual information and fine local details of objects. GLAF dynamically adjusts attention across regions by integrating long-range dependencies with short-range positional information, significantly enhancing detection performance for targets of varying sizes in complex maritime environments. In addition, the Dynamic Adaptive Multiscale Feature Fusion (DAMFF) module is proposed to promote cross-channel interaction among multiscale features. Guided by GLAF, DAMFF dynamically fuses these features, further enhancing the accuracy of multiscale object detection. The lightweight HGNetv2-IRLight backbone is designed to minimize network complexity and ensure real-time performance by reducing redundant information while maintaining strong infrared feature extraction. Extensive experiments conducted on an infrared maritime object dataset show that GLAF-DETR surpasses state-of-the-art methods in both detection accuracy and inference speed. It demonstrates outstanding performance, particularly in detecting objects across different scales, offering enhanced accuracy and robustness in challenging maritime scenarios.

With the development of Industry 4.0, mobile agents are deployed to coordinate with multi-loop control systems to perform manufacturing tasks, leading to heterogeneous Internet of Things (IoT). Due to shadow fading induced by the movement of mobile agents, the wireless channel closing the control loops is inherently unreliable, which can compromise the control system performance. This paper addresses the co-design problem of transmission scheduling and agents’ movement to ensure both control performance and energy efficiency. A generalized cyber-physical-agent framework is proposed to capture the coupling between IoT systems and a mobile agent through a state-dependent fading channel. Moreover, the movement of the mobile agent among areas exhibiting different levels of shadow effects is modeled by Markov decision process. To address such heterogeneous dynamics, the co-design problem is formulated into the optimization of a logic-based stochastic switched system by utilizing the semi-tensor product technique. Based on state mergence andH-representation methods, a tractable and effective algorithm is then proposed to design co-design policies, minimizing the average joint cost of communication and control. A parallel scheme is further developed to alleviate the computation burden of the algorithm. Theoretical guarantees are provided to ensure control system performance. Finally, simulation results are given to demonstrate effectiveness of the proposed method.

This paper aims to address the design problem of asynchronous controllers for networked jumping systems (NJSs), in which two communication channels are vulnerable to asynchronous denial-of-service (DoS) attacks. To this end, a hidden Markov model (HMM)-based active security control strategy is proposed to counter asynchronous dual-channel DoS attacks. Firstly, two maximum consecutive numbers are introduced to describe DoS attacks randomly initiated by adversaries. Subsequently, a mode-dependent predictor is designed to generate predictive states, which can be employed in the switched controller to stabilize the NJSs. Furthermore, sufficient conditions are derived by constructing Lyapunov functions to ensure the asymptotic mean-square stability of the NJSs under asynchronous dual-channel DoS attacks. Finally, a simulation using a space robot manipulator model is presented to validate the effectiveness and practicality of the proposed active security control strategy.

The global stabilization control issue concerning a class of general upper-triangular nonlinear systems subject to non-parametric uncertainties is dealt with in this paper by constructing a nonsmooth dynamic nonrecursive state-feedback controller. The major challenge in handling such systems is that they cannot be stabilized through the conventional feedback linearization approaches. The investigated strategy does not involve a nested process, commonly seen in existing methods, but rather constructs a homogeneous stabilizer directly via a low-gain design, which greatly facilitates the design of the controller and the analysis of global stability. Meanwhile, by developing a dual-layer adaptive low-gain online updating law, the system with unknown homogeneous nonlinearity growth conditions under consideration can be flexibly stabilized. A numerical simulation and an application to the nonlinear liquid level control resonant circuit system are implemented in this paper to demonstrate the efficacy of the built framework.

This paper focuses on a distributed cooperative guidance model-free control method for a cluster of under-actuated disk-type autonomous underwater gliders (AUGs) in the presence of unknown kinetic model parameters and ocean disturbances. Firstly, a distributed cooperative motion generator is designed to generate reference path points, and then a cooperative control method is proposed based on the update path parameters. Secondly, a three-dimensional (3D) guidance law is constructed by employing closed 3D vector fields. Finally, data-driven filtered adaptive extended state observers (DFAO) are proposed to deal with the unknown input gains, internal uncertainties and external disturbances of the disk-type AUGs, and an adaptive kinetic control law is designed by using the knowledge learned from the observers. Simulation results demonstrate the effectiveness of the proposed 3D distributed cooperative guidance model-free control method for disk-type AUGs subject to fully unknown kinetics. Note to Practitioners—The disk-type AUG has the characteristic of long operational endurance, capable of functioning continuously for several months when fully loaded. Consequently, this type of glider offers an advantage in establishing oceanic sensor networks. To achieve this goal, two technical challenges arise: the coordination among multiple gliders and the anti-disturbance control of individual glider. Our research focuses on distributed cooperative guidance and model-free control issues for multiple underwater gliders. First, we propose a distributed cooperative guidance scheme to maintain a specific formation among the gliders. Additionally, while ensuring control effectiveness, we employ data-driven methods to estimate uncertain kinetic model parameters. Our approach is not only theoretically viable but also ready for industrial application, thus filling a gap in underwater glider technology.

This paper presents a comprehensive mathematical approach to address the multi-player and multi-objective pursuit-evasion games problem, incorporating coalition structure constraints from a cooperation-competition perspective. Social interaction networks are developed to approximate priority communication alliances based on individual preferences, establishing a multi-connected topology and decision space for the games. An N-player variable-sum differential game model, featuring autonomous obstacle avoidance, is formulated by integrating kinematic constraints and the social forces method. Rigorous proofs are provided for the uniqueness of payoff distribution, the stability of alliance structures, and the convergence of many-to-many differential games to Nash Equilibrium. Simulation and experimental results are presented to validate the effectiveness and performance of the proposed method.

This paper studies the stabilization problem of two-dimensional (2D) Markov jump systems (MJSs) with directional communication delays, where delays exist in both states and modes. Based on whether the delay mode can be directly observed, the mode-delayed and asynchronous controllers are designed, respectively. For the mode-delayed case, the closed-loop system with current modes and delayed modes is re-planned as a closed-loop 2D MJS. For the asynchronous case, an extended hidden Markov model is developed to describe the asynchronous modes in controllers. Based on the Lyapunov theory, sufficient conditions are derived to ensure the asymptotic mean square stability of the closed-loop 2D MJSs under these two cases. Finally, two different examples from a representative model of some thermal processes are verified in simulations to demonstrate the effectiveness of the designed approaches. Note to Practitioners—2D systems have found extensive applications in thermal processes, gas absorption, and water stream heating, etc. In these applications, sudden changes in parameters and structures are difficult to avoid, which will result in the system being unable to be described. Fortunately, this problem can be handled by the Markov model, which consists of modes and states. In the control problem of 2D MJSs, delayed states are usually considered in the plant. Consider a more practical case that delays exist in directional communication channels between the plant and the controller, resulting in directional delayed modes and states in the controller. In this case, how to handle these complex modes and state information and stabilize the system is of practical significance. Based on whether the delay mode can be directly observed, the mode-delayed and asynchronous controllers are designed, respectively. Finally, two different examples from a representative model of some thermal processes are verified in simulations to demonstrate the effectiveness of the designed approaches.

This paper proposes a novel dynamic event-triggered control method for a class of completely unknown nonaffine hierarchical differential games, incorporating asymmetric boundaries in both system states and control strategies. To tackle this problem, dynamic feedback and mapping functions are first introduced to construct an unconstrained affine augmented system. Then, integral reinforcement learning techniques are used to derive the Hamilton-Jacobi equation without the original system dynamics. Furthermore, dynamic event-triggered control is employed to alleviate the network transmission burden. During the algorithm implementation, critic neural networks are designed for each agent. Analysis results show that the states and weights are ultimately uniformly bounded. Finally, simulation results using the torsional pendulum system and RLC circuit system validate the effectiveness of the present method.

This work addresses the design problem of the fault detection observer (FDO) based on dynamic event-triggered mechanism for Markov jump systems under denial-of-service (DoS) attacks. The concept of limited energy for attackers is employed to characterize the property of nonperiodic DoS attacks. A dynamic event-triggered mechanism is introduced to save the system's communication resources. The $H_{\infty }/H_{-}$ index is incorporated to ensure that the designed FDO possesses both robustness against disturbances and sensitivity to faults. After obtaining a set of nonlinear inequalities using Lyapunov functional techniques, a simulated annealing algorithm is employed to assist in solving, ensuring not only the discovery of global optimization solutions but also obtaining satisfactory parameters for the dynamic event-triggered mechanism. Finally, the effectiveness of the designed FDO is illustrated by an example of a vertical take-off and landing vehicle dynamical system.

In this article, an integral reinforcement learning (IRL) method is developed for dynamic event-triggered nonzero-sum (NZS) games to achieve the Nash equilibrium of unmanned surface vehicles (USVs) with state and input constraints. Initially, a mapping function is designed to map the state and control of the USV into a safe environment. Subsequently, IRL-based coupled Hamilton-Jacobi equations, which avoid dependence on system dynamics, are derived to solve the Nash equilibrium. To conserve computational resources and reduce network transmission burdens, a static event-triggered control is initially designed, followed by the development of a more flexible dynamic form. Finally, a critic neural network is designed for each player to approximate its value function and control policy. Rigorous proofs are provided for the uniform ultimate boundedness of the state and the weight estimation errors. The effectiveness of the present method is demonstrated through simulation experiments.

To improve the trajectory tracking performance of unmanned surface vehicle (USV), this article investigates the USV optimal control problem with the consideration of actuator wear. In the proposed algorithm, the USV control system is divide into kinematic subsystem and kinetic subsystem. In particular, corresponding performance indexes that looking forward to be optimized are defined for each subsystem. The related value functions, Hamilton-Jacobi-Bellman equations and optimal control policies are approximated by actor-critic neural networks. To reduce the wear of propeller and rudder, the event-triggered problem is considered as a zero-sum game solving problem, where the best control inputs and worst thresholds are delivered via minmax strategy. Also, the nonlinear uncertainties of the USV are approximated and environment disturbances are compensated in the value functions for better control performance. The USV closed-loop control system is proved semi-globally uniformly ultimately bounded stability via Lyapunov theory. Finally, a simulation case and harbor experiment are illustrated to verify the superiorities and engineering application values of the proposed algorithm.

Seeking the Pareto-Nash equilibrium in multi-agent, multi-objective general-sum games (MMGSG) poses a significant challenge, particularly in accurately capturing individual preferences and adhering to the fairness principle of the solution. To address this issue, this paper introduces, for the first time, a multi-level distributed fuzzy optimum policy iteration (MDFOPI) method for identifying the Pareto-Nash equilibrium point in MMGSG. This approach is grounded in fuzzy optimal membership degrees, and employs fuzzy measures and$\lambda$-mean classification to construct the coupled multi-objective optimum matrix, utilizing the strategy space as the foundation. The Pareto-Nash equilibrium point is sought through the MDFOPI method, with the multi-objective optimal membership degree matrix used to organize the sampled data and integrate the results of multi-objective evaluations. This work rigorously proves the existence of Nash equilibria in MMGSG and establishes the convergence of the MDFOPI method to a fixed point, specifically a Pareto-Nash equilibrium point. The accuracy and practical applicability of the research findings are verified through simulation experiments.

This article concentrates on the sliding mode control (SMC) problem of nonlinear unmanned marine vehicles (UMVs) over a finite time horizon. In view of the nonlinearity and variability of the marine environment, the UMVs are characterized by the Takagi-Sugeno (T-S) fuzzy system. To improve the utilization of network resources, a novel adaptive event-triggered protocol is proposed. This protocol can dynamically adjust the threshold parameters in response to denial-of-service (DoS) attacks. An integral sliding mode controller is designed, which can achieve the ideal sliding mode within any given brief time interval. Through the Lyapunov theory, sufficient conditions for finite-time$\mathcal {H}_{\infty }$control are given. Compared with existing results, our method presents more robust performance and faster convergence rates. Finally, simulations are presented to confirm the feasibility and effectiveness of the proposed method.

Focusing on control performance enhancement for a general class of nonlinear systems with mismatched disturbances, an intelligent composite regulator is investigated by integrating disturbance observation, nonrecursive nonsmooth control (NRNSC), and deep reinforcement learning (DRL) techniques in this article. With the help of the self-learning ability delivered by the DRL algorithm, a robust adaptive control scheme is constructed for handling the challenge of parameter configuration difficulty in the traditional NRNSC synthesis approach. A new feature is that the bandwidth factor optimization in both feedforward and feedback loops is simultaneously considered. While ensuring the system maintains certain robustness, the most suitable adaptive bandwidth factors are self-tuned to optimize the control performance. Thereafter, an appropriate tradeoff is promisingly achieved between the two performances. To enhance the persuasiveness of the proposed method in terms of performance improvement, numerical simulations, and experiment tests on a permanent magnet synchronous motor (PMSM) position servo platform are conducted.

The quadratic program (QP) with equality constraint is widely involved in science and engineering fields. Numerous solutions to the equality-constrained QP (ECQP) have been reported, particularly the zeroing neural network (ZNN) for the time-dependent ECQP. However, such solutions can be severely affected by the harmonic noise and may lose their efficacy. This study aims to address the above limitation by proposing the new ZNN model against harmonic noise with the only known frequency. Such a model, called the harmonic noise rejection ZNN (HNR-ZNN) model, is established by incorporating the dynamics of the harmonic signal (from which the unknown information for the signal's amplitude and phase can be eliminated). Theoretical analysis indicates that the proposed HNR-ZNN model effectively determines the optimal solution of time-dependent ECQP under harmonic noise interference. Comparative computer simulations and real-world robot applications further indicate the validity, excellence, and practicality of the presented HNR-ZNN model.

Traditional intelligent fault diagnosis models are usually capable of diagnosing known types of faults. However, in the field of industrial fault diagnosis in open environments, it is almost impossible to collect training samples that cover all fault categories. Therefore, when encountering unknown types of fault, traditional methods tend to misclassify them as known categories. To address this issue, a causal counterfactual faithfulness generation method is proposed for open-set fault diagnosis of complex industrial processes. Initially, the signal data from fault sensors are processed into graph data composed of nodes and edges. Then, the features of nodes and their adjacent nodes are learned and integrated into graph architecture to generate new fault sample attributes. Subsequently, the causal generative model infers the category features and combines known fault categories to generate counterfactual samples. Finally, the sample’s classification as an unknown category is ultimately determined by testing the principle of consistency. The proposed method can significantly improve the accuracy of open-set diagnosis without affecting the accuracy of closed-set classification. Comparison experiments with multiple baseline models in two fault datasets illustrated that the proposed method shows an improvement in almost all indicators, which ultimately verified the effectiveness of the proposed method in the task of fault diagnosis in open environments.

Graph neural networks (GNNs) are good at capturing the intricate topologies and dependencies among components and are outstanding in fault diagnosis tasks of complex industrial process. Bias substructures consisting of irrelevant sensor signals and noise data are simpler compared to causal substructures consisting of fault signals, and GNNs tend to utilize the letter to quickly achieve low loss. However, spurious correlations in the bias substructures will mislead predictions. To address this issue, this study takes the disentanglement of causal and bias substructures as the key to improve model stability. A causal disentangled GNN (CDGNN) is proposed. First, sensor signals are transformed into graph data employing an attention mechanism to capture the interactions between them. Then, a causal disentanglement learning module is designed to extract causal subgraphs from input graphs. Finally, causal subgraph features from different source machines are aggregated to form a complete graph representation. Experimental results on two complex industrial datasets indicate that CDGNN is an effective and stable method for fault diagnosis.

The series includes two parts, articulating the two novel avenues of research on intelligent fault diagnosis (FD) for nonlinear feedback control systems. In Part I of the series, we design a novel FD paradigm by elaborating an invertible neural network (INN) for feedback control systems. With the aid of a left manifold, the core idea behind the INN-based FD scheme is as follows: 1) formulation of residual generator used for FD as a projection of system data onto the null space that has the same dimension as system outputs; 2) in a topological space, elaboration of a homeomorphism that delivers an invertible relationship between system outputs and residual signals when the system input is given; and 3) skillful introduction of both the master and slave objective functions to achieve system/parameter identification with information loseless property. Comparing with the existing FD approaches, the three superior strengths of the proposed FD scheme deserving mentation are as follows: 1) it specializes in nonlinear feedback control systems; 2) it can effectively avoid the overfitting problem when approximating or learning nonlinear system dynamics; and 3) control theory guides the whole design, ensuring the interpretability of the learning process. Finally, two studies on nonlinear systems demonstrate the feasibility of the invertible left manifold (ILM)-based FD strategy. Part I would contribute to the future development of machine learning (ML)-based system identification and explainable FD approaches, and also benefits the right manifold-based FD designs in Part II.

The challenge of the exploration-exploitation dilemma persists in off-policy reinforcement learning (RL) algorithms, impeding the improvement of policy performance and sample efficiency. To tackle this challenge, a novel historical decision-making regularized maximum entropy (HDMRME) RL algorithm is developed to strike the balance between exploration and exploitation. Built upon the maximum entropy RL framework, the historical decision-making regularization method is proposed to enhance the exploitation capability of RL policies. The theoretical analysis involves proving the convergence of HDMRME, investigating the tradeoff between exploration and exploitation of HDMRME, examining the disparity between the Q-function learned through HDMRME and the classic one, and analyzing the suboptimality of the trained policy. The performance of HDMRME is evaluated across various continuous-action control tasks from Mujoco and OpenAI Gym platforms. Comparative experiments demonstrate that HDMRME exhibits superior sample efficiency and achieves more competitive performance compared with other state-of-the-art RL algorithms.

Multiagent reinforcement learning (RL) training is usually difficult and time-consuming due to mutual interference among agents. Safety concerns make an already difficult training process even harder. This study proposes a safe adaptive policy transfer RL approach for multiagent cooperative control. Specifically, a pioneer and follower off-policy policy transfer learning (PFOPT) method is presented to help follower agents acquire knowledge and experience from a single well-trained pioneer agent. Notably, the designed approach can transfer both the policy representation and sample experience provided by the pioneer policy in the off-policy learning. More importantly, the proposed method can adaptively adjust the learning weight of prior experience and exploration according to the Wasserstein distance between the policy probability distributions of the pioneer and the follower. Case studies show that the distributed agents trained by the proposed method can complete a collaborative task and acquire the maximum rewards while minimizing the violation of constraints. Moreover, the proposed method can also achieve satisfactory performance in terms of learning speed and success rate.

This article presents an efficient method for solving the optimal tracking control policy of unmanned surface vehicles (USVs) using a hybrid adaptive dynamic programming (ADP) approach. This approach integrates data-driven integral reinforcement learning (IRL) and dynamic event-driven (DED) mechanisms into the solution of the control policy of the established augmented system while obtaining both the feedforward and feedback components of the tracking controller. For the USV model and the reference trajectory, an augmented system is established, and the tracking Hamilton-Jacobi-Bellman (HJB) equation is derived based on IRL, aiming to fully utilize system data information and reduce model dependency. For the solution of the tracking HJB equation, the DED-based controller update rule is used to further reduce the burden of network transmission. In implementing the ADP method, the DED experience replay-based weight update rule is utilized to recycle data resources. Experiments show that compared with the static event-driven (SED) approach, the DED approach reduces the sample size by 78% and increases the average interval by about four times.

This article investigates an adaptive prescribed performance path-following control algorithm for rotor-assisted vehicles, incorporating reinforcement learning (RL) to execute energy-saving cruising missions. For obtaining a high-performance path-following controller, a concise prescribed performance control (PPC) algorithm is designed to tightly constrain the output errors within the defined boundaries, while a shifting function is introduced to solve the problem of initial condition restrictions. Furthermore, through integrating the Backstepping method and the optimal control technique, an improved RL with the form of actor-critic neural networks (AC-NNs) is proposed to offer an innovative approach to the challenges of the model uncertainties and external disturbances. In this approach, the actor NN is employed to create an appropriate control policy, while the critic NN is aimed at evaluating the cost-to-go function to modify the system action. Semi-global uniform ultimate bounded (SGUUB) stable properties of the proposed algorithm are guaranteed via the Lyapunov theory. Finally, the superiority and feasibility of the proposed algorithm are verified by two numerical experiments.

As the demand for efficient parcel delivery continues to grow in the logistics industry, optimizing multi-robot task assignment has become crucial for enhancing overall delivery performance. This paper addresses the precedence-constrained multi-truck multi-drone package delivery task assignment problem, where each truck coordinates with a drone to serve multiple dispersed customers under precedence constraints that specify the required order of service. While trucks deliver packages to designated customers, drones can simultaneously serve other customers, subject to their limited flight endurance and payload capacity. To tackle this challenge, a three-phase heuristic algorithm is proposed to minimize the total delivery time required to serve the last customer while ensuring all precedence constraints are satisfied. In the first phase, an extended minimum marginal cost algorithm is applied to quickly construct truck-only routes that comply with precedence constraints. In the second phase, a splitting algorithm combined with an endurance checking procedure is employed to generate hybrid truck–drone routes considering drone limitations. In the final phase, a variable neighborhood descent approach is introduced to further improve the solution by strategically perturbing the truck-only routes. Extensive simulations and experiments demonstrate that the proposed three-phase heuristic algorithm consistently achieves higher-quality solutions with reduced computation time compared with the widely used adaptive large neighborhood search method.

This article addresses a finite-time trajectory tracking control problem for autonomous underwater vehicles with parametric uncertainties, external disturbances, thruster faults, and saturation. First, considering the unpredictable oceanic environment with the thruster faults and model uncertainties, an event-triggered finite-time generalized extended state observer (ETFTGESO) is developed to estimate the synthetic failure and unmeasured velocities simultaneously. Triggered position data is used as feedback in the correction terms of ETFTGESO, which consequently reduces unnecessary communication or computational burden. The observer order is expanded by two additional states, which enhance the estimation accuracy. Then, a homogeneous output feedback controller is proposed to achieve finite-time stability of the vehicle. To improve the convergence rate of the position and velocity trajectories, the finite-time control law is updated by integrating a homogeneous integral sliding surface. Rigorous theoretical analysis verifies fast convergence, the influence of control parameters on bounded stable region, and accurate dynamic positioning. Finally, numerical simulations are carried out to demonstrate the superiority of the proposed control scheme.

This article copes with the distributed control and target tracking (DCTT) problem in general linear and Lipschitz multiagent systems (MASs). In comparison to the traditional DCTT algorithms that were developed for MASs in ideal conditions, two schemes based upon a resilient protocol are proposed for linear and nonlinear MASs to estimate and track a mobile target where all agents are subject to composite attacks, including camouflage attacks, DoS attacks, sensor attacks, and actuator attacks. Based on the digital twin approach, a twin layer (TL) with high privacy and security is introduced to separate the problem of DCTT into two tasks: 1) handling DoS attacks on the TL and defending against sensor and 2) actuator attacks on the cyber-physical layer (CPL). First, two distributed estimation algorithms are established to reconstruct the agents and target dynamics for every agent on the TL in the presence of DoS attacks. Second, using the reconstructed agents and target dynamics on the TL, a resilient distributed control protocol is designed to resist sensor and actuator attacks on the CPL. The current scheme guarantees the achievement of control and target tracking such that the DCTT error of the proposed design is ultimately bounded in terms of linear matrix inequality. By applying two simulation examples, the presented algorithms are also validated.

In this article, a novel visionary policy iteration (VPI) framework is proposed to address the continuous-action reinforcement learning (RL) tasks. In VPI, a visionary Q-function is constructed by incorporating the successor state into the standard Q-function. Due to the introduction of the successor state, the proposed visionary Q-function captures information about state transitions within the Markov decision process (MDP), thereby providing a forward-looking perspective that enables a more accurate and foresighted evaluation of potential action outcomes. The relationship between the visionary Q-function and the standard Q-function is analyzed. Subsequently, both the policy evaluation and policy improvement rules in VPI are designed based on the proposed visionary Q-function. The convergence proof for VPI is provided, ensuring that the iterative policy sequence in VPI will converge to the optimal policy. By combining the VPI framework with the twin delayed deep deterministic policy gradient (TD3) algorithm, a visionary TD3 (VTD3) algorithm is developed. The evaluation of VTD3 is performed on multiple continuous-action control tasks from Mujoco and OpenAI Gym platforms. The results of comparative experiments demonstrate that VTD3 can achieve more competitive performance than other state-of-the-art (SOTA) RL approaches. Additionally, the experimental results indicate that VPI enhances decision-making capability, reduces Q-function estimation bias, and improves sample efficiency, thereby boosting the performance of existing RL algorithms.

Constrained nonlinear equations (CNEs) are involved in numerous practical applications, and many solutions to CNEs have been reported. In particular, a special neural network called zeroing neural network (ZNN) has recently been developed to solve the time-dependent CNE (TDCNE). In this study, we propose a new discrete-time ZNN (DTZNN) model to determine the numerical solution of the TDCNE. Such a model, which is derived from the discretization of the previous ZNN model via a special difference formula, can achieve excellent performance on computing and solving the TDCNE. Theoretical analysis and comparative numerical results further denote the validity and superiority of the proposed DTZNN model. Finally, the proposed model is used to simulate the dual-arm robot system, which verifies the practicability and feasibility of the DTZNN.

The integration of cooperation and competition strategies in game theory emphasizes the systematic nature of strategy spaces and group interactions, forming the basis for achieving win-win scenarios. This is particularly crucial under coalition constraints and incomplete information. Addressing these challenges, this article introduces a comprehensive mathematical method for policy formation using co-opetition topological networks. This method enables autonomous decision-making and game equilibrium in group decision scenarios, considering individual preferences amidst constraints like incomplete information and alliance limitations. Leveraging the complementary entropy theorem on superiority, inferiority, and fuzzy measures, we propose a cognitive model for information interaction and attribute fusion. Utilizing the ordered weighted averaging operator and average tree solutions aids in identifying optimal alliance structures. We subsequently discuss evaluating missing information to complete the topological network. Updating the cognitive model and value function, we develop a Gaussian oscillation heuristic algorithm to explore alliance and component strategy spaces. Simulation results are provided and analyzed to illustrate the performance and effectiveness of our approach.

This article concerns the stochastic generalized Nash equilibrium problem (NEP) characterized by uncertain expected value cost functions and shared constraints. In a full-decision information setting, we develop a novel distributed stochastic reflected forward–backward (FB) algorithm, which requires that each agent has access to the others’ decisions. Considering that agents only know the decisions from their immediate neighbors, a distributed stochastic RFB (SRFB) algorithm under partial-decision information is proposed. By recasting the problem as a monotone inclusion problem, both algorithms almost surely converge to a stochastic generalized Nash equilibrium by combining the stochastic approximation scheme and the variance reduction scheme. Finally, the numerical experiment validates the feasibility of the proposed algorithms and confirms the correctness of the theory.

This article investigates a constrained safe cooperative maneuvering method for a group of autonomous surface vehicles (ASVs) with performance-quantized indices in an obstacle-loaded environment. Specifically, an avoidance-tolerant prescribed performance (ATPP) with one-sided tunnel bounds is designed to predetermine the cooperative maneuvering performance of multiple ASVs. Next, an auxiliary system is constructed to modify performance bounds of ATPP for tolerating possible collision avoidance actions of ASVs. In the guidance loop, nominal surge and yaw guidance laws are developed using the ATPP-based transformed relative distance and heading errors. A barrier-certified yaw velocity protocol is proposed by formulating a quadratic optimization problem, which unifies the nominal yaw guidance law and CBF-based collision-free constraints. In the control loop, two prescribed-time disturbance observers (PTDOs) are devised to estimate unknown external disturbances in the surge and yaw directions. The antidisturbance control laws are designed to track the guidance signals. By the stability and safety analysis, it is proved that error signals of the proposed closed-loop system are bounded and the multi-ASV system is input-to-state safe. Finally, simulation results are used to demonstrate the effectiveness of the presented constrained safe cooperative maneuvering method.

This article proposes an event-based asymptotic tracking control method for nonlinear strict-feedback systems with multiple unknown control directions. The system is characterized by multiple unknown control directions, which pose challenges to its performance. In contrast to traditional Nussbaum-type methods, we propose a novel Nussbaum-type function to handle multiple Nussbaum-type gains, ensuring robust asymptotic tracking. Additionally, two event-triggered mechanisms are developed to alleviate the computational complexity of adaptive Nussbaum design. The static event-triggered mechanism significantly improves the system’s responsiveness to dynamic changes by employing dynamically decreasing thresholds. Building on this, a dynamic event-triggered mechanism is introduced, incorporating an internal variable that continuously adjusts the triggering conditions over time. Furthermore, the proposed design not only achieves asymptotic tracking control but also ensures that both event-triggered mechanisms avoid the Zeno phenomenon. To validate the proposed design schemes, a simulation example of a marine surface vehicle is presented.

This article focuses on addressing the distributed three-dimensional (3-D) formation maneuver control problem of multiple autonomous underwater vehicles (AUVs) in undersea exploration. The 3-D affine formation maneuver strategy by fusion of the stress matrix is employed to maneuver the multi-AUV formation for the sake of achieving the formation pattern maneuver transformations (e.g., rotation, scaling, shear, coplanarity, collineation, etc.). The desired yaw angle of each AUV is calculated in real time on the basis of its individual desired trajectory, which can guarantee the attitude configuration for the multi-AUV formation. Meanwhile, the two-layered leader-follower framework is employed to guarantee the flexible maneuvers, in which the AUVs are divided into three layers: 1) first leader AUV; 2) second leader AUV group; and 3) follower AUV group. The desired formation maneuver information only needs to be known by the first leader AUV. For the second AUV group, the formation maneuver information is estimated by the designed distributed estimators to acquire their desired reference trajectories. The follower AUV group only needs to track their desired trajectories affinely localized by the leader AUVs. Furthermore, the adaptive fast nonsingular integral terminal sliding-mode controllers are designed for the leader layers and follower layer to guarantee the fast and accurate tracking of their desired trajectories, such that the multi-AUV formation system is able to realize the precise maneuvers. Finally, the effectiveness of the proposed control strategy is verified by the high-fidelity simulations with real water current disturbances.

Vision-and-Language Navigation (VLN) in continuous environments aims to navigate robot agents in unseen environments following natural language instructions. The majority of existing approaches rely on constructing semantic maps or topological maps to record information. However, semantic maps overlook the detailed information of objects and the correspondence among views during navigation, while topological maps lack the spatial representation between entities. To address these limitations, we propose a novel visual feature representation method for continuous VLN, called Multiple Visual Features in Topological Map (MV-Topo). MV-Topo utilizes three distinct visual encoders to extract visual features, which are integrated in the dynamically generated topological map. These fused features actively participate in the subsequent cross-modal planning to derive a long-term path towards a subgoal, effectively guiding the agent to reach the final location. We experimentally demonstrate the effectiveness of our approach and achieve competitive results on the full VLN-CE test splits. Notably, our method outperforms the state-of-the-art by 3.5% in terms of the Navigation Error (NE) metric, indicating that the utilization of multiple visual features significantly enhances the agent’s perception of semantic targets.

Object detection on unmanned aerial vehicle (UAV) images is an important branch of object detection, belonging to small object detection in a broad sense. Detecting objects in UAV images poses a greater challenge due to the predominance of small objects and dense occlusion caused by UAV capturing images from varying heights and angles. To solve the above problems, we propose Residual Spatial Reduced Transformer based on YOLOv5 (RSRT-YOLOv5). Specifically, Slice Aided Enhancement Module (SAEM) is introduced to enhance the feature quality of small objects. Secondly, a Global attention-based Bi-directional Feature Fusion (GBFF) module is proposed. In the Neck architecture, an efficient Residual Spatial Reduced Transformer (RSRT) module is integrated in order to achieve more efficient feature representation and richer global contextual associations. Finally, our method is evaluated on the Visdrone2019 dataset, and the experimental results show that RSRT-YOLOv5 outperforms the baseline model (yolov5) and successfully improves the detection performance of UAV images.

Bearing anomaly detection plays a crucial role in modern industries as most rotating machinery faults are attributed to faulty bearings. However, acquiring fault samples in industry is a time-consuming and expensive process. To address this issue, this paper presents an integrated unsupervised learning method named AE-AnoWGAN (Autoencoder Wasserstein Generative Adversarial Network). AE-AnoWGAN is capable of detecting abnormal bearings and performing anomaly localization without the need for labeled data. In this approach, industrial data is initially processed using continuous wavelet transform to convert it into time-frequency representations (TFRs). These TFRs are then fed into the integrated AE-AnoWGAN for training. AE-AnoWGAN consists of multiple encoder-decoder and discriminator pairs, which are randomly paired and trained using adversarial training. The encoder maps the TFRs to a latent space, and the pre-trained generator acts as the decoder to generate reconstructed TFRs. During the testing phase, the model calculates anomaly scores for the input TFRs. Experimental evaluations were conducted using the PU bearing dataset and IMS bearing dataset. Comparative results demonstrate that the proposed AE-AnoWGAN method outperforms existing approaches in terms of anomaly detection accuracy. Moreover, the method exhibits high anomaly detection efficiency, making it suitable for real-time monitoring applications. Furthermore, this method provides practical value by enabling anomaly localization and bearing degradation estimation of TFRs.

Offline reinforcement learning (RL) aims at learning an optimal policy from a static offline data set, without interacting with the environment. However, the theoretical understanding of the existing offline RL methods needs further studies, among which the conservatism of the learned Q-function and the learned policy is a major issue. In this article, we propose a simple and efficient offline RL with relaxed conservatism (ORL-RC) framework for addressing this concern by learning a Q-function that is close to the true Q-function under the learned policy. The conservatism of learned Q-functions and policies of offline RL methods is analyzed. The analysis results support that the conservatism can lead to policy performance degradation. We establish the convergence results of the proposed ORL-RC, and the bounds of learned Q-functions with and without sampling errors, respectively, suggesting that the gap between the learned Q-function and the true Q-function can be reduced by executing the conservative policy improvement. A practical implementation of ORL-RC is presented and the experimental results on the D4RL benchmark suggest that ORL-RC exhibits superior performance and substantially outperforms existing state-of-the-art offline RL methods.

In this work, we address the issue of asynchronous deconvolution filter design for 2-D Markov jump systems with random packet losses. First, the considered plant is established by a well-known Fornasini-Marchesini model. Then, an asynchronous 2-D deconvolution filter is proposed to reconstruct the 2-D signal with measurement noise to satisfy a prescribed performance specification. The asynchronization phenomenon between the system modes and filter modes is characterized by a hidden Markov model. Besides, in practical applications, the congestion of the transmission channel between the system and the filter may lead to data losses, which may make the system performance degraded or even unstable. For this, an improved 2-D single exponential smoothing scheme is proposed to generate some predictions of the lost information to compensate for lost packets. By means of the 2-D Lyapunov stability theory, some sufficient conditions are acquired, which can make the resultant system asymptotic mean-square stable and satisfies an$\mathcal{H}_{\infty}$disturbance attenuation performance. At last, an example concerning image processing is adopted to verify the correctness of the presented asynchronous 2-D deconvolution filtering scheme.Note to Practitioners—In practical applications, many dynamics may suffer from undergoing sudden structural or parameter changes, resulting in a system that is difficult to describe clearly. The Markov jump systems, consisting of states and modes, can handle this problem satisfactorily. Considering the effects of some unfavorable factors, i.e., delay, quantization, and environmental noise, a hidden Markov model is employed to handle the asynchronous problem between the system and the filter. On the other hand, the emergence of 2-D systems effectively solves the problem of the system’s state evolving in two directions. In addition, the congestion of the transmission channel between the system and the filter may lead to data loss. To compensate for the impact of data packet loss, an improved 2-D single exponential smoothing scheme is proposed.

This study proposes a resilient asynchronous controller for Markovian jump neural networks, which can be impervious to the dual cyber attacks that act on actuators and sensors. The complicated occasions of uncertain system modes, actuator and sensor attacks, and unknown attack information are all considered. It is known that sensor attacks can generate corrupted signals to destroy the controller, and actuator attacks can maliciously tamper with the control signals. Mindful of such circumstances, a resilient controller is developed to defend against actuator and sensor attacks as well as to guarantee good synchronization performances. To overcome the unknowns of the occurred attacks, some new adaptive laws for adjusting attack parameters are introduced into the controller to assist with offsetting attack-induced influences. Under the designed controller, the synchronization error dynamic system is proven to be ultimately bounded within a known region, and then the obtained results are extended to address some other cases. Furthermore, a practical example of an analog resistance-capacitance network circuit and some comparative studies are demonstrated to verify the feasibility and superiority of the proposed controller.

Offline reinforcement learning (offline RL) aims to find task-solving policies from prerecorded datasets without online environment interaction. It is unfortunate that extrapolation errors can cause over-optimistic Q-value estimates when learning with a fixed dataset, limiting the performance of the learned policy. To tackle this issue, this article proposes an offline actor-critic with behavior value regularization (OAC-BVR) method. In the policy evaluation stage, the difference between the Q-function and the value of the behavior policy is considered as the regularization term, driving the learned value function to approach the value of the behavior policy. The convergence of the proposed policy evaluation with behavior value regularization (PE-BVR) and the value function difference are analyzed, respectively. Compared with existing offline actor-critic methods, the proposed OAC-BVR method integrates the value of the behavior policy, thereby simultaneously alleviating over-optimistic Q-value estimates and reducing Q-function bias. Experimental results on the D4RL MuJoCo and Maze2d datasets demonstrate the validity of the proposed PE-BVR and the performance advantage of OAC-BVR over the state-of-the-art offline RL algorithms. The code of OAC-BVR is available at https://github.com/LongyangHuang/OAC-BVR.

This article investigates the cooperative rendezvous control problem for perturbed heterogeneous marine systems composed of an autonomous underwater vehicle (AUV) and an autonomous surface vehicle (ASV). A novel Lyapunov-based model predictive control (LMPC) framework is presented to accomplish safe and precise rendezvous under input limitations and external disturbances. First, by incorporating the prescribed performance control (PPC) technique into the LMPC framework, we transform the original ascending state of the AUV into a self-constrained state, which serves as the decision variable of the model predictive control (MPC) optimization problem. Then, PPC-aided auxiliary control laws based on disturbance observers (DOBs) are designed to establish a robust contractive constraint to provide stability margins. Combining the LMPC with the PPC technique makes the original state-constrained problem an equivalent state-constraint-free problem. By addressing the MPC problem for the equivalent unconstrained system, the proposed method preserves the rendezvous safety. With the robust contractive constraint, the proposed safety-preserving LMPC (SP-LMPC) controller can inherit robustness and stability from the robust auxiliary control laws. Furthermore, theoretical analyses are conducted to assess recursive feasibility and closed-loop stability. With comprehensive theoretical support, the proposed method provides a new framework to simultaneously address state constraints and disturbances for highly nonlinear marine systems. Finally, simulations and comparisons are conducted to demonstrate the effectiveness and advantages of the proposed algorithm.

Due to the complex network environment, the feedback information cannot be timely received by the controller. This article proposes a method on the exponential synchronization for the Markovian jump neural networks, which is achieved by designing a new asynchronous delayed-feedback controller, with its feedback delay taken into account. The quantized relationship between the exponential synchronization and the feedback delay is derived from a new designed Lyapunov functional, to acquire delay boundaries. With the help of a hidden-Markov process, the designed controller shows asynchrony, which allows controller modes to run free. In particular, the detection probability is assumed to be bounded known, marking a breakthrough over existing results. Moreover, the proposed method proves to be applicable in both synchronous and asynchronous cases. By using the proposed method, the computation freedom of the controller gain matrix can be substantially augmented. Further, comparative numerical studies are implemented to validate the effectiveness and superiority of the proposed method.

In this article, a distributed output-feedback consensus maneuvering problem is investigated for a class of uncertain multiagent systems with multi-input and multi-output (MIMO) strict-feedback dynamics. The followers are subject to immeasurable states and external disturbances. A distributed neural observer-based adaptive control method is designed for consensus maneuvering of uncertain MIMO multiagent systems. The method is based on a modular structure, resulting in the separation of three modules: 1) a variable update law for the parameterized path; 2) a high-order neural observer; and 3) an output-feedback consensus maneuvering control law. The proposed distributed neural observer-based adaptive control method ensures that all followers agree on a common motion guided by a desired parameterized path, and the proposed method evades adopting the adaptive backstepping or dynamic surface control design by reformulating the dynamics of agents, thereby reducing the complexity of the control structure. Combined with the cascade system analysis and interconnection system analysis, the input-to-state stability of the consensus maneuvering closed loop is established in the Lyapunov sense. A simulation example is presented to demonstrate the performance of the proposed distributed neural observer-based adaptive control method for output-feedback consensus maneuvering.

In this article, we consider the problem of switched-command-filtered-based adaptive fuzzy output-feedback funnel control for switched nonlinear multi-input multi-output (MIMO) delayed systems. A switched MIMO high-gain state observer is constructed for each subsystem to estimate unavailable system states. Compared with the conventional command filter technique, the main advantage is that the improved error-compensating signals are designed for each switched subsystem to remove the filtered errors and avoid an explosion of complexity and the singularity problem. Different from the traditional Lyapunov--Krasovskii functional method, design obstacles stemming from unknown time delays are overcome for the switched delayed systems by using appropriate multiple Lyapunov--Krasovskii functions and combining with the approximation capability of the fuzzy logic systems. Under a category of switching signals with mode-dependent average dwell time, all signals in the closed-loop switched system are semiglobally uniformly ultimate bounded under the output-feedback control; meanwhile, the tracking errors can remain in prespecified performance funnels. Case studies illustrate the flexibility and effectiveness of the proposed control approach.

This article investigates a containment control problem of networked autonomous surface vehicles (ASVs) with challenges of actuator faults, uncertainties, and environmental disturbances. There exist the individual tasks of networked ASVs and virtual leaders beyond the overall goal. The containment control can be transformed into a noncooperative game problem to balance individual and group objectives. With the noncooperative game theory, the containment task is reformulated as a Nash equilibrium seeking problem of networked ASVs regarded as players. To achieve the Nash equilibrium seeking of ASVs, a noncooperative-game-based fault-tolerant fuzzy containment controller is developed for networked ASVs with an adaptive compensation technique. First, a fuzzy predictor based on the high-order tuner is constructed to tackle the total disturbances. Next, a parameter estimator for unknown faults is designed using the adaptive compensation strategy. With identified disturbances and faults, a desired control law and an intermediate control variable are developed to enable ASVs to operate effectively despite faults. By the Lyapunov functions, theoretical results show that the actions of ASVs can converge to the neighborhood region of the Nash equilibrium. Finally, simulation results are presented to demonstrate the validity of the proposed fault-tolerant containment control method.

In this article, we study the fault detection problem of unmanned surface vehicles through the implementation of fuzzy multiprocessors. By employing the Takagi–Sugeno fuzzy technique, the linear approximation of unmanned surface vehicles is obtained, and a fuzzy multiprocessor architecture is proposed to estimate the state of unmanned surface vehicles. With the residual signal generated by multiprocessors, a detection logic is designed to realize the fault detection. Based on the Lyapunov method, sufficient conditions are given to ensure that the error dynamic system is asymptotically stable and meets the given$H_{\infty }$and$H\_$performance. Assisted by genetic algorithms, a two-step optimization algorithm is proposed to optimize the mixed$H_{\infty }$and$H\_$performance. Finally, case studies are provided to verify the effectiveness and superiority of the proposed method.

This article presents a sliding mode controller to address the challenge of achieving mean-square bounded consensus tracking for leader–follower multiagent systems (MASs) under stochastic denial-of-service (DoS) attacks. Such cyber attacks can reduce the effective transmission of measurement signals by interrupting the communication between the MASs and the control station, thereby corrupting the feasibility of control. Existing descriptions of DoS attacks typically rely on two energy assumptions regarding attack frequency and duration, which introduce conservatism into the stability analysis of the system. Conversely, this article models DoS attacks using a two-mode Markov process, thereby preventing the necessity for explicit energy constraints. To ensure control feasibility under DoS attacks, a control scheme that uses the latest uncontaminated control input signal and uses it as the new primary control input signal until the DoS attack ceases is adopted to mitigate the effects of DoS attacks effectively. Based on the Lyapunov function method, it is shown that the designed sliding mode controller guarantees the reachability and mean-square bounded consensus tracking of the resulting global tracking error dynamic system under Markov-type DoS attacks. At last, the correctness and the effectiveness are verified by a web-based multiple dc motors angle coordinated control experiment.

Dynamic target tracking technology has a broad application prospect in marine transportation, intelligent marine monitoring, border and coastal defense, etc. However, most target tracking guidance systems designed for unmanned surface vehicles (USVs) lack automatic obstacle avoidance capabilities, which limits their tracking performance. To address this challenge, this paper investigates target tracking guidance for USVs in the presence of obstacles. In order to track the target, the sensors fixed on the bow of the USVs need to be oriented toward the target, especially when the USV is sufficiently close to the target. For this purpose, a bias proportional navigation guidance law with look angle constraints is presented for guiding the follower USVs to orient and approach the moving target. In order to navigate the USVs along a safe route to avoid obstacles, the obstacle profile angle constraint is formulated into the guidance law by solving the bias function with final angle boundary conditions. The field experimentation takes place in a 40-meter-wide and 80-meter-long section of the Huchuntang River. Here, a USV equipped with the proposed guidance law effectively tracks a moving target while navigating around obstacles. Results indicate that the proposed guidance law is capable of tracking the object, avoiding obstacles, and orienting the USV to the target at the final time. The experimental test video is presented in (https://youtu.be/l5SQf2ZgcxM).

The sensor faults and the communication burden are the core issues in fields of the intelligent maritime search control. In this paper, a robust adaptive event-triggered control strategy is presented for the underactuated surface vessel-unmanned aerial vehicles (USV-UAVs) cooperative system to implement the maritime parallel search mission. The proposed scheme is comprised of two parts, i.e., the three-dimensional (3D) search guidance principle and the cooperative formation control law. The developed guidance principle can generate the reference signals for the USV and UAVs, which the maneuvering characteristics of the heterogeneous agents are considered at the waypoints. Linked with the guidance term, a robust adaptive event-triggered control algorithm is designed for the cooperative system by fusing the dynamic event-triggered mechanism and sensor-tolerant technique. The dynamic triggered threshold is constructed on basis of the state error rather than the predefined parameters. Besides, the constrains of the sensor faults and the model uncertainties are tackled by constructing the adaptive parameter and robust neural damping term. Through the Lyapunov theorem, the semi-global uniform ultimate bounded (SGUUB) stability is guaranteed for all state variables. Finally, the advantages of the proposed scheme are evaluated on simulation platform, exhibiting the good tracking accuracy and tolerant performance in presence of the external disturbances.

This paper investigates the tracking control of a multi-quadrotor slung-load system (MQSLS), incorporating a dynamic model that simultaneously accounts for underactuation, nonlinearity, dynamic coupling, and unmodeled dynamics. We introduce a novel force distribution algorithm, which bifurcates the cooperative control to two distinct components: slung-load position control; and cable configuration control along with quadrotor attitude control. Employing this strategy results in a cooperative controller that: (i) relaxes the constraints on cable configuration; and (ii) requires only up to the third time derivative of the reference trajectory. The proposed control scheme ensures almost asymptotic stability of the overall closed-loop error system under unknown constant disturbances affecting both quadrotors and payload. A comprehensive set of simulations and experimental results validates the effectiveness of the proposed control strategy.

This paper is concerned with a performance-prescribed coordinated control problem of multiple underactuated marine surface vehicles (MSVs) subject to internal uncertainties, external disturbances, and actuator faults. An echo state network-based (ESN-based) transient-reinforced tunnel coordinated control method is proposed for underactuated MSVs with prescribed performance metrics. Specifically, a graph-based trajectory generator is designed to generate reference signals for various application scenarios. In the guidance loop, a tunnel prescribed performance (TPP) is established to characterize the position and heading coordination metrics of underactuated MSVs. With the TPP-based equivalent transformation, the tunnel guidance laws are devised by an underactuation guidance principle. In the control loop, an ESN-based neural estimator is constructed to identify unknown kinetics consisting of internal uncertainties, external disturbances, and actuator faults. Utilizing the estimated information, the ESN-based surge and yaw control laws are presented. The proposed closed-loop system is proven to be input-to-state stable via the theoretical analysis, and position and heading tracking errors can evolve within TPP constraints regardless of actuator faults. Finally, comparison simulation results are employed to verify the effectiveness and superiority of the proposed method.

To improve the autonomy of marine ranching operations, this paper addresses the cooperative formation control and multi-task switching problem of ranch autonomous marine vehicles (AMVs) with the structure synchronized dynamic event-triggered mechanism (DETM). In the proposed algorithm, adaptive potential ship (APS) technique is adopted to guarantee the integrity and continuity of the guidance signal. Combined with the guidance principle, a cooperative formation control algorithm is proposed by employing the DETM and neural networks (NNs). The communication burden in the channel from the sensor to the controller and from the controller to actuator has been reduced for the merits of the proposed DETM. Unlike the existing results, the proposed DETM can activate the threshold parameters, adaptive parameters and NNs weight estimators at the triggering times synchronously. This releases the computation burden greatly. Considerable effort has been made to guarantee the semi-globally uniformly ultimately bounded (SGUUB) stability via the Lyapunov theorem. Finally, two simulations consist of the marine ranching path following and comparative example are carried out to evaluate the advantages of the proposed strategy.

In offline actor-critic (AC) algorithms, the distributional shift between the training data and target policy causes optimistic value estimates for out-of-distribution (OOD) actions. This leads to learned policies skewed toward OOD actions with falsely high values. The existing value-regularized offline AC algorithms address this issue by learning a conservative value function, leading to a performance drop. In this article, we propose a mild policy evaluation (MPE) by constraining the difference between the values of actions supported by the target policy and those of actions contained within the offline dataset. The convergence of the proposed MPE, the gap between the learned value function and the true one, and the suboptimality of the offline AC with MPE are analyzed, respectively. A mild offline AC (MOAC) algorithm is developed by integrating MPE into off-policy AC. Compared with existing offline AC algorithms, the value function gap of MOAC is bounded by the existence of sampling errors. Moreover, in the absence of sampling errors, the true state value function can be obtained. Experimental results on the D4RL benchmark dataset demonstrate the effectiveness of MPE and the performance superiority of MOAC compared to the state-of-the-art offline reinforcement learning (RL) algorithms.

In this article, a neural adaptive intermittent output feedback control is investigated for autonomous underwater vehicles (AUVs) with full-state quantitative designs (FSQDs). To achieve the prespecified tracking performance determined by quantitative indices (e.g., overshoot, convergence time, steady-state accuracy, and maximum deviation) at both kinematic and kinetic levels, FSQDs are designed by transforming constrained AUV model into an unconstrained model via one-sided hyperbolic cosecant boundaries and nonlinear mapping functions. An intermittent sampling-based neural estimator (ISNE) is devised to reconstruct the matched and mismatched lumped disturbances as well as immeasurable velocity states of transformed AUV model, where only system outputs after intermittent sampling are required. Using the estimations of ISNE and the system outputs after triggering, an intermittent output feedback control law incorporated with hybrid threshold event-triggered mechanism (HTETM) is designed to achieve ultimately uniformly bounded (UUB) results. Simulation results are provided and analyzed to validate the effectiveness of the studied control strategy with application to an omnidirectional intelligent navigator (ODIN).

This work solves the issue of event-triggered fault detection for networked systems under the denial-of-service (DoS) attacks. To improve the utilization rate of network resources, an event-triggered mechanism is employed to reduce the transmission frequency. A fault detection observer is designed to generate the residual signal for the concerned system with external disturbances and faults. Note that the input signal of the fault detection observer (FDO) transmitted over a communication network is assumed to be vulnerable to cyber attacks, in which the adversaries may interrupt the transmission process. The${\mathcal {H}}_\infty$attenuation index and${\mathcal {H}}_{\_}$increscent index are introduced into the fault detection observer design, which reflects the robustness to external disturbances and sensitivity to faults, respectively. By applying the Lyapunov functional technology, some nonlinear matrix inequalities are acquired to guarantee the existence of the fault detection observer with the appearance of DoS attacks. Then, a genetic algorithm is adopted to cope with the derived nonlinear matrix inequalities without introducing any conservatism. The simulation results related to an unmanned aerial vehicle model are presented to illustrate the correctness and effectiveness of the presented fault detection strategy.

This article develops a resilient-learning control strategy for a kind of cyber-physical system to mitigate the influence of a mixed-type of network attacks. Such an attack is composed of a false-data-injection attack and a replay attack, which can be represented comprehensively by using Markov jump signals. Note that the involved attacks are assumed to be uncertain, which requires a three-layer neural network to learn them. Based on attack approximations as the output from the neural network, a resilient and efficient controller is designed to defend against the mixed-type of network attacks, in which several adaptive laws are proposed to estimate the involved neural network weights. Under the designed controller, the ultimate boundness and asymptotical stability are discussed. Finally, a practical vertical taking-off and landing helicopter model is proposed to verify the developed controller.

This article proposes an event-triggered quantitative prescribed performance neural adaptive control method for autonomous underwater vehicles (AUVs). At kinematic level, to achieve a quantitative predetermined tracking performance without violating user-defined transient indices, a quantitative prescribed performance control (QPPC) scheme is devised, where the overshoot of the transient tracking response can be specified by a quantitative design relationship. To pursue a tradeoff between tracking accuracy and resource saving, a hybrid threshold-based event-triggered mechanism (HTETM) is designed and incorporated into the AUV controller design procedure. Additionally, a modified echo state neural network (MESNN) is employed for disturbance estimation, where intermittent system information produced by the HTETM is used for online learning, resulting in that both the communication data throughput between the controller and actuators and the online computational load can be diminished synchronously. Finally, a control law is devised at dynamic level to compensate for the triggered error induced by the aperiodic sampling of HTETM. Simulation results are provided and analyzed to validate the effectiveness of the proposed control strategy with application to an omni directional intelligent navigator.

In this article, the problem of finite-time$H_{\infty }$filtering design is studied for Markov jump systems (MJSs) with deception attacks and delays. Considering that data transmission networks between the system and filter will be subject to deception attacks and delays, a switching filter is designed by current states and modes as well as delayed states and modes. Since there are non-Markov jumps caused by the current mode and the delayed mode in the error dynamic systems, an extended state space method is employed to reconstruct it as switched error dynamic MJSs. By selecting multiple Lyapunov functionals, nonlinear sufficient conditions are given to ensure the finite-time boundedness and$H_{\infty }$performance of the switched error dynamic MJSs. In order to deal with the derived nonlinear conditions without introducing conservatism, a combination of genetic algorithms and linear matrix inequality tools is used to solve filter gains. Simultaneously, a multiobjective optimization between the finite-time boundary of system states and$H_{\infty }$performance index can be realized by the obtained filter gains. Simulation results are provided to illustrate the feasibility and effectiveness of the proposed approach.

This article concerns the co-design scheme of the adaptive event-triggered mechanism (AETM) and asynchronous$H_{\infty }$control for two-dimensional (2-D) Markov jump systems. First, we introduce a hidden Markov model with the observation that the asynchronous phenomenon is inevitable between the plant mode and the controller mode. Besides, for economizing the communication times, an innovative 2-D AETM is constructed, which can dynamically regulate the event-triggered thresholds to strive for better system performance. Then, by utilizing the 2-D Lyapunov stability theory, nonlinear matrix inequalities are built to ensure the asymptotic mean-square stability with an$H_{\infty }$performance for the closed-loop 2-D system. To avoid introducing any conservatism when handling the above nonlinear matrix inequalities, a binary-based genetic algorithm (BGA) is exploited to treat some variables as known, such that derive some directly solvable linear matrix inequalities. Finally, a simulation example is provided to verify the effectiveness of the proposed 2-D AETM-based asynchronous controller strategy with a BGA.

In this paper, we study the quantitative design paradigm (QDP) of tracing control for a class of second-order system and further extend this to solve the trajectory tracking problem of autonomous underwater vehicles. The key merit of QDP is the capability of assigning some quantitative indices (e.g., overshoot and convergence time). To pursue performance enhancement with regard to tracking performance and bandwidth saving, a sectionalized event-triggered mechanism (SETM) incorporated with prespecified convergence time is proposed. To recognize the peculiarities of the lumped disturbances, an estimation-triggered neural network (ETNN) is designed via a property indicator, such that the disturbances that deteriorate the performance of the closed-loop system will be compensated and beneficial disturbances will be reserved otherwise, enabling less energy consumption without sacrificing the tracking performance. Theoretical analysis and simulation results are provided and analyzed, validating the performance and efficiency of the proposed solution.

Vessels sailing in a single platoon could reduce resistance from the perspective of the whole platoon and the individual vessel, and contribute to improving energy benefits. Moreover, transportation energy costs and traffic efficiency are essential indicators for measuring waterborne transportation systems. We attempt to minimize transportation energy costs by coordinating platoon formation using a distributed framework of controllers. A large-scale coordinated vessel platooning program is proposed to minimize transportation energy costs and optimize traffic efficiency while guaranteeing safety. The control framework covers routing, energy consumption-dependent cooperative platooning decision and speed optimization based on graph search algorithm, cluster analysis, optimal control approach and model predictive control. Firstly, a local scheduling strategy combined with the leader vessel selection algorithm is adopted. Furthermore, we used cluster analysis to create a series of mergeable vessel platooning sets. Then, we used the mathematical planning method and a two-step hybrid optimal control approach to calculate the improvement and optimization of each vessel platoon’s path and speed. Finally, the scalability of the scheduling strategy is elucidated. In a simulation of large scale inland waterborne network, savings surpassed 3.5% when six hundreds vessels participated in the system. These simulation results reveal that the scheduling strategy coordinating vessels into vessel platooning, which improves transportation efficiency as well as descends cost, comparing to a fixed origin route in the waterway network.

In this work, we consider the problem of finite-region asynchronous dissipative control and pay more attention to the transient behavior of a class of two-dimensional fuzzy Markov jump systems (MJSs). First, the considered plant is modeled based on a well-known Fornasini–Marchesini equation. The asynchronization phenomenon between the system modes and controller modes is characterized by a hidden Markov model. Then, by a fuzzy-basis-dependent and mode-dependent Lyapunov function, sufficient conditions are established, which can make the overall closed-loop fuzzy dynamic MJSs be finite-region bounded with a strictly$(T, S, R)$-$\theta $-dissipative performance. Finally, a numerical example concerning the Darboux equation is employed to validate the effectiveness and performance of the presented control scheme.

In this article, a new asynchronous event-triggered-based output-feedback control method is proposed for a special type of networked Markovian jump systems susceptible to network delays and attacks. A novel controller is designed to make allowances for four cases that are common in practical situations: 1) a network delay; 2) false data injection (FDI) attacks; 3) asynchrony between system modes and controller modes; and 4) an event-triggered scheme. First, to avoid traditional assumptions about system delays, a novel Lyapunov function is proposed, based on which a new stability theory is formulated to guarantee exponential stability. Second, an FDI attack is represented as a stochastic process, which can be dealt with properly by the designed controller. Third, a new delay-based event-triggered scheme is brought into the controller design to reduce the network bandwidth consumption and save the network transmission resources. Then, an asynchronous controller is engineered with the aid of a hidden-Markov model, which can extend the application scope of the proposed method. Note that we put the above four factors into one framework, which implies a co-design of an anti-attack controller and an event-triggered scheme is developed. Finally, an operational amplifier circuit is simulated to verify the feasibility and superiority of the designed controller.

In the presence of static and moving obstacles, this article investigates an output-feedback finite-time safety-critical coordinated control method of multiple under-actuated marine surface vehicles (MSVs) subject to velocity and input constraints. Specifically, based on robust exact differentiators, a finite-time state observer (FTSO) is first developed to recover the unavailable velocities while estimating the total disturbances containing model uncertainties and environmental disturbances. Next, with the aid of estimated velocities from FTSO, a nominal finite-time guidance law is designed for achieving the distributed formation of MSVs at the kinematic level. By the forward invariance principle, finite-time control barrier functions (FTCBFs) are used to construct the collision-free velocity sets for the multi-MSV system. To unify the control and safety objectives, quadratic optimization problems are formulated under collision-free velocity sets and velocity constraints. To facilitate real-time implementations, one-layer recurrent neural networks are employed to solve the quadratic optimization problem. Then, a nominal finite-time control law based on FTSO is presented at the kinetic level. The optimal control laws are solved within the input constraints. All error signals of the closed-loop system are proved to be uniformly ultimately bounded, and the distributed formation of multiple MSVs is ensured to be safe. Simulation results are provided to demonstrate the effectiveness and superiority of the proposed FTCBF-based method.

This paper addresses the flexible formation problem for unmanned surface vehicles in the presence of obstacles. Building upon the leader-follower formation scheme, a hybrid line-of-sight based flexible platooning method is proposed for follower vehicle to keep tracking the leader ship. A fusion artificial potential field collision avoidance approach is tailored to generate optimal collision-free trajectories for the vehicle to track. To steer the vehicle towards and stay within the neighborhood of the generated collision-free trajectory, a nonlinear model predictive controller is designed. Experimental results are presented to validate the efficiency of proposed method, showing that the unmanned surface vehicle is able to track the leader ship without colliding with the surrounded static obstacles in the considered experiments.

To improve the autonomy of maritime search and rescue (SAR) operation, this paper concentrates on the formation control problem for autonomous surface vehicles (ASVs) with the limited communication resource. A novel parallel search guidance, considering the maneuvering characteristics of ASVs, is developed to guide the formation to execute the automatic SAR operation. That can guarantee that the corresponding guidance law is highly efficient, self-driving and suitable for the large-scale formation. Combined with the guidance principle, a formation control algorithm is proposed by fuse of the event-triggered control and neural networks (NNs). In the proposed scheme, the gain uncertainty of actuators is effectively compensated requiring no prior information around the model structure. Unlike the existing results, the proposed event-triggered mechanism can activate synchronously both the controller and the NNs weight estimator. Considerable effort has been made to guarantee the semi-global uniform ultimate bounded (SGUUB) stability. Finally, two examples are illustrated to verify the effectiveness of the algorithm.

In this article, an asynchronous output-feedback controller is proposed for a class of Markovian jump systems (MJSs) with generally bounded transition rates (TRs). Specifically, two cases have been considered, one of which assumes the TR being completely unknown, while the other specifies the TR range. In particular, the designed asynchronous output-feedback controller is independent of the system modes, implying a sustainable controlling behavior against unavailable system modes. It is worth noting that the mode-dependent controller can be treated as a special case of the independent one. Furthermore, the existing conditions of such a controller are acquired in terms of linear matrix inequalities. Finally a practical example, concerning a single-machine infinite-bus power system, is given to confirm the feasibility of the proposed controller.

Getting an accurate estimation of three-dimensional position of the driveable lane is crucial for autonomous driving. In this work, we introduce a novel attention module called Dual Attention (DA) which enables the model to perform robustly and accurately under complicated enviromental conditions. More specifically, the attention mechanism adopts a two-pathway correlated attention method to produce additional features and aggregate globle information. We demonstrate the effectiveness of our method by following and extending recently proposed state-of-the-art 3D lane marking detection methods. Moreover, we use a novel linear-interpolation loss to precisely fit the lane marking. Extensive conducted experiments demonstrate that our methods outperform baseline methods on Apollo synthetic 3D dataset.

This article has been retracted at the request of the first and corresponding author, Dr. Karthik Chandran. The author has alerted the Editor-in-Chief of IJUFKS the reasons for the retraction: The proposed system was modelled with the incorrect data set. The system response has become incorrect because of this incorrect data set. Two percent of the information (mathematical assumptions) was taken from one paper without proper citation of the source.

This article presents a novel composite neural learning fault-tolerant algorithm to implement the path-following activity of underactuated vehicles with event-triggered input. With the input event-triggered mechanism, the dominant superiority is to reduce the communication burden in the channel from the controller to actuators. In the proposed scheme, the system uncertainties are dealt with in the fusion of the neural networks (NNs) and the dynamic surface control (DSC) method. The serial-parallel estimation model (SPEM) is constructed to estimate the error dynamics, where the derived prediction error could improve the compensation effect of the NNs. As for the gain uncertainties and the unknown actuator faults, four adaptive parameters are designed to stabilize the related perturbation and not be affected by the triggering instants. Based on the direct Lyapunov theorem, considerable efforts have been made to guarantee the semiglobal uniformly ultimately bounded (SGUUB) stability of the closed-loop system. Finally, comparison and practical experiments are illustrated to verify the superiority of the proposed algorithm.

This article investigates the adaptive fuzzy event-triggered control for the underactuated surface vessels (USVs), considering constraints of the International Regulations for Preventing Collisions at Sea (COLREGs) and the actuator failures. The proposed scheme can be divided into the guidance module and the control module. An improved logic virtual ship guidance principle, considering the ship-to-ship collision avoidance, is developed to generate the real-time reference signal for USVs. The main characteristic of the guidance principle is to ensure USVs sailing in the path following mode and collision avoidance mode. Especially for the collision avoidance mode, the collision avoidance guidance is targetedly designed for three sailing situations (the head-on situation, the overtaking situation, and the crossing situation), which is consistent with the COLREGs. Furthermore, an adaptive fuzzy event-triggered law is designed to control the USVs to converge to the desired path. The model unknown terms and the basic fault of the actuator are identified by the fuzzy logic system, and the fuzzy logic state observer is designed to estimate the unmeasured states of the USVs. Unlike the existing results, the communication burden from the controller to the actuators is reduced for the merits of the input event-triggered rule. Through the Lyapunov theory, it is proved that all the signals of the closed-loop control system are the semiglobal uniform ultimate bounded. Finally, the simulated examples are provided to illustrate the validity of the proposed control approach.

When a group of autonomous surface vehicles (ASVs) sail from a wide waterway to a narrow waterway, one difficulty is to keep relative formation with collision avoidance. Scaling the formation sizes with formation shapes invariant is a promising way. This article investigates such a formation scaling control problem of ASVs with uncertainties and input saturation. A novel bearing-based adaptive neural formation scaling control scheme for ASVs is developed. The main idea of this formation scheme is as follows. Choose a small number of leader ASVs based on bearing rigidity theory and program their trajectories according to the kinematics of formation scaling maneuver. Steer remaining ASVs to follow leader ASVs via adaptive neural techniques and the formation sizes can be scaled only by leaders without redesigning control inputs of followers. To deal with the uncertainties of ASVs, weights updating of neural networks is simplified into one-parameter estimation in each control channel. Auxiliary systems are introduced for each ASV to reduce the effect of limited actuator capability. It is shown that desired formation scaling maneuver of ASVs can be achieved with the proposed formation scheme if the augmented formation is infinitesimally bearing rigid. Formation errors are guaranteed to be uniformly ultimately bounded. The main advantage of our scheme over existing results is that directional, computational, and actuator constraints are satisfied simultaneously in the formation scaling control of ASVs. Simulations and comparisons are provided to illustrate the effectiveness of theoretical results.

In reinforcement learning (RL), we always expect the agent to explore as many states as possible in the initial stage of training and exploit the explored information in the subsequent stage to discover the most returnable trajectory. Based on this principle, in this paper, we soften the proximal policy optimization by introducing the entropy and dynamically setting the temperature coefficient to balance the opportunity of exploration and exploitation. While maximizing the expected reward, the agent will also seek other trajectories to avoid the local optimal policy. Nevertheless, the increase of randomness induced by entropy will reduce the train speed in the early stage. Integrating the temporal-difference (TD) method and the general advantage estimator (GAE), we propose the dual-track advantage estimator (DTAE) to accelerate the convergence of value functions and further enhance the performance of the algorithm. Compared with other on-policy RL algorithms on the Mujoco environment, the proposed method not only significantly speeds up the training but also achieves the most advanced results in cumulative return.

The main reason of the extensive usage of the fuzzy systems in many branches of science is their approximation ability. In this paper, an interval type-3 fuzzy system (IT3FS) is proposed. The uncertainty modeling capability of the proposed IT3FS is improved in contrast to type-1 and type-2 fuzzy systems (T1FS and T2FS). Because in the proposed IT3FS, the membership is defined as an interval type-2 fuzzy set, whereas in T1FS and T2FS, the membership is crisp value and type-1 fuzzy set, respectively. An online fractional-order learning algorithm is given to optimize the consequent parameters of the IT3FS. The stability of the learning algorithm is proved by utilizing the Lyapunov method. The validity of the proposed fuzzy system is illustrated by both simulation and the experimental studies. It is shown that the proposed fuzzy system and associated learning algorithm result in better approximation performance in comparison with the other well-known approaches.

This article aims to develop an effective control method that can improve the convergence rate over the existing adaptive nonsingular integral terminal sliding mode control (ANITSMC) method for the trajectory tracking control of autonomous underwater vehicles (AUVs). To achieve this goal, an adaptive fast nonsingular integral terminal sliding mode control (AFNITSMC) method is proposed. First, considering that the existing nonsingular integral terminal sliding mode (NITSM) has slow convergence rate in the region far from the equilibrium point, a fast NITSM (FNITSM) is proposed, which guarantees fast transient convergence both at a distance from and at a close range of the equilibrium point, and therefore increases the convergence rate over the existing NITSM. Then, using this FNITSM and adaptive technique, an AFNITSMC method is designed for AUVs. It yields local finite-time convergence of the velocity tracking errors to zero and then local exponential convergence of the position tracking errors to zero, without requiring any a priori knowledge of the upper bounds of the uncertainties and disturbances. Compared with the existing ANITSMC method, the salient feature of the proposed AFNITSMC method is that it provides AUV dynamics a faster convergence rate. Finally, simulation results demonstrate the efficiency of the proposed AFNITSMC method and its superiority over the existing ANITSMC method.

For leader-following multiagent systems with input saturation, the existing protocols use a low gain feedback approach to achieve semi-global consensus. The main drawback of this approach is the ineffective utilization of the actuator potential, resulting in bad performance. To improve the transient performance of the consensus tracking, this paper proposes a gain scheduled approach for multiagent systems subject to the saturator saturations. A novel kind of scheduler-based protocols are proposed, which consists of state feedback controllers with time-varying gain and parameter schedulers. The role of the controllers is to achieve the consensus tracking, while the schedulers can accelerate this consensus progress by enlarging the gain parameter. To remove the dependence of the schedulers on global information, a minimum-value-based consensus algorithm is put forward, with idea of driving all values of agents throughout the network to their minimum value. Its implementation is guaranteed by the network-topology connectivity. Finally, our approach is further extended to the case where the leader's control input is nonzero, time-varying, and bounded. The discontinuous protocol and its continuous approximation counterpart are designed, yielding the exactand quasi-consensus tracking, respectively. Simulation results verify the theoretical analysis.

In this work, we propose a moderate policy update method for reinforcement learning, which encourages the agent to explore more boldly in early episodes but updates the policy more cautious. Based on the maximum entropy framework, we propose a softer objective with more conservative constraints and build the separated trust regions for optimization. To reduce the variance of expected entropy return, a calculated state policy entropy of Gaussian distribution is preferred instead of collecting log probability by sampling. This new method, which we call separated trust region for policy mean and variance (STRMV), can be view as an extension to proximal policy optimization (PPO) but it is gentler for policy update and more lively for exploration. We test our approach on a wide variety of continuous control benchmark tasks in the MuJoCo environment. The experiments demonstrate that STRMV outperforms the previous state of art on-policy methods, not only achieving higher rewards but also improving the sample efficiency.

This paper proposes the modeling of single phase symmetric flying capacitor multilevel inverter (SFC-MLI) for Static synchronous compensator (STATCOM) application. The proposed topology is composed of cascade-connected five-level SFC modules. The linear current controller with phase shifted and phase disposition pulse-width modulation (PS-PD-PWM) base switching technique has been implemented. To takes advantage of the redundant switching of the PD-PWM method to counteract the voltage-swapping phenomenon to balance DC side voltages. The SFC-MLI has certain advantages over a conventional five-level flying capacitor-MLI and is more scalable. Simulation and experimental results are provided to illustrate the operation and performance of the proposed cascaded multilevel inverter.

This brief aims to reduce the data requirement for the identification of Boolean networks (BNs) by using the premined network topology information. First, a matching table is created and used for sifting the true from the false dependences among the nodes in the BNs. Then, a dynamic extension to matching table is developed to enable the dynamic locating of matching pairs to start as soon as possible. Next, based on the pseudocommutative property of the semitensor product, a position-transform mining is carried out to further improve data utilization. Combining the above, the topology of the BNs can be premined for the subsequent identification. Examples are given to illustrate the efficiency of reducing the data requirement. Some excellent features, such as the online and parallel processing ability, are also demonstrated.

This paper addresses the robust consensus reliable control problem against actuator faults for linear parameter-varying multiagent systems. First, the actuator faults are modeled via a polytopic uncertainty method. Second, a distributed observer is designed for the single agent by sharing the communication network sensors to estimate the state information. Then by these estimated information, a robust consensus reliable control protocol against actuator faults is obtained and desired disturbance rejection performance can be guaranteed by this proposed protocol. Third, the nonconvexity conditions of the consensus control protocol can be translated into an linear matrix inequality optimization problem via simple matrix calculation. Finally, the effectiveness of the proposed reliable controller scheme is illustrated by two examples.

This paper deals with the optimum dynamic positioning control problem for marine ships in the presence of actuator gain uncertainties and unknown environmental disturbances. The proposed approach is formulated as two modules, i.e., the guidance part and the control part. By utilizing the improved extremum seeking algorithm, the optimum-seeking guidance is developed in this note to generate the reasonable heading guidance for dynamic positioning ships. The main purpose of this design is to ensure the closed-loop system running efficiently and environment-friendly in practice. Combined with the proposed guidance principle, a robust neural control algorithm is developed based on the dynamic surface control, neural networks, and the robust neural damping technique. In this algorithm, the strong couplings of state variables and the gain uncertainty of actuators are tackled, and the system uncertainties are compensated requiring less (or no) information of the hydrodynamic structure, the actuator model and the external disturbances. Considerable effort is made to guarantee the semiglobal uniform ultimate bounded stability by employing the Lyapunov theory. The advantages of the proposed control scheme could be summarized as two points. First, the control approach is with the properties of optimization and energy-saving, which is meaningful for applying the theoretical algorithm. Second, the pitch ratio of thrusters is selected as the control inputs of interest, which is measurable in the practical plant. These characteristics would facilitate the implementation of the algorithm in engineering. Two examples are provided to verify the performance of the proposed scheme.

In this paper, a decentralized adaptive fuzzy control has been developed for two cooperating robotic manipulators moving an object with impedance interaction. The contact forces are described using gradients of nonlinear potentials; then, the deformations of the contact surface can be obtained by an impedance approach. The cooperating manipulators are considered as a combination of subsystems, and the decentralized local dynamics coupled with physical interactions among the subsystems are developed. To compensate for the effect of dynamics uncertainties and external disturbances, decentralized fuzzy control combining parameter adaptations and disturbance observers is constructed. It guarantees the motion trajectories and impedance forces of the constrained object converging to the desired manifolds. It is theoretically established that the disturbance observers compensate for unparameterizable uncertainties, while the adaptive fuzzy mechanism compensates for the fast-changing components of the uncertainties that go beyond the disturbance observers. Moreover, unknown nonlinear dynamics such as the inertia matrix, Coriolis/centripetal matrix, and frictions, as well as interconnections with nonlinear bounds, can be accommodated through online learning. The experiments on two real robots have been carried out to verify the effectiveness of the proposed theoretical results.

A new auto-tuning method is presented in this paper for the TITO process with time delay. The first step is to identify the process model and the second step is to design the IMC-PID controller. In the identifying procedure, both the bias relay test and the idea relay test are involved to identify the model. The important feature of the proposed method is that it does not require the prior information about the process and the steady-state process gain can be directly obtained. In the second step, this method is used to design the IMC-PID controller of the TITO control system. The new auto-tuning scheme is implemented through the function code in typical DCSs (EDPF-NT, OVATION, Symphony, etc) and is used in 300MW fossil-fuel units. The industrial applications show that the scheme achieves better performance in specific load variation range.

This paper investigates two surface electromyogram (sEMG)-based control strategies developed for a power-assist exoskeleton arm. Different from most of the existing position control approaches, this paper develops force control methods to make the exoskeleton robot behave like humans in order to provide better assistance. The exoskeleton robot is directly attached to a user's body and activated by the sEMG signals of the user's muscles, which reflect the user's motion intention. In the first proposed control method, the forces of agonist and antagonist muscles pair are estimated, and their difference is used to produce the torque of the corresponding joints. In the second method, linear discriminant analysis-based classifiers are introduced as the indicator of the motion type of the joints. Then, the classifier's outputs together with the estimated force of corresponding active muscle determine the torque control signals. Different from the conventional approaches, one classifier is assigned to each joint, which decreases the training time and largely simplifies the recognition process. Finally, the extensive experiments are conducted to illustrate the effectiveness of the proposed approaches.

A simple and effective method to determine the region of fractional-order PIλDμcontrollers that can stabilize a given fractional-order system with time delay is proposed in this paper. For each known proportional, integral or derivative gain in the PIλDμcontrollers, the stability region with respect to the other two control gains is derived. Firstly, the boundaries of the fractional-order PIλDμcontrollers are determined by using the D-decomposition method. Then, an analytical approach is presented to judge which region is the stability one among a lot of areas divided by the resultant boundaries. In comparison with other relevant methods, the main advantage of the proposed method lies in that it can effectively avoid choosing one point from each divided area and finding the stability region of the fractional-order PID controller by testing the system stability corresponding to each chosen point. Moreover, a special phenomenon is revealed: if λ + μ ≠ 2, the boundaries of the stability region in ki-kdplane are the curves for a given k value; otherwise, the stability regions in ki-kdplane are convex polygons. A numerical example is presented to check the validity of the proposed method. The proposed method can be applied to the fractional-order system free of the detailed model and only the frequency response data of the fractional-order system is required.

This communication addresses the setpoint robust PID tuning for stable first order processes with time delay (FOPTD) from a general min-max model matching formulation. In order to get a standard PID compensator, several choices are possible. This work considers the problem of finding the simplest one, based on conveniently adopting an approximate delay-free model for the FOPTD along with a particularly simple instance of the general model matching problem. The adopted methodology leads to a PID tuning just depending on a single parameter. Attending to common performance/ robustness indicators, this parameter is finally fixed in order to provide an automatic tuning just depending on the model information.

Network topology design problem in industrial network is formulated, which is shown to be equivalent to a multi-constraint optimisation problem: the network design should minimise the amount of inter-network communication, and simultaneously balance the communication load and network size evenly over the resultant sub-networks. To solve this optimisation problem, a graph partitioning strategy is proposed, which can give a good network design by partitioning a graph-based representation of the network optimisation problem. Then, the network optimisation procedures using the graph partitioning strategy are detailed and two experimental, examples are studied. In the experiments, the network designs obtained by the graph partitioning strategy are compared with those obtained by a random partitioning method. The experimental results demonstrate the network designs obtained by the graph partitioning strategy are significantly better than those obtained by the random partitioning method.

In H/sub /spl infin// robust identification, the posteriori information to be utilized is system frequency domain point response which should be estimated from measured time domain data already contaminated by noise. Traditional method to obtain such frequency data is based on many separate time domain experiments according to each frequency point, which is offline and batch processing. The paper proposes a new recursive and online algorithm to get system frequency domain point response estimate. The method boasts such advantages: algorithm is only based on one time domain experiment; algorithm is recursive and online; system priori information can be well made use of in the algorithm.

In this paper, the problem of robust decentralized stabilization for large-scale stochastic interval dynamical systems with time delays is investigated. First, with special transformation, the systems convert to equivalent form, which is apt to analysis. Then, some sufficient conditions for robust stability of the system are given. Furthermore, the design laws for robust decentralized stabilization controller are proposed in terms of linear matrix inequalities (LMIs). Analyses for the cases of time invariant delays and time varying delays are presented respectively.

This paper studies the problem of L/sub 2/ almost disturbance decoupling with global asymptotic stability for a class of strict feedback nonlinear system with time delays. A new recursive design method is proposed. Based on backstepping design method, it can conclude that there exists a robust control that solves the almost disturbance attenuation problem for nonlinear system with time delay.

In this paper, we consider the design of robust filter for linear system with time-delay and parameter uncertainties. The parameter uncertainties are described by real time-varying norm-bounded form. Because of the introduction of generalized inverse of matrix, the filter can be obtained by solving two Riccati equations, and the resulting filter can provide the robust stability and guarantee H/sub /spl infin// norm performance.