Ranging sensors possess advantages such as robustness to lighting conditions, strong signal penetrability, and simplified data association. These merits have facilitated the widespread application of range-only positioning in fields such as intelligent warehousing and indoor navigation, thereby rendering research on the security of range-only positioning significant. In this paper, we propose a novel method for designing collaborative attacks on range-only localization systems, where an attacker strategically selects sensors to attack and allocates energy to maximize the deviation of the estimated position along a specified direction. With only the target’s location known up to an uncertainty set, we derive the attack strategy by solving a max-min optimization problem over a hybrid action space. Given the high complexity of this problem and the requirement for a fast and robust solution, we adopt a learning-based framework. This framework consists of three neural optimizers that are trained independently by directly using the objective function as the loss function. Unlike conventional non-cooperative or random attacks, our approach induces targeted and more severe disruptions in location estimates. Simulation and experiment results demonstrate that the proposed method significantly outperforms baseline strategies, highlighting the substantial threat of collaborative attacks and underscoring the need for further research into securing range-only localization systems.

This article investigates the mean-square output consensus problem for heterogeneous linear multiagent systems (MASs) over random packet loss channels. Agent heterogeneity is reflected in possibly different state dimensions and dynamic parameters. In addition to heterogeneity, a major challenge arises from relaxing the commonly adopted independent and identically distributed (i.i.d.) assumption on packet losses. To capture temporal correlations that are prevalent in practice, packet losses are modeled by a discrete-time Markov process. Since existing consensus controllers designed for i.i.d. losses may fail under Markovian packet losses, novel dedicated control schemes are developed. Two packet loss scenarios are considered: identical and nonidentical packet losses. For identical packet losses, where all channels drop packets simultaneously, both analytical and numerical consensus conditions are derived to guarantee consensus of the distributed observers. The analytical condition reveals the interplay among packet loss rate, communication topology, and system dynamics, while the numerical conditions are more computationally tractable. An output-regulation-based controller is then designed to achieve mean-square output consensus. For the more general case of nonidentical packet losses, edge Laplacian theory is employed to decouple packet loss processes from the communication topology, leading to consensus conditions for the distributed observers, as well as corresponding controllers that guarantee mean-square output consensus. Finally, numerical simulations are utilized to validate the results.

This article addresses the formation control problem of underactuated multi-autonomous surface vehicles (ASVs) under denial-of-service (DoS) attacks on the communication network and complex uncertainties, including unknown ASV dynamics, external disturbances, and obstacles. First, a novel distributed target estimator (DTE) using a first-order low-pass filter is designed to estimate the state of the target based on partial observability under target information constraints and DoS attacks. Second, a safe guidance law for the ASVs is developed using the estimated target state and a control barrier function. Third, a “dual-adaptation control and learning” bidirectional fusion model is constructed. Specifically, on one hand, a distributed adaptive formation controller based on value decomposition reinforcement learning (VDRL) is designed. By decomposing the global value function, this controller addresses the credit allocation issue in cooperative formation and allows the ASVs to adjust their strategies autonomously based on the environment. On the other hand, an adaptive mechanism is used to improve the computation strategy of the global value function in VDRL, enhancing the learning efficiency and stability of the reinforcement learning (RL) algorithm in complex environments. The proposed VDRL-based formation control algorithm of the underactuated multi-ASVs ensures accurate target state estimation and convergence of formation errors under DoS conditions. A rigorous theoretical analysis is further used to ensure the closed-loop stability of the multi-ASV systems. Finally, simulation results validate the effectiveness of the proposed distributed formation control algorithm.

Pursuit-evasion (PE) problem is a critical challenge in multi-robot systems (MRS). While reinforcement learning (RL) has shown its promise in addressing PE tasks, research has primarily focused on single-target pursuit, with limited exploration of multi-target encirclement, particularly in large-scale settings. This paper proposes a Transformer-Enhanced Reinforcement Learning (TERL) framework for large-scale multi-target encirclement. By integrating a transformer-based policy network with target selection, TERL enables robots to adaptively prioritize targets and safely coordinate robots. Results show that TERL outperforms existing RL-based methods in terms of encirclement success rate and task completion time, while maintaining good performance in large-scale scenarios. Notably, TERL, trained on small-scale scenarios (15 pursuers, 4 targets), generalizes effectively to large-scale settings (80 pursuers, 20 targets) without retraining, achieving a 100% success rate. The code and demonstration video are available at https://github.com/ApricityZ/TERL.

Multimodal Sentiment Analysis (MSA) aims to leverage heterogeneous data—typically language, vision, and acoustic modalities—to accurately interpret human emotional states. Despite recent advances, challenges persist due to the feature distribution difference caused by intrinsic modality heterogeneity. Prior works either neglect the contribution disparity among modalities, especially the dominant role of language in sentiment reasoning, or emphasize language dominance in fusion-space alignment, ignoring coordination in the early feature space. To address these limitations, we propose a novel Two-Stage Primary Modality-Guided (TSPMG) framework, which introduces primary-modality supervision into both feature-space distribution alignment and fusion-space attention modulation. This dual-level cooperative mechanism progressively amplifies the dominant modality’s influence throughout the entire representation learning pipeline. Extensive experiments on two benchmark datasets demonstrate that TSPMG achieves superior or comparable results to state-of-the-art baselines, with ablation studies further validating the effectiveness of primary-modality-guided strategies for robust and interpretable multimodal sentiment analysis. The code is available at https://github.com/Kaisa777/TSPMG.

This paper introduces an event-triggered multigradient recursive data-driven iterative learning control (ETMGRDDILC) scheme designed for consensus tracking in multi-agent systems (MASs). The data-driven control eliminates the need for precise system modeling, relying solely on the input-output data of the system. Meanwhile, compared to traditional single-gradient descent methods, a multigradient descent approach is adopted for the performance function of the consensus observation error, enabling faster error convergence. In addition, the proposed eventtriggered mechanism leverages historical error compensation, decay factors, and flexible multi-parameter adjustments to significantly reduce trigger frequency, enhance resource efficiency, and improve robustness in dynamic environments. Finally, simulation results validate the effectiveness of the proposed control scheme, demonstrating improvements in convergence speed and reduced controller updates.

Deep neural networks (DNNs) are increasingly being used to learn controllers due to their excellent approximation capabilities. However, their black-box nature poses significant challenges to closed-loop stability guarantees and performance analysis. In this brief, we introduce a structured DNN-based controller for the trajectory tracking control of Lagrangian systems using backing techniques. By properly designing neural network structures, the proposed controller can ensure closed-loop stability for any compatible neural network parameters. In addition, improved control performance can be achieved by further optimizing neural network parameters. Besides, we provide explicit upper bounds on tracking errors in terms of controller parameters, which allows us to achieve the desired tracking performance by properly selecting the controller parameters. Furthermore, when system models are unknown, we propose an improved Lagrangian neural network (LNN) structure to learn the system dynamics and design the controller. We show that in the presence of model approximation errors and external disturbances, the closed-loop stability and tracking control performance can still be guaranteed. The effectiveness of the proposed approach is demonstrated through simulations.

In this study, the fault-tolerant consensus control (FTCC) challenge is investigated for nonlinear multiagent systems (MASs) in the simultaneous occurrence of abrupt and incipient actuator/sensor faults in the physical level and hybrid Deception/Denial-of-Service (DoS) attacks in the cyber level. For security enhancement and/or safety maintenance purposes, an unknown state and fault decoupling-based augmented estimator is first devised, and a distributed event-triggered FTCC protocol is then developed to achieve strength against hostile attacks and faults, respectively, with the incorporation of augmented state estimation, neighboring sensor fault estimation, and latest successfully triggered output interaction. By constructing dual indicators along with average dwelling time and attack frequency technique, criteria of exponential mean-square consensus of the nonlinear MASs subject to hybrid attacks are obtained. In the end, simulation is outlined to illustrate the efficacy and improvements of the developed event-triggered FTCC methodology.

Sequential diagnosis prediction (SDP) is a complex and challenging task, aming to predict future diagnoses of patients by analyzing their historical medical records. Although graph neural networks(GNNs) has been applied to successfully address the challenge of heterogeneous data integration in electronic health records, relatively limited work has been done on GNNs for sequential diagnosis prediction. Graph neural network-based methods, aimed at capturing structural and relational patterns of EHR data for sequential diagnosis prediction, explore code-code pairwise relationships, resulting in an inability to learn fine-grained, higher-order interaction relationships among different types medical codes. As a result, they are difficult to effectively model complex, multi-dimensional interactions among different types of medical codes necessary for accurate and nuanced diagnosis predictions. To address these challenges, this paper proposes a novel approach called Multi-Channel Hypergraph Network (MCHN) predictive framework for sequential diagnosis prediction. The proposed method aims to explore the fine-grained higher-order interactions between different types of medical codes via multi-channel hypergraphs. Specifically, MCHN learns two levels of code embeddings from multi-channel hypergraph learning module and line graph learning module, respectively: (i) multi-channel hypergraph learning module, which is to learn multi-channel hypergraph level code embeddings by modeling the higher-order relationships between medical codes in different hypergraphs; and (ii) line graph learning module, which is to learn the line graph level code embeddings by modeling code-code pairwise relationships. In MCHN, we propose a novel channel-level attention mechanism to help our model attend to the informativeness of the different channel for forecasting future patient diagnoses. We also design a code-level attention mechanism, which can to pay more attention to the medical codes that are more important to the visit representation. Moreover, MCHN aggregates the learnt code embeddings in the two levels to generate the visit representation, which is used to predict the patient’s next diagnosis. Experimental results on two benchmark datasets consistently demonstrate that MCHN outperforms state-of-the-art methods1.

Drug combination therapy is generally more effective than monotherapy in the field of cancer treatment. However, screening for effective synergistic combinations from a wide range of drug combinations is particularly important given the increase in the number of available drug classes and potential drug-drug interactions. Existing methods for predicting the synergistic effects of drug combinations primarily focus on extracting structural features of drug molecules and cell lines, but neglect the interaction mechanisms between cell lines and drug combinations. Consequently, there is a deficiency in comprehensive understanding of the synergistic effects of drug combinations. To address this issue, we propose a drug combination synergy prediction model based on multi-source feature interaction learning, named MFSynDCP, aiming to predict the synergistic effects of anti-tumor drug combinations. This model includes a graph aggregation module with an adaptive attention mechanism for learning drug interactions and a multi-source feature interaction learning controller for managing information transfer between different data sources, accommodating both drug and cell line features. Comparative studies with benchmark datasets demonstrate MFSynDCP's superiority over existing methods. Additionally, its adaptive attention mechanism graph aggregation module identifies drug chemical substructures crucial to the synergy mechanism. Overall, MFSynDCP is a robust tool for predicting synergistic drug combinations. The source code is available from GitHub at https://github.com/kkioplkg/MFSynDCP .

False data injection attacks are widely investigated to exploit the cyber-vulnerability of Cyber-Physical System. However, the existing attack policies only consider the cyber-vulnerability in the one-way communication channel. In this letter, a bidirectional stealthy false data injection attack is proposed to bypass the hostile data detector and degrade the estimation performance in the distributed Kalman filtering system. The stealthiness and the influence of the bidirectional stealthy attack is demonstrated by the theoretical analysis. Furthermore, the alternate transmission protocol is proposed to prevent the bidirectional stealthy attack policy. To remedy the protocol and improve the detection sensitivity, an attack detector with multiple factors is proposed. Besides, the choosing principle of the detection factors is analyzed. Simulation examples are presented to investigate the bidirectional stealthy attack and the developed estimator.

We investigate the capacity of an adversary to learn the underlying interaction network through repeated best response actions in linear-quadratic games. The adversary strategically perturbs the decisions of a set of action-compromised players and observes the sequential decisions of a set of action-leaked players. The central question pertains to whether such an adversary can fully reconstruct or effectively estimate the underlying interaction structure among the players. To begin with, we establish a series of results that characterize the learnability of the interaction graph from the adversary’s perspective by drawing connections between this network learning problem in games and classical system identification theory. Subsequently, taking into account the inherent stability and sparsity constraints inherent in the network interaction structure, we propose a stable and sparse system identification framework for learning the interaction graph based on complete player action observations. Moreover, we present a stable and sparse subspace identification framework for learning the interaction graph when only partially observed player actions are available. Finally, we demonstrate the efficacy of the proposed learning frameworks through numerical examples.

State estimation is an essential part of autonomous systems. Integrating the Ultra-Wideband (UWB) technique has been shown to correct the long-term estimation drift and bypass the complexity of loop closure detection. However, few works on robotics treat UWB as a stand-alone state estimation solution. The primary purpose of this work is to investigate planar pose estimation using only UWB range measurements. We prove the excellent property of a two-step scheme, which says we can refine a consistent estimator to be asymptotically efficient by one step of Gauss-Newton iteration. Grounded on this result, we design the GN-ULS estimator, which reduces the computation time significantly compared to previous methods and presents the possibility of using only UWB for real-time state estimation.

Both goal-agnostic and goal-oriented tasks have practical value for robotic grasping: goal-agnostic tasks target all objects in the workspace, while goal-oriented tasks aim at grasping pre-assigned goal objects. However, most current grasping methods are only better at coping with one task. In this work, we propose a bifunctional push-grasping synergistic strategy for goal-agnostic and goal-oriented grasping tasks. Our method integrates pushing along with grasping to pick up all objects or pre-assigned goal objects with high action efficiency depending on the task requirement. We introduce a bifunctional network, which takes in visual observations and outputs dense pixel-wise maps of$Q$values for pushing and grasping primitive actions, to increase the available samples in the action space. Then we propose a hierarchical reinforcement learning framework to coordinate the two tasks by considering the goal-agnostic task as a combination of multiple goal-oriented tasks. To reduce the training difficulty of the hierarchical framework, we design a two-stage training method to train the two types of tasks separately. We perform pre-training of the model in simulation, and then transfer the learned model to the real world without any additional real-world fine-tuning. Experimental results show that the proposed approach outperforms existing methods in task completion rate and grasp success rate with less motion number. Supplementary material is available at https://github.com/DafaRen/Learning_Bifunctional_Push-grasping_Synergistic_Strategy_for_Goal-agnostic_and_Goal-oriented_Tasks.

Grasping objects in cluttered scenarios is a challenging task in robotics. Performing pre-grasp actions such as pushing and shifting to scatter objects is a way to reduce clutter. Based on deep reinforcement learning, we propose a Fast-Learning Grasping (FLG) framework, that can integrate pre-grasping actions along with grasping to pick up objects from cluttered scenarios with reduced real-world training time. We associate rewards for performing moving actions with the change of environmental clutter and utilize a hybrid triggering method, leading to data-efficient learning and synergy. Then we use the output of an extended fully convolutional network as the value function of each pixel point of the workspace and establish an accurate estimation of the grasp probability for each action. We also introduce a mask function as prior knowledge to enable the agents to focus on the accurate pose adjustment to improve the effectiveness of collecting training data and, hence, to learn efficiently. We carry out pre-training of the FLG over simulated environment, and then the learnt model is transferred to the real world with minimal fine-tuning for further learning during actions. Experimental results demonstrate a 94% grasp success rate and the ability to generalize to novel objects. Compared to state-of-the-art approaches in the literature, the proposed FLG framework can achieve similar or higher grasp success rate with lesser amount of training in the real world. Supplementary video is available at https://youtu.be/KTGj1fGU6ho.

Overtaking the lead vehicle on two-way roads in the presence of several oncoming vehicles is a complex task for autonomous vehicles. In this paper, we formulate the overtaking behavior of an ego vehicle based on a deep reinforcement learning (DRL) method. First, a two-way urban road is created, wherein the ego vehicle aims to reach the destination safely and efficiently while considering multiple traffic participants. We use different intelligent driver model (IDM) parameters to account for different drivers' habits. Furthermore, we introduce different responses of other vehicles when the ego vehicle takes overtaking maneuver. Then, a hierarchical control framework is proposed to manage vehicles on the road, which supervises vehicle behaviors at the high layer and controls the motion at the lower layer. The DRL method named Proximal Policy Optimization is applied to derive the high-level decision-making policies. A self-attention mechanism is further introduced to improve the performance of our algorithm. Finally, the overtaking maneuvers of the ego vehicle in different training timesteps are analyzed and how the responses of other vehicles affect the ego one's overtaking behavior is investigated. Simulation results show that our approach can achieve good performance to deal with the two-way road autonomous overtaking task. Supplementary video is available at https://youtu.be/jPEGjM7cBuk.

In this paper, an algorithm on circular circumnavigation of nonholonomic agents is proposed. The agents are required to enclose a static target with predefined radius and circumferential speed. The algorithm completely relies on local bearing angle measurement. Cyclic pursuit is adapted to coordinate the agents and generate an even formation at the circle. Theoretical analysis on the stability of algorithm is given. The applicability and effectiveness of the algorithm is testified with simulations on the unmanned surface vessel (USV) platform.

The D2D (Device-to-Device) communication has been very popular as it is a promising and low-cost solution to reduce the burden on the cellular network. However, there are rare concerns about the distribution and pairing of DUEs(D2D user equipments), which have a significant impact on QoS (Quality of Service) of D2D communication. In this paper, we propose a novel algorithm based on the coalitional game to optimally adjust the distribution of DUEs. The proposed algorithm aims to form the optimal coalition structure, which achieves a balance between the throughput and power consumption of each coalition, obtaining the enhanced QoS of D2D. We show that our algorithm is superior to the benchmark models in terms of the throughput and energy efficiency of the DUE coalition. To further improve the QoS, we also propose a method to predict and maximize the pairing probability of DUEs. The proposed prediction method adopts the Logistic Regression to model the global pairing probability according to the communication parameters of DUEs. Experimental results show that the proposed prediction method is significantly superior to the benchmark methods in terms of prediction accuracy. In addition, the pairing probability maximization algorithm proposed also significantly improves the pairing probability.