IEEE Transactions on Cybernetics最新文献

The topology of a communication system is crucial in determining data transmission. Although significant research has been conducted on the integration of control and communication, existing studies on communication for control systems predominantly emphasize control aspects and warrant further exploration. Furthermore, there is a lack of research on the impacts of topology changes on control systems. This article aims to establish a connection between control and communication via communication topology, examining how communication topologies affect controllers. This article also analyzes the relationship between communication and control in depth. For static topologies, specific controller forms are derived from a general controller to illustrate the impacts of static topologies on controllers. In dynamic topologies, communication is nondeterministic, so whether a controller can receive data from other nodes is nondeterministic. Therefore, controller forms in which some coefficients are random variables following a probability distribution are derived. We utilize them to establish a close connection between control and communication. Furthermore, extensive simulations are conducted to investigate the impact of different topologies on the control system.

This article addresses the resilient cooperative optimal output regulation (COOR) control problem for nonlinear strict-feedback multiagent systems (MASs) under denial-of-service (DoS) attacks. By constructing the resilient adaptive distributed observers, the leader's dynamics and states can be estimated by each follower. In the control design, a control input constructed by feedforward and feedback control input is proposed based on the system data. Neural networks (NNs) are employed to learn solutions of the feedforward and optimal feedback control problems. Meanwhile, to handle the influence caused by unknown nonlinear dynamics, combining off-policy integral reinforcement learning (IRL) algorithm with actor-critic NNs (A-C NNs), an optimal feedback security control law is designed. To illustrate the feasibility and effectiveness of the proposed optimal control strategy, numerical and practical simulation examples are provided. Unlike prior studies limited to linear systems, this work explicitly accounts for complex nonlinear dynamics, significantly broadening the applicability of resilient COOR control problem in real-world applications.

Multiagent reinforcement learning (MARL) has garnered extensive research attention due to its strong learning capabilities, leading to its deployment in increasingly challenging scenarios. Although progress has been made toward more generalizable solutions, many MARL algorithms continue to struggle with balancing scalability and heterogeneity, particularly under conditions of growing uncertainty. Research has shown that combining dense local interactions with sparse global interactions can significantly enhance scalability while preserving agent heterogeneity. Motivated by these insights and inspired by human social behavior, we propose a novel hierarchical method that integrates human guidance with multiagent systems (MASs). Rather than requiring agents to learn from scratch, our method transfers abstract knowledge from humans, employing fuzzy logic to manage the inherent uncertainty in this guidance and reduce the required human effort. To accommodate both local and global interactions, we introduce two levels of human guidance: individual action guidance for agents and an attention graph to describe agent relationships. Our proposed approach is end-to-end and compatible with diverse MARL algorithms. We evaluate our approach in the starcraft multiagent challenge (SMAC) and SMACv2 environments. Empirical results demonstrate its effectiveness, even under low-performance fuzzy human guidance.

This article investigates the problem of composite $H_{infty }$ control for cooperation-competition networks with hidden Markov jump parameters reaction-diffusions dynamics. Considering the difficulty of directly obtaining the mode information of systems, a continuous-time hidden Markov jump model is employed to represent the joint jump process. Specifically, the hidden process stands for the dynamics of real systems, which cannot be precisely known but can be observed through a detector. Due to the existence of multiple disturbances, the performance of the aforementioned systems can be deteriorated. To reduce the influence of these disturbances, a composite disturbance observer-based controller is constructed, which combines a disturbance observer with a feedback control mechanism. This design significantly improves the robustness and antidisturbance capability of systems. Then, sufficient criteria are derived to guarantee that the bipartite synchronization error system (BSES) is stochastically stable and meets a desired performance index. Finally, the effectiveness of the proposed control method is verified through the performance analysis.

A fan-powered tailsitter is capable of operating in both rotary-wing and fixed-wing flight modes. The transition between these modes is critical due to strong disturbances and considerable control complexity. This article investigates a predefined-time stability tracking control problem for tailsitters subject to parameter uncertainties and external disturbances. Based on the second-order dynamic model and high-order fully actuated (HOFA) system approach, a high-order robust controller is first developed to address the limitations of existing mode transitions, particularly in terms of control accuracy and disturbance suppression capabilities. On this basis, a novel predefined-time HOFA scheme is proposed by introducing adjustable parameters, which enables the system states to converge into a small neighborhood of the desired equilibrium within a prescribed time, while providing flexible tuning of the convergence time to adapt to varying mission and environmental requirements. Theoretical analysis and numerical simulations demonstrate that the proposed scheme achieves enhanced control accuracy, faster convergence, and improved robustness compared with conventional approaches. In contrast to existing approaches, the proposed HOFA-based predefined-time framework allows explicit tuning of the convergence time and provides robustness guarantees under parameter uncertainties, an aspect that has not been sufficiently addressed in the current literature.

The rapid development of deep learning-based image inpainting poses serious challenges to image authenticity. As inpainting methods continue to evolve, the inpainted images exhibit extremely high visual fidelity, presenting recognition difficulties to the forgery detection model due to differences in operational mode and forgery traces among methods. In particular, the detection performance tends to drop significantly in the testing phase when the test samples differ from the training data. To address this issue, we propose a test-time adaptive detection framework for image inpainting forgeries. First, we propose an image gradient-based metric that quantifies model uncertainty and orchestrates the entire adaptation process. Integrating this metric with sample-specific batch normalization (BN) statistics enhances the ability of pretrained models in the inference stage. Second, we introduce a cross-attention module as a side-tuning module, enabling the model to adapt dynamically to reliable test samples without altering the backbone network. To validate the effectiveness of the proposed method, we construct a dataset comprising synthetic images of multiple inpainting methods and design experiments under two scenarios of distributional bias. The results demonstrate that our proposed framework outperforms the existing baseline method, enhancing the adaptability and detection performance of the forgery detection model in dynamic environments.

With the rise of growing privacy concerns and "data silos," federated learning is gaining traction in wind turbine fault diagnosis. Most existing methods unrealistically assume that fault classes remain static over time. However, wind turbine data are collected as dynamic streams. Existing methods necessitate the storage of all historical fault class data and require real-time model retraining using this data whenever new faults are introduced. The high demands for storage, computation, and bandwidth are impractical as new data keeps coming in. Additionally, when these methods are applied to diagnose new fault classes in dynamic data streams with limited resources and heterogeneity across wind farms, the model suffers from significant memory degradation. To address these challenges, a federated incremental collaborative fault diagnosis method for dynamic data streams across multiple wind farms is proposed. First, a new fault class detection method is presented to ensure when and where to introduce new fault classes. Second, a balance between the plasticity and stability of the fault diagnosis model at each wind farm is proposed to alleviate the fading memory problem. Third, a global model adaptive compensatory method is presented to address the fading memory issue of the aggregated model caused by heterogeneity. Finally, the proposed method was validated with data from three real-world wind farms in Hubei, Jiangsu, and Yunnan provinces, China. The results showed that it effectively mitigates fading memory issues and outperforms several state-of-the-art methods.