IEEE Transactions on Cybernetics最新文献

The repetitiveness prerequisite of iterative learning control has always been the main obstacle to promoting its practical applications. In this article, a novel adaptive iterative learning reliable control scheme is proposed for the nonrepetitive systems with multiple iteration-varying parametric uncertainties, where actuator faults and state delays are considered simultaneously. During the design of the controller, the class- $k_{infty } $ function is leveraged to dispose of the unmodeled lumps of systems through neural networks, and the transformation of control signals is established to compensate for the negative impact of the inefficient actuator. The technical features of our approach lie in an innovative parametric estimation mechanism that integrates the hyperbolic tangent function and an auxiliary sequence is presented to accommodate the nonrepetitive uncertainties, thus achieving the zero-error convergence of output. As the main merits, the proposed control scheme is promising to manifest better performance and practicality than the existing methods, owing to the weak assumptions on the system dynamics, the little prior knowledge of parametric uncertainties, and the strong learning ability of the controller.

This article investigates the stealthy distributed pole-dynamics attacks (dPDAs) detection for multiagent systems (MASs) by distributed additive watermarking (DAW). First, the limitation of traditional MASs for dPDAs is revealed, where dPDAs cannot be detected. Second, unlike the well-established single-agent additive watermarking, to eliminate the side effect of watermarking signal on system state and enable dPDAs detection, the proposed DAW adds watermarking to the control signal of any agent for transmission and removes watermarking of the control signal after receiving it. Meanwhile, the covariance of the watermarking signal in DAW for all agents is different from each other to enable compromised links isolation. Furthermore, the relationship between the dPDAs detection performance and DAW is quantified in the sense of expectation, where the dPDAs detection performance is directly proportional to the sum of the watermarking covariance of the compromised links. Third, leveraging the relationship between dPDAs detection performance and DAW, a DAW-based link isolation scheme is proposed to accurately isolate the compromised links by comparing with the detection function and its approximation, where the approximation of the detection function is iteratively calculated on all possible attack links combination for the compromised agent. As a result, the adverse impacts of dPDAs on MASs are mitigated. Finally, simulation results are conducted to validate the theoretical results.

In this article, the secure consensus control problem is investigated for discrete-time multiagent systems (DTMASs) subjected to denial-of-service (DoS) attacks, where a model-free controller is proposed based on the Q-learning (QL) method. In an attack-free case, a dynamic decaying encryption key is designed to enable secure state transmission over communication channels through quantization-based encryption to prevent unauthorized access. Under DoS attacks, the system switches to a safe mode that partially halts communication, where the key transforms into a local scaling parameter to prevent quantizer saturation through dynamic expansion. The QL-driven algorithm is introduced to autonomously synthesize control gain matrices, without requiring system dynamics models. Moreover, sufficient conditions on the frequency and duration of DoS attacks are derived to ensure that the model-free controller guarantees consensus in DTMASs. Finally, simulation studies involving highly maneuverable aircraft technology vehicles (HiMATVs) are conducted, demonstrating that DTMASs equipped with the proposed approach exhibit significantly enhanced attack resistance compared to conventional methods.

This study addresses the cooperative tracking control for multiple vertical take-off and landing (VTOL) drones operating in networked environments. The problem is particularly challenging due to the strongly nonlinear dynamics of drones, uncertain time-varying disturbances, limited communication bandwidth, and control chattering on the first-order sliding manifold. Existing approaches often address only part of these challenges or lack rigorous fixed-time convergence guarantees. To tackle these issues, this article proposes a novel adaptive neural network event-triggered fixed-time super-twisting (ANEFS) control strategy within a double closed-loop hierarchical framework. In the outer loop, a novel auxiliary variable-based distributed fixed-time estimator (ADFE) is designed, which, unlike conventional asymptotic estimators, guarantees fast and accurate estimation of the leader's trajectory. This is integrated into an event-triggered fixed-time super-twisting (EFST) control law that ensures precise position tracking while significantly reducing network usage. In the inner loop, an adaptive neural network fixed-time super-twisting (ANFST) torque controller robustly handles complex system nonlinearities and uncertainties, ensuring rapid attitude tracking. The effectiveness of the proposed method in providing fast, robust, and resource-efficient cooperative tracking is demonstrated through both numerical simulations and real-world flight experiments using lightweight Crazyflie quadcopters.

By means of a fully actuated system (FAS) approach, this article is concerned with an anti-disturbance tracking control problem toward a class of lumped disturbances containing the model uncertainties and external disturbances. A FAS predictive control with a generalized proportional-integral observer (GPIO) is presented to address this problem. Concretely, a FAS model of discrete-time nonlinear systems with the lumped disturbances is firstly given as a control-oriented one. Then, a GPIO is developed to achieve an accurate estimation for the lumped disturbances by adopting a less conservative disturbance assumption, which provides a better foundation to construct a disturbance preview. Furthermore, an incremental FAS (IFAS) prediction model with a disturbance preview is constructed by utilizing a new type of Diophantine Equation. Dependent on this IFAS prediction model, the multistep ahead predictions can be obtained to minimize an objective function to yield an optimal anti-disturbance controller, such that the desired tracking performance can be guaranteed. The depth analysis derives a sufficient condition for the bounded stability and tracking performance of the closed-loop FASs. The proposed GPIO-based FAS predictive control provides a solution to the spacecraft attitude control for verifying the feasibility.

Effective policy optimization in multiagent reinforcement learning (MARL) necessitates extensive exploration of high-dimensional state-action spaces. However, such exploration may not only trigger unsafe states but also compromise system stability, posing significant challenges for deployment in safety-critical systems. To address this challenge, this article proposes a safety-stability layer that integrates robust control barrier functions (RCBFs) and input-to-state stable control Lyapunov functions (ISS-CLFs) for multiagent systems operating in unknown environments with uncertain dynamics. Furthermore, by integrating safety-stability constraints with a MARL framework, during the training phase, we exclusively focus on goal-reaching objectives to expand the policy network's exploration space, while in the deployment phase, policy outputs are filtered through a real-time safety-stability layer. In addition, an event-triggered mechanism for action compensation calculation is designed based on safety condition assessments to conserve computational resources. Finally, the effectiveness of the proposed method is validated through simulation experiments in dynamic multiunicycle environments. The results demonstrate that our approach not only ensures strict adherence to safety constraints but also significantly enhances the task execution efficiency of multiagent systems.