Resilient Human-in-the-Loop Containment of Multiagent Systems Against Actuator Fault Attack Based on Reinforcement Learning

This article addresses the optimal containment fault-tolerant resilient control issues in nonlinear strict feedback multi-agent system (MAS) under unknown fault disturbance. First, human operator interacted with each agent in the MAS. The agent’s control input is a combination of the human operator’s commands, which are not accessible to other agents. To ensure the fault-tolerant cooperative operation of MAS, a networked-based fault interference estimator is developed to observe fault online. In addition, the optimized control design utilizes an actor-critic architecture to approximate Hamilton–Jacobi–Bellman equation for MAS with nonlinear strict-feedback dynamics to realize optimal containment fault-tolerant control. Finally, the proposed optimal algorithm for MAS containment is validated through numerical simulations and practical multiple unmanned aerial vehicles systems (UAV). The proposed algorithm is named human-in-the-loop reinforcement learning with backstepping (HiRLBC). The results demonstrate rapid convergence, with the tracking error approaching near zero, ensuring containment control despite unknown time-varying disturbances. Simultaneously, additional comparative experiments offer further proof of the proposed algorithm’s effectiveness.