Fuzzy Reinforcement Learning-Based Secure Capture and Formation Control for Multiagent Pursuit-Evasion Game

This paper studies the distributed optimal strategy problem in multi-agent pursuit-evasion game for capture and formation control under false data injection attacks (FDIAs) and input saturation constraints. In the game, pursuers aim to approach evaders while evaders attempt to keep a distance, and agents within the same team are required to preserve cohesion. To achieve control objectives under the FDIAs and input saturation constraints, a hierarchical control framework is developed, which includes a sliding mode control (SMC) layer and an optimal control layer. Moreover, the SMC strategy is designed to mitigate the effects of FDIAs and input saturation. Then, since the sliding mode dynamics involves coupling terms associated with formation displacement, a fuzzy reinforcement learningbased optimal control strategy is proposed to achieve capture and formation aims. Furthermore, based on the Lyapunov method, it is proven that all closed-loop signals are uniformly ultimately bounded. Finally, the effectiveness of the proposed method is validated by simulations conducted on distributed mobile robots.