Consensus Tracking of Disturbed Second-Order Multiagent Systems With Actuator Attacks: Reinforcement-Learning-Based Approach
针对受执行器攻击的扰动二阶多智能体系统，提出两步控制策略：先用滑模控制解决无攻击时的一致性问题，再用离策略软演员-评论家算法训练安全控制策略，实现安全一致性跟踪。
This article is devoted to solving the leaderless and leader-following consensus tracking problems for a class of disturbed second-order multiagent systems (MASs) under the influence of actuator attacks. To achieve this, a two-step control strategy is developed, where the effects of disturbances and actuator attacks on the achievement of consensus tracking are addressed in distinct stages. In the first step, a reference system model is constructed for each agent. Upon which a sliding mode control (SMC) protocol is constructed and utilized to resolve the consensus tracking problem of disturbed second-order MASs in the absence of actuator attacks, facilitating the design of a baseline control term for the MASs under consideration. In the second step, a secure control policy is trained using an off-policy soft actor-critic algorithm, aiming at achieving secure consensus tracking in the presence of actuator attacks. Both numerical simulations and a multipendulum consensus example verify that the designed control structure has better control performance than using only the SMC method and also effectively improves the training efficiency over the traditional reinforcement learning (RL) alone method.