Adaptive optimal formation control for unmanned surface vehicles with guaranteed performance using actor‐critic learning architecture

Abstract

SummaryIn this article, an optimized formation control algorithm is presented for unmanned surface vehicles (USVs) with collision avoidance and prescribed performance. The prescribed formation geometry is designed in the leader‐follower formation architecture, in which each vehicle tracks its intermediary leader with preserving a desired separation. A prescribed performance control design technique is introduced to guarantee the transient and steady‐state performance specifications on formation errors. Radial basis function neural networks (NNs) are employed to approximate modeling uncertainties including damping terms and unmodeled dynamics. Based on an actor‐critic learning strategy, a reinforcement learning (RL) algorithm is proposed to ensure the optimality of formation control and the specified tracking accuracy simultaneously, in which actor NNs take appropriate control behaviors by interacting with the external environment, and critic NNs evaluate the control performance and generate a reinforcement signal to actor NNs for facilitating the improvement of subsequent behaviors. Stability analysis shows that the proposed optimal formation controller achieves semi‐global uniform ultimate boundedness of closed‐loop adaptive systems with prescribed performance. Comparative simulation results illustrate the effectiveness and superiority of the presented control algorithm.