Performance-prescribed reinforcement learning-based trajectory tracking control for an unmanned surface vehicle

Objective This study addresses oscillatory instability in trajectory tracking errors of unmanned surface vehicles (USV) caused by propulsion saturation under complex navigation conditions. A prescribed-performance reinforcement learning-based optimal control method is proposed.

Method First, a novel saturation function is introduced to handle USV input saturation. Second, an improved prescribed performance control scheme is designed, in which tracking error convergence is constrained by an asymmetric performance boundary, thereby relaxing the strict dependence on initial error conditions. Then, a reinforcement learning optimization framework based on an Actor-Critic architecture is constructed to iteratively learn the optimal control policy and value function, enabling performance optimization under state constraints. Finally, the stability of the closed-loop tracking system is rigorously proven using Lyapunov stability theory.

Results Numerical simulations conducted on the KVLCC2 tanker model demonstrate that the proposed method effectively addresses trajectory tracking under saturation constraints, with all tracking errors strictly confined within the prescribed performance boundaries.

Conclusion The study provides a new solution for high-performance tracking control of constrained USVs and demonstrates strong potential for practical engineering applications.