Event-triggered adaptive tracking control for USV based on enhanced optimized backstepping technique

This study addresses key challenges in the trajectory tracking control of unmanned surface vehicles, including external environmental disturbances, excessive sensor communication burdens, and complex controller design. An enhanced adaptive optimal backstepping control method based on an event-triggered mechanism is proposed. The approach employs an actor-critic reinforcement learning framework, in which the critic network performs online evaluation of system performance and the actor network generates optimal control decisions. Neural networks are designed to estimate the error gradient of the cost function, thereby simplifying the complex matrix differentiation process required in conventional methods. Additionally, an event-triggered mechanism is introduced to significantly reduce sensor communication frequency, while a disturbance observer is developed to estimate and compensate for environmental disturbances in real time, thus enhancing system robustness. Theoretical analysis establishes the stability and effectiveness of the proposed algorithm, and simulation results verify its superior performance.