Event-Driven Prescribed Optimal Disturbance Rejection for Dynamic Positioning of Ships via Reinforcement Learning
Xiaoyang Gao, Xin Hu, Jiarui Liu, Tieshan Li
Abstract
Dynamic positioning (DP) stands as the keystone underpinning ships’ operations in the abyssal depths and remote oceans. This paper proposes an event-driven disturbance rejection approximate optimal dynamic positioning scheme for surface ships with prescribed performance via reinforcement learning (RL). Firstly, a disturbance observer is established to achieve the online estimations of marine environmental disturbances such that the undesirable disturbance effects on control performance can be reduced. Meanwhile, the positioning error transformations with the prescribed performance function is established to combine with the backstepping method and the virtual controller can be designed to constrain the positioning error. Then, for the velocity error surface, the RL method provides the actor-critic architecture to approximate the actual optimal commanded control law and minimized the specified performance index function. Subsequently, the optimal commanded control design incorporates the event-driven mechanism to avoid communication resource waste as well as actuator wear and tear. By applying the Lyapunov stability theory, it is proven that the designed RL control law forces the ship’s actual position and yaw angle to converge to desired target with prescribed performance while ensuring all signals in the closed-loop system are uniformly ultimately bounded. The feature of this paper is the reasonable integration of prescribed performance and RL, which ensures that the performance index function of the ship is minimized while keeping the DP error within the safety range. Finally, simulations with comparisons based on a sea launch ship show the effectiveness further validating the superiority of the RL control scheme.