This article develops a reinforcement learning (RL) strategy to address the robust optimal tracking control problem for an intelligent surface vehicle (ISV) with modeling uncertainties and unknown ocean disturbances. A neural network (NN) identifier is constructed to learn uncertain nonlinear dynamics. Unlike the typical architecture of actor-critic networks, a single-critic network is employed to obtain the approximate solution of Hamilton-Jacobi-Bellman (HJB) equation. By introducing an additional stability term and experience replay (ER) technique, we present a novel critic weight update rule, such that (i) the traditional persistent excitation (PE) condition is relaxed, and (ii) the request of an initial admissible control is alleviated. Subsequently, a performance-guaranteed adaptive optimal tracking control algorithm is developed to guarantee the prescribed transient behavior of tracking errors and minimize the cost function simultaneously. A rigorous theoretical analysis indicates that the developed controller guarantees semi-globally uniformly ultimate boundedness of the closed-loop adaptive system with prescribed performance. Simulation studies demonstrate the effectiveness and robustness of the presented control algorithm.
Performance-Guaranteed Adaptive Optimized Control of Intelligent Surface Vehicle Using Reinforcement Learning
IEEE Transactions on Intelligent Vehicles ; 9 , 2 ; 3581-3592
2024-02-01
1895255 byte
Article (Journal)
Electronic Resource
English
Adaptive Routing with Guaranteed Delay Bounds using Safe Reinforcement Learning
BASE | 2020
|Optimal Q-laws via reinforcement learning with guaranteed stability
Elsevier | 2021
|Guaranteed Globally Optimal continuous Reinforcement Learning (AIAA 2014-0010)
British Library Conference Proceedings | 2014
|