Reinforcement learning based model-free optimized trajectory tracking strategy design for an AUV

作者：Duan, Kairong^*; Fong, Simon; Chen, C. L. Philip

来源：NEUROCOMPUTING, 2022, 469: 289-297.

DOI：10.1016/j.neucom.2021.10.056

• AUV
• HJI equation
• RL algorithm
• Robust control
• Model-free

Considering the fact that it is very difficult to fully model an autonomous underwater vehicle (AUV) in the complex water environment, this paper presents a model-free tracking control strategy for an AUV in the presence of unknown disturbances. We first formulate an optimized control problem by defining a track -ing Hamilton-Jacobi-Isaac (HJI) equation. Then, we present a reinforcement learning (RL) algorithm to compute an optimized solution by learning from the HJI equation online. It is noted that during the learn-ing period, no information about the AUV's dynamics is needed. In order to demonstrate the efficiency of the proposed strategy, numerical simulation is considered, results are validated and discussed.