Deep reinforcement learning based optimal trajectory tracking control of autonomous underwater vehicle

• Published in: 2017 36th Chinese Control Conference (CCC) pp. 4958 - 4965
• Main Authors: Runsheng Yu, Zhenyu Shi, Chaoxing Huang, Tenglong Li, Qiongxiong Ma
• Format: Conference Proceeding
• Language: English
• Published: Technical Committee on Control Theory, CAA 01-07-2017
• Subjects: Autonomous Underwater Vehicles; Deep Reinforcement Learning; Learning (artificial intelligence); Mathematical model; Neural networks; Optimal Control System; Stability analysis; Training; Trajectory tracking
• ISSN: 2161-2927
• DOI: 10.23919/ChiCC.2017.8028138

The aim of this paper is to solve the control problem of trajectory tracking of Autonomous Underwater Vehicles (AUVs) through using and improving deep reinforcement learning (DRL). The deep reinforcement learning of an underwater motion control system is composed of two neural networks: one network selects action and the other evaluates whether the selected action is accurate, and they modify themselves through a deep deterministic policy gradient(DDPG). These two neural networks are made up of multiple fully connected layers. Based on theories and simulations, this algorithm is more accurate than traditional PID control in solving the trajectory tracking of AUV in complex curves to a certain precision.