Deep reinforcement learning-based controller for path following of an unmanned surface vehicle. (1st July 2019)

• Record Type: Journal Article
• Authors: Woo, Joohyun; Yu, Chanwoo; Kim, Nakwan
• Is Part Of: Ocean engineering. Volume 183(2019)
• Page Start: 155
• Page End: 166
• Publication Date: 2019-07-01
• Subjects: Deep reinforcement learning -- Path following -- Unmanned surface vehicle -- Learning-based control -- Artificial intelligence; Ocean engineering -- Periodicals; Ocean engineering; Periodicals; 620.4162
• DOI: 10.1016/j.oceaneng.2019.04.099
• Languages: English
• ISSNs: 0029-8018

Abstract

Abstract: In this paper, a deep reinforcement learning (DRL)-based controller for path following of an unmanned surface vehicle (USV) is proposed. The proposed controller can self-develop a vehicle's path following capability by interacting with the nearby environment. A deep deterministic policy gradient (DDPG) algorithm, which is an actor-critic-based reinforcement learning algorithm, was adapted to capture the USV's experience during the path-following trials. A Markov decision process model, which includes the state, action, and reward formulation, specially designed for the USV path-following problem is suggested. The control policy was trained with repeated trials of path-following simulation. The proposed method's path-following and self-learning capabilities were validated through USV simulation and a free-running test of the full-scale USV. Highlights: A deep reinforcement learning-based controller for path following of an unmanned surface vehicle is proposed. Using the proposed method, control policy for USV path following is trained with USV simulation. The trained control policy is validated through USV free-running test of the full-scale USV.