Path Planning Algorithm for Unmanned Surface Vessel Based on Multiobjective Reinforcement Learning

• Published in: Computational intelligence and neuroscience Vol. 2023; no. 1; p. 2146314
• Main Authors: Yang, Caipei, Zhao, Yingqi, Cai, Xuan, Wei, Wei, Feng, Xingxing, Zhou, Kaibo
• Format: Journal Article
• Language: English
• Published: United States Hindawi 2023; John Wiley & Sons, Inc
• Subjects: Algorithms; Decision making; Deep learning; Learning; Machine learning; Marine environment; Methods; Neural networks; Obstacle avoidance; Optimization; Path planning; Questions and answers; Reinforcement; Robots; Sovereignty; Strategy; Task complexity; Vessels
• ISSN: 1687-5265; 1687-5273; 1687-5273
• DOI: 10.1155/2023/2146314

It is challenging to perform path planning tasks in complex marine environments as the unmanned surface vessel approaches the goal while avoiding obstacles. However, the conflict between the two subtarget tasks of obstacle avoidance and goal approaching makes the path planning difficult. Thus, a path planning method for unmanned surface vessel based on multiobjective reinforcement learning is proposed under the complex environment with high randomness and multiple dynamic obstacles. Firstly, the path planning scene is set as the main scene, and the two subtarget scenes including obstacle avoidance and goal approaching are divided from it. The action selection strategy in each subtarget scene is trained through the double deep Q-network with prioritized experience replay. A multiobjective reinforcement learning framework based on ensemble learning is further designed for policy integration in the main scene. Finally, by selecting the strategy from subtarget scenes in the designed framework, an optimized action selection strategy is trained and used for the action decision of the agent in the main scene. Compared with traditional value-based reinforcement learning methods, the proposed method achieves a 93% success rate in path planning in simulation scenes. Furthermore, the average length of the paths planned by the proposed method is 3.28% and 1.97% shorter than that of PER-DDQN and dueling DQN, respectively.