Unmanned ship path tracking method based on reinforcement learning

• Main Authors: DONG BOTAO, WU DI, SUN ZHIJIAN, XU XINLI, ZHANG WEIDONG, ZHANG YONGHUI, HUANG MENGXING
• Format: Patent
• Language: Chinese; English
• Published: 11.06.2021
• Subjects: CONTROLLING; PHYSICS; REGULATING; SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES

The invention provides an unmanned ship path tracking method based on reinforcement learning. The method comprises the following steps: setting a tracking path of an unmanned ship; establishing an MDP model for the tracking path of the unmanned ship and an obstacle avoidance process, and setting a reward function; performing reinforcement learning on a state information model by adopting a PPO algorithm to obtain control strategy parameters of the unmanned ship; enabling the unmanned ship to execute a path tracking task according to the control strategy parameters. According to the unmanned ship path tracking method based on reinforcement learning, the PPO algorithm is adopted in the strategy training process to improve the convergence of action strategy parameters, human intervention is not needed in the algorithm iteration process, and due to the fact that an agent actively interacts with the environment, various interference factors in the environment can be learned by the agent, the design process of the