Moving Target Tracking Control of Unmanned Ship Based on DDPG Algorithm
LI Haodong
LIN Wei
YUAN Yu
HU Zhiwei
FENG Youbing
Abstract：In order to achieve the target tracking of the unmanned ship in complex sea conditions,the DDPG algorithm is used to control the motion of the unmanned ship,so that the unmanned ship can complete the rapid tracking of the moving target.The No-moto model is used to model the motion model of the unmanned ship.According to the characteristics of large hysteresis of un-manned ship motion,the state variables of unmanned ship are reconstructed,and the unmanned ship agent can observe the high or-der difference of state variables.The reward function that is not easy to fall into the local optimal solution is set for the task of un-manned ship tracking the moving target.Finally,the reinforcement learning agent learns to effectively control the unmanned ship tracking the moving target through the interaction with the environment,and verifies the effectiveness of the algorithm.
Keywords：DDPGunmanned shipmotion controlmoving target tracking
Publication Date：2024-08-20
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：7( 2361-2366,2399 )