Straight-Path Following and Formation Control of USVs Using Distributed Deep Reinforcement Learning and Adaptive Neural Network
Straight-Path Following and Formation Control of USVs Using Distributed Deep Reinforcement Learning and Adaptive Neural Network作者机构:the School of Marine Science and TechnologyNorthwestern Polytechnical UniversityXi’an 710072China
出 版 物:《IEEE/CAA Journal of Automatica Sinica》 (自动化学报(英文版))
年 卷 期:2023年第10卷第2期
页 面:572-574页
核心收录:
学科分类:0710[理学-生物学] 12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0824[工学-船舶与海洋工程] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术(可授工学、理学学位)]
基 金:supported by the National Natural Science Foundation of China(U2141238)
摘 要:Dear Editor,This letter presents a distributed deep reinforcement learning(DRL) based approach to deal with the path following and formation control problems for underactuated unmanned surface vehicles(USVs). By constructing two independent actor-critic architectures,the deep deterministic policy gradient(DDPG) method is proposed to determine the desired heading and speed command for each USV.