Obstacle Avoidance in Multi-Agent Formation Process Based on Deep Reinforcement Learning
作者机构：Guangxi Key Laboratory of Auto Parts and Vehicle TechnologySchool of Electrical and Information EngineeringGuangxi University of Science and TechnologyLiuzhou 545006GuangxiChina Technology Center of Dongfeng Liuzhou Automobile Co.Ltd.Liuzhou 545000GuangxiChina
出 版 物：《Journal of Shanghai Jiaotong university(Science)》 (上海交通大学学报（英文版）)
年 卷 期：2021年第26卷第5期
页 面：680-685页
核心收录：
学科分类：0711[理学-系统科学] 07[理学] 08[工学] 070105[理学-运筹学与控制论] 081101[工学-控制理论与控制工程] 071101[理学-系统理论] 0811[工学-控制科学与工程] 0701[理学-数学]
基 金：the National Natural Science Foun-dation of China(No.61963006) the Nat-ural Science Foundation of Guangxi Province(Nos.2020GXNSFDA238011,2018GXNSFAA050029,and 2018GXNSFAA294085)
主 题：wheelbarrow multi-agent deep reinforcement learning(DRL) formation obstacle avoidance
摘 要：To solve the problems of difficult control law design,poor portability,and poor stability of traditional multi-agent formation obstacle avoidance algorithms,a multi-agent formation obstacle avoidance method based on deep reinforcement learning(DRL)is *** method combines the perception ability of convolutional neural networks(CNNs)with the decision-making ability of reinforcement learning in a general form and realizes direct output control from the visual perception input of the environment to the action through an end-to-end learning *** multi-agent system(MAS)model of the follow-leader formation method was designed with the wheelbarrow as the control *** improved deep Q netwrok(DQN)algorithm(we improved its discount factor and learning efficiency and designed a reward value function that considers the distance relationship between the agent and the obstacle and the coordination factor between the multi-agents)was designed to achieve obstacle avoidance and collision avoidance in the process of multi-agent formation into the desired *** simulation results show that the proposed method achieves the expected goal of multi-agent formation obstacle avoidance and has stronger portability compared with the traditional algorithm.
维普期刊数据库