记笔记

Multiple AMR Rigid Formation Control With Collision Avoidance Based On MADDPG

Kaiqi Wu¹Qing Wang²YongBao Wu³Jian Liu³Lei Xue³

1. The College of Software Engineering,Southeast University 2. SEU-Monash Joint Graduate school,Southeast University 3. School of Automation,Southeast University,Key Laboratory of Measurement and Control of Complex Systems of Engineering,Ministry of Education

摘要：Recently,the formation control of multiple autonomous mobile robots（AMRs） have gained significant attention,and autonomous mobile robots（AMRs） have applied to all aspects of our life.Multi-agent reinforcement learning is used to solve the autonomously sequential decision-making problem of agents in a common environment with competition or cooperation.Therefore,we present a utility function and a reward function to achieve formation control with collision avoidance for a rigid AMRs system,and build a simulation environment to meet environmental requirements based on MPE.

关键词：

Formation control; Reinforcement learning; Rigid system; Collision avoidance;

基金：

supported in part by the National Natural S cience Foundation of China under grants 62073225； the Natural Science Foundation of Jiangsu Province of China under grants BK20202006； ; the Fundamental Research Funds for the Central Universities； the "Zhishan" Scholars Programs of S outheast University；

会议名称：

第41届中国控制会议

会议时间：

2022-07-25

会议地点：

中国安徽合肥