Multiple AMR Rigid Formation Control With Collision Avoidance Based On MADDPG
Kaiqi Wu, Qing Wang, Yongbao Wu, Jian Liu, Lei Xue · 2022 41st Chinese Control Conference (CCC) · 2022
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.