Towards Deployment-Efficient and Collision-Free Multi-Agent Path Finding (Student Abstract)

Multi-agent pathfinding (MAPF) is essential to large-scale robotic coordination tasks. Planning-based algorithms show their advantages in collision avoidance while avoiding exponential growth in the number of agents. Reinforcement-learning (RL)-based algorithms can be deployed efficiently but cannot prevent collisions entirely due to the lack of hard constraints. This paper combines the merits of planning-based and RL-based MAPF methods to propose a deployment-efficient and collision-free MAPF algorithm. The experiments show the effectiveness of our approach.

Authors

• Feng Chen
• Chenghe Wang Nanjing University
• Fuxiang Zhang Nanjing University
• Hao Ding
• Qiaoyong Zhong Hikvision Research Institute
• Shiliang Pu Hikvision Research Institute, Zhejiang Key Laboratory of Social Security Big Data
• Zongzhang Zhang National Key Laboratory for Novel Software Technology, Nanjing University, China School of Artificial Intelligence, Nanjing University, China

Keywords

• Multi-Agent Path Finding
• Multi-Agent System
• Reinforcement Learning