English

Multi-Agent Path Finding with Prioritized Communication Learning

Robotics 2022-02-11 v2 Computer Science and Game Theory Machine Learning Multiagent Systems

Abstract

Multi-agent pathfinding (MAPF) has been widely used to solve large-scale real-world problems, e.g., automation warehouses. The learning-based, fully decentralized framework has been introduced to alleviate real-time problems and simultaneously pursue optimal planning policy. However, existing methods might generate significantly more vertex conflicts (or collisions), which lead to a low success rate or more makespan. In this paper, we propose a PrIoritized COmmunication learning method (PICO), which incorporates the \textit{implicit} planning priorities into the communication topology within the decentralized multi-agent reinforcement learning framework. Assembling with the classic coupled planners, the implicit priority learning module can be utilized to form the dynamic communication topology, which also builds an effective collision-avoiding mechanism. PICO performs significantly better in large-scale MAPF tasks in success rates and collision rates than state-of-the-art learning-based planners.

Keywords

Cite

@article{arxiv.2202.03634,
  title  = {Multi-Agent Path Finding with Prioritized Communication Learning},
  author = {Wenhao Li and Hongjun Chen and Bo Jin and Wenzhe Tan and Hongyuan Zha and Xiangfeng Wang},
  journal= {arXiv preprint arXiv:2202.03634},
  year   = {2022}
}

Comments

7 pages, 5 figures, 3 tables, ICRA 2022 Camera Ready

R2 v1 2026-06-24T09:25:29.779Z