Distributed Heuristic Multi-Agent Path Finding with Communication

TL;DR

This paper introduces a novel decentralized multi-agent pathfinding method combining communication, deep Q-learning, and graph convolution, guided by heuristics, achieving high success rates in obstacle-rich environments.

Contribution

It proposes a new RL-based MAPF approach that integrates communication, graph convolution, and heuristic guidance, trained in a distributed, curriculum learning setting.

Findings

High success rate in obstacle-rich environments

Low average steps to reach goals

Effective decentralized execution

Abstract

Multi-Agent Path Finding (MAPF) is essential to large-scale robotic systems. Recent methods have applied reinforcement learning (RL) to learn decentralized polices in partially observable environments. A fundamental challenge of obtaining collision-free policy is that agents need to learn cooperation to handle congested situations. This paper combines communication with deep Q-learning to provide a novel learning based method for MAPF, where agents achieve cooperation via graph convolution. To guide RL algorithm on long-horizon goal-oriented tasks, we embed the potential choices of shortest paths from single source as heuristic guidance instead of using a specific path as in most existing works. Our method treats each agent independently and trains the model from a single agent's perspective. The final trained policy is applied to each agent for decentralized execution. The whole system is distributed during training and is trained under a curriculum learning strategy. Empirical evaluation in obstacle-rich environment indicates the high success rate with low average step of our method.