Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding

Valeriy Vyaltsev, Alsu Sagirova, Anton Andreychuk, Oleg Bulichev, Yuri Kuratov, Konstantin Yakovlev, Aleksandr Panov, Alexey Skrynnik

arXiv:2605.07637 · 2026-05-15 공개 · arXiv · PDF

robotics imitation-learning path-planning pre-trained-model decentralized-rl local-communication multi-round-communication scalable-ai

Abstract

Multi-agent pathfinding (MAPF) is a widely used abstraction for multi-robot trajectory planning problems, where multiple homogeneous agents move simultaneously within a shared environment. Although solving MAPF optimally is NP-hard, scalable and efficient solvers are critical for real-world applications such as logistics and search-and-rescue. To this end, the research community has proposed various decentralized suboptimal MAPF solvers that leverage machine learning. Such methods frame MAPF (from a single agent perspective) as a Dec-POMDP where at each time step an agent has to decide an action based on the local observation and typically solve the problem via reinforcement learning or imitation learning. We follow the same approach but additionally introduce a learnable communication module tailored to enhance cooperation between agents via efficient feature sharing. We present the Local Communication for Multi-agent Pathfinding (LC-MAPF), a generalizable pre-trained model that applies multi-round communication between neighboring agents to exchange information and improve their coordination. Our experiments show that the introduced method outperforms the existing learning-based MAPF solvers, including IL and RL-based approaches, across diverse metrics in a diverse range of (unseen) test scenarios. Remarkably, the introduced communication mechanism does not compromise LC-MAPF's scalability, a common bottleneck for communication-based MAPF solvers.

한국어 요약

📋 한 줄 요약

**[멀티에이전트 / 경로 계획]** 학습 가능한 국소 통신 모듈을 추가해 대규모 분산 다중에이전트 경로찾기(MAPF)에서 학습 기반 방법들을 능가하는 사전 학습 모델 LC-MAPF 제안.

🎯 핵심 기여도

💡 핵심 아이디어

완전한 분산 의사결정과 글로벌 좌표가 모두 비현실적인 대규모 MAPF에서 핵심은 "국소 통신"의 효율성이며, 이를 학습 가능한 모듈로 모델링하면 협력과 확장성을 동시에 잡을 수 있다.

🔬 기술적 접근법

📊 주요 결과

💭 의의 및 한계

**의의**: 학습형 MAPF의 실용성을 끌어올리며 물류·창고 자동화·다중 로봇 시스템에서의 적용 가능성을 확장. **한계**: 통신 채널이 이상적이라는 가정에 기반, 통신 지연·손실이 큰 실환경에서의 견고성은 추가 검증 필요.

🚀 실용적 활용