Graph Attention-Guided Search for Dense Multi-Agent Pathfinding

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jain, Rishabh, Okumura, Keisuke, Amir, Michael, Prorok, Amanda
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917027491348480
author Jain, Rishabh
Okumura, Keisuke
Amir, Michael
Prorok, Amanda
author_facet Jain, Rishabh
Okumura, Keisuke
Amir, Michael
Prorok, Amanda
contents Finding near-optimal solutions for dense multi-agent pathfinding (MAPF) problems in real-time remains challenging even for state-of-the-art planners. To this end, we develop a hybrid framework that integrates a learned heuristic derived from MAGAT, a neural MAPF policy with a graph attention scheme, into a leading search-based algorithm, LaCAM. While prior work has explored learning-guided search in MAPF, such methods have historically underperformed. In contrast, our approach, termed LaGAT, outperforms both purely search-based and purely learning-based methods in dense scenarios. This is achieved through an enhanced MAGAT architecture, a pre-train-then-fine-tune strategy on maps of interest, and a deadlock detection scheme to account for imperfect neural guidance. Our results demonstrate that, when carefully designed, hybrid search offers a powerful solution for tightly coupled, challenging multi-agent coordination problems.
format Preprint
id arxiv_https___arxiv_org_abs_2510_17382
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Graph Attention-Guided Search for Dense Multi-Agent Pathfinding
Jain, Rishabh
Okumura, Keisuke
Amir, Michael
Prorok, Amanda
Artificial Intelligence
Machine Learning
Multiagent Systems
Robotics
Finding near-optimal solutions for dense multi-agent pathfinding (MAPF) problems in real-time remains challenging even for state-of-the-art planners. To this end, we develop a hybrid framework that integrates a learned heuristic derived from MAGAT, a neural MAPF policy with a graph attention scheme, into a leading search-based algorithm, LaCAM. While prior work has explored learning-guided search in MAPF, such methods have historically underperformed. In contrast, our approach, termed LaGAT, outperforms both purely search-based and purely learning-based methods in dense scenarios. This is achieved through an enhanced MAGAT architecture, a pre-train-then-fine-tune strategy on maps of interest, and a deadlock detection scheme to account for imperfect neural guidance. Our results demonstrate that, when carefully designed, hybrid search offers a powerful solution for tightly coupled, challenging multi-agent coordination problems.
title Graph Attention-Guided Search for Dense Multi-Agent Pathfinding
topic Artificial Intelligence
Machine Learning
Multiagent Systems
Robotics
url https://arxiv.org/abs/2510.17382