Enregistré dans:
Détails bibliographiques
Auteurs principaux: Feng, Mingyang, Zhang, Mengnuo, Li, Shaoyuan, Yin, Xiang
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2605.20929
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914582531932160
author Feng, Mingyang
Zhang, Mengnuo
Li, Shaoyuan
Yin, Xiang
author_facet Feng, Mingyang
Zhang, Mengnuo
Li, Shaoyuan
Yin, Xiang
contents We propose STEAM (Spatial, Temporal, and Emergent congestion Awareness for MAPF), a training-free test-time enhancement framework for learning-based decentralized Multi-Agent Path Finding (MAPF) in discrete environments. Given a pretrained decentralized policy, STEAM requires no retraining, architectural modification, or replacement by a centralized planner. Instead, it injects lightweight congestion-aware guidance into the original policy execution. STEAM first rolls out the shortest paths induced by the current cost-to-go maps to identify potential future congestion hotspots. Spatially avoidable congestion is mitigated by updating agent-specific cost-to-go information, while spatially unavoidable bottlenecks are handled through temporal logit correction. In addition, emergent local congestion is reduced by a density-aware logit correction based on neighboring agents' corrected cost-to-go maps. Extensive experiments on representative learning-based decentralized MAPF algorithms show that STEAM consistently improves success rate, makespan, and solution cost, with success-rate gains of up to 60% and only minor computational overhead. The implementation is available at https://anonymous.4open.science/r/STEAM-MAPF-7A62.
format Preprint
id arxiv_https___arxiv_org_abs_2605_20929
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle STEAM: A Training-Free Congestion-Aware Enhancement Framework for Decentralized Multi-Agent Path Finding
Feng, Mingyang
Zhang, Mengnuo
Li, Shaoyuan
Yin, Xiang
Robotics
We propose STEAM (Spatial, Temporal, and Emergent congestion Awareness for MAPF), a training-free test-time enhancement framework for learning-based decentralized Multi-Agent Path Finding (MAPF) in discrete environments. Given a pretrained decentralized policy, STEAM requires no retraining, architectural modification, or replacement by a centralized planner. Instead, it injects lightweight congestion-aware guidance into the original policy execution. STEAM first rolls out the shortest paths induced by the current cost-to-go maps to identify potential future congestion hotspots. Spatially avoidable congestion is mitigated by updating agent-specific cost-to-go information, while spatially unavoidable bottlenecks are handled through temporal logit correction. In addition, emergent local congestion is reduced by a density-aware logit correction based on neighboring agents' corrected cost-to-go maps. Extensive experiments on representative learning-based decentralized MAPF algorithms show that STEAM consistently improves success rate, makespan, and solution cost, with success-rate gains of up to 60% and only minor computational overhead. The implementation is available at https://anonymous.4open.science/r/STEAM-MAPF-7A62.
title STEAM: A Training-Free Congestion-Aware Enhancement Framework for Decentralized Multi-Agent Path Finding
topic Robotics
url https://arxiv.org/abs/2605.20929