Belief-Aware Multi-Agent Path Finding under Map Uncertainty

2026-09-30

AI Summary

This study addresses the inefficiency of frequent replanning in Multi-Agent Path Finding (MAPF) caused by map uncertainty and the underutilization of spatial correlations within observation spaces. To overcome this, we propose MAGIC, a framework that, for the first time, leverages the spatial dependencies of observations to infer the traversability of unobserved regions. Specifically, MAGIC constructs an online shared belief update mechanism based on Gaussian Markov Random Fields and belief propagation to infer unknown obstacles. Furthermore, it designs a detour-aware cost function to augment standard MAPF solvers, enabling proactive obstacle avoidance. Experimental results demonstrate that MAGIC significantly reduces total execution costs across 96.3% of test instances and scales effectively to large-scale scenarios involving up to 800 agents.

Abstract

Multi-Agent Path Finding (MAPF) aims to find collision-free paths for multiple agents in a shared environment. Classical MAPF assumes that all static obstacles are known in advance, but real-world environments can change unexpectedly due to fallen objects, spills, or other local disturbances. When such changes are spatially correlated, an observation can inform traversability estimates beyond the observed location. Prior approaches address uncertainty in traversability through contingent plans or replanning based on direct observations, but do not leverage this spatial dependence to infer the traversability of nearby unobserved locations. As a result, they cannot use one observation to anticipate nearby unobserved obstacles that may cause costly rerouting later. We focus on Belief-Aware MAPF, where map discrepancies are fixed during execution but initially unknown, and observations can be informative beyond the observed location. We propose Multi-Agent Gaussian belief Inference for Coordination (MAGIC), a framework that updates a shared belief about traversability online based on agents' observations. MAGIC uses a Gaussian Markov Random Field and Gaussian Belief Propagation to approximately infer traversability and construct detour-aware costs for standard MAPF planners. Our experiments on MAPF benchmarks show that MAGIC reduces the executed sum of costs compared to existing approaches on 96.3% of instances, across several planner families and teams of up to 800 agents, demonstrating its applicability to large-scale MAPF problems.

Problem

• Multi-Agent Path Finding
• Map Uncertainty
• Belief-Aware MAPF
• Spatial Correlation
• Traversability Inference

Innovation

• Multi-Agent Path Finding
• Belief-Aware MAPF
• Gaussian Markov Random Field
• Gaussian Belief Propagation
• Map Uncertainty