PC2P: Multi-Agent Path Finding via Personalized-Enhanced Communication and Crowd Perception

2025-10-19

IEEE/RJS International Conference on Intelligent RObots and Systems

AI Summary

This work addresses the limited collaborative capability and susceptibility to deadlocks of existing distributed multi-agent pathfinding (MAPF) methods in partially observable environments. The authors propose a Q-learning-based multi-agent reinforcement learning framework featuring an innovative three-stage communication mechanism—selection, generation, and aggregation—operating over dynamic graph topologies. This mechanism integrates static spatial constraints with dynamic group occupancy information to enhance local perception. Additionally, an expert-guided, region-based deadlock detection and resolution strategy is introduced. Experimental results demonstrate that the proposed approach significantly outperforms state-of-the-art distributed MAPF algorithms across diverse scenarios, and ablation studies confirm the effectiveness of each component.

Technology Category

• Multiagent Systems: Multiagent Planning
• Planning, Routing, and Scheduling: Planning with Markov Models (MDPs, POMDPs)
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Distributed Multi-Agent Path Finding (MAPF) integrated with Multi-Agent Reinforcement Learning (MARL) has emerged as a prominent research focus, enabling real-time cooperative decision-making in partially observable environments through inter-agent communication. However, due to insufficient collaborative and perceptual capabilities, existing methods are inadequate for scaling across diverse environmental conditions. To address these challenges, we propose PC2P, a novel distributed MAPF method derived from a Q-learning-based MARL framework. Initially, we introduce a personalized-enhanced communication mechanism based on dynamic graph topology, which ascertains the core aspects of "who" and "what" in interactive process through three-stage operations: selection, generation, and aggregation. Concurrently, we incorporate local crowd perception to enrich agents’ heuristic observation, thereby strengthening the model’s guidance for effective actions via the integration of static spatial constraints and dynamic occupancy changes. To resolve extreme deadlock issues, we propose a region-based deadlock-breaking strategy that leverages expert guidance to implement efficient coordination within confined areas. Experimental results demonstrate that PC2P achieves superior performance compared to state-of-the-art distributed MAPF methods in varied environments. Ablation studies further confirm the effectiveness of each module for overall performance.

Problem

• Multi-Agent Path Finding
• Distributed MARL
• Inter-agent Communication
• Crowd Perception
• Deadlock

Innovation

• Personalized Communication
• Crowd Perception
• Multi-Agent Path Finding
• Deadlock Resolution
• Dynamic Graph Topology