Deadlock-Free Hybrid RL-MAPF Framework for Zero-Shot Multi-Robot Navigation

TL;DR

This paper introduces a hybrid framework combining reinforcement learning and multi-agent path finding to enable deadlock-free, zero-shot multi-robot navigation in complex environments, significantly improving success rates.

Contribution

The paper presents a novel hybrid approach that integrates RL with MAPF to explicitly resolve deadlocks and improve generalization in multi-robot navigation.

Findings

Boosts task completion from marginal to near-universal success

Reduces deadlocks and collisions significantly

Enables coordinated navigation for heterogeneous robots

Abstract

Multi-robot navigation in cluttered environments presents fundamental challenges in balancing reactive collision avoidance with long-range goal achievement. When navigating through narrow passages or confined spaces, deadlocks frequently emerge that prevent agents from reaching their destinations, particularly when Reinforcement Learning (RL) control policies encounter novel configurations out of learning distribution. Existing RL-based approaches suffer from limited generalization capability in unseen environments. We propose a hybrid framework that seamlessly integrates RL-based reactive navigation with on-demand Multi-Agent Path Finding (MAPF) to explicitly resolve topological deadlocks. Our approach integrates a safety layer that monitors agent progress to detect deadlocks and, when detected, triggers a coordination controller for affected agents. The framework constructs globally feasible trajectories via MAPF and regulates waypoint progression to reduce inter-agent conflicts during navigation. Extensive evaluation on dense multi-agent benchmarks shows that our method boosts task completion from marginal to near-universal success, markedly reducing deadlocks and collisions. When integrated with hierarchical task planning, it enables coordinated navigation for heterogeneous robots, demonstrating that coupling reactive RL navigation with selective MAPF intervention yields a robust, zero-shot performance.