Multi-Agent Path Finding Among Dynamic Uncontrollable Agents with Statistical Safety Guarantees

2025-07-29

AI Summary

Traditional multi-agent path finding (MAPF) methods fail in dynamic environments due to uncertainty induced by uncontrollable agents. Method: This paper proposes the first robust MAPF framework integrating learning-based motion prediction with conformal prediction (CP). It introduces CP—novelly applied to path planning—to provide statistically valid, verifiable collision-free guarantees for single-step planning; extends the approach to lifelong tasks via receding-horizon optimization and enhanced conflict-based search (ECBS); and employs a learnable predictor to output trajectory distributions, with CP generating calibrated uncertainty intervals for safe navigation. Results: Experiments on warehouse and game maps demonstrate that our method significantly reduces collision rates while maintaining high-throughput path planning performance.

Technology Category

• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Multiagent Systems: Multiagent Planning
• Intelligent Robots: Motion and Path Planning

Application Category

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

Abstract

Existing multi-agent path finding (MAPF) solvers do not account for uncertain behavior of uncontrollable agents. We present a novel variant of Enhanced Conflict-Based Search (ECBS), for both one-shot and lifelong MAPF in dynamic environments with uncontrollable agents. Our method consists of (1) training a learned predictor for the movement of uncontrollable agents, (2) quantifying the prediction error using conformal prediction (CP), a tool for statistical uncertainty quantification, and (3) integrating these uncertainty intervals into our modified ECBS solver. Our method can account for uncertain agent behavior, comes with statistical guarantees on collision-free paths for one-shot missions, and scales to lifelong missions with a receding horizon sequence of one-shot instances. We run our algorithm, CP-Solver, across warehouse and game maps, with competitive throughput and reduced collisions.

Problem

• Handling uncertain behavior of uncontrollable agents in MAPF
• Providing statistical safety guarantees for collision-free paths
• Scaling solutions to lifelong missions in dynamic environments

Innovation

• Enhanced Conflict-Based Search for dynamic MAPF
• Learned predictor for uncontrollable agents
• Conformal prediction for statistical safety