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

TL;DR

This paper introduces CP-Solver, a novel multi-agent pathfinding method that incorporates statistical uncertainty quantification to handle dynamic uncontrollable agents, providing safety guarantees and scalability in complex environments.

Contribution

It presents a new MAPF algorithm integrating conformal prediction for uncertainty quantification, enabling collision avoidance with statistical safety guarantees in dynamic settings.

Findings

CP-Solver reduces collisions in dynamic environments.

The method provides statistical safety guarantees for one-shot missions.

Scales effectively to lifelong multi-agent pathfinding scenarios.

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.