On the Completeness of Conflict-Based Search: Temporally-Relative Duplicate Pruning

TL;DR

This paper introduces Temporally-Relative Duplicate Pruning (TRDP), a technique that guarantees the termination of Conflict-Based Search (CBS) in multi-agent pathfinding by effectively detecting and removing duplicate states, thus addressing its longstanding incompleteness.

Contribution

The paper presents TRDP, a novel duplicate detection method that ensures CBS's completeness in both classic and continuous-time MAPF domains, with minimal runtime impact.

Findings

TRDP guarantees CBS termination on unsolvable instances.

TRDP maintains efficiency with minimal runtime overhead.

In some cases, TRDP significantly improves performance.

Abstract

Conflict-Based Search (CBS) algorithm for the multi-agent pathfinding (MAPF) problem is that it is incomplete for problems which have no solution; if no mitigating procedure is run in parallel, CBS will run forever when given an unsolvable problem instance. In this work, we introduce Temporally-Relative Duplicate Pruning (TRDP), a technique for duplicate detection and removal in both classic and continuous-time MAPF domains. TRDP is a simple procedure which closes the long-standing theoretic loophole of incompleteness for CBS by detecting and avoiding the expansion of duplicate states. TRDP is shown both theoretically and empirically to ensure termination without a significant impact on runtime in the majority of problem instances. In certain cases, TRDP is shown to increase performance significantly