Multi-Goal Multi-Agent Path Finding via Decoupled and Integrated Goal Vertex Ordering

TL;DR

This paper introduces the multi-goal multi-agent path finding (MAPF$^{MG}$) problem, extending standard MAPF by requiring agents to visit multiple goals, and proposes two novel algorithms to solve it, with experimental analysis of their performance.

Contribution

The paper presents the first algorithms specifically designed for MAPF$^{MG}$, including a heuristic search method and an SMT-based compilation approach.

Findings

HCBS outperforms SMT-HCBS in experiments

Compilation-based approach has limitations in scalability

MAPF$^{MG}$ generalizes standard MAPF with new challenges

Abstract

We introduce multi-goal multi agent path finding (MAPF$^{MG}$) which generalizes the standard discrete multi-agent path finding (MAPF) problem. While the task in MAPF is to navigate agents in an undirected graph from their starting vertices to one individual goal vertex per agent, MAPF$^{MG}$ assigns each agent multiple goal vertices and the task is to visit each of them at least once. Solving MAPF$^{MG}$ not only requires finding collision free paths for individual agents but also determining the order of visiting agent's goal vertices so that common objectives like the sum-of-costs are optimized. We suggest two novel algorithms using different paradigms to address MAPF$^{MG}$: a heuristic search-based search algorithm called Hamiltonian-CBS (HCBS) and a compilation-based algorithm built using the SMT paradigm, called SMT-Hamiltonian-CBS (SMT-HCBS). Experimental comparison suggests limitations of compilation-based approach.