Multi-Agent Monte Carlo Tree Search for Makespan-Efficient Object Rearrangement in Cluttered Spaces

TL;DR

This paper presents CAM-MCTS, a multi-agent planning framework that efficiently rearranges objects in cluttered environments by reducing makespan through centralized task assignment and asynchronous execution, validated in simulations and real-world tests.

Contribution

Introduces CAM-MCTS, a novel multi-agent Monte Carlo Tree Search framework combining centralized task assignment with asynchronous execution for efficient object rearrangement.

Findings

Consistently reduces makespan in diverse tasks

Effective in both monotone and non-monotone environments

Validated on real-world multi-agent system

Abstract

Object rearrangement planning in complex, cluttered environments is a common challenge in warehouses, households, and rescue sites. Prior studies largely address monotone instances, whereas real-world tasks are often non-monotone-objects block one another and must be temporarily relocated to intermediate positions before reaching their final goals. In such settings, effective multi-agent collaboration can substantially reduce the time required to complete tasks. This paper introduces Centralized, Asynchronous, Multi-agent Monte Carlo Tree Search (CAM-MCTS), a novel framework for general-purpose makespan-efficient object rearrangement planning in challenging environments. CAM-MCTS combines centralized task assignment-where agents remain aware of each other's intended actions to facilitate globally optimized planning-with an asynchronous task execution strategy that enables agents to take on new tasks at appropriate time steps, rather than waiting for others, guided by a one-step look-ahead cost estimate. This design minimizes idle time, prevents unnecessary synchronization delays, and enhances overall system efficiency. We evaluate CAM-MCTS across a diverse set of monotone and non-monotone tasks in cluttered environments, demonstrating consistent reductions in makespan compared to strong baselines. Finally, we validate our approach on a real-world multi-agent system under different configurations, further confirming its effectiveness and robustness.