Train-Small Deploy-Large: Leveraging Diffusion-Based Multi-Robot Planning

TL;DR

This paper introduces a diffusion model-based multi-robot path planner that generalizes from a small training set to larger robot groups, offering scalable and adaptable multi-agent navigation.

Contribution

The work presents a diffusion model approach trained on few agents that effectively scales to larger groups during deployment, addressing limitations of existing methods.

Findings

The diffusion-based planner generalizes well to larger numbers of robots.

The approach achieves good accuracy across multiple scenarios.

It outperforms some existing reinforcement learning and heuristic methods.

Abstract

Learning based multi-robot path planning methods struggle to scale or generalize to changes, particularly variations in the number of robots during deployment. Most existing methods are trained on a fixed number of robots and may tolerate a reduced number during testing, but typically fail when the number increases. Additionally, training such methods for a larger number of agents can be both time consuming and computationally expensive. However, analytical methods can struggle to scale computationally or handle dynamic changes in the environment. In this work, we propose to leverage a diffusion model based planner capable of handling dynamically varying number of agents. Our approach is trained on a limited number of agents and generalizes effectively to larger numbers of agents during deployment. Results show that integrating a single shared diffusion model based planner with dedicated inter-agent attention computation and temporal convolution enables a train small deploy-large paradigm with good accuracy. We validate our method across multiple scenarios and compare the performance with existing multi-agent reinforcement learning techniques and heuristic control based methods.