Multi-Robot Motion Planning with Diffusion Models

2024-10-04

arXiv.org

AI Summary

Multi-robot coordinated motion planning faces challenges in handling high-dimensional collision constraints and accurately modeling real-world robot behavior distributions. Method: This paper proposes the MMD framework, the first to integrate single-robot diffusion models with A*-guided heuristic search, enabling scalable, collision-free, and distributionally faithful multi-robot trajectory generation using only single-robot trajectory data. It further introduces a multi-model ensemble mechanism and constraint-aware sampling to overcome the generalization limitations of single-model approaches in complex environments. Contribution/Results: Evaluated in a logistics simulation scenario, MMD successfully plans coordinated motions for dozens of robots. It achieves significant improvements in trajectory success rate and diversity, while reducing collision frequency by 87% compared to baseline methods.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Multiagent Systems: Multiagent Planning
• Planning, Routing, and Scheduling: Planning with Markov Models (MDPs, POMDPs)

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Diffusion models have recently been successfully applied to a wide range of robotics applications for learning complex multi-modal behaviors from data. However, prior works have mostly been confined to single-robot and small-scale environments due to the high sample complexity of learning multi-robot diffusion models. In this paper, we propose a method for generating collision-free multi-robot trajectories that conform to underlying data distributions while using only single-robot data. Our algorithm, Multi-robot Multi-model planning Diffusion (MMD), does so by combining learned diffusion models with classical search-based techniques -- generating data-driven motions under collision constraints. Scaling further, we show how to compose multiple diffusion models to plan in large environments where a single diffusion model fails to generalize well. We demonstrate the effectiveness of our approach in planning for dozens of robots in a variety of simulated scenarios motivated by logistics environments. View video demonstrations and code at: https://multi-robot-diffusion.github.io/.

Problem

• Learning multi-robot motion planning from single-robot data
• Generating collision-free trajectories using diffusion models
• Scaling diffusion models for large multi-robot environments

Innovation

• Uses diffusion models for multi-robot motion planning
• Combines diffusion models with search-based techniques
• Composes multiple diffusion models for large environments