Simultaneous Multi-Robot Motion Planning with Projected Diffusion Models

TL;DR

This paper introduces SMD, a diffusion-based method for multi-robot motion planning that enforces constraints, producing collision-free, feasible trajectories, and presents a benchmark for evaluating such algorithms.

Contribution

The paper proposes a novel diffusion-based approach with constrained optimization for multi-robot motion planning and introduces a comprehensive benchmark for evaluation.

Findings

SMD outperforms classical and learning-based planners in success rate.

SMD achieves higher efficiency in complex environments.

The benchmark enables systematic evaluation of MRMP algorithms.

Abstract

Recent advances in diffusion models hold significant potential in robotics, enabling the generation of diverse and smooth trajectories directly from raw representations of the environment. Despite this promise, applying diffusion models to motion planning remains challenging due to their difficulty in enforcing critical constraints, such as collision avoidance and kinematic feasibility. These limitations become even more pronounced in Multi-Robot Motion Planning (MRMP), where multiple robots must coordinate in shared spaces. To address these challenges, this work proposes Simultaneous MRMP Diffusion (SMD), a novel approach integrating constrained optimization into the diffusion sampling process to produce collision-free, kinematically feasible trajectories. Additionally, the paper introduces a comprehensive MRMP benchmark to evaluate trajectory planning algorithms across scenarios with varying robot densities, obstacle complexities, and motion constraints. Experimental results show SMD consistently outperforms classical and other learning-based motion planners, achieving higher success rates and efficiency in complex multi-robot environments.