Cascaded Diffusion Models for Neural Motion Planning

TL;DR

This paper introduces a hierarchical diffusion model approach for global motion planning in robots, enabling collision-free trajectories in complex environments by combining global prediction, local refinement, and online plan repair.

Contribution

It presents a novel cascaded diffusion model framework that unifies global and local planning with online repair, improving collision avoidance in challenging scenarios.

Findings

Outperforms baselines by approximately 5% on navigation and manipulation tasks.

Effectively generates collision-free trajectories in complex scenes.

Integrates global prediction with local refinement and online repair.

Abstract

Robots in the real world need to perceive and move to goals in complex environments without collisions. Avoiding collisions is especially difficult when relying on sensor perception and when goals are among clutter. Diffusion policies and other generative models have shown strong performance in solving local planning problems, but often struggle at avoiding all of the subtle constraint violations that characterize truly challenging global motion planning problems. In this work, we propose an approach for learning global motion planning using diffusion policies, allowing the robot to generate full trajectories through complex scenes and reasoning about multiple obstacles along the path. Our approach uses cascaded hierarchical models which unify global prediction and local refinement together with online plan repair to ensure the trajectories are collision free. Our method outperforms (by ~5%) a wide variety of baselines on challenging tasks in multiple domains including navigation and manipulation.