Cascaded Diffusion Models for Neural Motion Planning
This work addresses the challenge of collision-free motion planning for robots in cluttered settings, representing an incremental advancement over existing diffusion-based methods.
The paper tackles the problem of global motion planning for robots in complex environments by proposing cascaded diffusion models that unify global prediction and local refinement with online plan repair, achieving a ~5% performance improvement over various baselines in navigation and manipulation tasks.
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.