Cascaded Diffusion Models for Neural Motion Planning

-- Robots in the real world need to perceive and move to goals in complex environments without collisions. A voiding 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 ( 5%) a wide variety of baselines on challenging tasks in multiple domains including navigation and manipulation. A key requirement for useful robots is that they can generalize motions to new environments. While classical motion planning algorithms often show good generalization [1], they require privileged information (e.g., full scene geometry) about their world; this has led to interest in neural motion planning approaches which can operate off of raw sensor data [2], [3], [4], [5], [6], and leverage large-scale behavior cloning to guide sampling [7], [2], [3]. However, neural motion planning approaches often struggle at generalizing to the challenging, cluttered environments in which traditional motion planners excel. This limitation is because learned approaches fail to satisfy all of the many constraints necessary for a trajectory to be successful for a high-dimensional multi-modal planning problem.