EDMP: Ensemble-of-costs-guided Diffusion for Motion Planning

TL;DR

EDMP combines classical and deep-learning motion planning by guiding diffusion with scene-specific costs and an ensemble of cost functions, achieving high success rates and strong generalization across diverse scenes.

Contribution

Introduces EDMP, a diffusion-based motion planner guided by multiple costs, merging classical adaptability with deep-learning success rates.

Findings

Achieves higher success rates than classical methods.

Performs comparably to state-of-the-art deep-learning planners.

Maintains generalization across diverse scenes.

Abstract

Classical motion planning for robotic manipulation includes a set of general algorithms that aim to minimize a scene-specific cost of executing a given plan. This approach offers remarkable adaptability, as they can be directly used off-the-shelf for any new scene without needing specific training datasets. However, without a prior understanding of what diverse valid trajectories are and without specially designed cost functions for a given scene, the overall solutions tend to have low success rates. While deep-learning-based algorithms tremendously improve success rates, they are much harder to adopt without specialized training datasets. We propose EDMP, an Ensemble-of-costs-guided Diffusion for Motion Planning that aims to combine the strengths of classical and deep-learning-based motion planning. Our diffusion-based network is trained on a set of diverse kinematically valid trajectories. Like classical planning, for any new scene at the time of inference, we compute scene-specific costs such as "collision cost" and guide the diffusion to generate valid trajectories that satisfy the scene-specific constraints. Further, instead of a single cost function that may be insufficient in capturing diversity across scenes, we use an ensemble of costs to guide the diffusion process, significantly improving the success rate compared to classical planners. EDMP performs comparably with SOTA deep-learning-based methods while retaining the generalization capabilities primarily associated with classical planners.