EQM-MPD: EQUIVARIANT ON-MANIFOLD MOTION PLANNING DIFFUSION

Evangelos Chatzipantazis, Nishanth Rao, Kostas Daniilidis

Keywords: Diffusion Models, Equivariance, State-Space, Manipulation, Riemannian Gradient Descent

TL;DR: Novel Diffusion-based motion planner that works directly on the state space manifold and is equivariant to global transformations.

Abstract:

Fast, reliable and versatile motion planning algorithms are essential for robots
with many degrees of freedom in complex, dynamic environments. Diffusion
models have been proposed as a faster alternative to classical planners by providing informative priors on distributions of trajectories. However, they are currently
trained to overfit to environments with fixed object configurations and need to be
re-trained when these conditions change. This limits applicability in tasks like
robotic manipulation where environments change dynamically and initial configurations vary. We show that diffusion-guidance is not sufficient to adapt the model
to large changes that can happen during execution or even from different initialization. Moreover, current approaches ignore the underlying topology of the state
space thus requiring heavy guidance that dominates planning time and reduces
efficiency dramatically. To address these, we propose a novel diffusion motion
planner, EqM-MPD that operates directly on the robot’s state space manifold and
produces an equivariant prior distribution on trajectories. Our approach eliminates the need for retraining under rigid transformations. Moreover, our diffusion on state space manifold converges faster during guidance. We show that our
approach achieves efficient, robust and generalizable planning that is especially
useful for manipulation advancing beyond prior limitations.

Submission Number: 82