PRESTO: Fast Motion Planning Using Diffusion Models Based on Key-Configuration Environment Representation

TL;DR

PRESTO introduces a diffusion model-based motion planning framework that efficiently generates collision-free trajectories by leveraging environment representations of key configurations, outperforming previous methods.

Contribution

The paper presents a novel diffusion model approach conditioned on key configurations for fast, reliable motion planning in complex environments.

Findings

Outperforms previous learning-based and planning-based methods in narrow passages

Generates high-quality, collision-free trajectories efficiently

Utilizes environment representations of key configurations for improved planning

Abstract

We introduce a learning-guided motion planning framework that generates seed trajectories using a diffusion model for trajectory optimization. Given a workspace, our method approximates the configuration space (C-space) obstacles through an environment representation consisting of a sparse set of task-related key configurations, which is then used as a conditioning input to the diffusion model. The diffusion model integrates regularization terms that encourage smooth, collision-free trajectories during training, and trajectory optimization refines the generated seed trajectories to correct any colliding segments. Our experimental results demonstrate that high-quality trajectory priors, learned through our C-space-grounded diffusion model, enable the efficient generation of collision-free trajectories in narrow-passage environments, outperforming previous learning- and planning-based baselines. Videos and additional materials can be found on the project page: https://kiwi-sherbet.github.io/PRESTO.