• Classified by Topic • Classified by Publication Type • Sorted by Date • Sorted by First Author Last Name • Classified by Funding Source •
PRESTO: Fast Motion Planning Using Diffusion Models Based on Key-Configuration Environment Representation.
Mingyo
Seo, Yoonyoung Cho, Yoonchang Sung, Peter
Stone, Yuke Zhu, and Beomjoon Kim.
In IEEE International Conference
on Robotics and Automation (ICRA), May 2025.
[PDF]1.4MB [slides.pdf]2.1MB [poster.pdf]1.3MB
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) ob- stacles 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 op- timization 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.
@InProceedings{mingyo_seo_ICRA2025,
author = {Mingyo Seo and Yoonyoung Cho and Yoonchang Sung and Peter Stone and Yuke Zhu and Beomjoon Kim},
title = {PRESTO: Fast Motion Planning Using Diffusion Models Based on Key-Configuration Environment Representation},
booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
year = {2025},
month = {May},
location = {Atlanta, United States},
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) ob- stacles 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 op- timization 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.},
}
Generated by bib2html.pl (written by Patrick Riley ) on Wed Jun 10, 2026 15:26:44