Constraint-Aware Diffusion Guidance for Robotics: Real-Time Obstacle Avoidance for Autonomous Racing

Hao Ma, Sabrina Bodmer, Andrea Carron, Melanie Zeilinger, Michael Muehlebach
Proceedings of The 9th Conference on Robot Learning, PMLR 305:1756-1776, 2025.

Abstract

Diffusion models hold great potential in robotics due to their ability to capture complex, high-dimensional data distributions. However, their lack of constraint-awareness limits their deployment in safety-critical applications. We propose Constraint-Aware Diffusion Guidance (CoDiG), a data-efficient and general-purpose framework that integrates barrier functions into the denoising process, guiding diffusion sampling toward constraint-satisfying outputs. CoDiG enables constraint satisfaction even with limited training data and generalizes across tasks. We evaluate our framework in the challenging setting of miniature autonomous racing, where real-time obstacle avoidance is essential. Real-world experiments show that CoDiG generates safe outputs efficiently under dynamic conditions, highlighting its potential for broader robotic applications.

Cite this Paper

BibTeX
@InProceedings{pmlr-v305-ma25a, title = {Constraint-Aware Diffusion Guidance for Robotics: Real-Time Obstacle Avoidance for Autonomous Racing}, author = {Ma, Hao and Bodmer, Sabrina and Carron, Andrea and Zeilinger, Melanie and Muehlebach, Michael}, booktitle = {Proceedings of The 9th Conference on Robot Learning}, pages = {1756--1776}, year = {2025}, editor = {Lim, Joseph and Song, Shuran and Park, Hae-Won}, volume = {305}, series = {Proceedings of Machine Learning Research}, month = {27--30 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v305/main/assets/ma25a/ma25a.pdf}, url = {https://proceedings.mlr.press/v305/ma25a.html}, abstract = {Diffusion models hold great potential in robotics due to their ability to capture complex, high-dimensional data distributions. However, their lack of constraint-awareness limits their deployment in safety-critical applications. We propose Constraint-Aware Diffusion Guidance (CoDiG), a data-efficient and general-purpose framework that integrates barrier functions into the denoising process, guiding diffusion sampling toward constraint-satisfying outputs. CoDiG enables constraint satisfaction even with limited training data and generalizes across tasks. We evaluate our framework in the challenging setting of miniature autonomous racing, where real-time obstacle avoidance is essential. Real-world experiments show that CoDiG generates safe outputs efficiently under dynamic conditions, highlighting its potential for broader robotic applications.} }
Endnote
%0 Conference Paper %T Constraint-Aware Diffusion Guidance for Robotics: Real-Time Obstacle Avoidance for Autonomous Racing %A Hao Ma %A Sabrina Bodmer %A Andrea Carron %A Melanie Zeilinger %A Michael Muehlebach %B Proceedings of The 9th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2025 %E Joseph Lim %E Shuran Song %E Hae-Won Park %F pmlr-v305-ma25a %I PMLR %P 1756--1776 %U https://proceedings.mlr.press/v305/ma25a.html %V 305 %X Diffusion models hold great potential in robotics due to their ability to capture complex, high-dimensional data distributions. However, their lack of constraint-awareness limits their deployment in safety-critical applications. We propose Constraint-Aware Diffusion Guidance (CoDiG), a data-efficient and general-purpose framework that integrates barrier functions into the denoising process, guiding diffusion sampling toward constraint-satisfying outputs. CoDiG enables constraint satisfaction even with limited training data and generalizes across tasks. We evaluate our framework in the challenging setting of miniature autonomous racing, where real-time obstacle avoidance is essential. Real-world experiments show that CoDiG generates safe outputs efficiently under dynamic conditions, highlighting its potential for broader robotic applications.
APA
Ma, H., Bodmer, S., Carron, A., Zeilinger, M. & Muehlebach, M.. (2025). Constraint-Aware Diffusion Guidance for Robotics: Real-Time Obstacle Avoidance for Autonomous Racing. Proceedings of The 9th Conference on Robot Learning, in Proceedings of Machine Learning Research 305:1756-1776 Available from https://proceedings.mlr.press/v305/ma25a.html.

Related Material