STRiDE: STate-space Riemannian Diffusion for Equivariant Planning

Evangelos Chatzipantazis, Nishanth Rao, Kostas Daniilidis
Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, PMLR 283:1338-1352, 2025.

Abstract

Fast and reliable motion planning is essential for robots with many degrees of freedom in complex, dynamic environments. Diffusion models offer a promising alternative to classical planners by learning informative trajectory priors. In current imitation-learning paradigms, these models are kept lightweight—lacking encoders—and trained to overfit to a single environment. As a result, adaptation relies solely on diffusion guidance, which fails under large execution-time changes or varying initializations. In addition, current approaches ignore the underlying topology of the state space thus requiring heavy guidance that dominates planning time and reduces efficiency dramatically. We introduce STRiDE, a novel diffusion motion planner that operates directly on the state space manifold and learns equivariant trajectory priors. Our approach eliminates the need for retraining under rotations around the gravity axis and enables faster convergence using Riemannian (rather than ambient) guidance. STRiDE delivers efficient, robust, and generalizable planning, overcoming key limitations of existing approaches.

Cite this Paper

BibTeX
@InProceedings{pmlr-v283-chatzipantazis25a, title = {STRiDE: STate-space Riemannian Diffusion for Equivariant Planning}, author = {Chatzipantazis, Evangelos and Rao, Nishanth and Daniilidis, Kostas}, booktitle = {Proceedings of the 7th Annual Learning for Dynamics \& Control Conference}, pages = {1338--1352}, year = {2025}, editor = {Ozay, Necmiye and Balzano, Laura and Panagou, Dimitra and Abate, Alessandro}, volume = {283}, series = {Proceedings of Machine Learning Research}, month = {04--06 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v283/main/assets/chatzipantazis25a/chatzipantazis25a.pdf}, url = {https://proceedings.mlr.press/v283/chatzipantazis25a.html}, abstract = {Fast and reliable motion planning is essential for robots with many degrees of freedom in complex, dynamic environments. Diffusion models offer a promising alternative to classical planners by learning informative trajectory priors. In current imitation-learning paradigms, these models are kept lightweight—lacking encoders—and trained to overfit to a single environment. As a result, adaptation relies solely on diffusion guidance, which fails under large execution-time changes or varying initializations. In addition, current approaches ignore the underlying topology of the state space thus requiring heavy guidance that dominates planning time and reduces efficiency dramatically. We introduce STRiDE, a novel diffusion motion planner that operates directly on the state space manifold and learns equivariant trajectory priors. Our approach eliminates the need for retraining under rotations around the gravity axis and enables faster convergence using Riemannian (rather than ambient) guidance. STRiDE delivers efficient, robust, and generalizable planning, overcoming key limitations of existing approaches.} }
Endnote
%0 Conference Paper %T STRiDE: STate-space Riemannian Diffusion for Equivariant Planning %A Evangelos Chatzipantazis %A Nishanth Rao %A Kostas Daniilidis %B Proceedings of the 7th Annual Learning for Dynamics \& Control Conference %C Proceedings of Machine Learning Research %D 2025 %E Necmiye Ozay %E Laura Balzano %E Dimitra Panagou %E Alessandro Abate %F pmlr-v283-chatzipantazis25a %I PMLR %P 1338--1352 %U https://proceedings.mlr.press/v283/chatzipantazis25a.html %V 283 %X Fast and reliable motion planning is essential for robots with many degrees of freedom in complex, dynamic environments. Diffusion models offer a promising alternative to classical planners by learning informative trajectory priors. In current imitation-learning paradigms, these models are kept lightweight—lacking encoders—and trained to overfit to a single environment. As a result, adaptation relies solely on diffusion guidance, which fails under large execution-time changes or varying initializations. In addition, current approaches ignore the underlying topology of the state space thus requiring heavy guidance that dominates planning time and reduces efficiency dramatically. We introduce STRiDE, a novel diffusion motion planner that operates directly on the state space manifold and learns equivariant trajectory priors. Our approach eliminates the need for retraining under rotations around the gravity axis and enables faster convergence using Riemannian (rather than ambient) guidance. STRiDE delivers efficient, robust, and generalizable planning, overcoming key limitations of existing approaches.
APA
Chatzipantazis, E., Rao, N. & Daniilidis, K.. (2025). STRiDE: STate-space Riemannian Diffusion for Equivariant Planning. Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, in Proceedings of Machine Learning Research 283:1338-1352 Available from https://proceedings.mlr.press/v283/chatzipantazis25a.html.

Related Material