EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learning

Jingyun Yang, Ziang Cao, Congyue Deng, Rika Antonova, Shuran Song, Jeannette Bohg
Proceedings of The 8th Conference on Robot Learning, PMLR 270:1048-1068, 2025.

Abstract

Building effective imitation learning methods that enable robots to learn from limited data and still generalize across diverse real-world environments is a long-standing problem in robot learning. We propose EquiBot, a robust, data-efficient, and generalizable approach for robot manipulation task learning. Our approach combines SIM(3)-equivariant neural network architectures with diffusion models. This ensures that our learned policies are invariant to changes in scale, rotation, and translation, enhancing their applicability to unseen environments while retaining the benefits of diffusion-based policy learning such as multi-modality and robustness. We show on a suite of 6 simulation tasks that our proposed method reduces the data requirements and improves generalization to novel scenarios. In the real world, with 10 variations of 6 mobile manipulation tasks, we show that our method can easily generalize to novel objects and scenes after learning from just 5 minutes of human demonstrations in each task.

Cite this Paper

BibTeX
@InProceedings{pmlr-v270-yang25a, title = {EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learning}, author = {Yang, Jingyun and Cao, Ziang and Deng, Congyue and Antonova, Rika and Song, Shuran and Bohg, Jeannette}, booktitle = {Proceedings of The 8th Conference on Robot Learning}, pages = {1048--1068}, year = {2025}, editor = {Agrawal, Pulkit and Kroemer, Oliver and Burgard, Wolfram}, volume = {270}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v270/main/assets/yang25a/yang25a.pdf}, url = {https://proceedings.mlr.press/v270/yang25a.html}, abstract = {Building effective imitation learning methods that enable robots to learn from limited data and still generalize across diverse real-world environments is a long-standing problem in robot learning. We propose EquiBot, a robust, data-efficient, and generalizable approach for robot manipulation task learning. Our approach combines SIM(3)-equivariant neural network architectures with diffusion models. This ensures that our learned policies are invariant to changes in scale, rotation, and translation, enhancing their applicability to unseen environments while retaining the benefits of diffusion-based policy learning such as multi-modality and robustness. We show on a suite of 6 simulation tasks that our proposed method reduces the data requirements and improves generalization to novel scenarios. In the real world, with 10 variations of 6 mobile manipulation tasks, we show that our method can easily generalize to novel objects and scenes after learning from just 5 minutes of human demonstrations in each task.} }
Endnote
%0 Conference Paper %T EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learning %A Jingyun Yang %A Ziang Cao %A Congyue Deng %A Rika Antonova %A Shuran Song %A Jeannette Bohg %B Proceedings of The 8th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2025 %E Pulkit Agrawal %E Oliver Kroemer %E Wolfram Burgard %F pmlr-v270-yang25a %I PMLR %P 1048--1068 %U https://proceedings.mlr.press/v270/yang25a.html %V 270 %X Building effective imitation learning methods that enable robots to learn from limited data and still generalize across diverse real-world environments is a long-standing problem in robot learning. We propose EquiBot, a robust, data-efficient, and generalizable approach for robot manipulation task learning. Our approach combines SIM(3)-equivariant neural network architectures with diffusion models. This ensures that our learned policies are invariant to changes in scale, rotation, and translation, enhancing their applicability to unseen environments while retaining the benefits of diffusion-based policy learning such as multi-modality and robustness. We show on a suite of 6 simulation tasks that our proposed method reduces the data requirements and improves generalization to novel scenarios. In the real world, with 10 variations of 6 mobile manipulation tasks, we show that our method can easily generalize to novel objects and scenes after learning from just 5 minutes of human demonstrations in each task.
APA
Yang, J., Cao, Z., Deng, C., Antonova, R., Song, S. & Bohg, J.. (2025). EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learning. Proceedings of The 8th Conference on Robot Learning, in Proceedings of Machine Learning Research 270:1048-1068 Available from https://proceedings.mlr.press/v270/yang25a.html.

Related Material