EquiGraspFlow: SE(3)-Equivariant 6-DoF Grasp Pose Generative Flows

Byeongdo Lim, Jongmin Kim, Jihwan Kim, Yonghyeon Lee, Frank C. Park
Proceedings of The 8th Conference on Robot Learning, PMLR 270:5067-5086, 2025.

Abstract

Traditional methods for synthesizing 6-DoF grasp poses from 3D observations often rely on geometric heuristics, resulting in poor generalizability, limited grasp options, and higher failure rates. Recently, data-driven methods have been proposed that use generative models to learn the distribution of grasp poses and generate diverse candidate poses. The main drawback of these methods is that they fail to achieve SE(3)-equivariance, meaning that the generated grasp poses do not transform correctly with object rotations and translations. In this paper, we propose \textit{EquiGraspFlow}, a flow-based SE(3)-equivariant 6-DoF grasp pose generative model that can learn complex conditional distributions on the SE(3) manifold while guaranteeing SE(3)-equivariance. Our model achieves the equivariance without relying on data augmentation, by using network architectures that guarantee the equivariance by construction. Extensive experiments show that \textit{EquiGraspFlow} accurately learns grasp pose distribution, achieves the SE(3)-equivariance, and significantly outperforms existing grasp pose generative models. Code is available at https://github.com/bdlim99/EquiGraspFlow.

Cite this Paper

BibTeX
@InProceedings{pmlr-v270-lim25a, title = {EquiGraspFlow: SE(3)-Equivariant 6-DoF Grasp Pose Generative Flows}, author = {Lim, Byeongdo and Kim, Jongmin and Kim, Jihwan and Lee, Yonghyeon and Park, Frank C.}, booktitle = {Proceedings of The 8th Conference on Robot Learning}, pages = {5067--5086}, 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/lim25a/lim25a.pdf}, url = {https://proceedings.mlr.press/v270/lim25a.html}, abstract = {Traditional methods for synthesizing 6-DoF grasp poses from 3D observations often rely on geometric heuristics, resulting in poor generalizability, limited grasp options, and higher failure rates. Recently, data-driven methods have been proposed that use generative models to learn the distribution of grasp poses and generate diverse candidate poses. The main drawback of these methods is that they fail to achieve SE(3)-equivariance, meaning that the generated grasp poses do not transform correctly with object rotations and translations. In this paper, we propose \textit{EquiGraspFlow}, a flow-based SE(3)-equivariant 6-DoF grasp pose generative model that can learn complex conditional distributions on the SE(3) manifold while guaranteeing SE(3)-equivariance. Our model achieves the equivariance without relying on data augmentation, by using network architectures that guarantee the equivariance by construction. Extensive experiments show that \textit{EquiGraspFlow} accurately learns grasp pose distribution, achieves the SE(3)-equivariance, and significantly outperforms existing grasp pose generative models. Code is available at https://github.com/bdlim99/EquiGraspFlow.} }
Endnote
%0 Conference Paper %T EquiGraspFlow: SE(3)-Equivariant 6-DoF Grasp Pose Generative Flows %A Byeongdo Lim %A Jongmin Kim %A Jihwan Kim %A Yonghyeon Lee %A Frank C. Park %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-lim25a %I PMLR %P 5067--5086 %U https://proceedings.mlr.press/v270/lim25a.html %V 270 %X Traditional methods for synthesizing 6-DoF grasp poses from 3D observations often rely on geometric heuristics, resulting in poor generalizability, limited grasp options, and higher failure rates. Recently, data-driven methods have been proposed that use generative models to learn the distribution of grasp poses and generate diverse candidate poses. The main drawback of these methods is that they fail to achieve SE(3)-equivariance, meaning that the generated grasp poses do not transform correctly with object rotations and translations. In this paper, we propose \textit{EquiGraspFlow}, a flow-based SE(3)-equivariant 6-DoF grasp pose generative model that can learn complex conditional distributions on the SE(3) manifold while guaranteeing SE(3)-equivariance. Our model achieves the equivariance without relying on data augmentation, by using network architectures that guarantee the equivariance by construction. Extensive experiments show that \textit{EquiGraspFlow} accurately learns grasp pose distribution, achieves the SE(3)-equivariance, and significantly outperforms existing grasp pose generative models. Code is available at https://github.com/bdlim99/EquiGraspFlow.
APA
Lim, B., Kim, J., Kim, J., Lee, Y. & Park, F.C.. (2025). EquiGraspFlow: SE(3)-Equivariant 6-DoF Grasp Pose Generative Flows. Proceedings of The 8th Conference on Robot Learning, in Proceedings of Machine Learning Research 270:5067-5086 Available from https://proceedings.mlr.press/v270/lim25a.html.

Related Material