A Planar-Symmetric SO(3) Representation for Learning Grasp Detection

Tianyi Ko, Takuya Ikeda, Hiroya Sato, Koichi Nishiwaki
Proceedings of The 8th Conference on Robot Learning, PMLR 270:3674-3687, 2025.

Abstract

Planar-symmetric hands, such as parallel grippers, are widely adopted in both research and industrial fields. Their symmetry, however, introduces ambiguity and discontinuity in the SO(3) representation, which hinders both the training and inference of neural network-based grasp detectors. We propose a novel SO(3) representation that can parametrize a pair of planar-symmetric poses with a single parameter set by leveraging the 2D Bingham distribution. We also detail a grasp detector based on our representation, which provides a more consistent rotation output. An intensive evaluation with multiple grippers and objects in both the simulation and the real world quantitatively shows our approach’s contribution.

Cite this Paper

BibTeX
@InProceedings{pmlr-v270-ko25a, title = {A Planar-Symmetric SO(3) Representation for Learning Grasp Detection}, author = {Ko, Tianyi and Ikeda, Takuya and Sato, Hiroya and Nishiwaki, Koichi}, booktitle = {Proceedings of The 8th Conference on Robot Learning}, pages = {3674--3687}, 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/ko25a/ko25a.pdf}, url = {https://proceedings.mlr.press/v270/ko25a.html}, abstract = {Planar-symmetric hands, such as parallel grippers, are widely adopted in both research and industrial fields. Their symmetry, however, introduces ambiguity and discontinuity in the SO(3) representation, which hinders both the training and inference of neural network-based grasp detectors. We propose a novel SO(3) representation that can parametrize a pair of planar-symmetric poses with a single parameter set by leveraging the 2D Bingham distribution. We also detail a grasp detector based on our representation, which provides a more consistent rotation output. An intensive evaluation with multiple grippers and objects in both the simulation and the real world quantitatively shows our approach’s contribution.} }
Endnote
%0 Conference Paper %T A Planar-Symmetric SO(3) Representation for Learning Grasp Detection %A Tianyi Ko %A Takuya Ikeda %A Hiroya Sato %A Koichi Nishiwaki %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-ko25a %I PMLR %P 3674--3687 %U https://proceedings.mlr.press/v270/ko25a.html %V 270 %X Planar-symmetric hands, such as parallel grippers, are widely adopted in both research and industrial fields. Their symmetry, however, introduces ambiguity and discontinuity in the SO(3) representation, which hinders both the training and inference of neural network-based grasp detectors. We propose a novel SO(3) representation that can parametrize a pair of planar-symmetric poses with a single parameter set by leveraging the 2D Bingham distribution. We also detail a grasp detector based on our representation, which provides a more consistent rotation output. An intensive evaluation with multiple grippers and objects in both the simulation and the real world quantitatively shows our approach’s contribution.
APA
Ko, T., Ikeda, T., Sato, H. & Nishiwaki, K.. (2025). A Planar-Symmetric SO(3) Representation for Learning Grasp Detection. Proceedings of The 8th Conference on Robot Learning, in Proceedings of Machine Learning Research 270:3674-3687 Available from https://proceedings.mlr.press/v270/ko25a.html.

Related Material