Symmetries Here and There, Combined Everywhere: Cross-space Symmetry Compositions in Robotics
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913171878445056 |
|---|---|
| author | Hadjiloizou, Loizos Pérez-Dattari, Rodrigo Jaquier, Noémie |
| author_facet | Hadjiloizou, Loizos Pérez-Dattari, Rodrigo Jaquier, Noémie |
| contents | Robots exhibit a rich variety of symmetries arising from their mechanical structure and the properties of their tasks. Although many robotics problems exhibit several symmetries simultaneously, existing approaches typically treat them in isolation, failing to exploit their combined potential. This paper introduces cross-space symmetry compositions, a framework for learning robot policies that are jointly equivariant to multiple symmetries across configuration and task spaces. Leveraging the differential-geometric structure of the forward kinematics map, we both descend symmetries from configuration to task space and lift symmetries from task to configuration space, enabling their composition within a unified representation space. We validate our framework on simulated and real-world experiments on a dual-arm robot, demonstrating that jointly leveraging multiple symmetries yields improved generalization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_22639 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Symmetries Here and There, Combined Everywhere: Cross-space Symmetry Compositions in Robotics Hadjiloizou, Loizos Pérez-Dattari, Rodrigo Jaquier, Noémie Robotics Robots exhibit a rich variety of symmetries arising from their mechanical structure and the properties of their tasks. Although many robotics problems exhibit several symmetries simultaneously, existing approaches typically treat them in isolation, failing to exploit their combined potential. This paper introduces cross-space symmetry compositions, a framework for learning robot policies that are jointly equivariant to multiple symmetries across configuration and task spaces. Leveraging the differential-geometric structure of the forward kinematics map, we both descend symmetries from configuration to task space and lift symmetries from task to configuration space, enabling their composition within a unified representation space. We validate our framework on simulated and real-world experiments on a dual-arm robot, demonstrating that jointly leveraging multiple symmetries yields improved generalization. |
| title | Symmetries Here and There, Combined Everywhere: Cross-space Symmetry Compositions in Robotics |
| topic | Robotics |
| url | https://arxiv.org/abs/2605.22639 |