DexFormer: Cross-Embodied Dexterous Manipulation via History-Conditioned Transformer
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911433807101952 |
|---|---|
| author | Zhang, Ke Xu, Lixin Song, Chengyi Xu, Junzhe Lin, Xiaoyi Jiang, Zeyu Xu, Renjing |
| author_facet | Zhang, Ke Xu, Lixin Song, Chengyi Xu, Junzhe Lin, Xiaoyi Jiang, Zeyu Xu, Renjing |
| contents | Dexterous manipulation remains one of the most challenging problems in robotics, requiring coherent control of high-DoF hands and arms under complex, contact-rich dynamics. A major barrier is embodiment variability: different dexterous hands exhibit distinct kinematics and dynamics, forcing prior methods to train separate policies or rely on shared action spaces with per-embodiment decoder heads. We present DexFormer, an end-to-end, dynamics-aware cross-embodiment policy built on a modified transformer backbone that conditions on historical observations. By using temporal context to infer morphology and dynamics on the fly, DexFormer adapts to diverse hand configurations and produces embodiment-appropriate control actions. Trained over a variety of procedurally generated dexterous-hand assets, DexFormer acquires a generalizable manipulation prior and exhibits strong zero-shot transfer to Leap Hand, Allegro Hand, and Rapid Hand. Our results show that a single policy can generalize across heterogeneous hand embodiments, establishing a scalable foundation for cross-embodiment dexterous manipulation. Project website: https://davidlxu.github.io/DexFormer-web/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_08278 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DexFormer: Cross-Embodied Dexterous Manipulation via History-Conditioned Transformer Zhang, Ke Xu, Lixin Song, Chengyi Xu, Junzhe Lin, Xiaoyi Jiang, Zeyu Xu, Renjing Robotics Dexterous manipulation remains one of the most challenging problems in robotics, requiring coherent control of high-DoF hands and arms under complex, contact-rich dynamics. A major barrier is embodiment variability: different dexterous hands exhibit distinct kinematics and dynamics, forcing prior methods to train separate policies or rely on shared action spaces with per-embodiment decoder heads. We present DexFormer, an end-to-end, dynamics-aware cross-embodiment policy built on a modified transformer backbone that conditions on historical observations. By using temporal context to infer morphology and dynamics on the fly, DexFormer adapts to diverse hand configurations and produces embodiment-appropriate control actions. Trained over a variety of procedurally generated dexterous-hand assets, DexFormer acquires a generalizable manipulation prior and exhibits strong zero-shot transfer to Leap Hand, Allegro Hand, and Rapid Hand. Our results show that a single policy can generalize across heterogeneous hand embodiments, establishing a scalable foundation for cross-embodiment dexterous manipulation. Project website: https://davidlxu.github.io/DexFormer-web/. |
| title | DexFormer: Cross-Embodied Dexterous Manipulation via History-Conditioned Transformer |
| topic | Robotics |
| url | https://arxiv.org/abs/2602.08278 |