Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.01177 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918191598403584 |
|---|---|
| author | He, Zihao Ai, Bo Mu, Tongzhou Liu, Yulin Wan, Weikang Fu, Jiawei Du, Yilun Christensen, Henrik I. Su, Hao |
| author_facet | He, Zihao Ai, Bo Mu, Tongzhou Liu, Yulin Wan, Weikang Fu, Jiawei Du, Yilun Christensen, Henrik I. Su, Hao |
| contents | Cross-embodiment learning seeks to build generalist robots that operate across diverse morphologies, but differences in action spaces and kinematics hinder data sharing and policy transfer. This raises a central question: Is there any invariance that allows actions to transfer across embodiments? We conjecture that environment dynamics are embodiment-invariant, and that world models capturing these dynamics can provide a unified interface across embodiments. To learn such a unified world model, the crucial step is to design state and action representations that abstract away embodiment-specific details while preserving control relevance. To this end, we represent different embodiments (e.g., human hands and robot hands) as sets of 3D particles and define actions as particle displacements, creating a shared representation for heterogeneous data and control problems. A graph-based world model is then trained on exploration data from diverse simulated robot hands and real human hands, and integrated with model-based planning for deployment on novel hardware. Experiments on rigid and deformable manipulation tasks reveal three findings: (i) scaling to more training embodiments improves generalization to unseen ones, (ii) co-training on both simulated and real data outperforms training on either alone, and (iii) the learned models enable effective control on robots with varied degrees of freedom. These results establish world models as a promising interface for cross-embodiment dexterous manipulation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_01177 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Scaling Cross-Embodiment World Models for Dexterous Manipulation He, Zihao Ai, Bo Mu, Tongzhou Liu, Yulin Wan, Weikang Fu, Jiawei Du, Yilun Christensen, Henrik I. Su, Hao Robotics Cross-embodiment learning seeks to build generalist robots that operate across diverse morphologies, but differences in action spaces and kinematics hinder data sharing and policy transfer. This raises a central question: Is there any invariance that allows actions to transfer across embodiments? We conjecture that environment dynamics are embodiment-invariant, and that world models capturing these dynamics can provide a unified interface across embodiments. To learn such a unified world model, the crucial step is to design state and action representations that abstract away embodiment-specific details while preserving control relevance. To this end, we represent different embodiments (e.g., human hands and robot hands) as sets of 3D particles and define actions as particle displacements, creating a shared representation for heterogeneous data and control problems. A graph-based world model is then trained on exploration data from diverse simulated robot hands and real human hands, and integrated with model-based planning for deployment on novel hardware. Experiments on rigid and deformable manipulation tasks reveal three findings: (i) scaling to more training embodiments improves generalization to unseen ones, (ii) co-training on both simulated and real data outperforms training on either alone, and (iii) the learned models enable effective control on robots with varied degrees of freedom. These results establish world models as a promising interface for cross-embodiment dexterous manipulation. |
| title | Scaling Cross-Embodiment World Models for Dexterous Manipulation |
| topic | Robotics |
| url | https://arxiv.org/abs/2511.01177 |