DexKnot: Generalizable Visuomotor Policy Learning for Dexterous Bag-Knotting Manipulation
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_ | 1866911495596539904 |
|---|---|
| author | Zhang, Jiayuan Wu, Ruihai Chen, Haojun Wang, Yuran Zhong, Yifan Zhang, Ceyao Yang, Yaodong Chen, Yuanpei |
| author_facet | Zhang, Jiayuan Wu, Ruihai Chen, Haojun Wang, Yuran Zhong, Yifan Zhang, Ceyao Yang, Yaodong Chen, Yuanpei |
| contents | Knotting plastic bags is a common task in daily life, yet it is challenging for robots due to the bags' infinite degrees of freedom and complex physical dynamics. Existing methods often struggle in generalization to unseen bag instances or deformations. To address this, we present DexKnot, a framework that combines keypoint affordance with diffusion policy to learn a generalizable bag-knotting policy. Our approach learns a shape-agnostic representation of bags from keypoint correspondence data collected through real-world manual deformation. For an unseen bag configuration, the keypoints can be identified by matching the representation to a reference. These keypoints are then provided to a diffusion transformer, which generates robot action based on a small number of human demonstrations. DexKnot enables effective policy generalization by reducing the dimensionality of observation space into a sparse set of keypoints. Experiments show that DexKnot achieves reliable and consistent knotting performance across a variety of previously unseen instances and deformations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07136 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DexKnot: Generalizable Visuomotor Policy Learning for Dexterous Bag-Knotting Manipulation Zhang, Jiayuan Wu, Ruihai Chen, Haojun Wang, Yuran Zhong, Yifan Zhang, Ceyao Yang, Yaodong Chen, Yuanpei Robotics Knotting plastic bags is a common task in daily life, yet it is challenging for robots due to the bags' infinite degrees of freedom and complex physical dynamics. Existing methods often struggle in generalization to unseen bag instances or deformations. To address this, we present DexKnot, a framework that combines keypoint affordance with diffusion policy to learn a generalizable bag-knotting policy. Our approach learns a shape-agnostic representation of bags from keypoint correspondence data collected through real-world manual deformation. For an unseen bag configuration, the keypoints can be identified by matching the representation to a reference. These keypoints are then provided to a diffusion transformer, which generates robot action based on a small number of human demonstrations. DexKnot enables effective policy generalization by reducing the dimensionality of observation space into a sparse set of keypoints. Experiments show that DexKnot achieves reliable and consistent knotting performance across a variety of previously unseen instances and deformations. |
| title | DexKnot: Generalizable Visuomotor Policy Learning for Dexterous Bag-Knotting Manipulation |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.07136 |