Leveraging Neural Descriptor Fields for Learning Contact-Aware Dynamic Recovery
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909850244481024 |
|---|---|
| author | Yang, Fan Huang, Zixuan Kumar, Abhinav Marinovic, Sergio Aguilera Iba, Soshi Zarrin, Rana Soltani Berenson, Dmitry |
| author_facet | Yang, Fan Huang, Zixuan Kumar, Abhinav Marinovic, Sergio Aguilera Iba, Soshi Zarrin, Rana Soltani Berenson, Dmitry |
| contents | Real-world dexterous manipulation often encounters unexpected errors and disturbances, which can lead to catastrophic failures, such as dropping the manipulated object. To address this challenge, we focus on the problem of catching a falling object while it remains within grasping range and, importantly, resetting the system to a configuration favorable for resuming the primary manipulation task. We propose Contact-Aware Dynamic Recovery (CADRE), a reinforcement learning framework that incorporates a Neural Descriptor Field (NDF)-inspired module to extract implicit contact features. Compared to methods that rely solely on object pose or point cloud input, NDFs can directly reason about finger-object correspondence and adapt to different object geometries. Our experiments show that incorporating contact features improves training efficiency, enhances convergence performance for RL training, and ultimately leads to more successful recoveries. Additionally, we demonstrate that CADRE can generalize zero-shot to unseen objects with different geometries. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_14768 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging Neural Descriptor Fields for Learning Contact-Aware Dynamic Recovery Yang, Fan Huang, Zixuan Kumar, Abhinav Marinovic, Sergio Aguilera Iba, Soshi Zarrin, Rana Soltani Berenson, Dmitry Robotics Real-world dexterous manipulation often encounters unexpected errors and disturbances, which can lead to catastrophic failures, such as dropping the manipulated object. To address this challenge, we focus on the problem of catching a falling object while it remains within grasping range and, importantly, resetting the system to a configuration favorable for resuming the primary manipulation task. We propose Contact-Aware Dynamic Recovery (CADRE), a reinforcement learning framework that incorporates a Neural Descriptor Field (NDF)-inspired module to extract implicit contact features. Compared to methods that rely solely on object pose or point cloud input, NDFs can directly reason about finger-object correspondence and adapt to different object geometries. Our experiments show that incorporating contact features improves training efficiency, enhances convergence performance for RL training, and ultimately leads to more successful recoveries. Additionally, we demonstrate that CADRE can generalize zero-shot to unseen objects with different geometries. |
| title | Leveraging Neural Descriptor Fields for Learning Contact-Aware Dynamic Recovery |
| topic | Robotics |
| url | https://arxiv.org/abs/2510.14768 |