TwinTrack: Bridging Vision and Contact Physics for Real-Time Tracking of Unknown Objects in Contact-Rich Scenes
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_ | 1866914403264233472 |
|---|---|
| author | Yang, Wen Xie, Zhixian Wang, Yiting Tadepalli, Abhijit Amor, Heni Ben Lin, Shan Jin, Wanxin |
| author_facet | Yang, Wen Xie, Zhixian Wang, Yiting Tadepalli, Abhijit Amor, Heni Ben Lin, Shan Jin, Wanxin |
| contents | Real-time tracking of previously unseen, highly dynamic objects in contact-rich scenes, such as during dexterous in-hand manipulation, remains a major challenge. Pure vision-based approaches often fail under heavy occlusions due to frequent contact interactions and motion blur caused by abrupt impacts. We propose Twintrack, a physics-aware perception system that enables robust, real-time 6-DoF pose tracking of unknown dynamic objects in contact-rich scenes by leveraging contact physics cues. At its core, Twintrack integrates Real2Sim and Sim2Real. Real2Sim combines vision and contact physics to jointly estimate object geometry and physical properties: an initial reconstruction is obtained from vision, then refined by learning a geometry residual and simultaneously estimating physical parameters (e.g., mass, inertia, and friction) based on contact dynamics consistency. Sim2Real achieves robust pose estimation by adaptively fusing a visual tracker with predictions from the updated contact dynamics. Twintrack is implemented on a GPU-accelerated, customized MJX engine to guarantee real-time performance. We evaluate our method on two contact-rich scenarios: object falling with environmental contacts and multi-fingered in-hand manipulation. Results show that, compared to baselines, Twintrack delivers significantly more robust, accurate, and real-time tracking in these challenging settings, with tracking speeds above 20 Hz. Project page: https://irislab.tech/TwinTrack-webpage/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_22882 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TwinTrack: Bridging Vision and Contact Physics for Real-Time Tracking of Unknown Objects in Contact-Rich Scenes Yang, Wen Xie, Zhixian Wang, Yiting Tadepalli, Abhijit Amor, Heni Ben Lin, Shan Jin, Wanxin Robotics Real-time tracking of previously unseen, highly dynamic objects in contact-rich scenes, such as during dexterous in-hand manipulation, remains a major challenge. Pure vision-based approaches often fail under heavy occlusions due to frequent contact interactions and motion blur caused by abrupt impacts. We propose Twintrack, a physics-aware perception system that enables robust, real-time 6-DoF pose tracking of unknown dynamic objects in contact-rich scenes by leveraging contact physics cues. At its core, Twintrack integrates Real2Sim and Sim2Real. Real2Sim combines vision and contact physics to jointly estimate object geometry and physical properties: an initial reconstruction is obtained from vision, then refined by learning a geometry residual and simultaneously estimating physical parameters (e.g., mass, inertia, and friction) based on contact dynamics consistency. Sim2Real achieves robust pose estimation by adaptively fusing a visual tracker with predictions from the updated contact dynamics. Twintrack is implemented on a GPU-accelerated, customized MJX engine to guarantee real-time performance. We evaluate our method on two contact-rich scenarios: object falling with environmental contacts and multi-fingered in-hand manipulation. Results show that, compared to baselines, Twintrack delivers significantly more robust, accurate, and real-time tracking in these challenging settings, with tracking speeds above 20 Hz. Project page: https://irislab.tech/TwinTrack-webpage/ |
| title | TwinTrack: Bridging Vision and Contact Physics for Real-Time Tracking of Unknown Objects in Contact-Rich Scenes |
| topic | Robotics |
| url | https://arxiv.org/abs/2505.22882 |