Geometric Retargeting: A Principled, Ultrafast Neural Hand Retargeting Algorithm
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917950074650624 |
|---|---|
| author | Yin, Zhao-Heng Wang, Changhao Pineda, Luis Bodduluri, Krishna Wu, Tingfan Abbeel, Pieter Mukadam, Mustafa |
| author_facet | Yin, Zhao-Heng Wang, Changhao Pineda, Luis Bodduluri, Krishna Wu, Tingfan Abbeel, Pieter Mukadam, Mustafa |
| contents | We introduce Geometric Retargeting (GeoRT), an ultrafast, and principled neural hand retargeting algorithm for teleoperation, developed as part of our recent Dexterity Gen (DexGen) system. GeoRT converts human finger keypoints to robot hand keypoints at 1KHz, achieving state-of-the-art speed and accuracy with significantly fewer hyperparameters. This high-speed capability enables flexible postprocessing, such as leveraging a foundational controller for action correction like DexGen. GeoRT is trained in an unsupervised manner, eliminating the need for manual annotation of hand pairs. The core of GeoRT lies in novel geometric objective functions that capture the essence of retargeting: preserving motion fidelity, ensuring configuration space (C-space) coverage, maintaining uniform response through high flatness, pinch correspondence and preventing self-collisions. This approach is free from intensive test-time optimization, offering a more scalable and practical solution for real-time hand retargeting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_07541 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Geometric Retargeting: A Principled, Ultrafast Neural Hand Retargeting Algorithm Yin, Zhao-Heng Wang, Changhao Pineda, Luis Bodduluri, Krishna Wu, Tingfan Abbeel, Pieter Mukadam, Mustafa Robotics Artificial Intelligence Graphics Human-Computer Interaction Machine Learning We introduce Geometric Retargeting (GeoRT), an ultrafast, and principled neural hand retargeting algorithm for teleoperation, developed as part of our recent Dexterity Gen (DexGen) system. GeoRT converts human finger keypoints to robot hand keypoints at 1KHz, achieving state-of-the-art speed and accuracy with significantly fewer hyperparameters. This high-speed capability enables flexible postprocessing, such as leveraging a foundational controller for action correction like DexGen. GeoRT is trained in an unsupervised manner, eliminating the need for manual annotation of hand pairs. The core of GeoRT lies in novel geometric objective functions that capture the essence of retargeting: preserving motion fidelity, ensuring configuration space (C-space) coverage, maintaining uniform response through high flatness, pinch correspondence and preventing self-collisions. This approach is free from intensive test-time optimization, offering a more scalable and practical solution for real-time hand retargeting. |
| title | Geometric Retargeting: A Principled, Ultrafast Neural Hand Retargeting Algorithm |
| topic | Robotics Artificial Intelligence Graphics Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2503.07541 |