Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.07988 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914878984290304 |
|---|---|
| author | Liu, Xueyi Lyu, Kangbo Zhang, Jieqiong Du, Tao Yi, Li |
| author_facet | Liu, Xueyi Lyu, Kangbo Zhang, Jieqiong Du, Tao Yi, Li |
| contents | We explore the dexterous manipulation transfer problem by designing simulators. The task wishes to transfer human manipulations to dexterous robot hand simulations and is inherently difficult due to its intricate, highly-constrained, and discontinuous dynamics and the need to control a dexterous hand with a DoF to accurately replicate human manipulations. Previous approaches that optimize in high-fidelity black-box simulators or a modified one with relaxed constraints only demonstrate limited capabilities or are restricted by insufficient simulation fidelity. We introduce parameterized quasi-physical simulators and a physics curriculum to overcome these limitations. The key ideas are 1) balancing between fidelity and optimizability of the simulation via a curriculum of parameterized simulators, and 2) solving the problem in each of the simulators from the curriculum, with properties ranging from high task optimizability to high fidelity. We successfully enable a dexterous hand to track complex and diverse manipulations in high-fidelity simulated environments, boosting the success rate by 11\%+ from the best-performed baseline. The project website is available at https://meowuu7.github.io/QuasiSim/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_07988 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | QuasiSim: Parameterized Quasi-Physical Simulators for Dexterous Manipulations Transfer Liu, Xueyi Lyu, Kangbo Zhang, Jieqiong Du, Tao Yi, Li Robotics Computer Vision and Pattern Recognition Graphics We explore the dexterous manipulation transfer problem by designing simulators. The task wishes to transfer human manipulations to dexterous robot hand simulations and is inherently difficult due to its intricate, highly-constrained, and discontinuous dynamics and the need to control a dexterous hand with a DoF to accurately replicate human manipulations. Previous approaches that optimize in high-fidelity black-box simulators or a modified one with relaxed constraints only demonstrate limited capabilities or are restricted by insufficient simulation fidelity. We introduce parameterized quasi-physical simulators and a physics curriculum to overcome these limitations. The key ideas are 1) balancing between fidelity and optimizability of the simulation via a curriculum of parameterized simulators, and 2) solving the problem in each of the simulators from the curriculum, with properties ranging from high task optimizability to high fidelity. We successfully enable a dexterous hand to track complex and diverse manipulations in high-fidelity simulated environments, boosting the success rate by 11\%+ from the best-performed baseline. The project website is available at https://meowuu7.github.io/QuasiSim/. |
| title | QuasiSim: Parameterized Quasi-Physical Simulators for Dexterous Manipulations Transfer |
| topic | Robotics Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2404.07988 |