Correspondence-Free, Function-Based Sim-to-Real Learning for Deformable Surface Control
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912869803622400 |
|---|---|
| author | Tian, Yingjun Fang, Guoxin Su, Renbo Lyu, Aoran Dutta, Neelotpal Wang, Weiming Gill, Simeon Weightman, Andrew Wang, Charlie C. L. |
| author_facet | Tian, Yingjun Fang, Guoxin Su, Renbo Lyu, Aoran Dutta, Neelotpal Wang, Weiming Gill, Simeon Weightman, Andrew Wang, Charlie C. L. |
| contents | This paper presents a correspondence-free, function-based sim-to-real learning method for controlling deformable freeform surfaces. Unlike traditional sim-to-real transfer methods that strongly rely on marker points with full correspondences, our approach simultaneously learns a deformation function space and a confidence map -- both parameterized by a neural network -- to map simulated shapes to their real-world counterparts. As a result, the sim-to-real learning can be conducted by input from either a 3D scanner as point clouds (without correspondences) or a motion capture system as marker points (tolerating missed markers). The resultant sim-to-real transfer can be seamlessly integrated into a neural network-based computational pipeline for inverse kinematics and shape control. We demonstrate the versatility and adaptability of our method on both vision devices and across four pneumatically actuated soft robots: a deformable membrane, a robotic mannequin, and two soft manipulators. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_00060 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Correspondence-Free, Function-Based Sim-to-Real Learning for Deformable Surface Control Tian, Yingjun Fang, Guoxin Su, Renbo Lyu, Aoran Dutta, Neelotpal Wang, Weiming Gill, Simeon Weightman, Andrew Wang, Charlie C. L. Robotics This paper presents a correspondence-free, function-based sim-to-real learning method for controlling deformable freeform surfaces. Unlike traditional sim-to-real transfer methods that strongly rely on marker points with full correspondences, our approach simultaneously learns a deformation function space and a confidence map -- both parameterized by a neural network -- to map simulated shapes to their real-world counterparts. As a result, the sim-to-real learning can be conducted by input from either a 3D scanner as point clouds (without correspondences) or a motion capture system as marker points (tolerating missed markers). The resultant sim-to-real transfer can be seamlessly integrated into a neural network-based computational pipeline for inverse kinematics and shape control. We demonstrate the versatility and adaptability of our method on both vision devices and across four pneumatically actuated soft robots: a deformable membrane, a robotic mannequin, and two soft manipulators. |
| title | Correspondence-Free, Function-Based Sim-to-Real Learning for Deformable Surface Control |
| topic | Robotics |
| url | https://arxiv.org/abs/2509.00060 |