Right-Side-Out: Learning Zero-Shot Sim-to-Real Garment Reversal
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910013720625152 |
|---|---|
| author | Yu, Chang Ma, Siyu Du, Wenxin Zong, Zeshun Xue, Han Chen, Wendi Lu, Cewu Yang, Yin Han, Xuchen Masterjohn, Joseph Castro, Alejandro Jiang, Chenfanfu |
| author_facet | Yu, Chang Ma, Siyu Du, Wenxin Zong, Zeshun Xue, Han Chen, Wendi Lu, Cewu Yang, Yin Han, Xuchen Masterjohn, Joseph Castro, Alejandro Jiang, Chenfanfu |
| contents | Turning garments right-side out is a challenging manipulation task: it is highly dynamic, entails rapid contact changes, and is subject to severe visual occlusion. We introduce Right-Side-Out, a zero-shot sim-to-real framework that effectively solves this challenge by exploiting task structures. We decompose the task into Drag/Fling to create and stabilize an access opening, followed by Insert&Pull to invert the garment. Each step uses a depth-inferred, keypoint-parameterized bimanual primitive that sharply reduces the action space while preserving robustness. Efficient data generation is enabled by our custom-built, high-fidelity, GPU-parallel Material Point Method (MPM) simulator that models thin-shell deformation and provides robust and efficient contact handling for batched rollouts. Built on the simulator, our fully automated pipeline scales data generation by randomizing garment geometry, material parameters, and viewpoints, producing depth, masks, and per-primitive keypoint labels without any human annotations. With a single depth camera, policies trained entirely in simulation deploy zero-shot on real hardware, achieving up to 81.3% success rate. By employing task decomposition and high fidelity simulation, our framework enables tackling highly dynamic, severely occluded tasks without laborious human demonstrations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_15953 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Right-Side-Out: Learning Zero-Shot Sim-to-Real Garment Reversal Yu, Chang Ma, Siyu Du, Wenxin Zong, Zeshun Xue, Han Chen, Wendi Lu, Cewu Yang, Yin Han, Xuchen Masterjohn, Joseph Castro, Alejandro Jiang, Chenfanfu Robotics Turning garments right-side out is a challenging manipulation task: it is highly dynamic, entails rapid contact changes, and is subject to severe visual occlusion. We introduce Right-Side-Out, a zero-shot sim-to-real framework that effectively solves this challenge by exploiting task structures. We decompose the task into Drag/Fling to create and stabilize an access opening, followed by Insert&Pull to invert the garment. Each step uses a depth-inferred, keypoint-parameterized bimanual primitive that sharply reduces the action space while preserving robustness. Efficient data generation is enabled by our custom-built, high-fidelity, GPU-parallel Material Point Method (MPM) simulator that models thin-shell deformation and provides robust and efficient contact handling for batched rollouts. Built on the simulator, our fully automated pipeline scales data generation by randomizing garment geometry, material parameters, and viewpoints, producing depth, masks, and per-primitive keypoint labels without any human annotations. With a single depth camera, policies trained entirely in simulation deploy zero-shot on real hardware, achieving up to 81.3% success rate. By employing task decomposition and high fidelity simulation, our framework enables tackling highly dynamic, severely occluded tasks without laborious human demonstrations. |
| title | Right-Side-Out: Learning Zero-Shot Sim-to-Real Garment Reversal |
| topic | Robotics |
| url | https://arxiv.org/abs/2509.15953 |