Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.09109 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918396272050176 |
|---|---|
| author | Chen, Yuxing Xiao, Bowen Wang, He |
| author_facet | Chen, Yuxing Xiao, Bowen Wang, He |
| contents | Due to the deformability of garments, generating a large amount of high-quality data for robotic garment manipulation tasks is highly challenging. In this paper, we present a synthetic garment dataset that can be used for robotic garment folding. We begin by constructing geometric garment templates based on keypoints and applying generative models to generate realistic texture patterns. Leveraging these keypoint annotations, we generate folding demonstrations in simulation and train folding policies via closed-loop imitation learning. To improve robustness, we propose KG-DAgger, which uses a keypoint-based strategy to generate demonstration data for recovering from failures. KG-DAgger significantly improves the model performance, boosting the real-world success rate by 25\%. After training with 15K trajectories (about 2M image-action pairs), the model achieves a 75\% success rate in the real world. Experiments in both simulation and real-world settings validate the effectiveness of our proposed framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_09109 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FoldNet: Learning Generalizable Closed-Loop Policy for Garment Folding via Keypoint-Driven Asset and Demonstration Synthesis Chen, Yuxing Xiao, Bowen Wang, He Robotics Computer Vision and Pattern Recognition Due to the deformability of garments, generating a large amount of high-quality data for robotic garment manipulation tasks is highly challenging. In this paper, we present a synthetic garment dataset that can be used for robotic garment folding. We begin by constructing geometric garment templates based on keypoints and applying generative models to generate realistic texture patterns. Leveraging these keypoint annotations, we generate folding demonstrations in simulation and train folding policies via closed-loop imitation learning. To improve robustness, we propose KG-DAgger, which uses a keypoint-based strategy to generate demonstration data for recovering from failures. KG-DAgger significantly improves the model performance, boosting the real-world success rate by 25\%. After training with 15K trajectories (about 2M image-action pairs), the model achieves a 75\% success rate in the real world. Experiments in both simulation and real-world settings validate the effectiveness of our proposed framework. |
| title | FoldNet: Learning Generalizable Closed-Loop Policy for Garment Folding via Keypoint-Driven Asset and Demonstration Synthesis |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.09109 |