Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.08372 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913987016261632 |
|---|---|
| author | Chen, Haonan Li, Junxiao Wu, Ruihai Liu, Yiwei Hou, Yiwen Xu, Zhixuan Guo, Jingxiang Gao, Chongkai Wei, Zhenyu Xu, Shensi Huang, Jiaqi Shao, Lin |
| author_facet | Chen, Haonan Li, Junxiao Wu, Ruihai Liu, Yiwei Hou, Yiwen Xu, Zhixuan Guo, Jingxiang Gao, Chongkai Wei, Zhenyu Xu, Shensi Huang, Jiaqi Shao, Lin |
| contents | Garment folding is a common yet challenging task in robotic manipulation. The deformability of garments leads to a vast state space and complex dynamics, which complicates precise and fine-grained manipulation. Previous approaches often rely on predefined key points or demonstrations, limiting their generalization across diverse garment categories. This paper presents a framework, MetaFold, that disentangles task planning from action prediction, learning each independently to enhance model generalization. It employs language-guided point cloud trajectory generation for task planning and a low-level foundation model for action prediction. This structure facilitates multi-category learning, enabling the model to adapt flexibly to various user instructions and folding tasks. Experimental results demonstrate the superiority of our proposed framework. Supplementary materials are available on our website: https://meta-fold.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_08372 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MetaFold: Language-Guided Multi-Category Garment Folding Framework via Trajectory Generation and Foundation Model Chen, Haonan Li, Junxiao Wu, Ruihai Liu, Yiwei Hou, Yiwen Xu, Zhixuan Guo, Jingxiang Gao, Chongkai Wei, Zhenyu Xu, Shensi Huang, Jiaqi Shao, Lin Robotics Garment folding is a common yet challenging task in robotic manipulation. The deformability of garments leads to a vast state space and complex dynamics, which complicates precise and fine-grained manipulation. Previous approaches often rely on predefined key points or demonstrations, limiting their generalization across diverse garment categories. This paper presents a framework, MetaFold, that disentangles task planning from action prediction, learning each independently to enhance model generalization. It employs language-guided point cloud trajectory generation for task planning and a low-level foundation model for action prediction. This structure facilitates multi-category learning, enabling the model to adapt flexibly to various user instructions and folding tasks. Experimental results demonstrate the superiority of our proposed framework. Supplementary materials are available on our website: https://meta-fold.github.io/. |
| title | MetaFold: Language-Guided Multi-Category Garment Folding Framework via Trajectory Generation and Foundation Model |
| topic | Robotics |
| url | https://arxiv.org/abs/2503.08372 |