FineGrasp: Towards Robust Grasping for Delicate Objects
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_ | 1866916832580993024 |
|---|---|
| author | Du, Yun Zhao, Mengao Lin, Tianwei Jin, Yiwei Huang, Chaodong Su, Zhizhong |
| author_facet | Du, Yun Zhao, Mengao Lin, Tianwei Jin, Yiwei Huang, Chaodong Su, Zhizhong |
| contents | Recent advancements in robotic grasping have led to its integration as a core module in many manipulation systems. For instance, language-driven semantic segmentation enables the grasping of any designated object or object part. However, existing methods often struggle to generate feasible grasp poses for small objects or delicate components, potentially causing the entire pipeline to fail. To address this issue, we propose a novel grasping method, FineGrasp, which introduces improvements in three key aspects. First, we introduce multiple network modifications to enhance the ability of to handle delicate regions. Second, we address the issue of label imbalance and propose a refined graspness label normalization strategy. Third, we introduce a new simulated grasp dataset and show that mixed sim-to-real training further improves grasp performance. Experimental results show significant improvements, especially in grasping small objects, and confirm the effectiveness of our system in semantic grasping. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_05978 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FineGrasp: Towards Robust Grasping for Delicate Objects Du, Yun Zhao, Mengao Lin, Tianwei Jin, Yiwei Huang, Chaodong Su, Zhizhong Robotics Recent advancements in robotic grasping have led to its integration as a core module in many manipulation systems. For instance, language-driven semantic segmentation enables the grasping of any designated object or object part. However, existing methods often struggle to generate feasible grasp poses for small objects or delicate components, potentially causing the entire pipeline to fail. To address this issue, we propose a novel grasping method, FineGrasp, which introduces improvements in three key aspects. First, we introduce multiple network modifications to enhance the ability of to handle delicate regions. Second, we address the issue of label imbalance and propose a refined graspness label normalization strategy. Third, we introduce a new simulated grasp dataset and show that mixed sim-to-real training further improves grasp performance. Experimental results show significant improvements, especially in grasping small objects, and confirm the effectiveness of our system in semantic grasping. |
| title | FineGrasp: Towards Robust Grasping for Delicate Objects |
| topic | Robotics |
| url | https://arxiv.org/abs/2507.05978 |