Enhancing task-oriented robotic grasping via 3D affordance grounding from vision-language models
Abstract Existing task-oriented grasping approaches often rely on 2D pixel-wise affordance segmentation or predefined part annotations, limiting their applicability in unstructured 3D environments and constraining the grasp planning space. To overcome these limitations, we introduce a novel affordan...
Furkejuvvon:
| Váldodahkkit: | , , , , |
|---|---|
| Materiálatiipa: | Artigo |
| Giella: | Inglês |
| Almmustuhtton: |
Springer
2025-12-01
|
| Ráidu: | Complex & Intelligent Systems |
| Fáttát: | |
| Liŋkkat: | https://doi.org/10.1007/s40747-025-02169-0 |
| Fáddágilkorat: |
Eai fáddágilkorat, Lasit vuosttaš fáddágilkora!
|