IFG: Internet-Scale Guidance for Functional Grasping Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914153677979648 |
|---|---|
| author | Liu, Ray Muxin Li, Mingxuan Shaw, Kenneth Pathak, Deepak |
| author_facet | Liu, Ray Muxin Li, Mingxuan Shaw, Kenneth Pathak, Deepak |
| contents | Large Vision Models trained on internet-scale data have demonstrated strong capabilities in segmenting and semantically understanding object parts, even in cluttered, crowded scenes. However, while these models can direct a robot toward the general region of an object, they lack the geometric understanding required to precisely control dexterous robotic hands for 3D grasping. To overcome this, our key insight is to leverage simulation with a force-closure grasping generation pipeline that understands local geometries of the hand and object in the scene. Because this pipeline is slow and requires ground-truth observations, the resulting data is distilled into a diffusion model that operates in real-time on camera point clouds. By combining the global semantic understanding of internet-scale models with the geometric precision of a simulation-based locally-aware force-closure, \our achieves high-performance semantic grasping without any manually collected training data. For visualizations of this please visit our website at https://ifgrasping.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_09558 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | IFG: Internet-Scale Guidance for Functional Grasping Generation Liu, Ray Muxin Li, Mingxuan Shaw, Kenneth Pathak, Deepak Robotics Artificial Intelligence Computer Vision and Pattern Recognition Graphics Machine Learning Large Vision Models trained on internet-scale data have demonstrated strong capabilities in segmenting and semantically understanding object parts, even in cluttered, crowded scenes. However, while these models can direct a robot toward the general region of an object, they lack the geometric understanding required to precisely control dexterous robotic hands for 3D grasping. To overcome this, our key insight is to leverage simulation with a force-closure grasping generation pipeline that understands local geometries of the hand and object in the scene. Because this pipeline is slow and requires ground-truth observations, the resulting data is distilled into a diffusion model that operates in real-time on camera point clouds. By combining the global semantic understanding of internet-scale models with the geometric precision of a simulation-based locally-aware force-closure, \our achieves high-performance semantic grasping without any manually collected training data. For visualizations of this please visit our website at https://ifgrasping.github.io/ |
| title | IFG: Internet-Scale Guidance for Functional Grasping Generation |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition Graphics Machine Learning |
| url | https://arxiv.org/abs/2511.09558 |