Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors
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_ | 1866911258876313600 |
|---|---|
| author | Zhao, Haoyu Zhuang, Linghao Zhao, Xingyue Zeng, Cheng Xu, Haoran Jiang, Yuming Cen, Jun Wang, Kexiang Guo, Jiayan Huang, Siteng Li, Xin Zhao, Deli Zou, Hua |
| author_facet | Zhao, Haoyu Zhuang, Linghao Zhao, Xingyue Zeng, Cheng Xu, Haoran Jiang, Yuming Cen, Jun Wang, Kexiang Guo, Jiayan Huang, Siteng Li, Xin Zhao, Deli Zou, Hua |
| contents | A dexterous hand capable of generalizable grasping objects is fundamental for the development of general-purpose embodied AI. However, previous methods focus narrowly on low-level grasp stability metrics, neglecting affordance-aware positioning and human-like poses which are crucial for downstream manipulation. To address these limitations, we propose AffordDex, a novel framework with two-stage training that learns a universal grasping policy with an inherent understanding of both motion priors and object affordances. In the first stage, a trajectory imitator is pre-trained on a large corpus of human hand motions to instill a strong prior for natural movement. In the second stage, a residual module is trained to adapt these general human-like motions to specific object instances. This refinement is critically guided by two components: our Negative Affordance-aware Segmentation (NAA) module, which identifies functionally inappropriate contact regions, and a privileged teacher-student distillation process that ensures the final vision-based policy is highly successful. Extensive experiments demonstrate that AffordDex not only achieves universal dexterous grasping but also remains remarkably human-like in posture and functionally appropriate in contact location. As a result, AffordDex significantly outperforms state-of-the-art baselines across seen objects, unseen instances, and even entirely novel categories. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_08896 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors Zhao, Haoyu Zhuang, Linghao Zhao, Xingyue Zeng, Cheng Xu, Haoran Jiang, Yuming Cen, Jun Wang, Kexiang Guo, Jiayan Huang, Siteng Li, Xin Zhao, Deli Zou, Hua Robotics A dexterous hand capable of generalizable grasping objects is fundamental for the development of general-purpose embodied AI. However, previous methods focus narrowly on low-level grasp stability metrics, neglecting affordance-aware positioning and human-like poses which are crucial for downstream manipulation. To address these limitations, we propose AffordDex, a novel framework with two-stage training that learns a universal grasping policy with an inherent understanding of both motion priors and object affordances. In the first stage, a trajectory imitator is pre-trained on a large corpus of human hand motions to instill a strong prior for natural movement. In the second stage, a residual module is trained to adapt these general human-like motions to specific object instances. This refinement is critically guided by two components: our Negative Affordance-aware Segmentation (NAA) module, which identifies functionally inappropriate contact regions, and a privileged teacher-student distillation process that ensures the final vision-based policy is highly successful. Extensive experiments demonstrate that AffordDex not only achieves universal dexterous grasping but also remains remarkably human-like in posture and functionally appropriate in contact location. As a result, AffordDex significantly outperforms state-of-the-art baselines across seen objects, unseen instances, and even entirely novel categories. |
| title | Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors |
| topic | Robotics |
| url | https://arxiv.org/abs/2508.08896 |