{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T14:05:47Z","timestamp":1773929147609,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"15","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.1609\/aaai.v40i15.38313","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:17:48Z","timestamp":1773793068000},"page":"13126-13134","source":"Crossref","is-referenced-by-count":1,"title":["Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors"],"prefix":"10.1609","volume":"40","author":[{"given":"Haoyu","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Linghao","family":"Zhuang","sequence":"additional","affiliation":[]},{"given":"Xingyue","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Cheng","family":"Zeng","sequence":"additional","affiliation":[]},{"given":"Haoran","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Yuming","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Cen","sequence":"additional","affiliation":[]},{"given":"Kexiang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jiayan","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Siteng","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Xin","family":"Li","sequence":"additional","affiliation":[]},{"given":"Deli","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Hua","family":"Zou","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38313\/42275","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38313\/42275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:17:48Z","timestamp":1773793068000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/38313"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i15.38313","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}