自动化学报2026，Vol.52Issue(5)：992-1007,16.DOI:10.16383/j.aas.c250512
以数据手套为媒介的人手-机械手抓握技能传递
Data Glove-mediated Grasping Skill Transfer From Human Hands to Robotic Hands
摘要
Abstract
Imitation learning provides an effective way for transferring manipulation skills from human hands to ro-botic hands.However,traditional demonstration methods face problems including non-intuitive demonstration,poor reusability of demonstration data,and difficulties in effectively transferring tactile and kinesthetic perception fea-tures.To address these problems,this paper designs an integrated data glove capable of simultaneously collecting tactile and kinesthetic features,and proposes a data glove-mediated grasping skill transfer scheme.This scheme en-compasses a multimodal feature representation based on graph structures and polar coordinates,estimation of un-known contact forces under static force equilibrium assumptions,and a dynamic remapping method utilizing de-sired joint angles and contact force distributions.Experimental results demonstrate that for objects with diverse properties,such as deformable and irregular geometries,the proposed scheme achieves a high grasping success rate while maintaining proper contact force control,producing results that relatively more closely resemble direct hu-man grasping among the baseline schemes.关键词
数据手套/模仿学习/触觉感知/机械手/抓握Key words
data glove/imitation learning/tactile perception/robotic hands/grasping引用本文复制引用
郭策,郭子睿,陈斯灏,李依鸿,肖浩然,李金哲,陈谢沅澧,曾志文,卢惠民..以数据手套为媒介的人手-机械手抓握技能传递[J].自动化学报,2026,52(5):992-1007,16.基金项目
国家自然科学基金(U22A2059,62203460,62403478,T2521006),中国科协青年人才托举工程(2023QNRC001),国防科技大学自主科研基金资助 Supported by National Natural Science Foundation of China(U22A2059,62203460,62403478,T2521006),Young Elite Scient-ists Sponsorship Program by CAST(2023QNRC001),and the In-novation Research Foundation of National University of Defense Technology （U22A2059,62203460,62403478,T2521006）
