A Powered Prosthetic Hand With Vision System for Enhancing the Anthropopathic Grasp

The anthropomorphic grasping capability of prosthetic hands is critical for enhancing user experience and functional efficiency. Existing prosthetic hands relying on brain-computer interfaces (BCI) and electromyography (EMG) face limitations in achieving natural grasping due to insufficient gesture...

Full description

Saved in:
Bibliographic Details
Main Authors: Yansong Xu, Xiaohui Wang, Junlin Li, Xiaoqian Zhang, Feng Li, Qing Gao, Chenglong Fu, Yuquan Leng
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Transactions on Neural Systems and Rehabilitation Engineering
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10988884/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850189619032752128
author Yansong Xu
Xiaohui Wang
Junlin Li
Xiaoqian Zhang
Feng Li
Qing Gao
Chenglong Fu
Yuquan Leng
author_facet Yansong Xu
Xiaohui Wang
Junlin Li
Xiaoqian Zhang
Feng Li
Qing Gao
Chenglong Fu
Yuquan Leng
author_sort Yansong Xu
collection DOAJ
description The anthropomorphic grasping capability of prosthetic hands is critical for enhancing user experience and functional efficiency. Existing prosthetic hands relying on brain-computer interfaces (BCI) and electromyography (EMG) face limitations in achieving natural grasping due to insufficient gesture adaptability and intent recognition. While vision systems enhance object perception, they lack dynamic human-like gesture control during grasping. To address these challenges, we propose a vision-powered prosthetic hand system that integrates two innovations. Spatial Geometry-based Gesture Mapping (SG-GM) dynamically models finger joint angles as polynomial functions of hand-object distance, derived from geometric features of human grasping sequences. These functions enable continuous anthropomorphic gesture transitions, mimicking natural hand movements. Motion Trajectory Regression-based Grasping Intent Estimation (MTR-GIE) predicts user intent in multi-object environments by regressing wrist trajectories and spatially segmenting candidate objects. Experiments with eight daily objects demonstrated high anthropomorphism (similarity coefficient <inline-formula> <tex-math notation="LaTeX">${R}^{{2}}=0.911$ </tex-math></inline-formula>, root mean squared error <inline-formula> <tex-math notation="LaTeX">$\textit {RMSE}=2.47 {^{\circ}}$ </tex-math></inline-formula>), rapid execution (<inline-formula> <tex-math notation="LaTeX">$3.07\pm 0.41$ </tex-math></inline-formula> s), and robust success rates (95.43% single-object; 88.75% multi-object). The MTR-GIE achieved 94.35% intent estimation accuracy under varying object spacing. This work pioneers vision-driven dynamic gesture synthesis for prosthetics, eliminating dependency on invasive sensors and advancing real-world usability.
format Article
id doaj-art-fef86b7718274230ba8b282dcbc69dfd
institution OA Journals
issn 1534-4320
1558-0210
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Transactions on Neural Systems and Rehabilitation Engineering
spelling doaj-art-fef86b7718274230ba8b282dcbc69dfd2025-08-20T02:15:34ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1534-43201558-02102025-01-01331827184010.1109/TNSRE.2025.356739210988884A Powered Prosthetic Hand With Vision System for Enhancing the Anthropopathic GraspYansong Xu0https://orcid.org/0000-0003-2106-9827Xiaohui Wang1https://orcid.org/0009-0005-9055-4799Junlin Li2https://orcid.org/0000-0003-0456-3778Xiaoqian Zhang3https://orcid.org/0009-0003-8026-3141Feng Li4https://orcid.org/0000-0002-9677-0207Qing Gao5https://orcid.org/0000-0002-5395-6175Chenglong Fu6https://orcid.org/0000-0002-8955-5429Yuquan Leng7https://orcid.org/0000-0003-4063-4545State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, ChinaState Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, ChinaState Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, ChinaState Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, ChinaState Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, ChinaSchool of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen, ChinaDepartment of Mechanical and Energy Engineering, Southern University of Science and Technology, Shenzhen, ChinaSchool of Biomedical Engineering and the State Key Laboratory of Robotics and Systems, Harbin Institute of Technology at Shenzhen, Shenzhen, ChinaThe anthropomorphic grasping capability of prosthetic hands is critical for enhancing user experience and functional efficiency. Existing prosthetic hands relying on brain-computer interfaces (BCI) and electromyography (EMG) face limitations in achieving natural grasping due to insufficient gesture adaptability and intent recognition. While vision systems enhance object perception, they lack dynamic human-like gesture control during grasping. To address these challenges, we propose a vision-powered prosthetic hand system that integrates two innovations. Spatial Geometry-based Gesture Mapping (SG-GM) dynamically models finger joint angles as polynomial functions of hand-object distance, derived from geometric features of human grasping sequences. These functions enable continuous anthropomorphic gesture transitions, mimicking natural hand movements. Motion Trajectory Regression-based Grasping Intent Estimation (MTR-GIE) predicts user intent in multi-object environments by regressing wrist trajectories and spatially segmenting candidate objects. Experiments with eight daily objects demonstrated high anthropomorphism (similarity coefficient <inline-formula> <tex-math notation="LaTeX">${R}^{{2}}=0.911$ </tex-math></inline-formula>, root mean squared error <inline-formula> <tex-math notation="LaTeX">$\textit {RMSE}=2.47 {^{\circ}}$ </tex-math></inline-formula>), rapid execution (<inline-formula> <tex-math notation="LaTeX">$3.07\pm 0.41$ </tex-math></inline-formula> s), and robust success rates (95.43% single-object; 88.75% multi-object). The MTR-GIE achieved 94.35% intent estimation accuracy under varying object spacing. This work pioneers vision-driven dynamic gesture synthesis for prosthetics, eliminating dependency on invasive sensors and advancing real-world usability.https://ieeexplore.ieee.org/document/10988884/Computer visiongesture modelingfull-automatic controlprosthetic hand system
spellingShingle Yansong Xu
Xiaohui Wang
Junlin Li
Xiaoqian Zhang
Feng Li
Qing Gao
Chenglong Fu
Yuquan Leng
A Powered Prosthetic Hand With Vision System for Enhancing the Anthropopathic Grasp
IEEE Transactions on Neural Systems and Rehabilitation Engineering
Computer vision
gesture modeling
full-automatic control
prosthetic hand system
title A Powered Prosthetic Hand With Vision System for Enhancing the Anthropopathic Grasp
title_full A Powered Prosthetic Hand With Vision System for Enhancing the Anthropopathic Grasp
title_fullStr A Powered Prosthetic Hand With Vision System for Enhancing the Anthropopathic Grasp
title_full_unstemmed A Powered Prosthetic Hand With Vision System for Enhancing the Anthropopathic Grasp
title_short A Powered Prosthetic Hand With Vision System for Enhancing the Anthropopathic Grasp
title_sort powered prosthetic hand with vision system for enhancing the anthropopathic grasp
topic Computer vision
gesture modeling
full-automatic control
prosthetic hand system
url https://ieeexplore.ieee.org/document/10988884/
work_keys_str_mv AT yansongxu apoweredprosthetichandwithvisionsystemforenhancingtheanthropopathicgrasp
AT xiaohuiwang apoweredprosthetichandwithvisionsystemforenhancingtheanthropopathicgrasp
AT junlinli apoweredprosthetichandwithvisionsystemforenhancingtheanthropopathicgrasp
AT xiaoqianzhang apoweredprosthetichandwithvisionsystemforenhancingtheanthropopathicgrasp
AT fengli apoweredprosthetichandwithvisionsystemforenhancingtheanthropopathicgrasp
AT qinggao apoweredprosthetichandwithvisionsystemforenhancingtheanthropopathicgrasp
AT chenglongfu apoweredprosthetichandwithvisionsystemforenhancingtheanthropopathicgrasp
AT yuquanleng apoweredprosthetichandwithvisionsystemforenhancingtheanthropopathicgrasp
AT yansongxu poweredprosthetichandwithvisionsystemforenhancingtheanthropopathicgrasp
AT xiaohuiwang poweredprosthetichandwithvisionsystemforenhancingtheanthropopathicgrasp
AT junlinli poweredprosthetichandwithvisionsystemforenhancingtheanthropopathicgrasp
AT xiaoqianzhang poweredprosthetichandwithvisionsystemforenhancingtheanthropopathicgrasp
AT fengli poweredprosthetichandwithvisionsystemforenhancingtheanthropopathicgrasp
AT qinggao poweredprosthetichandwithvisionsystemforenhancingtheanthropopathicgrasp
AT chenglongfu poweredprosthetichandwithvisionsystemforenhancingtheanthropopathicgrasp
AT yuquanleng poweredprosthetichandwithvisionsystemforenhancingtheanthropopathicgrasp