Biophysical Models With Adaptive Online Learning for Direct Neural Control of Prostheses

IF 5.2 2区 医学 Q2 ENGINEERING, BIOMEDICAL
Joris Gentinetta;Michael F. Fernandez;Junqing Qiao;Maria Ramos Gonzalez;Hugh M. Herr
{"title":"Biophysical Models With Adaptive Online Learning for Direct Neural Control of Prostheses","authors":"Joris Gentinetta;Michael F. Fernandez;Junqing Qiao;Maria Ramos Gonzalez;Hugh M. Herr","doi":"10.1109/TNSRE.2025.3599114","DOIUrl":null,"url":null,"abstract":"Direct neural control of multi-articulating prosthetic hands is critical for achieving dexterous manipulation in unstructured environments. However, such control — predicting continuous movements over independent degrees of freedom — remains confined to research settings. In contrast, pattern recognition systems are widely employed for their simple, user-friendly training procedures, though their limitation to a set of discrete whole-hand poses restricts functionality. To bridge this gap, we designed a direct neural controller and a training procedure to support adaptive retraining, enabling users to improve controller predictions or incorporate new movements using a single RGB camera. It explicitly models musculoskeletal dynamics and employs a neural network-based method for motor intent disambiguation, which we term “synergy inversion”. The defined dynamics constrain the predicted kinetics and kinematics to a physiologically realizable manifold, while synergy inversion can capture nonlinear patterns of muscle coactivation missing from traditional musculoskeletal models. In experiments with eight biologically intact participants and two individuals with unilateral transradial amputation, the proposed paradigm predicted trajectories for seven degrees of freedom and improved performance through online learning, achieving lower error than both purely neural and purely biophysical baseline models. This work represents a step toward the adoption of direct neural control of upper extremity prostheses in real-world settings, offering the flexibility of pattern recognition training within a more performant control framework.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"3201-3211"},"PeriodicalIF":5.2000,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11124939","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/11124939/","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}
引用次数: 0

Abstract

Direct neural control of multi-articulating prosthetic hands is critical for achieving dexterous manipulation in unstructured environments. However, such control — predicting continuous movements over independent degrees of freedom — remains confined to research settings. In contrast, pattern recognition systems are widely employed for their simple, user-friendly training procedures, though their limitation to a set of discrete whole-hand poses restricts functionality. To bridge this gap, we designed a direct neural controller and a training procedure to support adaptive retraining, enabling users to improve controller predictions or incorporate new movements using a single RGB camera. It explicitly models musculoskeletal dynamics and employs a neural network-based method for motor intent disambiguation, which we term “synergy inversion”. The defined dynamics constrain the predicted kinetics and kinematics to a physiologically realizable manifold, while synergy inversion can capture nonlinear patterns of muscle coactivation missing from traditional musculoskeletal models. In experiments with eight biologically intact participants and two individuals with unilateral transradial amputation, the proposed paradigm predicted trajectories for seven degrees of freedom and improved performance through online learning, achieving lower error than both purely neural and purely biophysical baseline models. This work represents a step toward the adoption of direct neural control of upper extremity prostheses in real-world settings, offering the flexibility of pattern recognition training within a more performant control framework.
基于自适应在线学习的生物物理模型用于假肢的直接神经控制。
多关节假肢手的直接神经控制是在非结构化环境中实现灵巧操作的关键。然而,这种控制——预测独立自由度上的连续运动——仍然局限于研究环境。相比之下,模式识别系统因其简单、用户友好的训练程序而被广泛应用,尽管它们对一组离散的全手姿势的限制限制了功能。为了弥补这一差距,我们设计了一个直接神经控制器和一个训练程序,旨在支持自适应再训练,使用户能够改进控制器预测或使用单个RGB相机合并新的运动。它明确地模拟肌肉骨骼动力学,并采用基于神经网络的方法来消除运动意图歧义,我们称之为“协同反转”。定义的动力学将预测的动力学和运动学约束为生理上可实现的流形,而协同反转可以捕获传统肌肉骨骼模型中缺失的肌肉协同激活的非线性模式。在8名生物完整的参与者和2名单侧经桡骨截肢患者的实验中,该模型预测了7个自由度的轨迹,并通过在线学习提高了性能,其误差低于纯神经和纯生物物理基线模型。这项工作代表了在现实环境中采用上肢假肢直接神经控制的一步,在更高性能的控制框架内提供模式识别训练的灵活性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
8.60
自引率
8.20%
发文量
479
审稿时长
6-12 weeks
期刊介绍: Rehabilitative and neural aspects of biomedical engineering, including functional electrical stimulation, acoustic dynamics, human performance measurement and analysis, nerve stimulation, electromyography, motor control and stimulation; and hardware and software applications for rehabilitation engineering and assistive devices.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信