Progressive unsupervised control of myoelectric upper limbs

被引:3
|
作者
Gigli, Andrea [1 ,3 ]
Gijsberts, Arjan
Nowak, Markus [1 ]
Vujaklija, Ivan [2 ]
Castellini, Claudio [1 ,3 ]
机构
[1] German Aerosp Ctr DLR, Inst Robot & Mechatron, Wessling, Germany
[2] Aalto Univ, Dept Elect Engn & Automat, Espoo, Finland
[3] Friedrich Alexander Univ Erlangen Nurnberg, Assist Intelligent Robot Lab, Erlangen, Germany
关键词
coadaptive myocontrol; unsupervised myocontrol; muscle synergies; surface electromyography; motor skill learning; MATRIX FACTORIZATION; MUSCLE SYNERGIES; CHALLENGE POINT; PERFORMANCE; HAND; ELECTROMYOGRAPHY; ALGORITHMS; PROSTHESES; FRAMEWORK; AMPUTEES;
D O I
10.1088/1741-2552/ad0754
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Objective. Unsupervised myocontrol methods aim to create control models for myoelectric prostheses while avoiding the complications of acquiring reliable, regular, and sufficient labeled training data. A limitation of current unsupervised methods is that they fix the number of controlled prosthetic functions a priori, thus requiring an initial assessment of the user's motor skills and neglecting the development of novel motor skills over time. Approach. We developed a progressive unsupervised myocontrol (PUM) paradigm in which the user and the control model coadaptively identify distinct muscle synergies, which are then used to control arbitrarily associated myocontrol functions, each corresponding to a hand or wrist movement. The interaction starts with learning a single function and the user may request additional functions after mastering the available ones, which aligns the evolution of their motor skills with an increment in system complexity. We conducted a multi-session user study to evaluate PUM and compare it against a state-of-the-art non-progressive unsupervised alternative. Two participants with congenital upper-limb differences tested PUM, while ten non-disabled control participants tested either PUM or the non-progressive baseline. All participants engaged in myoelectric control of a virtual hand and wrist. Main results. PUM enabled autonomous learning of three myocontrol functions for participants with limb differences, and of all four available functions for non-disabled subjects, using both existing or newly identified muscle synergies. Participants with limb differences achieved similar success rates to non-disabled ones on myocontrol tests, but faced greater difficulties in internalizing new motor skills and exhibited slightly inferior movement quality. The performance was comparable with either PUM or the non-progressive baseline for the group of non-disabled participants. Significance. The PUM paradigm enables users to autonomously learn to operate the myocontrol system, adapts to the users' varied preexisting motor skills, and supports the further development of those skills throughout practice.
引用
收藏
页数:19
相关论文
共 50 条
  • [41] Synergy-Driven Myoelectric Control for EMG-Based Prosthetic Manipulation: A Case Study
    Li, Shunchong
    He, Jiayuan
    Sheng, Xinjun
    Liu, Honghai
    Zhu, Xiangyang
    INTERNATIONAL JOURNAL OF HUMANOID ROBOTICS, 2014, 11 (02)
  • [42] Muscular synergy classification and myoelectric control using high-order cross-cumulants
    Orosco, Eugenio C.
    di Sciascio, Fernando
    NEURAL COMPUTING & APPLICATIONS, 2017, 28 (10) : 2979 - 2993
  • [43] Towards online myoelectric control based on muscle synergies-to-force mapping for robotic applications
    Camardella, Cristian
    Barsotti, Michele
    Buongiorno, Domenico
    Frisoli, Antonio
    Bevilacqua, Vitoantonio
    NEUROCOMPUTING, 2021, 452 : 768 - 778
  • [44] The role of muscle synergies in myoelectric control: trends and challenges for simultaneous multifunction control
    Ison, Mark
    Artemiadis, Panagiotis
    JOURNAL OF NEURAL ENGINEERING, 2014, 11 (05)
  • [45] Upper Limb Prosthesis Control for High-Level Amputees via Myoelectric Recognition of Leg Gestures
    Lyons, Kenneth R.
    Joshi, Sanjay S.
    IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2018, 26 (05) : 1056 - 1066
  • [46] DYNAMIC RECURRENT NEURAL NETWORK BASED CLASSIFICATION SCHEME FOR MYOELECTRIC CONTROL OF UPPER LIMB REHABILITATION ROBOT
    Cui, Yuding
    Xiong, Caihua
    JOURNAL OF MECHANICS IN MEDICINE AND BIOLOGY, 2014, 14 (06)
  • [47] Toward Robust, Adaptiveand Reliable Upper-Limb Motion Estimation Using Machine Learning and Deep Learning-A Survey in Myoelectric Control
    Bao, Tianzhe
    Xie, Sheng Quan
    Yang, Pengfei
    Zhou, Ping
    Zhang, Zhi-Qiang
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2022, 26 (08) : 3822 - 3835
  • [48] Comparison of Online Adaptive Learning Algorithms for Myoelectric Hand Control
    Zhang, Yue
    Wang, Zheng
    Zhang, Zhuo
    Fang, Yinfeng
    Liu, Honghai
    2016 9TH INTERNATIONAL CONFERENCE ON HUMAN SYSTEM INTERACTIONS (HSI), 2016, : 69 - 75
  • [49] Progressive muscle-strength protocol for the functionality of upper limbs and quality of life in individuals with Parkinson's disease: Pilot study
    Correa, Thais Vianna
    Rocha Paz, Thiago da Silva
    Allodi, Silvana
    Santos de Britto, Vera Lucia
    Correa, Clynton Lourenco
    COMPLEMENTARY THERAPIES IN MEDICINE, 2020, 52
  • [50] Myoelectric control techniques for a rehabilitation robot
    Smith, Alan
    Brown, Edward E.
    APPLIED BIONICS AND BIOMECHANICS, 2011, 8 (01) : 21 - 37