1
|
Gigli A, Gijsberts A, Nowak M, Vujaklija I, Castellini C. Progressive unsupervised control of myoelectric upper limbs. J Neural Eng 2023; 20:066016. [PMID: 37883969 DOI: 10.1088/1741-2552/ad0754] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/23/2023] [Accepted: 10/26/2023] [Indexed: 10/28/2023]
Abstract
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.
Collapse
Affiliation(s)
- Andrea Gigli
- Institute of Robotics and Mechatronics, German Aerospace Center (DLR), Wessling, Germany
- Assistive Intelligent Robotics Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | | | - Markus Nowak
- Institute of Robotics and Mechatronics, German Aerospace Center (DLR), Wessling, Germany
| | - Ivan Vujaklija
- Department of Electrical Engineering and Automation, Aalto University, Espoo, Finland
| | - Claudio Castellini
- Institute of Robotics and Mechatronics, German Aerospace Center (DLR), Wessling, Germany
- Assistive Intelligent Robotics Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| |
Collapse
|
2
|
Szymaniak K, Krasoulis A, Nazarpour K. Recalibration of myoelectric control with active learning. Front Neurorobot 2022; 16:1061201. [PMID: 36590085 PMCID: PMC9797496 DOI: 10.3389/fnbot.2022.1061201] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2022] [Accepted: 11/21/2022] [Indexed: 12/16/2022] Open
Abstract
Introduction Improving the robustness of myoelectric control to work over many months without the need for recalibration could reduce prosthesis abandonment. Current approaches rely on post-hoc error detection to verify the certainty of a decoder's prediction using predefined threshold value. Since the decoder is fixed, the performance decline over time is inevitable. Other approaches such as supervised recalibration and unsupervised self-recalibration entail limitations in scaling up and computational resources. The objective of this paper is to study active learning as a scalable, human-in-the-loop framework, to improve the robustness of myoelectric control. Method Active learning and linear discriminate analysis methods were used to create an iterative learning process, to modify decision boundaries based on changes in the data. We simulated a real-time scenario. We exploited least confidence, smallest margin and entropy reduction sampling strategies in single and batch-mode sample selection. Optimal batch-mode sampling was considered using ranked batch-mode active learning. Results With only 3.2 min of data carefully selected by the active learner, the decoder outperforms random sampling by 4-5 and ~2% for able-bodied and people with limb difference, respectively. We observed active learning strategies to systematically and significantly enhance the decoders adaptation while optimizing the amount of training data on a class-specific basis. Smallest margin and least confidence uncertainty were shown to be the most supreme. Discussion We introduce for the first time active learning framework for long term adaptation in myoelectric control. This study simulates closed-loop environment in an offline manner and proposes a pipeline for future real-time deployment.
Collapse
Affiliation(s)
- Katarzyna Szymaniak
- Edinburgh Neuroprosthetics Laboratory, School of Informatics, The University of Edinburgh, Edinburgh, United Kingdom
| | - Agamemnon Krasoulis
- School of Engineering, Newcastle University, Newcastle-upon-Tyne, United Kingdom
| | - Kianoush Nazarpour
- Edinburgh Neuroprosthetics Laboratory, School of Informatics, The University of Edinburgh, Edinburgh, United Kingdom,*Correspondence: Kianoush Nazarpour
| |
Collapse
|
3
|
Dyson M, Olsen J, Dupan S. A Network-Enabled Myoelectric Platform for Prototyping Research Outside of the Lab. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2021; 2021:7422-7425. [PMID: 34892812 DOI: 10.1109/embc46164.2021.9630318] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
We present a network-enabled myoelectric platform for performing research outside of the laboratory environment. A low-cost, flexible, modular design based on common Internet of Things connectivity technology allows home-based research to be piloted. An outline of the platform is presented followed by technical results obtained from ten days of home-based tests with three participants. Results show the system enabled collection of close to 12,000 trials during around 28 cumulative hours of use. Home-based testing of multiple participants in parallel offers efficiency gains and provides a intuitive route toward long-term testing of upper-limb prosthetic devices in more naturalistic settings.Clinical relevance- In-home myoelectric training reduces clinician time. Network-enabled systems with back-end dashboards allow clinicians to monitor patients myoelectric ability over time and will provide a new way of accessing information about how upper-limb prosthetics are commonly used.
Collapse
|
4
|
Nazarpour K. A more human prosthetic hand. Sci Robot 2021; 5:5/46/eabd9341. [PMID: 32967992 DOI: 10.1126/scirobotics.abd9341] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2020] [Accepted: 09/01/2020] [Indexed: 11/02/2022]
Abstract
Co-creation leads the way for bioinspired prosthetics with improved design and performance.
Collapse
Affiliation(s)
- Kianoush Nazarpour
- School of Informatics, University of Edinburgh, 10 Crichton Street, Edinburgh EH8 9AB, UK.
| |
Collapse
|
5
|
Laffranchi M, Boccardo N, Traverso S, Lombardi L, Canepa M, Lince A, Semprini M, Saglia JA, Naceri A, Sacchetti R, Gruppioni E, De Michieli L. The Hannes hand prosthesis replicates the key biological properties of the human hand. Sci Robot 2020; 5:5/46/eabb0467. [DOI: 10.1126/scirobotics.abb0467] [Citation(s) in RCA: 37] [Impact Index Per Article: 9.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/25/2020] [Accepted: 08/18/2020] [Indexed: 11/02/2022]
Affiliation(s)
- M. Laffranchi
- Rehab Technologies, Istituto Italiano di Tecnologia, Via Morego, 30, 16163 Genova, Italy
| | - N. Boccardo
- Rehab Technologies, Istituto Italiano di Tecnologia, Via Morego, 30, 16163 Genova, Italy
| | - S. Traverso
- Rehab Technologies, Istituto Italiano di Tecnologia, Via Morego, 30, 16163 Genova, Italy
| | - L. Lombardi
- Rehab Technologies, Istituto Italiano di Tecnologia, Via Morego, 30, 16163 Genova, Italy
| | - M. Canepa
- Rehab Technologies, Istituto Italiano di Tecnologia, Via Morego, 30, 16163 Genova, Italy
| | - A. Lince
- Rehab Technologies, Istituto Italiano di Tecnologia, Via Morego, 30, 16163 Genova, Italy
| | - M. Semprini
- Rehab Technologies, Istituto Italiano di Tecnologia, Via Morego, 30, 16163 Genova, Italy
| | - J. A. Saglia
- Rehab Technologies, Istituto Italiano di Tecnologia, Via Morego, 30, 16163 Genova, Italy
| | - A. Naceri
- Advanced Robotics, Istituto Italiano di Tecnologia, Via Morego, 30, 16163 Genova, Italy
| | - R. Sacchetti
- Centro Protesi INAIL, Istituto Nazionale per l’Assicurazione contro gli Infortuni sul Lavoro, Via Rabuina 14, 40054, Vigorso di Budrio (BO) Italy
| | - E. Gruppioni
- Centro Protesi INAIL, Istituto Nazionale per l’Assicurazione contro gli Infortuni sul Lavoro, Via Rabuina 14, 40054, Vigorso di Budrio (BO) Italy
| | - L. De Michieli
- Rehab Technologies, Istituto Italiano di Tecnologia, Via Morego, 30, 16163 Genova, Italy
| |
Collapse
|
6
|
Learning, Generalization, and Scalability of Abstract Myoelectric Control. IEEE Trans Neural Syst Rehabil Eng 2020; 28:1539-1547. [DOI: 10.1109/tnsre.2020.3000310] [Citation(s) in RCA: 20] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
|