Concurrent Adaptation of Human and Machine Improves Simultaneous and Proportional Myoelectric Control

Janne M. Hahne, Sven Dähne, Han Jeong Hwang, Klaus Muller, Lucas C. Parra

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

Myoelectric control of a prosthetic hand with more than one degree of freedom (DoF) is challenging, and clinically available techniques require a sequential actuation of the DoFs. Simultaneous and proportional control of multiple DoFs is possible with regression-based approaches allowing for fluent and natural movements. Conventionally, the regressor is calibrated in an open-loop with training based on recorded data and the performance is evaluated subsequently. For individuals with amputation or congenital limb-deficiency who need to (re)learn how to generate suitable muscle contractions, this open-loop process may not be effective. We present a closed-loop real-time learning scheme in which both the user and the machine learn simultaneously to follow a common target. Experiments with ten able-bodied individuals show that this co-adaptive closed-loop learning strategy leads to significant performance improvements compared to a conventional open-loop training paradigm. Importantly, co-adaptive learning allowed two individuals with congenital deficiencies to perform simultaneous 2-D proportional control at levels comparable to the able-bodied individuals, despite having to a learn completely new and unfamiliar mapping from muscle activity to movement trajectories. To our knowledge, this is the first study which investigates man-machine co-adaptation for regression-based myoelectric control. The proposed training strategy has the potential to improve myographic prosthetic control in clinically relevant settings.

Original languageEnglish
Article number7038151
Pages (from-to)618-627
Number of pages10
JournalIEEE Transactions on Neural Systems and Rehabilitation Engineering
Volume23
Issue number4
DOIs
Publication statusPublished - 2015 Jul 1
Externally publishedYes

Fingerprint

Learning
Prosthetics
Muscle
Muscle Contraction
Extremities
Hand
Muscles
Trajectories
Experiments
Congenital Amputation

Keywords

  • Closed-loop-control
  • co-adaptation
  • Electromyography
  • myoelectric control
  • prosthetic hand
  • real-time-learning
  • regression
  • simultaneous control

ASJC Scopus subject areas

  • Neuroscience(all)
  • Computer Science Applications
  • Biomedical Engineering

Cite this

Concurrent Adaptation of Human and Machine Improves Simultaneous and Proportional Myoelectric Control. / Hahne, Janne M.; Dähne, Sven; Hwang, Han Jeong; Muller, Klaus; Parra, Lucas C.

In: IEEE Transactions on Neural Systems and Rehabilitation Engineering, Vol. 23, No. 4, 7038151, 01.07.2015, p. 618-627.

Research output: Contribution to journalArticle

Hahne, Janne M. ; Dähne, Sven ; Hwang, Han Jeong ; Muller, Klaus ; Parra, Lucas C. / Concurrent Adaptation of Human and Machine Improves Simultaneous and Proportional Myoelectric Control. In: IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2015 ; Vol. 23, No. 4. pp. 618-627.
@article{75f7a8baeeed409fa5802cf9ba943a7b,
title = "Concurrent Adaptation of Human and Machine Improves Simultaneous and Proportional Myoelectric Control",
abstract = "Myoelectric control of a prosthetic hand with more than one degree of freedom (DoF) is challenging, and clinically available techniques require a sequential actuation of the DoFs. Simultaneous and proportional control of multiple DoFs is possible with regression-based approaches allowing for fluent and natural movements. Conventionally, the regressor is calibrated in an open-loop with training based on recorded data and the performance is evaluated subsequently. For individuals with amputation or congenital limb-deficiency who need to (re)learn how to generate suitable muscle contractions, this open-loop process may not be effective. We present a closed-loop real-time learning scheme in which both the user and the machine learn simultaneously to follow a common target. Experiments with ten able-bodied individuals show that this co-adaptive closed-loop learning strategy leads to significant performance improvements compared to a conventional open-loop training paradigm. Importantly, co-adaptive learning allowed two individuals with congenital deficiencies to perform simultaneous 2-D proportional control at levels comparable to the able-bodied individuals, despite having to a learn completely new and unfamiliar mapping from muscle activity to movement trajectories. To our knowledge, this is the first study which investigates man-machine co-adaptation for regression-based myoelectric control. The proposed training strategy has the potential to improve myographic prosthetic control in clinically relevant settings.",
keywords = "Closed-loop-control, co-adaptation, Electromyography, myoelectric control, prosthetic hand, real-time-learning, regression, simultaneous control",
author = "Hahne, {Janne M.} and Sven D{\"a}hne and Hwang, {Han Jeong} and Klaus Muller and Parra, {Lucas C.}",
year = "2015",
month = "7",
day = "1",
doi = "10.1109/TNSRE.2015.2401134",
language = "English",
volume = "23",
pages = "618--627",
journal = "IEEE Transactions on Neural Systems and Rehabilitation Engineering",
issn = "1534-4320",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - Concurrent Adaptation of Human and Machine Improves Simultaneous and Proportional Myoelectric Control

AU - Hahne, Janne M.

AU - Dähne, Sven

AU - Hwang, Han Jeong

AU - Muller, Klaus

AU - Parra, Lucas C.

PY - 2015/7/1

Y1 - 2015/7/1

N2 - Myoelectric control of a prosthetic hand with more than one degree of freedom (DoF) is challenging, and clinically available techniques require a sequential actuation of the DoFs. Simultaneous and proportional control of multiple DoFs is possible with regression-based approaches allowing for fluent and natural movements. Conventionally, the regressor is calibrated in an open-loop with training based on recorded data and the performance is evaluated subsequently. For individuals with amputation or congenital limb-deficiency who need to (re)learn how to generate suitable muscle contractions, this open-loop process may not be effective. We present a closed-loop real-time learning scheme in which both the user and the machine learn simultaneously to follow a common target. Experiments with ten able-bodied individuals show that this co-adaptive closed-loop learning strategy leads to significant performance improvements compared to a conventional open-loop training paradigm. Importantly, co-adaptive learning allowed two individuals with congenital deficiencies to perform simultaneous 2-D proportional control at levels comparable to the able-bodied individuals, despite having to a learn completely new and unfamiliar mapping from muscle activity to movement trajectories. To our knowledge, this is the first study which investigates man-machine co-adaptation for regression-based myoelectric control. The proposed training strategy has the potential to improve myographic prosthetic control in clinically relevant settings.

AB - Myoelectric control of a prosthetic hand with more than one degree of freedom (DoF) is challenging, and clinically available techniques require a sequential actuation of the DoFs. Simultaneous and proportional control of multiple DoFs is possible with regression-based approaches allowing for fluent and natural movements. Conventionally, the regressor is calibrated in an open-loop with training based on recorded data and the performance is evaluated subsequently. For individuals with amputation or congenital limb-deficiency who need to (re)learn how to generate suitable muscle contractions, this open-loop process may not be effective. We present a closed-loop real-time learning scheme in which both the user and the machine learn simultaneously to follow a common target. Experiments with ten able-bodied individuals show that this co-adaptive closed-loop learning strategy leads to significant performance improvements compared to a conventional open-loop training paradigm. Importantly, co-adaptive learning allowed two individuals with congenital deficiencies to perform simultaneous 2-D proportional control at levels comparable to the able-bodied individuals, despite having to a learn completely new and unfamiliar mapping from muscle activity to movement trajectories. To our knowledge, this is the first study which investigates man-machine co-adaptation for regression-based myoelectric control. The proposed training strategy has the potential to improve myographic prosthetic control in clinically relevant settings.

KW - Closed-loop-control

KW - co-adaptation

KW - Electromyography

KW - myoelectric control

KW - prosthetic hand

KW - real-time-learning

KW - regression

KW - simultaneous control

UR - http://www.scopus.com/inward/record.url?scp=84936929558&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84936929558&partnerID=8YFLogxK

U2 - 10.1109/TNSRE.2015.2401134

DO - 10.1109/TNSRE.2015.2401134

M3 - Article

C2 - 25680209

AN - SCOPUS:84936929558

VL - 23

SP - 618

EP - 627

JO - IEEE Transactions on Neural Systems and Rehabilitation Engineering

JF - IEEE Transactions on Neural Systems and Rehabilitation Engineering

SN - 1534-4320

IS - 4

M1 - 7038151

ER -