A Practical and Adaptive Method to Achieve EMG-based Torque Estimation for A Robotic Exoskeleton

Kai Gui, Honghai Liu, Dingguo Zhang

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

To improve the efficacy of robotic exoskeleton-based rehabilitation training, active joint torque of subjects should be detected. This paper presents a practical and adaptive method to estimate active joint torque using electromyography (EMG) signals for a custom lower limb robotic exoskeleton with two degrees of freedom (DOFs). This estimator, constructed of radial basis function neural networks (RBFNNs), was used to form an extended Slotine-Li controller. This extended controller eliminated the need for the calibration for EMG-torque model. The adaptive control of exoskeleton and adaptive estimation of active joint torque were performed within the same framework. By introducing a two-step learning strategy into the controller, the estimator can continuously adapt to changes in the EMG-torque model, and overcome the problems due to the time-varying property of EMG signals. Simulation and experimental results show that the presented estimator can predict the active joint torque of subjects in a practical and adaptive manner. Additionally, the accurate movement control of exoskeleton is also guaranteed. At present, the experiments are conducted only for the swing phase due to the lack of the force plate sensors.
Original languageEnglish
Pages (from-to)483-494
Number of pages12
JournalIEEE/ASME Transactions on Mechatronics
Volume24
Issue number2
Early online date14 Jan 2019
DOIs
Publication statusPublished - 1 Apr 2019

Keywords

  • Adaptive control
  • electromyography (EMG)
  • exoskeleton
  • human-robot interaction
  • radial basis function neural networks (RBFNNs)
  • torque estimation

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

A Practical and Adaptive Method to Achieve EMG-based Torque Estimation for A Robotic Exoskeleton. / Gui, Kai; Liu, Honghai; Zhang, Dingguo.

In: IEEE/ASME Transactions on Mechatronics, Vol. 24, No. 2, 01.04.2019, p. 483-494.

Research output: Contribution to journalArticle

@article{94fe57d9418c47c3afa5e4e2885f90a6,
title = "A Practical and Adaptive Method to Achieve EMG-based Torque Estimation for A Robotic Exoskeleton",
abstract = "To improve the efficacy of robotic exoskeleton-based rehabilitation training, active joint torque of subjects should be detected. This paper presents a practical and adaptive method to estimate active joint torque using electromyography (EMG) signals for a custom lower limb robotic exoskeleton with two degrees of freedom (DOFs). This estimator, constructed of radial basis function neural networks (RBFNNs), was used to form an extended Slotine-Li controller. This extended controller eliminated the need for the calibration for EMG-torque model. The adaptive control of exoskeleton and adaptive estimation of active joint torque were performed within the same framework. By introducing a two-step learning strategy into the controller, the estimator can continuously adapt to changes in the EMG-torque model, and overcome the problems due to the time-varying property of EMG signals. Simulation and experimental results show that the presented estimator can predict the active joint torque of subjects in a practical and adaptive manner. Additionally, the accurate movement control of exoskeleton is also guaranteed. At present, the experiments are conducted only for the swing phase due to the lack of the force plate sensors.",
keywords = "Adaptive control, electromyography (EMG), exoskeleton, human-robot interaction, radial basis function neural networks (RBFNNs), torque estimation",
author = "Kai Gui and Honghai Liu and Dingguo Zhang",
year = "2019",
month = "4",
day = "1",
doi = "10.1109/TMECH.2019.2893055",
language = "English",
volume = "24",
pages = "483--494",
journal = "IEEE - ASME Transactions on Mechatronics",
issn = "1083-4435",
publisher = "IEEE",
number = "2",

}

TY - JOUR

T1 - A Practical and Adaptive Method to Achieve EMG-based Torque Estimation for A Robotic Exoskeleton

AU - Gui, Kai

AU - Liu, Honghai

AU - Zhang, Dingguo

PY - 2019/4/1

Y1 - 2019/4/1

N2 - To improve the efficacy of robotic exoskeleton-based rehabilitation training, active joint torque of subjects should be detected. This paper presents a practical and adaptive method to estimate active joint torque using electromyography (EMG) signals for a custom lower limb robotic exoskeleton with two degrees of freedom (DOFs). This estimator, constructed of radial basis function neural networks (RBFNNs), was used to form an extended Slotine-Li controller. This extended controller eliminated the need for the calibration for EMG-torque model. The adaptive control of exoskeleton and adaptive estimation of active joint torque were performed within the same framework. By introducing a two-step learning strategy into the controller, the estimator can continuously adapt to changes in the EMG-torque model, and overcome the problems due to the time-varying property of EMG signals. Simulation and experimental results show that the presented estimator can predict the active joint torque of subjects in a practical and adaptive manner. Additionally, the accurate movement control of exoskeleton is also guaranteed. At present, the experiments are conducted only for the swing phase due to the lack of the force plate sensors.

AB - To improve the efficacy of robotic exoskeleton-based rehabilitation training, active joint torque of subjects should be detected. This paper presents a practical and adaptive method to estimate active joint torque using electromyography (EMG) signals for a custom lower limb robotic exoskeleton with two degrees of freedom (DOFs). This estimator, constructed of radial basis function neural networks (RBFNNs), was used to form an extended Slotine-Li controller. This extended controller eliminated the need for the calibration for EMG-torque model. The adaptive control of exoskeleton and adaptive estimation of active joint torque were performed within the same framework. By introducing a two-step learning strategy into the controller, the estimator can continuously adapt to changes in the EMG-torque model, and overcome the problems due to the time-varying property of EMG signals. Simulation and experimental results show that the presented estimator can predict the active joint torque of subjects in a practical and adaptive manner. Additionally, the accurate movement control of exoskeleton is also guaranteed. At present, the experiments are conducted only for the swing phase due to the lack of the force plate sensors.

KW - Adaptive control

KW - electromyography (EMG)

KW - exoskeleton

KW - human-robot interaction

KW - radial basis function neural networks (RBFNNs)

KW - torque estimation

UR - http://www.scopus.com/inward/record.url?scp=85064649999&partnerID=8YFLogxK

U2 - 10.1109/TMECH.2019.2893055

DO - 10.1109/TMECH.2019.2893055

M3 - Article

VL - 24

SP - 483

EP - 494

JO - IEEE - ASME Transactions on Mechatronics

JF - IEEE - ASME Transactions on Mechatronics

SN - 1083-4435

IS - 2

ER -