A noninvasive brain-computer interface approach for predicting motion intention of activities of daily living tasks for an upper-limb wearable robot

D. S.V. Bandara, Jumpei Arata, Kazuo Kiguchi

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Brain-computer interfaces are emerging as an important research area and are intended to create an understanding between a computer and the human brain to ensure that robot-human interactions become more intuitive and userfriendly. However, encoding of brain information to derive the intended motion of the user in real time continues to present a problem with respect to the control of wearable robots with multiple degrees of freedom. In this study, a new approach to control several degrees of freedom in a wearable robot is proposed and its feasibility is studied by estimating the user’s motion intention in real time, in terms of the user’s intended tasks to perform, by using electroencephalography signals measured from the scalp of the user. A time-delayed feature matrix is introduced to provide inputs to neural network and support vector machine-based classifiers that harvest the dynamic nature of the electroencephalography signals for motion intention prediction. The experimental results indicate the effectiveness of the proposed methodology in the estimation of user motion intention, in terms of intended task to perform.

Original languageEnglish
JournalInternational Journal of Advanced Robotic Systems
Volume15
Issue number2
DOIs
Publication statusPublished - Mar 1 2018

Fingerprint

Brain computer interface
Electroencephalography
Brain
Robots
Human robot interaction
Support vector machines
Classifiers
Neural networks

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Science Applications
  • Artificial Intelligence

Cite this

@article{6490b4bc2802442dae5df19c2f3c4bed,
title = "A noninvasive brain-computer interface approach for predicting motion intention of activities of daily living tasks for an upper-limb wearable robot",
abstract = "Brain-computer interfaces are emerging as an important research area and are intended to create an understanding between a computer and the human brain to ensure that robot-human interactions become more intuitive and userfriendly. However, encoding of brain information to derive the intended motion of the user in real time continues to present a problem with respect to the control of wearable robots with multiple degrees of freedom. In this study, a new approach to control several degrees of freedom in a wearable robot is proposed and its feasibility is studied by estimating the user’s motion intention in real time, in terms of the user’s intended tasks to perform, by using electroencephalography signals measured from the scalp of the user. A time-delayed feature matrix is introduced to provide inputs to neural network and support vector machine-based classifiers that harvest the dynamic nature of the electroencephalography signals for motion intention prediction. The experimental results indicate the effectiveness of the proposed methodology in the estimation of user motion intention, in terms of intended task to perform.",
author = "Bandara, {D. S.V.} and Jumpei Arata and Kazuo Kiguchi",
year = "2018",
month = "3",
day = "1",
doi = "10.1177/1729881418767310",
language = "English",
volume = "15",
journal = "International Journal of Advanced Robotic Systems",
issn = "1729-8806",
publisher = "Vienna University of Technology",
number = "2",

}

TY - JOUR

T1 - A noninvasive brain-computer interface approach for predicting motion intention of activities of daily living tasks for an upper-limb wearable robot

AU - Bandara, D. S.V.

AU - Arata, Jumpei

AU - Kiguchi, Kazuo

PY - 2018/3/1

Y1 - 2018/3/1

N2 - Brain-computer interfaces are emerging as an important research area and are intended to create an understanding between a computer and the human brain to ensure that robot-human interactions become more intuitive and userfriendly. However, encoding of brain information to derive the intended motion of the user in real time continues to present a problem with respect to the control of wearable robots with multiple degrees of freedom. In this study, a new approach to control several degrees of freedom in a wearable robot is proposed and its feasibility is studied by estimating the user’s motion intention in real time, in terms of the user’s intended tasks to perform, by using electroencephalography signals measured from the scalp of the user. A time-delayed feature matrix is introduced to provide inputs to neural network and support vector machine-based classifiers that harvest the dynamic nature of the electroencephalography signals for motion intention prediction. The experimental results indicate the effectiveness of the proposed methodology in the estimation of user motion intention, in terms of intended task to perform.

AB - Brain-computer interfaces are emerging as an important research area and are intended to create an understanding between a computer and the human brain to ensure that robot-human interactions become more intuitive and userfriendly. However, encoding of brain information to derive the intended motion of the user in real time continues to present a problem with respect to the control of wearable robots with multiple degrees of freedom. In this study, a new approach to control several degrees of freedom in a wearable robot is proposed and its feasibility is studied by estimating the user’s motion intention in real time, in terms of the user’s intended tasks to perform, by using electroencephalography signals measured from the scalp of the user. A time-delayed feature matrix is introduced to provide inputs to neural network and support vector machine-based classifiers that harvest the dynamic nature of the electroencephalography signals for motion intention prediction. The experimental results indicate the effectiveness of the proposed methodology in the estimation of user motion intention, in terms of intended task to perform.

UR - http://www.scopus.com/inward/record.url?scp=85046888617&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046888617&partnerID=8YFLogxK

U2 - 10.1177/1729881418767310

DO - 10.1177/1729881418767310

M3 - Article

AN - SCOPUS:85046888617

VL - 15

JO - International Journal of Advanced Robotic Systems

JF - International Journal of Advanced Robotic Systems

SN - 1729-8806

IS - 2

ER -