Adaptive Gesture Recognition System for Robotic Control using Surface EMG Sensors

Benjamin Marchiex, Bryan Gardiner, Sonya Coleman

Research output: Contribution to conferencePaper

Abstract

Traditionally, Electromyography (EMG) technology was used primarily in the medical domain for the investigation of neuromuscular normalities. However, the development of cheap surface EMG armbands have made this high-end technology commonly accessible to a much wider community. For example, providing gesture interfaces for gaming or controlling peripheral hardware devices. So far, research within this field has typically used complex machine learning classifiers, substantially large databases and long learning/training phases to develop applications-based approaches.
In this paper, a novel algorithm is presented based on one shot learning, i.e. requiring only one example per gesture, therefore substantially reducing the training time and database size. To assess the reliability and the usefulness of the developed system, the accuracy of the algorithm has been compared with classic machine learning approaches providing comparable accuracy. Additionally, the algorithm is successfully demonstrated via a robotic control experiment using various gestures for mobile platform and manipulator control.

Conference

ConferenceIEEE International Symposium on Signal Processing and Information Technology
Abbreviated titleISSPIT
CountryUnited Arab Emirates
CityAjman
Period10/12/1912/12/19

Fingerprint

Electromyography
Gesture recognition
Control surfaces
Robotics
Learning systems
Sensors
Manipulators
Classifiers
Hardware
Experiments

Keywords

  • Electromyography (EMG)
  • robotic control
  • adaptive gesture recognition

Cite this

Marchiex, B., Gardiner, B., & Coleman, S. (Accepted/In press). Adaptive Gesture Recognition System for Robotic Control using Surface EMG Sensors. Paper presented at IEEE International Symposium on Signal Processing and Information Technology, Ajman, United Arab Emirates.
Marchiex, Benjamin ; Gardiner, Bryan ; Coleman, Sonya. / Adaptive Gesture Recognition System for Robotic Control using Surface EMG Sensors. Paper presented at IEEE International Symposium on Signal Processing and Information Technology, Ajman, United Arab Emirates.
@conference{0c42418bfc484183b85fc99b00a3ceab,
title = "Adaptive Gesture Recognition System for Robotic Control using Surface EMG Sensors",
abstract = "Traditionally, Electromyography (EMG) technology was used primarily in the medical domain for the investigation of neuromuscular normalities. However, the development of cheap surface EMG armbands have made this high-end technology commonly accessible to a much wider community. For example, providing gesture interfaces for gaming or controlling peripheral hardware devices. So far, research within this field has typically used complex machine learning classifiers, substantially large databases and long learning/training phases to develop applications-based approaches.In this paper, a novel algorithm is presented based on one shot learning, i.e. requiring only one example per gesture, therefore substantially reducing the training time and database size. To assess the reliability and the usefulness of the developed system, the accuracy of the algorithm has been compared with classic machine learning approaches providing comparable accuracy. Additionally, the algorithm is successfully demonstrated via a robotic control experiment using various gestures for mobile platform and manipulator control.",
keywords = "Electromyography (EMG), robotic control, adaptive gesture recognition",
author = "Benjamin Marchiex and Bryan Gardiner and Sonya Coleman",
year = "2019",
month = "11",
day = "2",
language = "English",
note = "IEEE International Symposium on Signal Processing and Information Technology, ISSPIT ; Conference date: 10-12-2019 Through 12-12-2019",

}

Marchiex, B, Gardiner, B & Coleman, S 2019, 'Adaptive Gesture Recognition System for Robotic Control using Surface EMG Sensors' Paper presented at IEEE International Symposium on Signal Processing and Information Technology, Ajman, United Arab Emirates, 10/12/19 - 12/12/19, .

Adaptive Gesture Recognition System for Robotic Control using Surface EMG Sensors. / Marchiex, Benjamin; Gardiner, Bryan; Coleman, Sonya.

2019. Paper presented at IEEE International Symposium on Signal Processing and Information Technology, Ajman, United Arab Emirates.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Adaptive Gesture Recognition System for Robotic Control using Surface EMG Sensors

AU - Marchiex, Benjamin

AU - Gardiner, Bryan

AU - Coleman, Sonya

PY - 2019/11/2

Y1 - 2019/11/2

N2 - Traditionally, Electromyography (EMG) technology was used primarily in the medical domain for the investigation of neuromuscular normalities. However, the development of cheap surface EMG armbands have made this high-end technology commonly accessible to a much wider community. For example, providing gesture interfaces for gaming or controlling peripheral hardware devices. So far, research within this field has typically used complex machine learning classifiers, substantially large databases and long learning/training phases to develop applications-based approaches.In this paper, a novel algorithm is presented based on one shot learning, i.e. requiring only one example per gesture, therefore substantially reducing the training time and database size. To assess the reliability and the usefulness of the developed system, the accuracy of the algorithm has been compared with classic machine learning approaches providing comparable accuracy. Additionally, the algorithm is successfully demonstrated via a robotic control experiment using various gestures for mobile platform and manipulator control.

AB - Traditionally, Electromyography (EMG) technology was used primarily in the medical domain for the investigation of neuromuscular normalities. However, the development of cheap surface EMG armbands have made this high-end technology commonly accessible to a much wider community. For example, providing gesture interfaces for gaming or controlling peripheral hardware devices. So far, research within this field has typically used complex machine learning classifiers, substantially large databases and long learning/training phases to develop applications-based approaches.In this paper, a novel algorithm is presented based on one shot learning, i.e. requiring only one example per gesture, therefore substantially reducing the training time and database size. To assess the reliability and the usefulness of the developed system, the accuracy of the algorithm has been compared with classic machine learning approaches providing comparable accuracy. Additionally, the algorithm is successfully demonstrated via a robotic control experiment using various gestures for mobile platform and manipulator control.

KW - Electromyography (EMG)

KW - robotic control

KW - adaptive gesture recognition

M3 - Paper

ER -

Marchiex B, Gardiner B, Coleman S. Adaptive Gesture Recognition System for Robotic Control using Surface EMG Sensors. 2019. Paper presented at IEEE International Symposium on Signal Processing and Information Technology, Ajman, United Arab Emirates.