Real-time EMG-based Human Machine Interface using dynamic hand gestures

Sungtae Shin, Reza Tafreshi, Reza Langari

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This study proposes a myoelectric Human Machine Interface (HMI) to control a 6-DOF robotic manipulator with a 1-DOF gripper. Previous study has shown that using dynamic gestures such as 'snapping fingers' is more reliable in the limb position changes than using static gestures such as 'closed hand'. This work utilizes dynamic gestures and additionally infers muscle forces from the EMG signals to activate/inactivate a myoelectric HMI system. In order to estimate the performance of the myoelectric interface, real-time classification accuracy, path efficiency, and time-related measures are introduced. For comparison purposes, the performance of a GUI button-based jog interface was also measured. The average real-time classification accuracy of the myoelectric interface is approximately 95%. The path efficiency of the myoelectric interface also appears to be similar to that of the jog interface reflecting the utility of this approach for HMI applications in robotics.

Original languageEnglish
Title of host publication2017 American Control Conference, ACC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5456-5461
Number of pages6
ISBN (Electronic)9781509059928
DOIs
Publication statusPublished - 29 Jun 2017
Event2017 American Control Conference, ACC 2017 - Seattle, United States
Duration: 24 May 201726 May 2017

Other

Other2017 American Control Conference, ACC 2017
CountryUnited States
CitySeattle
Period24/5/1726/5/17

Fingerprint

Robotics
Grippers
Graphical user interfaces
Interfaces (computer)
Manipulators
Muscle

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Shin, S., Tafreshi, R., & Langari, R. (2017). Real-time EMG-based Human Machine Interface using dynamic hand gestures. In 2017 American Control Conference, ACC 2017 (pp. 5456-5461). [7963803] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/ACC.2017.7963803

Real-time EMG-based Human Machine Interface using dynamic hand gestures. / Shin, Sungtae; Tafreshi, Reza; Langari, Reza.

2017 American Control Conference, ACC 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 5456-5461 7963803.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shin, S, Tafreshi, R & Langari, R 2017, Real-time EMG-based Human Machine Interface using dynamic hand gestures. in 2017 American Control Conference, ACC 2017., 7963803, Institute of Electrical and Electronics Engineers Inc., pp. 5456-5461, 2017 American Control Conference, ACC 2017, Seattle, United States, 24/5/17. https://doi.org/10.23919/ACC.2017.7963803
Shin S, Tafreshi R, Langari R. Real-time EMG-based Human Machine Interface using dynamic hand gestures. In 2017 American Control Conference, ACC 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 5456-5461. 7963803 https://doi.org/10.23919/ACC.2017.7963803
Shin, Sungtae ; Tafreshi, Reza ; Langari, Reza. / Real-time EMG-based Human Machine Interface using dynamic hand gestures. 2017 American Control Conference, ACC 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 5456-5461
@inproceedings{87ae159eeb964af59b454691418eed47,
title = "Real-time EMG-based Human Machine Interface using dynamic hand gestures",
abstract = "This study proposes a myoelectric Human Machine Interface (HMI) to control a 6-DOF robotic manipulator with a 1-DOF gripper. Previous study has shown that using dynamic gestures such as 'snapping fingers' is more reliable in the limb position changes than using static gestures such as 'closed hand'. This work utilizes dynamic gestures and additionally infers muscle forces from the EMG signals to activate/inactivate a myoelectric HMI system. In order to estimate the performance of the myoelectric interface, real-time classification accuracy, path efficiency, and time-related measures are introduced. For comparison purposes, the performance of a GUI button-based jog interface was also measured. The average real-time classification accuracy of the myoelectric interface is approximately 95{\%}. The path efficiency of the myoelectric interface also appears to be similar to that of the jog interface reflecting the utility of this approach for HMI applications in robotics.",
author = "Sungtae Shin and Reza Tafreshi and Reza Langari",
year = "2017",
month = "6",
day = "29",
doi = "10.23919/ACC.2017.7963803",
language = "English",
pages = "5456--5461",
booktitle = "2017 American Control Conference, ACC 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Real-time EMG-based Human Machine Interface using dynamic hand gestures

AU - Shin, Sungtae

AU - Tafreshi, Reza

AU - Langari, Reza

PY - 2017/6/29

Y1 - 2017/6/29

N2 - This study proposes a myoelectric Human Machine Interface (HMI) to control a 6-DOF robotic manipulator with a 1-DOF gripper. Previous study has shown that using dynamic gestures such as 'snapping fingers' is more reliable in the limb position changes than using static gestures such as 'closed hand'. This work utilizes dynamic gestures and additionally infers muscle forces from the EMG signals to activate/inactivate a myoelectric HMI system. In order to estimate the performance of the myoelectric interface, real-time classification accuracy, path efficiency, and time-related measures are introduced. For comparison purposes, the performance of a GUI button-based jog interface was also measured. The average real-time classification accuracy of the myoelectric interface is approximately 95%. The path efficiency of the myoelectric interface also appears to be similar to that of the jog interface reflecting the utility of this approach for HMI applications in robotics.

AB - This study proposes a myoelectric Human Machine Interface (HMI) to control a 6-DOF robotic manipulator with a 1-DOF gripper. Previous study has shown that using dynamic gestures such as 'snapping fingers' is more reliable in the limb position changes than using static gestures such as 'closed hand'. This work utilizes dynamic gestures and additionally infers muscle forces from the EMG signals to activate/inactivate a myoelectric HMI system. In order to estimate the performance of the myoelectric interface, real-time classification accuracy, path efficiency, and time-related measures are introduced. For comparison purposes, the performance of a GUI button-based jog interface was also measured. The average real-time classification accuracy of the myoelectric interface is approximately 95%. The path efficiency of the myoelectric interface also appears to be similar to that of the jog interface reflecting the utility of this approach for HMI applications in robotics.

UR - http://www.scopus.com/inward/record.url?scp=85027061002&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027061002&partnerID=8YFLogxK

U2 - 10.23919/ACC.2017.7963803

DO - 10.23919/ACC.2017.7963803

M3 - Conference contribution

SP - 5456

EP - 5461

BT - 2017 American Control Conference, ACC 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -