NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Neuroelectric Virtual DevicesThis paper presents recent results in neuroelectric pattern recognition of electromyographic (EMG) signals used to control virtual computer input devices. The devices are designed to substitute for the functions of both a traditional joystick and keyboard entry method. We demonstrate recognition accuracy through neuroelectric control of a 757 class simulation aircraft landing at San Francisco International Airport using a virtual joystick as shown. This is accomplished by a pilot closing his fist in empty air and performing control movements that are captured by a dry electrode array on the arm which are then analyzed and routed through a flight director permitting full pilot outer loop control of the simulation. We then demonstrate finer grain motor pattern recognition through a virtual keyboard by having a typist tap his traders on a typical desk in a touch typist position. The EMG signals are then translated to keyboard presses and displayed. The paper describes the bioelectric pattern recognition methodology common to both examples. Figure 2 depicts raw EMG data from typing, the numeral '8' and the numeral '9'. These two gestures are very close in appearance and statistical properties yet are distinguishable by our hidden Kharkov model algorithms. Extensions of this work to NASA emissions and robotic control are considered.
Document ID
20020044094
Acquisition Source
Ames Research Center
Document Type
Preprint (Draft being sent to journal)
Authors
Wheeler, Kevin
(NASA Ames Research Center Moffett Field, CA United States)
Jorgensen, Charles
(NASA Ames Research Center Moffett Field, CA United States)
Date Acquired
September 7, 2013
Publication Date
January 1, 2000
Subject Category
Aerospace Medicine
Meeting Information
Meeting: NASA DoD Workshop on Bio-Inspired Engineering for Exploration Systems
Location: Pasadena, CA
Country: United States
Start Date: December 4, 2000
End Date: December 6, 2000
Distribution Limits
Public
Copyright
Work of the US Gov. Public Use Permitted.
No Preview Available