Application of a gesture classification system to the control of a rehabilitation robotic manipulator

Author

Gill, Reine ; White, A.S.

Volume

2

fYear

1996

fDate

31 Oct-3 Nov 1996

Firstpage

514

Abstract

This paper describes the development of a low-cost gesture measurement and recognition system employing electrolytic tilt sensors. Two methods of gesture classification by software are compared: a dynamic programming algorithm and an artificial neural network. The artificial neural network is shown to have greater classification performance when classifying degraded gestures. The gesture recognition system is employed as part of a multimodal communication platform for the control of a rehabilitation robotic system

Keywords

biocontrol; computational complexity; dynamic programming; handicapped aids; intelligent sensors; manipulators; motion control; pattern classification; perceptrons; robot programming; user interfaces; artificial neural network; classification performance; controller software; degraded gestures; dynamic programming algorithm; electrolytic tilt sensors; fast convergence; gesture classification system; gesture measurement and recognition system; low-cost system; manipulator control; multimodal communication platform; rehabilitation robotic manipulator; single layer perceptron; wheelchair mounted manipulator; Application software; Artificial neural networks; Communication system control; Control systems; Degradation; Dynamic programming; Heuristic algorithms; Sensor phenomena and characterization; Sensor systems; Software algorithms;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 1996. Bridging Disciplines for Biomedicine. Proceedings of the 18th Annual International Conference of the IEEE

Conference_Location

Amsterdam

Print_ISBN

0-7803-3811-1

Type

conf

DOI

10.1109/IEMBS.1996.651842

Filename

651842