DocumentCode :
3199201
Title :
A generalised neural network for a humanoid hand
Author :
Zsíros, Péter ; Baranyi, Péter ; KQvári, Lászlo ; Korondi, Péter
Author_Institution :
Dept. of Autom. & Appl. Inf., Budapest Univ. of Technol. & Econ., Hungary
Volume :
2
fYear :
2000
fDate :
2000
Firstpage :
523
Abstract :
The main contribution of this paper is a practical application of generalised neural networks for a dextrous hand moved by shape memory alloys (SMA). Since SMA have highly nonlinear characteristics and their parameters depend on the environment (mainly on temperature) so the robot hand is controlled by a generalised neural network, which can learn the actual nonlinear characteristics of the robot hand. The experimental setup consists of a 20 degree of freedom hand moved by SMA string used as artificial muscle. A video camera is used to detect the position of joints. The position is then sent to the visual display computer via the Internet, which displays the hand in 3D using OpenGl
Keywords :
Internet; dexterous manipulators; generalisation (artificial intelligence); neural nets; position control; shape memory effects; telerobotics; 20 degree of freedom hand; Internet; OpenGl; SMA string; artificial muscle; dextrous hand; generalised neural network; humanoid hand; joints position; nonlinear characteristics; robot hand control; shape memory alloys; video camera; visual display computer; Artificial neural networks; Computer displays; Muscles; Neural networks; Robot control; Robot vision systems; Shape memory alloys; Temperature control; Temperature dependence; Three dimensional displays;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Industrial Electronics, 2000. ISIE 2000. Proceedings of the 2000 IEEE International Symposium on
Conference_Location :
Cholula, Puebla
Print_ISBN :
0-7803-6606-9
Type :
conf
DOI :
10.1109/ISIE.2000.930352
Filename :
930352
Link To Document :
بازگشت