DocumentCode
1904137
Title
Identification of a PUMA-560 two-link robot using a stable neural network
Author
Jubien, Chris M. ; Dimopoulos, Nikitas J.
Author_Institution
Dept. of Electr. & Comput. Eng., Victoria Univ., BC, Canada
fYear
1993
fDate
1993
Firstpage
568
Abstract
A training procedure for a class of neural networks that are asymptotically stable is presented. The training procedure is a gradient method which adapts the interconnection weights, as well as the relaxation constants and the slopes of the activation functions used, so that the error between the expected and obtained responses is minimized. A method for assuring that stability is maintained throughout the training procedure is given. Such a network is used to identify a simulated nonlinear system and a PUMA-560 two-link robot
Keywords
adaptive control; identification; industrial robots; learning (artificial intelligence); neural nets; PUMA-560 two-link robot; activation functions; asymptotically stable; gradient method; interconnection weights; relaxation constants; stable neural network; training procedure; Asymptotic stability; Control systems; Cost function; Gradient methods; Intelligent networks; Neural networks; Neurons; Nonlinear control systems; Nonlinear systems; Robots;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1993., IEEE International Conference on
Conference_Location
San Francisco, CA
Print_ISBN
0-7803-0999-5
Type
conf
DOI
10.1109/ICNN.1993.298620
Filename
298620
Link To Document