Stability and convergence of neurologic model based robotic controllers

Author

Ciliz, M.K. ; Isik, C.

Author_Institution

Dept. of Electr. Eng., Bosphorous Univ., Istanbul

fYear

1992

fDate

12-14 May 1992

Firstpage

2051

Abstract

The authors investigate the local convergence properties of an artificial-neural-network (ANN)-based learning controller, using linearization techniques. The controller utilizes generic multilayer ANNs to adaptively approximate the manipulator dynamics over a specified region of the state space for a given desired trajectory. This generic neural network structure can be viewed as a nonlinear extension of a deterministic autoregressive model which is commonly used in model matching problems for linear systems

Keywords

convergence; feedforward neural nets; learning (artificial intelligence); linearisation techniques; robots; stability; deterministic autoregressive model; generic neural network; linear systems; linearization; local convergence; manipulator dynamics; model matching; neural net based learning; neurologic model based robotic controllers; stability; state space; Artificial neural networks; Convergence; Linear systems; Linearization techniques; Manipulator dynamics; Multi-layer neural network; Orbital robotics; Robots; Stability; State-space methods;

fLanguage

English

Publisher

ieee

Conference_Titel

Robotics and Automation, 1992. Proceedings., 1992 IEEE International Conference on

Conference_Location

Nice

Print_ISBN

0-8186-2720-4

Type

conf

DOI

10.1109/ROBOT.1992.219979

Filename

219979