Experiments in On-Line Learning Neuro-Control

A. G. Pipe, M. Randall and Y. Jin, University of the West of England

We apply our on-line learning neural network approach to control of non-linear systems; first to joint level trajectory control of an industrial welding robot, and then to one front leg of a hexapod walking robot. The first application demonstrates the ability of neuro-control to model complex non-linear components of a plant, thereby yielding impressive improvements in accuracy compared to the original robot’s controller. The second aplication illustrates the strength of an on-line learning approach in coping with disturbances to a plant’s characteristics. In order to set the work in context we briefly review our on-line learning neuro-control method, used for both sets of experiments. It has a strict theoretical basis including guarantees of the whole system’s stability.

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.