PERFORMANCE IMPROVEMENT OF ROBOT CONTINUOUS-PATH OPERATION THROUGH ITERATIVE LEARNING USING NEURAL NETWORKS

Citation
Pcy. Chen et al., PERFORMANCE IMPROVEMENT OF ROBOT CONTINUOUS-PATH OPERATION THROUGH ITERATIVE LEARNING USING NEURAL NETWORKS, Machine learning, 23(2-3), 1996, pp. 191-220
Citations number
23
Categorie Soggetti
Computer Sciences","Computer Science Artificial Intelligence",Neurosciences
Journal title
ISSN journal
08856125
Volume
23
Issue
2-3
Year of publication
1996
Pages
191 - 220
Database
ISI
SICI code
0885-6125(1996)23:2-3<191:PIORCO>2.0.ZU;2-W
Abstract
In this article, an approach to improving the performance of robot con tinuous-path operation is proposed. This approach utilizes a multilaye r feedforward neural network to compensate for model uncertainty assoc iated with the robotic operation. Closed-loop stability and performanc e are analyzed. it is shown that the closed-loop system is stable in t he sense that all signals are bounded; it is further proved that the p erformance of the closed-loop system is improved in the sense that cer tain error measure of the closed-loop system decreases as the network learning process is iterated. These analytical results are confirmed b y computer simulation. The effectiveness of the proposed approach is d emonstrated through a laboratory experiment.