PERFORMANCE IMPROVEMENT OF ROBOT CONTINUOUS-PATH OPERATION THROUGH ITERATIVE LEARNING USING NEURAL NETWORKS
by Peter C.Y. Chen, James K. Mills, and Kenneth C. Smith
In this article, an approach to improving the performance of robot continuous-path operation is proposed. This approach utilizes a multilayer feedforward neural network to compensate for model uncertainty associated with the robotic operation. Closed-loop stability and performance are analyzed. It is shown that the closed-loop system is stable in the sense that all signals are bounded; it is further proved that the performance of the closed-loop system is improved in the sense that certain error measure of the closed-loop system decreases as the network learning process is iterated. These analytical results are confirmed by computer simulation. The effectiveness of the proposed approach is demonstrated through a laboratory experiment.