Parameter uncertainty compensation in robot trajectory tracking: a neural network approach

Abstract

An approach employing a multilayer feedforward neural network (with the error-backpropagation algorithm) for uncertainty compensation in the problem of robot trajectory tracking is proposed. It is proved, and verified through computer simulation, that the resulting closed-loop system (with a neural network as the uncertainty compensator) is stable in the sense that all signals in the closed-loop system are bounded, while the performance of the closed-loop system improves as the neural network learning process iterates.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>