Trajectory following control of robotic manipulators using neural networks

Abstract

A novel learning control architecture utilizing nonlinear computational properties of neural networks is presented. The nonlinear dynamics of the manipulator is assumed to be unknown, and the control scheme efficiently learns the required feedforward torques for a specified trajectory after a repeated number of trials. Simulation tests give promising results for real-time implementation of the algorithm.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>