A comparison of control strategies of robotic manipulators using neural networks

Abstract

The authors present a comparison of control strategies for robotic manipulators based on artificial neural networks. Two position control strategies of a two-degree-of-freedom (DOF) SCARA manipulator are investigated: the direct inverse neurocontroller and the nonlinear neural compensator. The performances of the two strategies are compared in terms of error convergence and adaptation to parameter variation. Satisfactory simulation results of position control for the SCARA manipulator by using neurocontrollers are presented.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>