An adaptive neural controller and direct adaptive controllers for robot manipulators in the joint space

Abstract

Direct adaptive control techniques for robot manipulators in joint space coordinates are provided. Comparison between a proposed adaptive neural controller and direct adaptive control techniques (computed-torque and passivity-based controllers) are simulated for the same trajectory, considering the presence of the friction torques. Performances are evaluated according to behavior of errors of position and velocity tracking, absolute position error, absolute velocity error, control torques, and to trajectory tracking accuracy.