Control of Adept One SCARA robot using neural networks

Abstract

This paper presents an enhanced feedback error learning control (EFELC) strategy for an n-degree-of-freedom robotic manipulator. It covers the design and simulation study of the neural network-based controller for the manipulator with a view of tracking a predetermined trajectory of motion in the joint space. An industrial robotic manipulator, the Adept One Robot, was used to evaluate the effectiveness of the proposed scheme. The Adept One Robot was simulated as a three-axis manipulator with the dynamics of the tool (fourth link) neglected and the mass of the load incorporated into the mass of the third link. For simplicity, only the first two joints of the manipulator were considered in the simulation study. The overall performance of the control system under different conditions, namely, trajectory tracking, variations in trajectory and different initial weight values were studied and comparison made with the existing feedback error learning control strategy. The enhanced version was shown to outperform the existing method.