Paper Details

[ Downloads: 10 | Abstract Viewed: 1551 | Pages: 7 ]

Abstract of the Article

Note: English CIVILICA is in its Trial Period so Full Texts can not be provided! Persian users can download it here

Control of Flexible Joint Manipulator, Using Neural Network with Animation via MATLAB and VRML

Authors:

[ S.S. Tayarani-Bathaie ] - Amirkabir University of Technology/Department of Electrical Engineering, Tehran, Iran
[ H.A Talebi ] - Amirkabir University of Technology/Department of Electrical Engineering, Tehran, Iran
[ S.N ayarani-Bathaie ] - Amirkabir University of Technology/Department of Computer Engineering, Tehran, Iran

Abstract:

This paper presents trajectory tracking control of manipulators with joint flexibility based on eural etworks. In detail, the control system is designed with two parallel subsystems designed separately. One is a linear controller, and another one is neural network controller. The former is designed for trajectory tracking error regulation, the later for torque generation required by the designed dynamic trajectory. A learning law for online weight updating of the neural network controller is derived based on simplified dynamic model of the robot. The eural net controller does not rely on accurate a priori knowledge of the manipulator dynamics, but instead can learn these dynamics Simulations and experiments are carried out on single link and two link flexible joint robot and the result of Feedback linearization Control and eural etwork Control was investigated. From the simulation and experimental results, the effectiveness and usefulness of this control system are confirmed. A virtual reality model for a teleoperation control is also presented for remote control of robot manipulators

Keywords:

eural etwork, Flexible joint, Robot Manipulator, Trajectory Control