Positioning control of an under-actuated robot manipulator using artificial neural network inversion technique

Abstract

This chapter is devoted to solve the positioning control problem of under-actuated robot manipulator. Artificial Neural Networks Inversion technique was used where a network representing the forward dynamics of the system was trained to learn the position of the passive joint over the working space of a 2R under-actuated robot. The obtained weights from the learning process were fixed and the network was inverted to represent the inverse dynamics of the system, and then used in the estimation phase to estimate the position of the passive joint for a new set of data the network was not previously trained for in order to show the success of the control strategy. Data used in this research are recorded experimentally from sensors fixed on the robot joints in order to overcome whichever uncertainties presence in the real world such as ill-defined linkage parameters, links flexibility and backlashes in gear trains. The technique was implemented in two phases, the first phase was the forward learning phase that used to obtain the training weights which are used in the second phase which is the inverse estimation phase that is used to estimate the passive joint's position for any set of data the network was not trained for. The results were verified experimentally to show the ability of the proposed technique to solve the problem efficiently. © 2011 by Nova Science Publishers, Inc. All rights reserved.