AN INTELLIGENT METHOD TO ESTIMATE THE INERTIA MATRIX OF A ROBOT ARM FOR ACTIVE FORCE CONTROL USING ON-LINE NEURAL NETWORK TRAINING SCHEME
Keywords:
KeywordsAbstract
This paper presents a new intelligent controller algorithm comprising
an on-line multi-layer artificial neural network (ANN) training
scheme to estimate the inertia matrix ofthe robot arm to enhance the
performance of the active force control (AFC) scheme. The robot
under study is a planar two-link rigid robot which is subjected to a
non-linear disturbance torques acting at the robot joints. The
algorithm has two stages, namely the ANN training stage and -the
implementation stage. During the training stage, the proposed ANN
scheme trains the ANNparameters (weights and biases) for a period
oftime by utilising the back-propagation (BP) learning method. After
a sufficient training period, the training session is switched off, and
the ANN is ready to be used in the implementation stage of the
intelligent AFC-ANN controller scheme. The results of the training
and implementation stages are shown and discussed. It is shown that the proposed controller scheme is very effective and robust. The simulation is accomplished using MATLAB@ software.
References
Malcolm D. R., Robotics: An Introduction, PWS-Kent Publishing, 2nd ed., Boston, 1988:
Lewis F.L., Abdallah C.T., Dawson D.M., Control ofRobot Manipulators , Ed. John Griffin, Macmillan Pub., New York, 1993.
Lasky T.A..and Hsia T.C., Force Control of Robot Manipulators, Applied Control, Ed. S. G. Tzafestas, Marcel Dekker inc., New York, pp.639-661, 1993.
Slotine J.J.E and Li W., On the adaptive control of robot manipulators, Int. J Robotics Research, 1987.
Asada H.and Slotine J.J.E., Robot Analysis and Control, John Wiley and Sons, 1986.
Mailah M., Intelligent Active Force Control Using Neural Network and Iterative Learning Algorithms, Ph.D Thesis, University of Dundee, 1998.
Mailah M., A Simulation Study on the Intelligent Active Force Control of a Robot Arm using Neural Network, Jurnal Teknologi UTM, No.30(D), June 1999, pp. 55-78.
Hewit J.R. and Burdess J.S., Fast Dynamic Decoupled Control for Robotics Using Active Force Control, Mechanism and Machine Theory, Vol. 16, No.5, 1981,535-542.
Pham D. T. and Oh S. J., Adaptive Control of a Robot Using Neural Ne10. lung S., Neural Network Controllers for Robot Manipulators, Ph.D thesis, University of California Davis, 1996.
Rana A. and Zalzala A. M. S., A Neural Network Based Collision Detection Engine for Multi-Ann Robotic Systems, International Journal ofIntelligent Control Systems, Vol. 2, No.4, 1998, pp. 531-558.tworks, Robotica, vol. 12, 1994, pp. 553-561.
Downloads
Published
How to Cite
Issue
Section
License
Copyright of articles that appear in Jurnal Mekanikal belongs exclusively to Penerbit Universiti Teknologi Malaysia (Penerbit UTM Press). This copyright covers the rights to reproduce the article, including reprints, electronic reproductions or any other reproductions of similar nature.
