Robotic Arm Control with Neural Networks Using Genetic Algorithm Optimization Approach

Authors: A. Pajaziti, H. Cana

Abstract:

In this paper, the structural genetic algorithm is used to optimize the neural network to control the joint movements of robotic arm. The robotic arm has also been modeled in 3D and simulated in real-time in MATLAB. It is found that Neural Networks provide a simple and effective way to control the robot tasks. Computer simulation examples are given to illustrate the significance of this method. By combining Genetic Algorithm optimization method and Neural Networks for the given robotic arm with 5 D.O.F. the obtained the results shown that the base joint movements overshooting time without controller was about 0.5 seconds, while with Neural Network controller (optimized with Genetic Algorithm) was about 0.2 seconds, and the population size of 150 gave best results.

Keywords: Robotic Arm, Neural Network, Genetic Algorithm, Optimization.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1094351

References:

[1] "Intelligent Control Techniques in Mechatronics - Genetic algorithm”, http://www.ro.feri.uni-mb.si/predmeti/int_reg/Predavanja/Eng/ 3.Genetic%20algorithm/_17.html
[2] A. Pajaziti, I. Gojani, A. Shala, and P. Kopacek, "Optimization of Biped Gait Synthesis Using Fuzzy Neural Network Controller”, in DETC/CIE 2005-84191, September 2005.
[3] R. K. Elsley, "A learning architecture for control based on back-propagation neural networks,” in International Conference on Neural Networks, vol. 2, pp. 587-594, IEEE, July 1988.
[4] G. Josin, D. Charney, and D. White, "Robot control using neural networks,” in International Conference on Neural Networks, vol. 2, pp. 625-631, IEEE, July 1988.
[5] S. Lee and R. M. Kil, "Robot kinematic control based on bi-directional mapping neural network,” in International Joint Conference on Neural Networks, vol. 3, pp. 327-335, 1990.
[6] T. Yabuta and T. Yamada, "Possibility of neural networks controller for robot manipulators,” in International Conference on Robotics and Automation, pp. 16861691, IEEE, May 1990.
[7] J. M. Zurada, M. Kavari, and J. H. Lilly, "Robot kinematics modeling using multilayer feedforward neural networks,” in Artificial Neural Networks in Engineering, pp. 785-790, ASME Press, November 1992.
[8] L. C. Rabelo and X. J. R. Avula, "Hierarchical neurocontroller architecture for robotic manipulation,” IEEE Control Systems Magazine, vol. 12, no. 2, pp. 3741, April 1992.
[9] K. Liu and J. P. H. Steele, "A new artificial neural systems architecture and its application to robot control,” in Artificial Neural Networks in Engineering, pp. 505-510, ASME Press, November 1993.
[10] K. Liu and J. P. H. Steele, "A new artificial neural systems architecture and its application to robot control,” in Artificial Neural Networks in Engineering, pp. 505-510, ASME Press, November 1993.
[11] D. Mandelc, "Soft computing in non-linear regulation”, individual research project, FEECS, University of Maribor, 2006
[12] H. Cana, "Manual and Semi-Automatic Control of Robotic Arm”, Master Thesis, University of Prishtina, Kosovo, 2014.