Advertisement

ROMANSY 11 pp 327-334 | Cite as

Application of Neural Networks for Control of Robot Manipulators-Simulation and Implementation

  • T. Uhl
  • M. Szymkat
  • T. Bojko
  • Z. Korendo
  • J. Ród
Part of the International Centre for Mechanical Sciences book series (CISM, volume 381)

Abstract

Several approaches to using neural networks for solving the kinematics, dynamics, motion planning and control problems in robotics applications have been proposed in past years. In the literature some applications of neural networks in kinematics are presented [3, 6, 7, 14, 17] and motion planning [7,14,17]. The use of neural networks for control of robotic manipulators motion has been proposed in the number of papers [1, 5, 7, 9, 10, 11, 12, 19, 22]. In this paper the problem of the trajectory tracking is considered. The desired trajectory for the motion of a manipulator is generated by the path planner. Having the desired trajectory with the initial and final positions of the centerpoint of the end-effector, controllers need to be constructed for the actuators that make the end-effector follow the specified trajectory as closely as possible.This is achieved by determining the torques acting on the joint shafts or inputs to the joint actuators so that the system follows the desired trajectory with minimal tracking error. The dynamic model of the general manipulator represents a multiple-inputmultiple-output (MIMO) system, in which equations are nonlinear and coupled. We consider two alternatives of control of such systems: the classical control and the intelligent one. One class of intelligent control is control scheme based on neural networks.

Keywords

Neural Network Model Predictive Control Robot Manipulator Trajectory Tracking Back Propagation Neural Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Literature

  1. 1.
    Antslakis P., Special issue on neural networks in control, IFFF.Control System Magazine, vol.12, not, 1992, pp.8–57.Google Scholar
  2. 2.
    Barto A.G., Connectionist learning for control–An overview, Neural Networks for Control, Ed. Miller W.T., Sutton R.S., Paul J., MIT Press, Cambridge, 1990, pp. 5–59.Google Scholar
  3. 3.
    Cavalieri S., Martini M., Petrone F., Sinatra R., A neural network approach for position-error optimisation problem in a redundant robot, Proceedings of IX World Congress on the Theory of Machines and Mechanisms, Milan, 1995, pp. 1684–1689.Google Scholar
  4. 4.
    Chen F.C., Back propagation neural networks for nonlinear self-tuning adaptive control, IEEE, Control System Magazine, pp. 1448–1453, 1989.Google Scholar
  5. 5.
    Gehlot N.S., Alsina P.J., A comparison of control strategies of robotic manipulators using neural networks, International Conference on IECON, 1922, pp. 688–693.Google Scholar
  6. 6.
    Gou J., Cherkaysky V., A solution to the inverse kinematics problem in robotics using neural network processing, IEEE Int. Conf. on NN, Washington D.C., Vol. II, pp 299–304, 1989.Google Scholar
  7. 7.
    Hamavand Z., Schwartz M., Trajectory control of robotic manipulators by using a feedback-error-learning neural network, Robotica, vol. 13, 1995, pp. 449–459.CrossRefGoogle Scholar
  8. 8.
    Hanselman H., DSP in Control: The Total development Environment, Proc. of Int. Conf. on signal processing Applications & Technology, Boston, 1995. pp. 107–114.Google Scholar
  9. 9.
    Hunt K.J., Sabraro, Zbikowski R., Gawthrop, Neural networks for control system–a survey, Automatica, vol. 28, no. 6, 1992, pp. 1083–1112.CrossRefMATHMathSciNetGoogle Scholar
  10. 10.
    Jung S., Hsia T.C., A new neural network control technique for robot manipulators, Robotica, vol. 13, 1995, pp. 449–459.CrossRefGoogle Scholar
  11. 11.
    Kawato M., Wada Y., A neural network model for arm trajectory forming using forward and inverse dynamics model, Neural networks, vol.6, no.7., 1993,pp. 919–933.Google Scholar
  12. 12.
    Khemaissia S., Morris A.S.,Neuro-adaptive control of robotic manipulators, Robotica, vol.11, no.5, pp. 465473, 1993.Google Scholar
  13. 13.
    Sciavicco L., Siciliano B., Modeling and Control of robot manipulators, The McGraw-Hill Companies,Inc., 1996.Google Scholar
  14. 14.
    Simon D., Neural network based robot trajectory generation, IEEE Transaction on Neural Networks vol. 5, pp. 540–545, 1993.Google Scholar
  15. 15.
    Sontag E.D., Neural networks for control, in Essay on Control: Perspective in theory and its application, Ed. Trentelman H.L., Birkhauser, Boston, 1993.Google Scholar
  16. 16.
    Szymkat M, Ravn O., Turnau A, Kolek K, Pjeturson A., Integrated mechatronic modelling environments, Int. Conf. on Recent Advances in Mechatronics, pp. 767–772, Istanbul, 1995.Google Scholar
  17. 17.
    Szymkat M., Uhl T., Biennier F., Neural network support for simultaneous optimisation of torque and deviation in robot path planning, Proc. of the IEEE Int. Symp. on Intelligent Control, pp. 241–252., Chicago IL, 1993.Google Scholar
  18. 18.
    Uhl T., Lisowski W., Bojko T., R6d J., Identification of robotic joints models using model adjustment techniques, MMAR’95, Miedzyzdroje, 1995, pp. 659–664.Google Scholar
  19. 19.
    UhI T., Szymkat M., Application of neural nets for control of robotic manipulators, Proc. of ROMANSY 10: Theory and practice of robots and manipulators, Springer Verlag, 1994.Google Scholar
  20. 20.
    Uhl T., Szymkat M., A comparison of the classical and neural-based approach to control of manipulation robots, XVII ISMA, Leuven, 1992. pp. 255–284.Google Scholar
  21. 21.
    Uhl T., Rod J.,Modeling and identification of robotics systems using MATLAB/SIMULINK environment, In ICRAM, Istanbul, August 1995.Google Scholar
  22. 22.
    Yabuta T., Yamada T., Possibility of Neural Networks Controller for robot manipulator, Proc. of IEEE Int. Conf. on Robotics and Automation, 1990, pp 1686–1691.Google Scholar

Copyright information

© Springer-Verlag Wien 1997

Authors and Affiliations

  • T. Uhl
    • 1
  • M. Szymkat
    • 1
  • T. Bojko
    • 1
  • Z. Korendo
    • 1
  • J. Ród
    • 1
  1. 1.St. Staszic Technical UniversityCracowPoland

Personalised recommendations