Application of Neural Nets for Control of Robotic Manipulators

  • T. Uhl
  • M. Szymkat
Conference paper
Part of the International Centre for Mechanical Sciences book series (CISM, volume 361)


Fine motion control of robotic manipulators has become a desired goal in the last few years as a result of new robot morphology and the definition of new tasks involving high velocity motions and end effector tracking precision. In order to achieve better performance of robotic manipulators the artificial intelligence can be introduced into the control system. One way for accomplishing this is application of neural nets. Main advantage claimed for neural based controllers is their ability to learn and generalize from partial data and ability to perform parall processing. Many papers present possibilities of neural nets application for control [Hunt,92],[Sontag 93],[Anstaklis,92]. They have discussed the use in adaptive control, predictive control, optimal control, gain sheduling in PID with variable gain. A large area of neural nets application for control is control of nonlinear systems. Neural nets can be applied as a forward or inverse model of manipulator. Such neural net can learn a behaviour of the real system, without knowledge about robot’s model structure.


Trajectory Tracking Trajectory Planning Robotic Manipulator Linear Controller Neural Controller 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [Abetisjan, 87]
    W. W. Abetisjan, L. D., Akulienko, N. N. Bolotnik, Energy consumption optimization control of robotic manipulator, Techniceskaja Kihemetika, no. 3, 1987, pp 100–107.Google Scholar
  2. [Antsaklis, 92]
    P. Ansaklis, “Special issue on neural networks in control”, IEEE Control System Magazine, vol. 12, no. 2, Aprili 1992, pp. 8–57.Google Scholar
  3. [Barto, 90]
    A. G. Barto, “Connectionist learning for control-An overview”, Neural Networks for Control, Ed. W. T. Miller, R. S. Sutton, J Paul, MIT Press, Camhridge, 1990, pp. 5–59.Google Scholar
  4. [Craig, 90]
    J. J. Craig, “Introduction to robotics, mechanics and control”, Addison-Wesley, Reading, 1990.Google Scholar
  5. [Funahashi, 89]
    K. Funahashi, “On the approximate realization of continuous mappings by neural networks”, Neural Networks. Vo1. 2. 1989, pp. 183–192.Google Scholar
  6. [Galla, 81]
    D. F. Golla, S. C. Garg. P. C. Hughes, “Linear state-feedback control of manipulators”, Mech. Machine Theory. Vol. 16, 1981. pp. 93–103.CrossRefGoogle Scholar
  7. [Hunt, 92]
    K. J. Hunt, D. Sabraro, R. Zbikowski, P. J. Gawthrop. Neural networks for control systems–a survey. Automatica, vol. 28. no. 6, 1992, pp. 641–657CrossRefGoogle Scholar
  8. [Kawato, 89]
    M. Kawato, M. Isobe. R. Suzuki, “Hierarchical learning of voluntary movement by cerebellum and sensory association cortex”, Dynamic Interaction in Neural Networks-Models and Data, Ed. hy A. Arhih, S. Amori, Springer Verla g. 1989, pp. 195–214.Google Scholar
  9. [Kawato, 90]
    M. Kawato, “Computational schemes and neural network models for formation and control of multi joint arm trajectory”, Neural Networks for Control, Ed. W. T. Miller, R. S. Sutton, J. Paul, MIT Press, Cambridge, 1990, pp. 197–229.Google Scholar
  10. [Kawato, 93]
    M. Kawato, Y. Wada, “Aneural Network Model for Arm trajectory Forming Using Forward and Inverse Dynamics Model, Neural Networks, vol. 6, no 7, 1993, pp. 919–933.CrossRefGoogle Scholar
  11. [Maltadi, 92]
    S. R. Malladi, Mulder M. C., K. P. Valavanis, “Behavior of a minimum effort control algorithm for a multi joined robotic arm”, IEEE Symposium on Inteligent Control, Glasgow, 1992, pp. 34–40.Google Scholar
  12. [Rieswijk, 92]
    T. A. Riejswijk, G. G., Brown, “A robust and efficient approach for the time optimization of path constrained motion of robotic manipulators incorporating actuator torque and jerk constraints, IEEE Inter. Symposium on Inteligent Control, Glasgow, 1992, pp. 507–513.Google Scholar
  13. [Simon, 93]
    D. Simon, C. Isik, “The generation and optimization of trigonometric joint trajectories for robotic manipulators”, Int. J. of Control vol. 42 no. 2, 1993.Google Scholar
  14. [Sontag, 93]
    E. D. Sontag, “Neural Networks for Control”in Essays on Control: Perspectives in Theory and it’s Applications, Ed. Trentelman H, L., Birkhauser, Boston, 1993.Google Scholar
  15. [Szymkat, 92]
    M. Szymkat, M. Brdyg, J. Sacha, “NC an object oriented programming tool for neural control design, Neuro-Nimes’91, pp. 741–744.Google Scholar
  16. [Szymkat, 93]
    M. Szymkat, T. UhI, “Neural network approach to planning and tracking of robots trajectories”, IEEE Inteligent Control Conference, Chicago, 1992, pp. 244–268Google Scholar
  17. [Szymkat, 94]
    M. Szymkat, T. Uhl, “On-line robot arms trajectory planning using quadratic criteria” submitted to Int. J. of MechatronicsGoogle Scholar
  18. [Uh1, 92]
    T. Uhl, Szymkat M., “A comparision of the classical and neural-based approach to control of Manipulation rohots, XVII IMSA, Leuven, September, 1992, pp. 255–284.Google Scholar
  19. [Zvi, 89]
    S. Zvi, D. Steven, “Robot path planning with obstacles, actuator, gripper and payload, International Journal of Robotic Research, vol. 8, no. 6, 1989, pp. 3–18.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Wien 1995

Authors and Affiliations

  • T. Uhl
    • 1
  • M. Szymkat
    • 1
  1. 1.University of Mining and MetallurgyKrakowPoland

Personalised recommendations