Skip to main content
SpringerLink
Log in

Calculation of a robot manipulator model in the form of arecurrent neural net

Berechnung eines Robotermanipulatormodells in Form eines rekurrenten Neuronenetzes

  • Reviewed Original Papers
  • Published:
e&i Elektrotechnik und Informationstechnik Aims and scope Submit manuscript

Abstract

A neural model for robot manipulator is proposed similar to the mathematical model of a robot manipulator in the form of a Lagrange-Euler equation. A learning algorithm based on the backpropagation method is given for a neural model. A numerical example of calculation of a neural model for Puma 560 robot is presented.

Zusammenfassung

Es wird ein neurales Modell für einen Robotermanipulator vorgeschlagen, das dem mathematischen Modell in Form einer Lagrange-Euler-Gleichung ähnelt. Für neurale Modelle wird ein Lernalgorithmus präsentiert, der auf der Backpropagation-Methode basiert, sowie ein numerisches Beispiel für die Berechnung eines neuralen Modells für einen Puma 560 Roboter.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Corke, P. I., Armstrong-Hélouvry, B.: A meta study of PUMA 560 dynamics: A critical appraisal of literature data. Robotica 13 (1995), 253–258.

    Article  Google Scholar 

  2. Demuth, H., Beale, M.: Neural network toolbox user’s guide. Nattick: The Math Works, Inc. Massachusetts. 1994.

    Google Scholar 

  3. Elman, J. L.: Finding structure in time. Cognitive Science 14 (1990), pp. 179–211.

    Article  Google Scholar 

  4. Fu, C. S. G., Gonzales, R. C., Lee, C. S. G.: Robotics, control, sensing, vision and intelligence. New York: McGraw-Hill. 1987.

    Google Scholar 

  5. Hertz, J., Krogh, A., Palmer, R. G.: Introduction to the theory of neural computation. Reading, USA: Addison-Wesley. 1991.

    Google Scholar 

  6. Korbicz, J., Obuchowski, A., Ucinski, D.: Sztuczne Sieci Neuronowe — Podstawy i Zastosowania, Akademicka Oficyna Wyd. PLJ. Warszawa, Poland. 1994 (in Polish).

  7. Kurek, J. E.: Introduction to neural network, internal report. Grupo de Visión y Robotica, Universidad de Murcia, Cartagena (Murcia), Spain. 1997.

  8. Kurek, J. E., Balibrea, L. M., Iterative learning control of Puma 560 robot. 3rd Conference on Mechatronics Mechatronika ’97, Warsaw, Poland. 1997 (in Polish).

  9. Kurek, J. E.: Neural net model of robot manipulator. Proceedings Neural Computing NC ’98, Vienna, Austria, 1998, pp. 778–783.

  10. Marichal, G. N., Acosta, L., Moreno, L., Hamilton, A., Méndez, J. A.: An approach to the Inverse Kinematics of a redundant planar arm by dynamic Neural Networks. Proceedings Neural Computing NC ’98. Vienna, Austria, 1998, pp. 772–777.

  11. Zurada, J.: Introduction to Artificial Neural Systems. West Publishing Company. 1992.

Download references

Author information

Authors and Affiliations

  1. Instytut Automatyki i Robotyki, Politechnika Warszawska, ul. Chodkiewicza 8, PL-02-525, Warszawa, Poland

    J. E. Kurek

Authors
  1. J. E. Kurek
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Kurek, J.E. Calculation of a robot manipulator model in the form of arecurrent neural net. Elektrotech. Inftech. 116, 354–359 (1999). https://doi.org/10.1007/BF03159195

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF03159195

Keywords

Search

Navigation