Verification of Multilayer Neural-Net Controller in Manipulator Tracking Control

Abstract:

In this paper a multilayer neural-net (NN) controller is applied for tracking control of robotic manipulator, which is a nonlinear object having unknown and changeable parameters. Dynamics equations of a rigid manipulator are presented. The NN controller is used for compensating manipulator nonlinearities. The controller is realized in a form of a multilayer NN, which is nonlinear in the weights. The standard delta rule using backpropagation tuning is inadequate, so a term correcting the delta rule as well as a robustifying term is added. The presented control law and tuning algorithm are derived from the Lyapunov’s direct method. Results of the experiment are presented in this paper.

• Periodical: Solid State Phenomena (Volume 164)
• Pages: 99-104
• DOI: https://doi.org/10.4028/www.scientific.net/SSP.164.99
• Online since: June 2010
• Authors: Wiesław Żylski, Piotr Gierlak
• Keywords: Control System, Lyapunov Stability, Neural Network (NN), Robotic Manipulator

References

[1] C. Canudas de Wit, B. Siciliano and G. Bastin: Theory of robot control, Springer-Verlag, London (1996).

[2] M.J. Giergiel, Z. Hendzel and W. Żylski: Modelling and control of wheeled mobile robots, PWN, Warsaw (2002) (in Polish).

[3] J. Giergiel, Z. Hendzel, W. Żylski and M. Trojnacki: An application of artificial intelligence methods in mechatronic designing of wheeled mobile robots. Monographs on KRiDM AGH, Krakow (2004) (in Polish).

[4] P. Gierlak: Adaptive control of manipulator, Proc. of InterTech Int. Interdysc. Tech. Conf. Young Scient. USDPP, Poznan (2009), p.143.

[5] A. Isidori: �onlinear control system: An introduction, Springer-Verlag, Berlin (1985).

[6] J.J. Slotine and W. Li: Applied of robot control, Prentice Hall, New Jersey (1991).

[7] M.W. Spong and M. Vidyasagar: Robots dynamics and control, WNT, Warsaw (1997) (in Polish).

[8] P. Gierlak and W. Żylski: Tracking control of manipulator, Proc. of XIV MMAR, Miedzyzdroje (2009).

[9] K.J. Hunt, D. Sbarbaro, R. Żbikowski and P.J. Gawthrop: �eural networks for control systemsA survey, Automatica, Vol. 28 (1992), p.1083.

DOI: 10.1016/0005-1098(92)90053-i

[10] J. Korbicz, A. Obuchowicz and D. Uciński: Artificial neural networks. Basis and applications. AOW PLJ, Warsaw (1994) (in Polish).

[11] B. Kosko: �eural networks and fuzzy systems, Prentince Hall, Englewood Cliffs (1992).

[12] F.L. Lewis, K. Liu and A. Yesildirek: �eural-�et robot controller with guaranteed tracking performance, IEEE Transaction on Neural Networks, Vol. 6 (1995), p.703.

DOI: 10.1109/72.377975

[13] F.L. Lewis, A. Yesildirek and K. Liu: Multilayer �eural-�et robot controller with guaranteed tracking performance, IEEE Transaction on Neural Networks, Vol. 7 (1996), p.388.

DOI: 10.1109/72.485674

[14] A.M.S. Zalzala and A.S. Morris: �eural networks for robotic control, Ellis Horwood (1996).

[15] K. Hornik, M. Stinchombe and H. White: Multilayer feedforward networks are universal approximators. Neural Networks, Vol. 2 (1989), p.359.

DOI: 10.1016/0893-6080(89)90020-8

[16] K. Hornik: Approximation capabilities of multilayer feedforward networks. Neural Networks, Vol. 4 (1991), p.251.

DOI: 10.1016/0893-6080(91)90009-t

[17] D. Rutkowska, M. Piliński and L. Rutkowski: �eural networks, genetic algorithms, and fuzzy systems. PWN, Warsaw (1997) (in Polish).

[18] R. Tadeusiewicz: �eural networks, AOW, Warsaw (1993).