ADAPTIVE CONTROL SYSTEM OF QUADROTOR

S.H. Zabihafar
Bauman Moscow State Technical University, Postgraduate Student, 5-1, 2-ya Baumanskaya ul., Moscow, 105005, Russia, tel.: +7(499)165-17-01, This email address is being protected from spambots. You need JavaScript enabled to view it.

K.R. Lebedev
Bauman Moscow State Technical University, Student, 5-1, 2-ya Baumanskaya ul., Moscow, 105005, Russia, tel.: +7(499)165-17-01, This email address is being protected from spambots. You need JavaScript enabled to view it.

A.S. Yuschenko
Doctor of Technical Science, Bauman Moscow State Technical University, Professor, Head of Сhair, 5-1, 2-ya Baumanskaya ul., Moscow, 105005, Russia, tel.: +7(499)263-63-91, This email address is being protected from spambots. You need JavaScript enabled to view it., This email address is being protected from spambots. You need JavaScript enabled to view it.

Received 5 November 2017.

Abstract
This paper proposes to solve the problem of controlling such a complex dynamical object as a quadrotor by using an adaptive neural network controller. This method enables to control the system without a priori information on parameters of a controlled object dynamic model. Controller provides the system motion in vicinity of sliding surface that in turn ensures its invariance to external disturbance including wind pressure. The pecularity of this control method is use of the adaptive algorithm of neural network tuning during network operation.
The proposed control method achieves good results; it is proved through the simulation of a neural network controller and a dynamic quadrotor model in the MATLAB environment.

Key words
Quadrotor, nonlinear control, sliding-mode, adaptive neural network.

Bibliographic description 
Zabihafar, S., Lebedev, K. and Yuschenko, A. (2017). Adaptive control system of quadrotor. Robotics and Technical Cybernetics, 4(17), pp.41-46.

UDC identifier
62-503.57

References

1. Bouabdalla, S., Noth, A. and Siegwart, R. (2004). PID vs LQ control techniques applied to an indoor micro quadrotor. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), vol. 3. pp.2451-2456.
2. Naidoo, Y., Stopforth, R. and Bright, G. (2011). Helicopter Modelling and Control. Int Jоurnal of Advanced Robotic Systems, [online] 8(4), pp.139-149. Available at: http://cdn.intechopen.com [Accessed 1 Nov. 2017].
3. Aissaoui, A., Abid, H. and Abid, M. (2009). Robust Fuzzy Sliding Mode Controller Design for Motor Driver. Acta Electrotechnica et Informatica, [online] 9(2), pp.64-71. Available at: http://www.aei.tuke.sk/papers/2009/2/10_Aissaoui.pdf [Accessed 1 Nov. 2017].
4. Hung, L.-C. and Chung, H.-Y. (2005). Hybrid Neural Sliding Mode Controller Design for a Robot Manipulator. The Journal of Grey System, 17(2), pp.183-200.
5. Zabikhifar, S., Markasi, A. and Yuschenko, A. (2015). Two Link Manipulator Control Using Fuzzy Sliding Mode Approach. Herald of the Bauman Moscow State Technical University. Series Instrument Engineering, 6, pp.30-45.
6. Bouhali, O. and Boudjedir, H. (2011). Neural Network Control with Neuro-sliding Mode Observer Applied to Quadrotor Helicopter. In: The International Symposium on Innovations in Intelligent Systems and Applications (INISTA'11). pp.24-28.
7. Jagannathan, S., Yesildirak, A. and Lewis, F. (1998). Neural Network Control of Robot Manipulators and Non-Linear Systems. London, England: Taylor & Francis Publ., p.468.
8. Ge, S., Hang, C., Lee, T. and Zhang, T. (2002). Stable adaptive neural network control. Boston, England: Kluwer Academic, p.296.