A computationally efficient approach for NN based system identification of a rotary wing UAV

  • Mahendra Kumar SamalEmail author
  • Sreenatha Anavatti
  • Tapabrata Ray
  • Matthew Garratt
Regular Papers Control Theory


Neural Network (NN) models based on autoregressive structures have long been used for nonlinear system identification problems. Their application for on-line implementations, however require them to be trained within a prescribed time span, which is often related to the sampling time of the system. In this paper, we introduce a NN model that is embedded with a dimensionality reduction mechanism in order to reduce the size of the network. The dimensionality reduction is based on Principal Component Analysis (PCA) and the resulting smaller NN trains faster. The longitudinal and lateral dynamics of a rotary wing Unmanned Aerial Vehicle (UAV) is modelled using flight test data. The results of system identification, error statistics and training times are provided to highlight the benefits of the proposed approach for NN based system identification models.


Dynamic modelling neural network principal component analysis rotary wing UAV system identification 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    A. Ollero and I. Maza, Multiple Heterogeneous Unmanned Aerial Vehicles, vol. 37 of Springer Tracts in Advanced Robotics, Springer Verlag, Berlin, Heidelberg, 2007.zbMATHGoogle Scholar
  2. [2]
    K. P. Valavanis, Advances in Unmanned Aerial Vehicles: State of the Art and the Road to Autonomy, Springer, 2007.Google Scholar
  3. [3]
    B. Mettler, M. B. Tischler, and T. Kanade, “System identification modelling of a small-scale unmanned rotorcraft for flight control design,” Journal of the American Helicopter Society, pp. 50–63, January 2002.Google Scholar
  4. [4]
    M. K. Samal, S. Anavatti, and M. Garratt, “Neural network based system identification for autonomous flight of an eagle helicopter,” Proc. of the 17th IFAC World Congress, Seoul, Korea, July 2008.Google Scholar
  5. [5]
    R. Jategaonkar, D. Fischenberg, and W. von Gruenhagen, “Aerodynamic modeling and system identification from flight data-recent applications at dlr,” Journal of Aircraft, vol. 41, pp. 681–691, July–August 2004.CrossRefGoogle Scholar
  6. [6]
    G. Chowdhary and R. Jategaonkar, “Aerodynamic parameter estimation from flight data applying extended and unscented Kalman filter,” Proc. of AIAA Atmospheric Flight Mechanics Conference, August 2006.Google Scholar
  7. [7]
    A. Kallapur, S. Ali, and S. Anavatti, “Experiences using emid and ekf for uav online identification,” Proc. of the Third International Conference on Autonomous Robots and Agents, Palmerston North, New Zealand, pp. 207–212, Springer Verlag, December 2006.Google Scholar
  8. [8]
    M. K. Samal, S. Anavatti, and M. Garratt, “Identification of an unmanned helicopter using neural network,” Proc of the 27th IASTED International Conference on Modelling, Identification, and Control, Innsbruck, Austria, February 2008.Google Scholar
  9. [9]
    M. K. Samal, S. Anavatti, and M. Garratt, “Identification of a flexible aircraft using neural network,” Proc. of the 27th IASTED International Conference on Modelling, Identification, and Control, Innsbruck, Austria, February 2008.Google Scholar
  10. [10]
    M. Norgaard, O. Ravn, N. K. Poulsen, and L. Hansen, Neural Networks for Modeling and Control of Dynamic Systems A Practitioner’s Handbook, Springer-Verlag London Limited, 2000.Google Scholar
  11. [11]
    V. R. Puttige and D. S. G. Anavatti, “Real-time neural network based online identification technique for a UAV platform,” Proc. of International Conference on Computational Intelligence for Modeling Control Application, 2006.Google Scholar
  12. [12]
    L. Ljung, System Identification: Theory for the User, Prentice-Hall, Inc., Englewood Cliffs, New Jersey, 1987.zbMATHGoogle Scholar
  13. [13]
    K. S. Narendra and K. Parthasarathy, “Identification and control of dynamic systems using neural network,” IEEE Trans. on Neural Networks, vol. 1, pp. 4–27, March 1990.CrossRefGoogle Scholar
  14. [14]
    S. Haykin, Neural Networks: A Comprehensive Foundation, Macmillan College Publishing Company, 1994.Google Scholar
  15. [15]
    G. H. Dunteman, Principal Components Analysis, SAGE, 1989.Google Scholar
  16. [16]
    M. A. Garratt, Biologically Inspired Vision and Control for an Autonomous Flying Vehicle, Ph.D. Thesis, The Australian National University, October 2007.Google Scholar
  17. [17]
    B. Mettler, Identification Modeling and Characteristics of Miniature Rotorcraft, Springer, 2002.Google Scholar
  18. [18]
    R. C. Nelson, Flight Stability and Automatic Control, McGraw-Hill, 1997.Google Scholar

Copyright information

© Institute of Control, Robotics and Systems and The Korean Institute of Electrical Engineers and Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Mahendra Kumar Samal
    • 1
    Email author
  • Sreenatha Anavatti
    • 1
  • Tapabrata Ray
    • 1
  • Matthew Garratt
    • 1
  1. 1.School of Engineering and Information Technology, Australian Defence Force AcademyUniversity of New South Wales, UNSW@ADFACanberraAustralia

Personalised recommendations