Advertisement

State Estimation and Tracking Problems: A Comparison Between Kalman Filter and Recurrent Neural Networks

  • S. Kumar Chenna
  • Yogesh Kr. Jain
  • Himanshu Kapoor
  • Raju S. Bapi
  • N. Yadaiah
  • Atul Negi
  • V. Seshagiri Rao
  • B. L. Deekshatulu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3316)

Abstract

The aim of this paper is to demonstrate the suitability of recurrent neural networks (RNN) for state estimation and tracking problems that are traditionally solved using Kalman Filters (KF). This paper details a simulation study in which the performance of a basic discrete time KF is compared with that of an equivalent neural filter built using an RNN. Real time recurrent learning (RTRL) algorithm is used to train the RNN. The neural network is found to provide comparable performance to that of the KF in both the state estimation and tracking problems. The relative merits and demerits of KF vs RNN are discussed with respect to computational complexity, ease of training and real time issues.

Keywords

Recurrent Neural Network KF Real time recurrent learning Tracking State estimation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Brookner, E.: Tracking and kalman filtering made easy. John Wiley and Sons, Inc, New York (1998)CrossRefGoogle Scholar
  2. 2.
    Pillai, S.K., Seshagiri Rao, V., Balakrishanan, S.S., Sankar, S.: A New Method of Model Compensation in Kalman Filter - Application to Launch Vehicles. In: Proceedings of The Fourteenth International Symposium on Space Technology and Science, Tokyo (1984)Google Scholar
  3. 3.
    Williams, R.J., Zipser, D.: A learning algorithm for continually running fully recurrent neural networks. Neural Computation 1, 270–280 (1989)CrossRefGoogle Scholar
  4. 4.
    Haykin, S.: Neural Networks, 2nd edn. Pearson Eductation, Inc, New Delhi (1999)zbMATHGoogle Scholar
  5. 5.
    Werbos, P.: J. Backpropagation Through Time: What it does and how to do it? In: Proc. of the ICNN, SanFrancisco, CA, USA (1993)Google Scholar
  6. 6.
    DeCruyenaere, J.P., Hafez, H.M.: A comparison between Kalman filters and recurrent neural networks. In: Proc. of the IJCNN, Baltimore, USA, vol. IV, pp. 247–251. IEEE Press, Los Alamitos (1992)Google Scholar
  7. 7.
    Narendra, K.S., Parthasarathy, K.: Identification and control of dynamical systems using neural networks. IEEE Transactions on Neural Networks 1(I), 4–27 (1990)CrossRefGoogle Scholar
  8. 8.
    Puskorius, G.V., Feldkamp, L.A.: Neurocontrol of Nonlinear Dynamical Systems with Kalman Filter Trained Recrrent Networks. IEEE Transactions on Neural Networks 5(2), 279–297 (1994)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • S. Kumar Chenna
    • 1
    • 2
  • Yogesh Kr. Jain
    • 1
  • Himanshu Kapoor
    • 1
  • Raju S. Bapi
    • 1
  • N. Yadaiah
    • 3
  • Atul Negi
    • 1
  • V. Seshagiri Rao
    • 4
  • B. L. Deekshatulu
    • 1
  1. 1.Dept. of Computer and Information SciencesUniversity of HyderabadIndia
  2. 2.Honeywell Technology SolutionsBangalore
  3. 3.Dept. of Electrical EngineeringJNTUHyderabadIndia
  4. 4.SHAR Computer FacilityISROSriharikotaIndia

Personalised recommendations