Dirac Mixture Approximation for Nonlinear Stochastic Filtering

  • Oliver C. Schrempf
  • Uwe D. Hanebeck
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 24)


This work presents a filter for estimating the state of nonlinear dynamic systems. It is based on optimal recursive approximation the state densities by means of Dirac mixture functions in order to allow for a closed form solution of the prediction and filter step. The approximation approach is based on a systematic minimization of a distance measure and is hence optimal and deterministic. In contrast to non-deterministic methods we are able to determine the optimal number of components in the Dirac mixture. A further benefit of the proposed approach is the consideration of measurements during the approximation process in order to avoid parameter degradation.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Huber, M., Brunn, D., Hanebeck, U.D.: Closed-Form Prediction of Nonlinear Dynamic Systems by Means of Gaussian Mixture Approximation of the Transition Density. In: International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI 2006), Heidelberg, Deutschland. (2006) 98–103Google Scholar
  2. 2.
    Doucet, A., Freitas, N.D., Gordon, N.: Sequential Monte Carlo Methods in Practice. Springer-Verlag, New York (2001)zbMATHGoogle Scholar
  3. 3.
    Geweke, J.: Bayesian Inference in Econometric Models using Monte Carlo Integration. Econometrica 24 (1989) 1317–1399CrossRefMathSciNetGoogle Scholar
  4. 4.
    Gordon, N.: Bayesian Methods for Tracking. PhD thesis, University of London (1993)Google Scholar
  5. 5.
    Julier, S., Uhlmann, J.: A New Extension of the Kalman Filter to Nonlinear Systems. In: Proceedings of SPIE AeroSense, 11th International Symposium on Aerospace/Defense Sensing, Simulation, and Controls, Orlando, FL. (1997)Google Scholar
  6. 6.
    Alspach, D.L., Sorenson, H.W.: Nonlinear Bayesian Estimation Using Gaussian Sum Approximation. IEEE Transactions on Automatic Control AC–17 (1972) 439–448CrossRefGoogle Scholar
  7. 7.
    Hanebeck, U.D., Briechle, K., Rauh, A.: Progressive Bayes: A New Framework for Nonlinear State Estimation. In: Proceedings of SPIE. Volume 5099., Orlando, Florida (2003) 256–267 AeroSense Symposium.Google Scholar
  8. 8.
    Schrempf, O.C., Brunn, D., Hanebeck, U.D.: Dirac Mixture Density Approximation Based on Minimization of the Weighted Cramér–von Mises Distance. In: Proceedings of the International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI 2006), Heidelberg, Germany. (2006) 512–517Google Scholar
  9. 9.
    Schrempf, O.C., Hanebeck, U.D.: Recursive Prediction of Stochastic Nonlinear Systems Based on Dirac Mixture Approximations. In: Proceedings of the American Control Conference (ACC ’07), New York City, USA. (2007)Google Scholar
  10. 10.
    Schrempf, O.C., Hanebeck, U.D.: A State Estimator for Nonlinear Stochastic Systems Based on Dirac Mixture Approximations. In: 4th Intl. Conference on Informatics in Control, Automation and Robotics (ICINCO 2007). Volume SPSMC., Angers, France (2007) 54–61Google Scholar
  11. 11.
    Kullback, S., Leibler, R.A.: On Information and Sufficiency. Annals of Mathematical Statistics 22 (1951) 79–86zbMATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    Boos, D.D.: Minimum Distance Estimators for Location and Goodness of Fit. Journal of the American Statistical association 76 (1981) 663–670zbMATHCrossRefMathSciNetGoogle Scholar
  13. 13.
    Bucy, R.S.: Bayes Theorem and Digital Realizations for Non-Linear Filters. Journal of Astronautical Sciences 17 (1969) 80–94Google Scholar
  14. 14.
    Schrempf, O.C., Brunn, D., Hanebeck, U.D.: Density Approximation Based on Dirac Mixtures with Regard to Nonlinear Estimation and Filtering. In: Proceedings of the 45th IEEE Conference on Decision and Control (CDC’06), San Diego, California, USA. (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Oliver C. Schrempf
    • 1
  • Uwe D. Hanebeck
    • 1
  1. 1.Intelligent Sensor-Actuator-Systems LaboratoryUniversität Karlsruhe (TH)Germany

Personalised recommendations