Abstract
We consider the one-step prediction problem for discrete-time linear systems in correlated plant and observation noises, and non-Gaussian initial conditions. Explicit representations are obtained for the MMSE and LMMSE (or Kalman) estimates of the state given past observations, as well as for the expected square of their difference. These formulae are obtained with the help of the Girsanov transformation for Gaussian white noise sequences, and display explicitly the dependence of the quantities of interest on the initial distribution. With the help of these formulae, we completely characterize the asymptotic behavior of the error sequence in the scalar time-invariant case.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
P. Caines and D. Mayne, “On the discrete-time Ricatti equation of optimal control,” Inter. J. of Control 12, pp. 785 - 794 (1970)
P. Caines and D. Mayne, “On the discrete-time Ricatti equation of optimal control,” Inter. J. of Control 14, pp. 205 - 207 (1971).
G. DiMasi and W. Runggaldier, “On measure transformations for combined filtering and parameter estimation in discrete time,” Systems E4 Control Letters 2, pp. 57 - 62 (1982).
A. M. Makowski, “Filtering formulae for partially observed linear systems with non-Gaussian initial conditions,” Stochastics 16, pp. 1 - 24 (1986).
R. B. Sowers, New Results in Discrete-Time Nonlinear Filtering, M.S. Thesis, Electrical Engineering Department, University of Maryland, College Park (MD), August 1988.
R.B. Sowers and A.M. Makowski, “Discrete-time filtering for linear systems in correlated noise with non-Gaussian initial conditions,” Proceedings of the Conference on Information Sciences and Systems, The Johns Hopkins University, Baltimore (MD ), March 1989.
R. B. Sowers and A.M. Makowski, “Filtering for discrete-time linear systems with non-Gaussian initial conditions: Asymptotic behavior of the difference between the MMSE and LMSE estimates,” submitted to IEEE Transactions on Automatic Control(1989).
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1990 Birkhäuser Boston
About this chapter
Cite this chapter
Sowers, R.B., Makowski, A.M. (1990). Discrete-Time Filtering for Linear Systems in Correlated Noise with Non-Gaussian Initial Conditions: Formulas and Asymptotics. In: Kaashoek, M.A., van Schuppen, J.H., Ran, A.C.M. (eds) Robust Control of Linear Systems and Nonlinear Control. Progress in Systems and Control Theory, vol 4. Birkhäuser Boston. https://doi.org/10.1007/978-1-4612-4484-4_39
Download citation
DOI: https://doi.org/10.1007/978-1-4612-4484-4_39
Publisher Name: Birkhäuser Boston
Print ISBN: 978-1-4612-8839-8
Online ISBN: 978-1-4612-4484-4
eBook Packages: Springer Book Archive