An alternate algorithm for discrete-time filtering

Author

Zeitz, Frederick H., III ; Maybeck, Peter S.

Author_Institution

Dept. of Electr. & Comput. Eng., Air Force Inst. of Technol., Wright-Patterson AFB, OH, USA

Volume

29

Issue

4

fYear

1993

fDate

10/1/1993 12:00:00 AM

Firstpage

1123

Lastpage

1136

Abstract

The discrete-time Kalman filter is an optimal estimator for the states of a linear, stochastic system. It assumes that measurements are linear combinations of the states, and all disturbances are Gaussian. The influence diagram, a decision analysis tool that provides an algorithm for discrete-time filtering equivalent to the Kalman filter when the influence diagram represents Gaussian random variables, is discussed. The influence diagram algorithm is a factored form of the Kalman filter, similar to other factored forms such as the U-D filter. Compared with the Kalman filter, it offers improved numerical properties. Compared with other factored forms, it offers a reduced computational load

Keywords

Kalman filters; State estimation; diagrams; discrete time systems; filtering and prediction theory; matrix algebra; random noise; state estimation; stochastic systems; Gaussian noise; Kalman filter; decision analysis tool; discrete-time filtering; influence diagram; linear stochastic system; matrix representation; optimal estimator; Algorithm design and analysis; Computer errors; Covariance matrix; Eigenvalues and eigenfunctions; Filtering algorithms; Nonlinear filters; Random variables; Roundoff errors; State estimation; Stochastic systems;

fLanguage

English

Journal_Title

Aerospace and Electronic Systems, IEEE Transactions on

Publisher

ieee

ISSN

0018-9251

Type

jour

DOI

10.1109/7.259516

Filename

259516