State estimation using an approximate reduced statistics algorithm

Author

Iltis, Ronald A.

Author_Institution

California Univ., Santa Barbara, CA, USA

Volume

35

Issue

4

fYear

1999

fDate

10/1/1999 12:00:00 AM

Firstpage

1161

Lastpage

1172

Abstract

The problem of state estimation using nonlinear additive Gaussian noise measurements is addressed. A geometric model for the posterior state density is assumed based on a multidimensional Haar basis representation. An approximate reduced statistics (ARS) algorithm, suggested by the parameter estimator of Kulhavy is then developed, using successive minimization of relative entropy between model densities and an approximate posterior density. The state estimator thus derived is applied to a bearings-only target tracking problem in a multiple sensor scenario

Keywords

Gaussian noise; Haar transforms; entropy; parameter estimation; state estimation; target tracking; Kulhavy estimator; geometric model; model densities; multidimensional Haar basis representation; nonlinear additive Gaussian noise measurements; parameter estimator; posterior state density; reduced statistics algorithm; relative entropy; state estimation; successive minimization; target tracking problem; Additive noise; Entropy; Gaussian noise; Minimization methods; Multidimensional systems; Noise measurement; Parameter estimation; Solid modeling; State estimation; Statistics;

fLanguage

English

Journal_Title

Aerospace and Electronic Systems, IEEE Transactions on

Publisher

ieee

ISSN

0018-9251

Type

jour

DOI

10.1109/7.805434

Filename

805434