Sensitivity of discrete-time Kalman filter to statistical modeling errors

The optimum filtering results of Kalman filtering for linear dynamic systems require an exact knowledge of the process noise covariance matrix Qk, the measurement noise covariance matrix Rk and the initial error covariance matrix P0. In a number of practical solutions, Qk, Rk and P0, are either unkn...

Full description

Saved in:
Bibliographic Details
Main Author: Saab, Samer S. (author)
Other Authors: Nasr, George E. (author)
Format: article
Published: 1999
Online Access:http://hdl.handle.net/10725/3163
http://dx.doi.org/10.1002/(SICI)1099-1514(199909/10)20:5<249::AID-OCA659>3.0.CO;2-2
https://onlinelibrary.wiley.com/doi/abs/10.1002/(SICI)1099-1514(199909/10)20:5%3C249::AID-OCA659%3E3.0.CO;2-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513460172226560
author Saab, Samer S.
author2 Nasr, George E.
author2_role author
author_facet Saab, Samer S.
Nasr, George E.
author_role author
dc.creator.none.fl_str_mv Saab, Samer S.
Nasr, George E.
dc.date.none.fl_str_mv 1999
2016-02-23T09:05:19Z
2016-02-23T09:05:19Z
2016-02-23
dc.identifier.none.fl_str_mv 0143-2087
http://hdl.handle.net/10725/3163
http://dx.doi.org/10.1002/(SICI)1099-1514(199909/10)20:5<249::AID-OCA659>3.0.CO;2-2
Saab, S. S., & Nasr, G. E. (1999). Sensitivity of discrete‐time Kalman filter to statistical modeling errors. Optimal Control Applications and Methods, 20(5), 249-259.
https://onlinelibrary.wiley.com/doi/abs/10.1002/(SICI)1099-1514(199909/10)20:5%3C249::AID-OCA659%3E3.0.CO;2-2
dc.language.none.fl_str_mv en
dc.relation.none.fl_str_mv Optimal Control Applications and Methods
dc.rights.*.fl_str_mv info:eu-repo/semantics/openAccess
dc.title.none.fl_str_mv Sensitivity of discrete-time Kalman filter to statistical modeling errors
dc.type.none.fl_str_mv Article
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description The optimum filtering results of Kalman filtering for linear dynamic systems require an exact knowledge of the process noise covariance matrix Qk, the measurement noise covariance matrix Rk and the initial error covariance matrix P0. In a number of practical solutions, Qk, Rk and P0, are either unknown or are known only approximately. In this paper the sensitivity due to a class of errors in statistical modelling employing a Kalman Filter is discussed. In particular, we present a special case where it is shown that Kalman filter gains can be insensitive to scaling of covariance matrices. Some basic results are derived to describe the mutual relations among the three covariance matrices (actual and perturbed covariance matrices), their respective Kalman gain Kk and the error covariance matrices Pk. It is also shown that system modelling errors, particularly scaling errors of the input matrix, do not perturb the Kalman gain. A numerical example is presented to illustrate the theoretical results, and also to show the Kalman gain insensitivity to less restrictive statistical uncertainties in an approximate sense.
eu_rights_str_mv openAccess
format article
id LAURepo_b8dffe0197c6366f13df0a53787e5643
identifier_str_mv 0143-2087
Saab, S. S., & Nasr, G. E. (1999). Sensitivity of discrete‐time Kalman filter to statistical modeling errors. Optimal Control Applications and Methods, 20(5), 249-259.
language_invalid_str_mv en
network_acronym_str LAURepo
network_name_str Lebanese American University repository
oai_identifier_str oai:laur.lau.edu.lb:10725/3163
publishDate 1999
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Sensitivity of discrete-time Kalman filter to statistical modeling errorsSaab, Samer S.Nasr, George E.The optimum filtering results of Kalman filtering for linear dynamic systems require an exact knowledge of the process noise covariance matrix Qk, the measurement noise covariance matrix Rk and the initial error covariance matrix P0. In a number of practical solutions, Qk, Rk and P0, are either unknown or are known only approximately. In this paper the sensitivity due to a class of errors in statistical modelling employing a Kalman Filter is discussed. In particular, we present a special case where it is shown that Kalman filter gains can be insensitive to scaling of covariance matrices. Some basic results are derived to describe the mutual relations among the three covariance matrices (actual and perturbed covariance matrices), their respective Kalman gain Kk and the error covariance matrices Pk. It is also shown that system modelling errors, particularly scaling errors of the input matrix, do not perturb the Kalman gain. A numerical example is presented to illustrate the theoretical results, and also to show the Kalman gain insensitivity to less restrictive statistical uncertainties in an approximate sense.PublishedN/A2016-02-23T09:05:19Z2016-02-23T09:05:19Z19992016-02-23Articleinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article0143-2087http://hdl.handle.net/10725/3163http://dx.doi.org/10.1002/(SICI)1099-1514(199909/10)20:5<249::AID-OCA659>3.0.CO;2-2Saab, S. S., & Nasr, G. E. (1999). Sensitivity of discrete‐time Kalman filter to statistical modeling errors. Optimal Control Applications and Methods, 20(5), 249-259.https://onlinelibrary.wiley.com/doi/abs/10.1002/(SICI)1099-1514(199909/10)20:5%3C249::AID-OCA659%3E3.0.CO;2-2enOptimal Control Applications and Methodsinfo:eu-repo/semantics/openAccessoai:laur.lau.edu.lb:10725/31632019-07-25T10:10:59Z
spellingShingle Sensitivity of discrete-time Kalman filter to statistical modeling errors
Saab, Samer S.
status_str publishedVersion
title Sensitivity of discrete-time Kalman filter to statistical modeling errors
title_full Sensitivity of discrete-time Kalman filter to statistical modeling errors
title_fullStr Sensitivity of discrete-time Kalman filter to statistical modeling errors
title_full_unstemmed Sensitivity of discrete-time Kalman filter to statistical modeling errors
title_short Sensitivity of discrete-time Kalman filter to statistical modeling errors
title_sort Sensitivity of discrete-time Kalman filter to statistical modeling errors
url http://hdl.handle.net/10725/3163
http://dx.doi.org/10.1002/(SICI)1099-1514(199909/10)20:5<249::AID-OCA659>3.0.CO;2-2
https://onlinelibrary.wiley.com/doi/abs/10.1002/(SICI)1099-1514(199909/10)20:5%3C249::AID-OCA659%3E3.0.CO;2-2