Přístupnostní navigace
E-application
Search Search Close
Publication detail
DOKOUPIL, J. VÁCLAVEK, P.
Original Title
Adaptive fading Kalman filter design using the geometric mean of normal probability densities
Type
conference paper
Language
English
Original Abstract
The paper extends the Kalman filter to operate with the potential process model uncertainty by relying on the use of a variable fading factor. A loss functional evaluating the prediction step of the Kalman filter is constructed based on Bayesian decision-making. This evaluation results in coupling two normal probability density functions (pdfs), defining a lower and upper bound for a state uncertainty increase. The coupling policy is identical with the geometric mean of pdfs weighted by adaptively adjusted probabilities. In this respect, the fading factor is optimally determined by being treated as a probability assigned to the more conservative pdf. The proposed schema corrects state filtering in the presence of model uncertainty through controlling the Kalman gain matrix in response to observed performance.
Keywords
Kalman filter; fading factor; Kullback-Leibler divergence; Normal distribution
Authors
DOKOUPIL, J.; VÁCLAVEK, P.
Released
16. 8. 2018
Publisher
IEEE
ISBN
978-1-5386-5428-6
Book
2018 Annual American Control Conference
Pages from
5037
Pages to
5042
Pages count
6
URL
https://ieeexplore.ieee.org/document/8431008
BibTex
@inproceedings{BUT150466, author="Jakub {Dokoupil} and Pavel {Václavek}", title="Adaptive fading Kalman filter design using the geometric mean of normal probability densities", booktitle="2018 Annual American Control Conference", year="2018", pages="5037--5042", publisher="IEEE", doi="10.23919/ACC.2018.8431008", isbn="978-1-5386-5428-6", url="https://ieeexplore.ieee.org/document/8431008" }