Bayesian Quadrature in Nonlinear Filtering

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F15%3A43925657" target="_blank" >RIV/49777513:23520/15:43925657 - isvavai.cz</a>

Výsledek na webu

<a href="http://www.scitepress.org/portal/PublicationsDetail.aspx?ID=oZ3U7lm9GNY%3d&t=1" target="_blank" >http://www.scitepress.org/portal/PublicationsDetail.aspx?ID=oZ3U7lm9GNY%3d&t=1</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.5220/0005534003800387" target="_blank" >10.5220/0005534003800387</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Bayesian Quadrature in Nonlinear Filtering

Popis výsledku v původním jazyce

The paper deals with the state estimation of nonlinear stochastic discrete-time systems by means of quadrature- based filtering algorithms. The algorithms use quadrature to approximate the moments given by integrals. The aim is at evaluation of the integral by Bayesian quadrature. The Bayesian quadrature perceives the integral itself as a random variable, on which inference is to be performed by conditioning on the function evaluations. Advantage of this approach is that in addition to the value of the integral, the variance of the integral is also obtained. In this paper, we improve estimation of covariances in quadrature-based filtering algorithms by taking into account the integral variance. The proposed modifications are applied to the Gauss-Hermite Kalman filter and the unscented Kalman filter algorithms. Finally, the performance of the modified filters is compared with the unmodified versions in numerical simulations. The modified versions of the filters exhibit significantly improved estimate credibility and a comparable root-mean-square error.

Název v anglickém jazyce

Bayesian Quadrature in Nonlinear Filtering

Popis výsledku anglicky

The paper deals with the state estimation of nonlinear stochastic discrete-time systems by means of quadrature- based filtering algorithms. The algorithms use quadrature to approximate the moments given by integrals. The aim is at evaluation of the integral by Bayesian quadrature. The Bayesian quadrature perceives the integral itself as a random variable, on which inference is to be performed by conditioning on the function evaluations. Advantage of this approach is that in addition to the value of the integral, the variance of the integral is also obtained. In this paper, we improve estimation of covariances in quadrature-based filtering algorithms by taking into account the integral variance. The proposed modifications are applied to the Gauss-Hermite Kalman filter and the unscented Kalman filter algorithms. Finally, the performance of the modified filters is compared with the unmodified versions in numerical simulations. The modified versions of the filters exhibit significantly improved estimate credibility and a comparable root-mean-square error.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

<a href="/cs/project/GC13-07058J" target="_blank" >GC13-07058J: Konzervativní fúze v systémech odhadu propojených v síti</a><br>

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2015

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 12th International Conference on Informatics in Control, Automation and Robotics (ICINCO)

ISBN

978-989-758-122-9

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

380-387

Název nakladatele

SCITEPRESS

Místo vydání

Colmar

Místo konání akce

Colmar, Francie

Datum konání akce

21. 7. 2015

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000381618600052