Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

(Semi-)analytic Gaussian mixture filter

: Huber, Marco F.; Beutler, Frederik; Hanebeck, Uwe D.

Preprint urn:nbn:de:0011-n-1848526 (556 KByte PDF)
MD5 Fingerprint: 6fcb1e7182e725465049d42b1acd076e
Erstellt am: 12.11.2011

Bittanti, S. ; International Federation of Automatic Control -IFAC-:
18th World Congress of the International Federation of Automatic Control 2011. Proceedings : Milano (Italy), August 28 - September 2, 2011
Braunschweig: IFAC, 2011
ISBN: 978-3-902661-93-7
International Federation of Automatic Control (World Congress) <18, 2011, Milano>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IOSB ()
state estimation; nonlinear system; stochastic system; decomposition method

In nonlinear filtering, special types of Gaussian mixture filters are a straightforward extension of Gaussian filters, where linearizing the system model is performed individually for each Gaussian component. In this paper, two novel types of linearization are combined with Gaussian mixture filters. The first linearization is called analytic stochastic linearization, where the linearization is performed analytically and exactly, i.e., without Taylor-series expansion or approximate sample-based density representation. In cases where a full analytical linearization is not possible, the second approach decomposes the nonlinear system into a set of nonlinear subsystems that are conditionally integrable in closed form. These approaches are more accurate than fully applying classical linearization.