KIT | KIT-Bibliothek | Impressum | Datenschutz

Closed-Form Prediction of Nonlinear Dynamic Systems by Means of Gaussian Mixture Approximation of the Transition Density

Huber, Marco; Brunn, Dietrich; Hanebeck, Uwe D.


Recursive prediction of the state of a nonlinear stochastic dynamic system cannot be efficiently performed in general, since the complexity of the probability density function characterizing the system state increases with every prediction step. Thus, representing the density in an exact closed-form manner is too complex or even impossible. So, an appropriate approximation of the density is required. Instead of directly approximating the predicted density, we propose the approximation of the transition density by means of Gaussian mixtures. We treat the approximation task as an optimization problem that is solved offline via progressive processing to bypass initialization problems and to achieve high quality approximations. Once having calculated the transition density approximation offline, prediction can be performed efficiently resulting in a closed-form density representation with constant complexity.

Volltext §
DOI: 10.5445/IR/1000013962
DOI: 10.1109/MFI.2006.265622
Zitationen: 7
Cover der Publikation
Zugehörige Institution(en) am KIT Fakultät für Informatik – Institut für Anthropomatik (IFA)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2006
Sprache Englisch
Identifikator ISBN: 1-424-40566-1
KITopen-ID: 1000013962
Erschienen in Proceedings / 2006 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, 3 - 6 September 2006, Heidelberg, Germany
Verlag IEEE Service Center
Seiten 98 - 103
Nachgewiesen in Dimensions
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page