Nonlinear Filtering with Transfer Operator

Abstract : This paper presents a new nonlinear filtering algorithm that is shown to outperform state-of-the-art particle filters with resampling. Starting from the Itˆo stochastic differential equation, the proposed algorithm harnesses Karhunen- Lo'eve expansion to derive an approximate non-autonomous dynamical system, for which transfer operator based density computation can be performed in exact arithmetic. It is proved that the algorithm is asymptotically consistent in mean-square sense. Numerical results demonstrate that explicitly accounting prior dynamics entail significant performance improvement for nonlinear non-Gaussian estimation problems with infrequent measurement updates, as compared to the performance of particle filters.
Complete list of metadatas

Cited literature [26 references]  Display  Hide  Download

https://hal.inria.fr/hal-00785159
Contributor : Parikshit Dutta <>
Submitted on : Tuesday, February 5, 2013 - 3:04:48 PM
Last modification on : Wednesday, April 11, 2018 - 1:59:16 AM
Long-term archiving on : Monday, June 17, 2013 - 7:26:10 PM

File

KLPFfilterACC2013Final.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Parikshit Dutta, Abhishek Halder, Raktim Bhattacharya. Nonlinear Filtering with Transfer Operator. IEEE American Control Conference, Jun 2013, Washington, D.C., United States. pp.3069-3074, ⟨10.1109/ACC.2013.6580302⟩. ⟨hal-00785159⟩

Share

Metrics

Record views

545

Files downloads

464