Sigma-Point Filtering for Nonlinear Systems with Non-Additive Heavy-Tailed Noise

Filip Tronarp, Roland Hostettler, Simo Särkkä

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

23 Citations (Scopus)
68 Downloads (Pure)


This paper is concerned with sigma-point methods for filtering in nonlinear systems, where the process and measurement noise are heavy tailed and enter the system nonadditively. The problem is approached within the framework of assumed density filtering and the necessary statistics are approximated using sigma-point methods developed for Student’s t-distribution. This leads to UKF/CKF-type of filters for Student’s t-distribution. Four different sigma-point methods are considered that compute exact expectations of polynomials for orders up to 3, 5, 7, and 9, respectively. The resulting algorithms are evaluated in a simulation example and real data from a pedestrian
dead-reckoning experiment. In the simulation experiment the nonlinear Student’s t filters are found to be faster in suppressing large errors in the state estimates in comparison to the UKF when filtering in nonlinear Gaussian systems with outliers in process and measurement noise. In the pedestrian dead-reckoning experiment the sigma-point Student’s t filter was found to yield better loop closure and path length estimates as well as significantly improved robustness towards extreme accelerometer measurement spikes.
Original languageEnglish
Title of host publicationProceedings of the 19th International Conference on Information Fusion, FUSION 2016
Pages1859 - 1866
ISBN (Electronic)978-0-9964527-4-8
Publication statusPublished - 5 Jul 2016
MoE publication typeA4 Article in a conference publication
EventInternational Conference on Information Fusion - Heidelberg, Germany
Duration: 5 Jul 20168 Jul 2016
Conference number: 19


ConferenceInternational Conference on Information Fusion
Abbreviated titleFUSION
Internet address

Fingerprint Dive into the research topics of 'Sigma-Point Filtering for Nonlinear Systems with Non-Additive Heavy-Tailed Noise'. Together they form a unique fingerprint.

Cite this