liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Dynamically Iterated Filters: A Unified Framework for Improved Iterated Filtering via Smoothing
Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0002-0572-2665
Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0001-9183-3427
Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, Faculty of Science & Engineering.
Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, The Institute of Technology. Linköping University, Faculty of Science & Engineering. Linköping University. (Automatic Control)ORCID iD: 0000-0002-1971-4295
2025 (English)In: Journal of Advances in Information Fusion, ISSN 1557-6418, Vol. 20, no 1, p. 8-81Article in journal (Refereed) Published
Abstract [en]

Typical iterated filters, such as the iterated extended Kalman filter (IEKF), KF (IUKF), and , have been developed to improve the linearization point (or density) ofthe likelihood linearization in the well-known extended KF (EKF) and unscented KF (UKF). A shortcoming of typical iterated filters is thatthey do not treat the linearization of the transition model of the system. To remedy this shortcoming, we introduce dynamically iterated filters (DIFs), a unified framework for iterated linearization-based nonlinear filters that deals with nonlinearities in both the transition modeland the likelihood, thereby constituting a generalization of the afore mentioned iterated filters. We further establish a relationship between the general DIF and the approximate iterated Rauch–Tung–Striebel smoother. This relationship allows for a Gauss–Newton interpretation, which in turn enables explicit step-size correction, leading to dampedversions of the DIFs. The developed algorithms, both damped and non-damped, are numerically demonstrated in three examples, showing superior mean squared error as well as improved parameter tuning robustness as compared to the analogous standard iterated filters.

Place, publisher, year, edition, pages
2025. Vol. 20, no 1, p. 8-81
Keywords [en]
Estimation; Iterated Kalman Filter; Unscented Transform; Stochastic Linearization; iterated posterior linearization filter (IPLF); WASP_publications
National Category
Signal Processing Control Engineering Probability Theory and Statistics
Identifiers
URN: urn:nbn:se:liu:diva-219281OAI: oai:DiVA.org:liu-219281DiVA, id: diva2:2011495
Projects
WASP
Funder
Wallenberg AI, Autonomous Systems and Software Program (WASP)Available from: 2025-11-04 Created: 2025-11-04 Last updated: 2025-11-21

Open Access in DiVA

No full text in DiVA

Other links

Journal entryArticle

Authority records

Kullberg, AntonSkoglund, MartinSkog, Isaac

Search in DiVA

By author/editor
Kullberg, AntonSkoglund, MartinSkog, IsaacHendeby, Gustaf
By organisation
Automatic ControlFaculty of Science & EngineeringThe Institute of Technology
In the same journal
Journal of Advances in Information Fusion
Signal ProcessingControl EngineeringProbability Theory and Statistics

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 83 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf