Detail publikačního výsledku

Bayesian Knowledge Transfer for a Kalman Fixed-Lag Interval Smoother

SKALSKÝ, O.; DOKOUPIL, J.

Originální název

Bayesian Knowledge Transfer for a Kalman Fixed-Lag Interval Smoother

Anglický název

Bayesian Knowledge Transfer for a Kalman Fixed-Lag Interval Smoother

Druh

Článek WoS

Originální abstrakt

A Bayesian knowledge transfer mechanism that leverages external information to improve the performance of the Kalman fixed-lag interval smoother (FLIS) is proposed. Exact knowledge of the external observation model is assumed to be missing, which hinders the direct application of Bayes' rule in traditional transfer learning approaches. This limitation is overcome by the fully probabilistic design, conditioning the targeted task of state estimation on external information. To mitigate the negative impact of inaccurate external data while leveraging precise information, a latent variable is introduced. Favorably, in contrast to a filter, FLIS retrospectively refines past decisions up to a fixed time horizon, reducing the accumulation of estimation error and consequently improving the performance of state inference. Simulations indicate that the proposed algorithm better exploits precise external knowledge compared to a similar technique and achieves comparable results when the information is imprecise.

Anglický abstrakt

A Bayesian knowledge transfer mechanism that leverages external information to improve the performance of the Kalman fixed-lag interval smoother (FLIS) is proposed. Exact knowledge of the external observation model is assumed to be missing, which hinders the direct application of Bayes' rule in traditional transfer learning approaches. This limitation is overcome by the fully probabilistic design, conditioning the targeted task of state estimation on external information. To mitigate the negative impact of inaccurate external data while leveraging precise information, a latent variable is introduced. Favorably, in contrast to a filter, FLIS retrospectively refines past decisions up to a fixed time horizon, reducing the accumulation of estimation error and consequently improving the performance of state inference. Simulations indicate that the proposed algorithm better exploits precise external knowledge compared to a similar technique and achieves comparable results when the information is imprecise.

Klíčová slova

Bayesian knowledge transfer, fixed-lag interval smoothing, state estimation, fully probabilistic design

Klíčová slova v angličtině

Bayesian knowledge transfer, fixed-lag interval smoothing, state estimation, fully probabilistic design

Autoři

SKALSKÝ, O.; DOKOUPIL, J.

Vydáno

16.06.2025

Nakladatel

IEEE

Periodikum

IEEE Control Systems Letters

Svazek

9

Číslo

1

Stát

Spojené státy americké

Strany od

2037

Strany do

2042

Strany počet

6

URL

https://ieeexplore.ieee.org/document/11036741

Plný text v Digitální knihovně

http://hdl.handle.net/11012/256248

BibTex

@article{BUT199372,
  author="Ondřej {Skalský} and Jakub {Dokoupil}",
  title="Bayesian Knowledge Transfer for a Kalman Fixed-Lag Interval Smoother",
  journal="IEEE Control Systems Letters",
  year="2025",
  volume="9",
  number="1",
  pages="2037--2042",
  doi="10.1109/LCSYS.2025.3580047",
  url="https://ieeexplore.ieee.org/document/11036741"
}