EUVIMEDEUVIMED entdecken
Crossref

Sparse Kalman Identification for Partially Observable Systems via Adaptive Bayesian Learning

Jilan Mei, Tengjie Zheng, Lin Cheng, Shengping Gong, Xu Huang

Journal of Guidance, Control, and Dynamics · 2026-09 · 49 (9) · 2551-2568

DOI: 10.2514/1.g009696 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Guidance, Control, and Dynamics, 2026-09. Verfasst von Jilan Mei und 4 weiteren Autor:innen. Die Arbeit nennt 54 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Beijing Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sparse dynamics identification is an essential tool for discovering interpretable physical models and enabling efficient control in engineering systems. However, existing methods rely on batch learning with full historical data, limiting their applicability to real-time scenarios involving sequential and partially observable data. To overcome this limitation, this paper proposes an online sparse Kalman identification (SKI) method by integrating the augmented Kalman filter (AKF) and automatic relevance determination. The main contributions are 1) a theoretically grounded Bayesian sparsification scheme that is seamlessly integrated into the AKF framework and adapted to sequentially collected data in online scenarios, 2) an update mechanism that adapts the Kalman posterior to reflect the updated selection of the basis functions that define the model structure, and 3) an explicit gradient-descent formulation that enhances computational efficiency. Consequently, the SKI method achieves accurate model structure selection with millisecond-level efficiency and higher identification accuracy, as demonstrated by extensive simulations and real-world experiments.

Förderung

  • National Natural Science Foundation of China
  • Beijing Natural Science Foundation

Zitieren

APA

Mei, J., Zheng, T., Cheng, L., Gong, S., & Huang, X. (2026). Sparse Kalman Identification for Partially Observable Systems via Adaptive Bayesian Learning. Journal of Guidance, Control, and Dynamics, 49(9), 2551-2568. https://doi.org/10.2514/1.g009696

Vancouver

Mei J, Zheng T, Cheng L, Gong S, Huang X. Sparse Kalman Identification for Partially Observable Systems via Adaptive Bayesian Learning. Journal of Guidance, Control, and Dynamics. 2026;49(9):2551-2568. doi:10.2514/1.g009696

BibTeX
@article{Mei2026,
  author = {Mei, Jilan and Zheng, Tengjie and Cheng, Lin and Gong, Shengping and Huang, Xu},
  title = {Sparse Kalman Identification for Partially Observable Systems via Adaptive Bayesian Learning},
  journal = {Journal of Guidance, Control, and Dynamics},
  year = {2026},
  volume = {49},
  number = {9},
  pages = {2551--2568},
  doi = {10.2514/1.g009696}
}
Kostenlos starten →