Since the Gaussian-inverse Wishart hierarchical form has similar properties to Student’s $t$ distribution, we name it generalized $t$ distribution in this article. Based on this, a robust generalized $t$ distribution-based Kalman filter (GTKF) is proposed for state-space models that are eroded by state and measurement outliers. Different from the existing algorithms, the state transition and measurement likelihood densities are directly modeled as generalized $t$ distributions by employing the one-step smoothing strategy.An analytical closed-form solution can be obtained through the variational inference approach. Moreover, two variants of the proposed GTKF are also presented to apply to different engineering scenarios. Simulation and experimental examples demonstrate that the proposed GTKFs yield improved robustness over the existing algorithms.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A Robust Generalized $t$ Distribution-Based Kalman Filter


    Beteiligte:
    Bai, Mingming (Autor:in) / Sun, Chengjiao (Autor:in) / Zhang, Yonggang (Autor:in)


    Erscheinungsdatum :

    01.10.2022


    Format / Umfang :

    1475993 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Stable Robust Extended Kalman Filter

    Mu, He-Qing | Online Contents | 2016


    Stable Robust Extended Kalman Filter

    Mu, He-Qing | Online Contents | 2017


    Maximum Correntropy Criterion Based Robust Kalman Filter

    Wang, Liansheng / Gao, XingWei / Yin, Lijian | British Library Conference Proceedings | 2018


    Stable Robust Extended Kalman Filter

    Mu, He-Qing / Kuok, Sin-Chi / Yuen, Ka-Veng | ASCE | 2016


    A Novel Robust Student's t-Based Kalman Filter

    Huang, Yulong / Zhang, Yonggang / Li, Ning et al. | IEEE | 2017