A Novel Inverse-Wishart-Student's t Mixture Distribution-Based Variational Bayesian Kalman Filter

被引:1
|
作者
Li, Shuaiyong [1 ]
Guo, Chengchun [1 ]
机构
[1] Chongqing Univ Posts & Telecommun, Sch Automat, Chongqing 400065, Peoples R China
关键词
Inverse-Wishart-student's t-distribution; Kalman filter (KF); thick-tailed measurement noise;
D O I
10.1109/JSEN.2024.3472092
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Considering the conventional Kalman filter (KF) has insufficient accuracy in state estimation under nonsmooth thick-tailed noise, a novel inverse-Wishart-student's t mixed distribution (IWSTM) is proposed to adaptively learn the state vectors and associated auxiliary parameters using variational Bayesian (VB) approach. Then, a novel VB adaptive Kalman filter (VBAKF-IWSTM) is proposed to enhance state estimation accuracy under the conditions of nonsmooth thick-tailed measurement noise. Compared with RSTKF and GSTMKF, the novel VBAKF-IWSTM has a better fitting effect of nonsmooth thick-tailed noise based on the two auxiliary parameters, which are learned adaptively by VB to realize the correction of location parameter and scale parameter of the student's t-distribution. The performance of the novel IWSTM is also demonstrated to outperform the existing KF in the simulation experiments and real trajectory experiments of the mobile robot conducted in this article.
引用
收藏
页码:39325 / 39333
页数:9
相关论文
共 50 条
  • [41] An Adaptive Robust Student's t-Based Kalman Filter Based on Multi-sensor Fusion
    Wang, Dapeng
    Zhang, Hai
    Huang, Hongliang
    INTELLIGENT ROBOTICS AND APPLICATIONS (ICIRA 2022), PT II, 2022, 13456 : 603 - 613
  • [42] Student's t-Based Robust Kalman Filter for a SINS/USBL Integration Navigation Strategy
    Wang, Jian
    Zhang, Tao
    Jin, Bonan
    Zhu, Yongyun
    Tong, Jinwu
    IEEE SENSORS JOURNAL, 2020, 20 (10) : 5540 - 5553
  • [43] A New Process Uncertainty Robust Student's t Based Kalman Filter for SINS/GPS Integration
    Huang, Yulong
    Zhang, Yonggang
    IEEE ACCESS, 2017, 5 : 14391 - 14404
  • [44] New look at the Student's t-based Kalman filter from maximum a posterior perspective
    Qin, Fangjun
    Chang, Lubin
    Zha, Feng
    IET RADAR SONAR AND NAVIGATION, 2018, 12 (08): : 795 - 800
  • [45] Variational Bayesian Sparse Kernel-Based Blind Image Deconvolution With Student's-t Priors
    Tzikas, Dimitris G.
    Likas, Aristidis C.
    Galatsanos, Nikolaos P.
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2009, 18 (04) : 753 - 764
  • [46] A Robust Kalman Filter Based on the Pearson Type VII-Inverse Wishart Distribution: Symmetrical Treatment of Time-Varying Measurement Bias and Heavy-Tailed Noise
    Liang, Shen
    Zhang, Xun
    SYMMETRY-BASEL, 2025, 17 (01):
  • [47] Spatially Constrained Student’s t-Distribution Based Mixture Model for Robust Image Segmentation
    Abhirup Banerjee
    Pradipta Maji
    Journal of Mathematical Imaging and Vision, 2018, 60 : 355 - 381
  • [48] Spatially Constrained Student's t-Distribution Based Mixture Model for Robust Image Segmentation
    Banerjee, Abhirup
    Maji, Pradipta
    JOURNAL OF MATHEMATICAL IMAGING AND VISION, 2018, 60 (03) : 355 - 381
  • [49] Speech recognition based on student's t-distribution derived from total Bayesian framework
    Watanabe, S
    Nakamura, A
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2006, E89D (03): : 970 - 980
  • [50] A Novel Image Segmentation Approach Based on Truncated Infinite Student's t-mixture Model
    Li, Lu
    Fan, Wentao
    Du, JiXiang
    Wang, Jing
    INTELLIGENT COMPUTING METHODOLOGIES, ICIC 2016, PT III, 2016, 9773 : 271 - 281