Variational Bayesian IMM-Filter for JMSs With Unknown Noise Covariances

被引：37

作者：

Wang, Guoqing ^{[1
]}

Wang, Xiaodong ^{[2
]}

Zhang, Yonggang ^{[1
]}

机构：

[1] Harbin Engn Univ, Coll Automat, Harbin 150001, Peoples R China

[2] Columbia Univ, Dept Elect Engn, New York, NY 10027 USA

来源：

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS | 2020年 / 56卷 / 02期

基金：

中央高校基本科研业务费专项资金资助; 中国国家自然科学基金;

关键词：

Noise measurement; Markov processes; Bayes methods; Covariance matrices; State estimation; Probability density function; Simulation; Adaptive Kalman filter; interacting multiple model (IMM); jump Markov systems; unknown noise covariance; variational Bayesian (VB); STATE ESTIMATION; TARGET TRACKING; SYSTEMS; ALGORITHM; CONSENSUS; FUSION;

D O I：

10.1109/TAES.2019.2929975

中图分类号：

V [航空、航天];

学科分类号：

08 ; 0825 ;

摘要：

In this paper, we derive a modified interacting multiple model filter for jump Markov systems with unknown process and measurement noise covariances. Using the inverse-Wishart distribution as the conjugate prior of noise covariances, the system state together with the noise parameters for each mode are inferred by the variational Bayesian method. The mixing and output estimates are calculated according to the weighted Kullback-Leibler average of mode-conditioned estimates. Simulation results show the effectiveness of the proposed algorithm.

引用

页码：1652 / 1661

页数：10

共 33 条

[1] Gaussian filters for parameter and state estimation: A general review of theory and recent trends [J].

Afshari, H. H. ;

Gadsden, S. A. ;

Habibi, S. .

SIGNAL PROCESSING, 2017, 135 :218-238

[2] Approximate Bayesian Smoothing with Unknown Process and Measurement Noise Covariances [J].

Ardeshiri, Tohid ;

Ozkan, Emre ;

Orguner, Umut ;

Gustafsson, Fredrik .

IEEE SIGNAL PROCESSING LETTERS, 2015, 22 (12) :2450-2454

[3] Kullback-Leibler average, consensus on probability densities, and distributed state estimation with guaranteed stability [J].

Battistelli, Giorgio ;

Chisci, Luigi .

AUTOMATICA, 2014, 50 (03) :707-718

[4] THE INTERACTING MULTIPLE MODEL ALGORITHM FOR SYSTEMS WITH MARKOVIAN SWITCHING COEFFICIENTS [J].

BLOM, HAP ;

BARSHALOM, Y .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1988, 33 (08) :780-783

[5] Measurement Error Observer-Based IMM Filtering for Mobile Node Localization Using WLAN RSSI Measurement [J].

Cho, Seong Yun .

IEEE SENSORS JOURNAL, 2016, 16 (08) :2489-2499

[6] Variational Bayesian Adaptive Cubature Information Filter Based on Wishart Distribution [J].

Dong, Peng ;

Jing, Zhongliang ;

Leung, Henry ;

Shen, Kai .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2017, 62 (11) :6051-6057

[7] Particle filters for state estimation of jump Markov linear systems [J].

Doucet, A ;

Gordon, NJ ;

Krishnamurthy, V .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2001, 49 (03) :613-624

[8] Multi-Sensor Centralized Fusion without Measurement Noise Covariance by Variational Bayesian Approximation [J].

Gao, Xinbo ;

Chen, Jinguang ;

Tao, Dacheng ;

Li, Xuelong .

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 2011, 47 (01) :718-727

[9] Applications of Kalman Filtering in Aerospace 1960 to the Present [J].

Grewal, Mohinder S. ;

Andrews, Angus P. .

IEEE CONTROL SYSTEMS MAGAZINE, 2010, 30 (03) :69-78

[10] A Novel Adaptive Kalman Filter With Inaccurate Process and Measurement Noise Covariance Matrices [J].

Huang, Yulong ;

Zhang, Yonggang ;

Wu, Zhemin ;

Li, Ning ;

Chambers, Jonathon .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2018, 63 (02) :594-601

← 1 2 3 4 →