Minimum error entropy based multiple model estimation for multisensor hybrid uncertain target tracking systems

In the multisensor target tracking system, the key of the target tracking performance depends on the state estimation accuracy to a great extent. However, the system uncertainties will seriously affect the performance of the state estimation. Up to now, little research focuses on the state estimation for the multi-sensor hybrid target tracking systems with multiple uncertainties including the multiple models, the unknown inputs and the systematic biases. In this study, the minimum error entropy based on the multiple model estimation for the multisensor hybrid uncertain target tracking systems with the multiple system uncertainties is presented. The minimum variance unbiased filter based on the general systematic bias evolution model decoupled with the unknown state is designed to estimate the optimal systematic biases and compensate the system measurements. Taking full advantage of the compensated measurement information in time and space, the multiple model observer based on the minimum error entropy is designed to obtain the optimal state estimation. The simulation results of the target tracking scenario illustrate the effectiveness of the proposed method, and the indoor target tracking and positioning experiment based on the ultrawideband further verifies that the proposed method is satisfying.

[1]  Yanjun Ma,et al.  Multiple-Model State Estimation Based on Variational Bayesian Inference , 2019, IEEE Transactions on Automatic Control.

[2]  Dirk Söffker,et al.  The uncertainty learning filter: A revised smooth variable structure filter , 2018, Signal Process..

[3]  Zhengqiang Jiang,et al.  Multiple Pedestrian Tracking From Monocular Videos in an Interacting Multiple Model Framework , 2018, IEEE Transactions on Image Processing.

[4]  Jonathon A. Chambers,et al.  A Novel Robust Gaussian–Student's t Mixture Distribution Based Kalman Filter , 2019, IEEE Transactions on Signal Processing.

[5]  Jie Zhou,et al.  State Estimation for Dynamic Systems With Unknown Process Inputs and Applications , 2018, IEEE Access.

[6]  Lingjuan Miao,et al.  Adaptive Two-stage Kalman Filter for SINS/Odometer Integrated Navigation Systems , 2016, Journal of Navigation.

[7]  Zhihua Wang,et al.  An adaptive three-stage extended Kalman filter for nonlinear discrete-time system in presence of unknown inputs. , 2018, ISA transactions.

[8]  José A. B. Gerald,et al.  A Close to Optimal Adaptive Filter for Sudden System Changes , 2017, IEEE Signal Processing Letters.

[9]  S. Andrew Gadsden,et al.  Gaussian filters for parameter and state estimation: A general review of theory and recent trends , 2017, Signal Process..

[10]  Quan Pan,et al.  Linear minimum mean squared estimation of measurement bias driven by structured unknown inputs , 2014 .

[11]  Zhihua Wang,et al.  Augmented robust three-stage extended Kalman filter for Mars entry-phase autonomous navigation , 2018, Int. J. Syst. Sci..

[12]  Anke Xue,et al.  Geometrical entropy approach for variable structure multiple-model estimation , 2015 .

[13]  Shesheng Gao,et al.  Interacting multiple model estimation-based adaptive robust unscented Kalman filter , 2017 .

[14]  Lamine Mili,et al.  A Theoretical Framework of Robust H-Infinity Unscented Kalman Filter and Its Application to Power System Dynamic State Estimation , 2019, IEEE Transactions on Signal Processing.

[15]  Jun Fang,et al.  Robust Gaussian Kalman Filter With Outlier Detection , 2018, IEEE Signal Processing Letters.

[16]  Jonathon A. Chambers,et al.  A Novel Kullback–Leibler Divergence Minimization-Based Adaptive Student's t-Filter , 2019, IEEE Transactions on Signal Processing.

[17]  Yunpeng Cao,et al.  A strong tracking filter based multiple model approach for gas turbine fault diagnosis , 2018 .

[18]  Saeid Habibi,et al.  Reliable state of charge and state of health estimation using the smooth variable structure filter , 2018, Control Engineering Practice.

[19]  Jun Dong,et al.  Design the finite-time H∞ resilient filter of a class of switched systems with uncertain parameters , 2018, Trans. Inst. Meas. Control.

[20]  Yuriy S. Shmaliy,et al.  Comparing Robustness of the Kalman, $H_\infty$ , and UFIR Filters , 2018, IEEE Transactions on Signal Processing.

[21]  Yan Liang,et al.  Bias estimation for asynchronous multi-rate multi-sensor fusion with unknown inputs , 2018, Inf. Fusion.

[22]  Joel P. Conte,et al.  A dual adaptive filtering approach for nonlinear finite element model updating accounting for modeling uncertainty , 2019, Mechanical Systems and Signal Processing.

[23]  Lamine Mili,et al.  Robust Unscented Kalman Filter for Power System Dynamic State Estimation With Unknown Noise Statistics , 2019, IEEE Transactions on Smart Grid.

[24]  Yingmin Jia,et al.  Kullback-Leibler divergence for interacting multiple model estimation with random matrices , 2014, IET Signal Process..

[25]  Wonkeun Youn,et al.  Combined Quaternion-Based Error State Kalman Filtering and Smooth Variable Structure Filtering for Robust Attitude Estimation , 2019, IEEE Access.

[26]  Quan Pan,et al.  Minimum upper-bound filter of Markovian jump linear systems with generalized unknown disturbances , 2016, Autom..

[27]  Fang Deng,et al.  Adaptive Unscented Kalman Filter Based Estimation and Filtering for Dynamic Positioning with Model Uncertainties , 2019, International Journal of Control, Automation and Systems.

[28]  Roozbeh Dehghannasiri,et al.  Intrinsically Bayesian Robust Kalman Filter: An Innovation Process Approach , 2017, IEEE Transactions on Signal Processing.

[29]  Xianxing Liu,et al.  Joint estimation of state and system biases in non-linear system , 2017, IET Signal Process..

[30]  Yuriy V. Zakharov,et al.  RLS Adaptive Filter With Inequality Constraints , 2016, IEEE Signal Processing Letters.

[31]  Zhihua Wang,et al.  Nonlinear unbiased minimum-variance filter for Mars entry autonomous navigation under large uncertainties and unknown measurement bias. , 2018, ISA transactions.