logo

SCIENCE CHINA Information Sciences, Volume 63 , Issue 12 : 222202(2020) https://doi.org/10.1007/s11432-019-2725-8

Sequential fusion estimation for multisensor systems with non-Gaussian noises

More info
  • ReceivedJul 5, 2019
  • AcceptedNov 1, 2019
  • PublishedNov 2, 2020

Abstract


Acknowledgment

This work was supported by Beijing Natural Science Foundation (Grant No. 4202071).


References

[1] Bar-Shalom Y, Li X R, Kirubarajan T. Estimation With Applications to Tracking and Navigation: Theory Algorithm and Software. Hoboken: John Wiley & Sons, Inc., 2001. Google Scholar

[2] Khaleghi B, Khamis A, Karray F O. Multisensor data fusion: A review of the state-of-the-art. Inf Fusion, 2013, 14: 28-44 CrossRef Google Scholar

[3] Deng Z, Zhang P, Qi W. Sequential covariance intersection fusion Kalman filter. Inf Sci, 2012, 189: 293-309 CrossRef Google Scholar

[4] Edward W, James L. Multisensor Data Fusion, Boston: Artech House, 1990. Google Scholar

[5] Yan L, Li X R, Xia Y. Modeling and estimation of asynchronous multirate multisensor system with unreliable measurements. IEEE Trans Aerosp Electron Syst, 2015, 51: 2012-2026 CrossRef Google Scholar

[6] Hu J, Wang Z, Chen D. Estimation, filtering and fusion for networked systems with network-induced phenomena: New progress and prospects. Inf Fusion, 2016, 31: 65-75 CrossRef Google Scholar

[7] Yan L, Xia Y, Fu M. Optimal fusion estimation for stochastic systems with cross-correlated sensor noises. Sci China Inf Sci, 2017, 60: 120205 CrossRef Google Scholar

[8] Ma L, Wang Z, Han Q L. Variance-Constrained Distributed Filtering for Time-Varying Systems With Multiplicative Noises and Deception Attacks Over Sensor Networks. IEEE Sens J, 2017, 17: 2279-2288 CrossRef Google Scholar

[9] Ma L, Wang Z, Han Q L. Automatica, 2018, 93: 527-534 CrossRef Google Scholar

[10] Zhu H, Leung H, He Z. A variational Bayesian approach to robust sensor fusion based on Student-t distribution. Inf Sci, 2013, 221: 201-214 CrossRef Google Scholar

[11] Shen C, Li J, Huang W. Robust centralized multi-sensor fusion using cubature information filter. In: Proceedings of the 30th Chinese Control and Decision Conference (2018 CCDC), 2018. 3297--3302. Google Scholar

[12] Wang X, Liang Y, Pan Q. Nonlinear Gaussian Smoothers With Colored Measurement Noise. IEEE Trans Automat Contr, 2015, 60: 870-876 CrossRef Google Scholar

[13] Piché R, Särkkä S, Hartikainen J. Recursive outlier--robust filtering and smoothing for nonlinear systems using the multivariate student--$t$-distribution. In: Proceedings of IEEE International Workshop on Machine Learning for Signal Processing, Santander, 2012. 1--6. Google Scholar

[14] Huang Y, Zhang Y, Li N, et al. A robust gaussian approximate filter for nonlinear systems with heavy tailed measurement noises. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016. 4209--4213. Google Scholar

[15] Huang Y, Zhang Y, Li N, et al. A robust student's $t$ based cubature filter. In: Proceedings of the 19th International Conference on Information Fusion, Heidelberg, 2016. 9--16. Google Scholar

[16] Amor N, Kahlaoui S, Chebbi S. Unscented particle filter using student--$t$ distribution with non-protectGaussian measurement noise. In: Proceedings of 2018 International Conference on Advanced Systems and Electric Technologies, 2018. 34--38. Google Scholar

[17] Roth M, O"zkan E, Gustafsson F. A student's filter for heavy tailed process and measurement noise. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2013. 5770--5774. Google Scholar

[18] Huang Y, Zhang Y, Li N. Robust student's t based nonlinear filter and smoother. IEEE Trans Aerosp Electron Syst, 2016, 52: 2586-2596 CrossRef Google Scholar

[19] Zhang W A, Shi L. Sequential fusion estimation for clustered sensor networks. Automatica, 2018, 89: 358-363 CrossRef Google Scholar

[20] Lin H, Sun S. Optimal Sequential Fusion Estimation With Stochastic Parameter Perturbations, Fading Measurements, and Correlated Noises. IEEE Trans Signal Process, 2018, 66: 3571-3583 CrossRef Google Scholar

[21] Wang Y, Jing Z L, Hu S Q. On the sensor order in sequential integrated probability data association filter. Sci China Inf Sci, 2012, 55: 491-500 CrossRef Google Scholar

[22] Wen C, Cai Y, Wen C. Optimal sequential Kalman filtering with cross-correlated measurement noises. Aerospace Sci Tech, 2013, 26: 153-159 CrossRef Google Scholar

[23] Yan L, Rong Li X, Xia Y. Optimal sequential and distributed fusion for state estimation in cross-correlated noise. Automatica, 2013, 49: 3607-3612 CrossRef Google Scholar

[24] Ge Q, Zheng Z, Zhang S, et al. A data fusion approach based on sequential and strong tracking filters with nonlinear dynamic systems. In: Proceedings of 2006 1st International Symposium on Systems and Control in Aerospace and Astronautics, Harbin, 2006. 1344--1349. Google Scholar

[25] Duan Z, Li X R, Han C, et al. Sequential unscented protectKalman filter for radar target tracking with range rate measurements. In: Proceedings of the 7th International Conference on Information Fusion (FUSION 2005), 2005. 130--137. Google Scholar

[26] Ristic B, Arulampalam S, Gordon N. Beyond the protectKalman Filter, Artech House, 2004. Google Scholar

[27] Yan L, Xia Y, Liu B, et al. Multisensor Optimal Estimation Theory and its Application, Beijing: The Science Publishing House, 2015. Google Scholar

[28] DeGroot M H. Optimal Statistical Decisions, Beijing: Publishing House of Tsinghua University, 2006. Google Scholar

[29] Koop G M. Bayesian Econometrics. Hoboken: John Wiley & Sons Inc., 2003. Google Scholar

[30] Roth M. On the Multivariate $t$ Distribution. Technical Report, Division of automatic control, Linköping University Electronic Press, 2013. Google Scholar

[31] Agamennoni G, Nieto J I, Nebot E M. Approximate Inference in State-Space Models With Heavy-Tailed Noise. IEEE Trans Signal Process, 2012, 60: 5024-5037 CrossRef Google Scholar

[32] Kailath T, Sayed A H, Hassibi B. Linear Estimation. Upper Saddle River: Prentice--Hall, 2000. Google Scholar

  • Figure 1

    (Color online) True values and the fusion estimates of (a) position and (b) velocity.

  • Figure 2

    (Color online) RMSEs of the position by using the presented SF algorithm compared with (a) other fusion algorithms and (b) single sensors.

  • Figure 3

    (Color online) RMSEs of the velocity by using the presented SF algorithm compared with (a) other fusion algorithms and (b) single sensors.

  • Table 1  

    Table 1Average RMSEs by using single sensors and different fusion algorithms

    Sensor ${\rm~RMSE_p}$ ${\rm~RMSE_v}$ Algorithm ${\rm~RMSE_p}$ ${\rm~RMSE_v}$
    S1 $2.6945$ $2.0883$ G-CF $4.1684$ $2.4537$
    S2 $3.9596$ $2.4450$ CF $2.3128$ $1.9949$
    S3 $5.0342$ $2.6874$ SF $2.3677$ $1.9840$
  • Table 2  

    Table 2Average CPU time per Monte Carlo run of single sensors and different fusion algorithms

    Sensor CPU time (ms) Algorithm CPU time (ms)
    S1 $1.94$ G-CF $5.24$
    S2 $1.93$ CF $9.52$
    S3 $1.96$ SF $5.87$