×
Liu, Xi; Chen, Badong; Xu, Bin; Wu, Zongze; Honeine, Paul

Maximum correntropy unscented filter. (English) Zbl 1362.93155

Int. J. Syst. Sci., Princ. Appl. Syst. Integr. 48, No. 8, 1607-1615 (2017).
Summary: The unscented transformation (UT) is an efficient method to solve the state estimation problem for a non-linear dynamic system, utilising a derivative-free higher-order approximation by approximating a Gaussian distribution rather than approximating a non-linear function. Applying the UT to a Kalman filter type estimator leads to the well-known unscented Kalman filter (UKF). Although the UKF works very well in Gaussian noises, its performance may deteriorate significantly when the noises are non-Gaussian, especially when the system is disturbed by some heavy-tailed impulsive noises. To improve the robustness of the UKF against impulsive noises, a new filter for non-linear systems is proposed in this work, namely the maximum correntropy unscented filter (MCUF). In MCUF, the UT is applied to obtain the prior estimates of the state and covariance matrix, and a robust statistical linearisation regression based on the maximum correntropy criterion is then used to obtain the posterior estimates of the state and covariance matrix. The satisfying performance of the new algorithm is confirmed by two illustrative examples.

Cited in 9 Documents

MSC:

93E11 Filtering in stochastic control theory
93E10 Estimation and detection in stochastic control theory
93C55 Discrete-time control/observation systems
93C10 Nonlinear systems in control theory

Keywords:

unscented Kalman filter (UKF); unscented transformation (UT); maximum correntropy criterion (MCC)
Cite Review PDF
Full Text: DOI arXiv HAL

References:

[1] DOI: 10.1017/CBO9780511543005 · doi:10.1017/CBO9780511543005
[2] Anderson B., Optimal filtering (1979)
[3] DOI: 10.1109/TPWRS.2009.2030291 · doi:10.1109/TPWRS.2009.2030291
[4] Bryson A., Applied optimal control: Optimization, estimation and control (1975)
[5] DOI: 10.1016/j.automatica.2016.10.004 · Zbl 1352.93095 · doi:10.1016/j.automatica.2016.10.004
[6] DOI: 10.1109/LSP.2012.2204435 · doi:10.1109/LSP.2012.2204435
[7] DOI: 10.1109/LSP.2015.2428713 · doi:10.1109/LSP.2015.2428713
[8] DOI: 10.1109/LSP.2014.2319308 · doi:10.1109/LSP.2014.2319308
[9] DOI: 10.1109/TSP.2016.2539127 · doi:10.1109/TSP.2016.2539127
[10] DOI: 10.1016/j.neucom.2012.05.004 · doi:10.1016/j.neucom.2012.05.004
[11] Chen B., System parameter identification: Information criteria and algorithms (2013)
[12] DOI: 10.1049/iet-smt.2009.0003 · doi:10.1049/iet-smt.2009.0003
[13] DOI: 10.1109/48.380248 · doi:10.1109/48.380248
[14] DOI: 10.1007/978-3-319-07416-0 · Zbl 1317.68004 · doi:10.1007/978-3-319-07416-0
[15] DOI: 10.1109/TIP.2010.2103949 · Zbl 1372.94369 · doi:10.1109/TIP.2010.2103949
[16] DOI: 10.1109/TPAMI.2010.220 · doi:10.1109/TPAMI.2010.220
[17] DOI: 10.1214/aoms/1177703732 · Zbl 0136.39805 · doi:10.1214/aoms/1177703732
[18] DOI: 10.1109/9.847726 · Zbl 0973.93053 · doi:10.1109/9.847726
[19] DOI: 10.1115/1.3662552 · doi:10.1115/1.3662552
[20] DOI: 10.2514/1.27968 · doi:10.2514/1.27968
[21] DOI: 10.1109/TSP.2003.816758 · Zbl 1369.94195 · doi:10.1109/TSP.2003.816758
[22] DOI: 10.3969/j.issn.1004-4132.2010.04.023 · doi:10.3969/j.issn.1004-4132.2010.04.023
[23] DOI: 10.1109/TAC.2013.2263650 · doi:10.1109/TAC.2013.2263650
[24] DOI: 10.1109/TSP.2007.896065 · Zbl 1390.94277 · doi:10.1109/TSP.2007.896065
[25] Nahi N.E, Estimation theory and applications (1969)
[26] DOI: 10.1109/WCICA.2014.7053776 · doi:10.1109/WCICA.2014.7053776
[27] DOI: 10.1007/978-1-4419-1570-2 · Zbl 1206.94003 · doi:10.1007/978-1-4419-1570-2
[28] DOI: 10.1214/aos/1176325511 · Zbl 0815.62014 · doi:10.1214/aos/1176325511
[29] DOI: 10.1109/LSP.2014.2337899 · doi:10.1109/LSP.2014.2337899
[30] DOI: 10.1002/0470045345 · doi:10.1002/0470045345
[31] DOI: 10.1109/ICASSP.2010.5495055 · doi:10.1109/ICASSP.2010.5495055
[32] DOI: 10.1049/iet-rsn.2009.0170 · doi:10.1049/iet-rsn.2009.0170
[33] DOI: 10.1109/TIP.2015.2456508 · doi:10.1109/TIP.2015.2456508
[34] DOI: 10.1109/TASL.2008.2002039 · doi:10.1109/TASL.2008.2002039
[35] DOI: 10.1109/IJCNN.2011.6033473 · doi:10.1109/IJCNN.2011.6033473
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.