Maximum correntropy square-root cubature Kalman filter with application to SINS/GPS integrated systems. (September 2018)

• Record Type: Journal Article
• Authors: Liu, Xi; Qu, Hua; Zhao, Jihong; Yue, Pengcheng
• Is Part Of: ISA transactions. Volume 80(2018)
• Page Start: 195
• Page End: 202
• Publication Date: 2018-09
• Subjects: Square-root cubature Kalman filter (SCKF) -- Maximum correntropy criterion (MCC) -- SINS/GPS integrated systems; Engineering instruments -- Periodicals; Engineering instruments; Periodicals; Electronic journals; 629.805
• DOI: 10.1016/j.isatra.2018.05.001
• Languages: English
• ISSNs: 0019-0578

Abstract

Abstract: For a nonlinear system, the cubature Kalman filter (CKF) and its square-root version are useful methods to solve the state estimation problems, and both can obtain good performance in Gaussian noises. However, their performances often degrade significantly in the face of non-Gaussian noises, particularly when the measurements are contaminated by some heavy-tailed impulsive noises. By utilizing the maximum correntropy criterion (MCC) to improve the robust performance instead of traditional minimum mean square error (MMSE) criterion, a new square-root nonlinear filter is proposed in this study, named as the maximum correntropy square-root cubature Kalman filter (MCSCKF). The new filter not only retains the advantage of square-root cubature Kalman filter (SCKF), but also exhibits robust performance against heavy-tailed non-Gaussian noises. A judgment condition that avoids numerical problem is also given. The results of two illustrative examples, especially the SINS/GPS integrated systems, demonstrate the desirable performance of the proposed filter. Highlights: A square-root nonlinear filter based on maximum correntropy criterion is proposed. A nonlinear regression model is reconstructed to obtain the optimal solution. A judgment condition that avoids numerical problem is given. The superior performance of proposed filter is confirmed by illustrative examples.