Minimum Error Entropy Rauch–Tung–Striebel Smoother
Jiacheng He, Hongwei Wang, Gang Wang, Shan Zhong, Bei Peng
Abstract
In real applications, non-Gaussian distributions are frequently caused by outliers and impulsive disturbances, and these will impair the performance of the Rauch–Tung–Striebel (RTS) smoother. In this study, a modified RTS smoothing algorithm combined with the minimum error entropy (MEE) criterion (MEE-RTS) is developed, and by employing the Taylor series linearization method, it is also expanded to the state estimation of nonlinear systems. The proposed methods improve the robustness of the conventional RTS smoother against complex non-Gaussian noises. In addition, we examine the MEE-RTS smoother's mean error behavior, mean square error behavior, and computational complexity, and the performance of the proposed algorithms is verified by comparing it with existing RTS-type smoothers.