Adaptive Robust High-degree Cubature Filter Based On Target Tracking

Abstract

Target tracking system has strong-nonlinearity with non-Gaussian noise, thus making traditional Cubature Kalman Filter have low tracking accuracy due to sensitivity to non-Gaussian noise. Considering that the High-degree CKF and Maximum Correntropy Kalman Filter can conquer the nonlinearity of system and non-Gaussianity of measurement noise and system noise respectively, the measurement update process of HCKF is transformed to statistical linear regression equation based on the combination of Maximum Correntropy Criterion and HCKF, and adjust the kernel width adaptively, which solves the nonlinearity and non-Gaussianity problem. Simulation proves that the proposed robust generalized high-degree cubature filter is better than traditional CKF and simple MCKF both in tracing accuracy.