A Pseudolinear Maximum Correntropy Kalman Filter Framework for Bearings-Only Target Tracking
Shan Zhong, Bei Peng, Lingqiang Ouyang, Xinyue Yang, Hongyu Zhang, Gang Wang
Abstract
This article presents a framework for a pseudolinear Kalman filter (PLKF) based on the maximum correntropy criterion for the bearings-only target tracking problem in non-Gaussian environments. We first derive a pseudolinear maximum correntropy Kalman filter (PMCKF). To solve the offset problem, bias compensation is merged into PMCKF to realize bias-compensated PMCKF (BC-PMCKF). In the real scenario, the speed variation of the target is continuous during motion. Based on this premise, we implement the speed-constrained PMCKF (SC-PMCKF) algorithm in this framework, which suppresses the effect of impulsive noise on velocity estimation well. Finally, a posterior Cramér–Rao lower bound (PCRLB) under non-Gaussian noises is derived for the framework. Simulations and physical experiments show that the proposed estimation method is better than the traditional Kalman filter in non-Gaussian noise environments.