基于当前加速度模型的抗差自适应KALMAN滤波

Adaptive Robust Kalman Filtering Based on the Current Statistical Model

动态导航与定位的质量取决于对动态载体扰动和观测异常扰动的认知和控制。首先介绍机动载体的当前统计模型,分析该模型存在的问题,提出一种基于“当前”加速度模型的抗差自适应卡尔曼滤波算法。跟以往建立的自适应KALMAN滤波进行比较,计算结果表明,该算法不仅可以提高滤波器的精度,而且更能有效地控制观测异常和动态扰动异常对导航解的影响,使导航解更能反映导航系统的真实情况。

The quality of kinematic navigation and positioning lies on the detecting and controlling of the measurement outliers and kinematic state disturbing. Firstly the current statistical model is introduced and its shortcomings are analyzed, then an adaptively robust Kalman fihering arithmetic based on the current statistical model is presentcd. It is shown, by derivations and calculations, that the new algorithm can not only improve the filtering estimation accuracy, but also control the influences of measurement outliers and the disturbances of the dynamical model. The new algorithm gives more actual and reliable parameter estimates of the maneuvering vehicles.