基于概率密度特性的高阶UT样点设计方法

The Higher Order Unscented Filter Sigma Points Design Algorithm Based on Density Function

针对UT变换通过非线性矩近似方程组获得样点的复杂性,提出了一种基于概率密度特性的高阶UT样点设计方法.该方法利用高斯概率密度函数导数的极值点与各种对称Sigma样点集分布相对应的特性,采用高斯概率密度函数高阶导数的极值得到Sigma样点的分布来进行Sigma样点设计,提高了估计精度.理论分析推导和仿真实验证明了该方法的有效性.

Due to the complexity of the nonlinear moment approximation equations, a higher order sigma points design algorithm based on the characteristics of the probability density function is proposed. The correspondence of the extremum of higher order derivatives of the Gaussian density function and the location of the sigma points are exploited. Thus the extremum of higher order derivatives of the Gaussian density function are selected to be the location of the sigma points that can improve the estimation precision. It is corroborated in the theoretical analysis and the simulation that the proposed algorithm can easily derive higher order unscented filters with high efficiency.