截断的自适应容积粒子滤波器

在现有的高斯粒子滤波算法(Gaussian particle filter, GPF)中,粒子的重要性密度函数是由高斯滤波器（Gaussian filter, GF）结合当前最新量测来构建的。在高精度、强非线性的量测条件下,传统GF并不能很好地近似状态真实后验概率密度函数，为了解决这一问题,提出一种截断的自适应容积卡尔曼滤波器,并用其来构建粒子的重要性密度函数,从而推导出了截断的自适应容积粒子滤波器。仿真表明,在高精度、强非线性的量测条件下,所提出的滤波算法比现有的GPF具有更高的估计精度。

Truncated adaptive cubature particle filter

In the existing Gussian particle filter (GPF), sample importance density function is constructed through combining the latest measurement based on the Gaussian filter (GF).However, the true posterior probability density could be approximated badly by the GF under the condition of high accuracy, strong nonlinearity measurements.In order to solve this problem, a truncated adaptive cubature kalman filter is proposed, based on which a new sample importance density function is constructed, so that a truncated adaptive cubature particle filtering method can be derived.Simulation results show that the proposed filtering algorithm has higher estimation accuracy than the existing GPF for addressing the nonlinear state estimation with high accuracy and strong nonlinearity measurements.