基于粒子滤波的改进算法

An improved particle filtering algorithm

通过将粒子滤波算法与无迹卡尔曼滤波算法相结合,提出一种用于解决非线性、非高斯系统估计的改良粒子滤波算法。该算法在经典粒子滤波的基础上,利用无迹卡尔曼滤波生成更能够逼近真实后验概率分布的重要函数。实验结果表明,这种算法在预测结果收敛性能方面明显优于标准粒子滤波、广义卡尔曼滤波和无迹卡尔曼滤波等现有的非线性滤波器。

In this paper we propose, by combinating the particle filer algorithm with the unscented Kalman filter algorithm , a novel method for the state estimation of nonlinear and non-Gaussian systemses. Based on the classic particle filter, the algorithm consists of a particle filter that uses an unscented Kalman filter to generate the im- portance proposal distribution, which matchs the true posterior more closely. The experimental results show that the convergence results predict that the new filter exceeds standard particle filters, Kalman filters and unscented Kalman filters and other nonlinear filters.