一种用于解决粒子滤波粒子退化现象的重要性重采样算法的研究

粒子滤波通过蒙特卡罗模拟来实现递推贝叶斯估计，在非线性非高斯系统中体现出良好的特性；但粒子滤波存在粒子退化现象的缺陷，针对这一问题，提出一种新的重采样算法，即分区重采样算法，其主要思想是根据多项式重采样与分层重采样算法的特点，把随机数区间划分成若干个区，每个区内的随机数任意排列，而区与区之间按升序排列。与目前常用的其他重采样算法相比，该方法提高了粒子滤波的平均性能，仿真实验验证了该算法的有效性和实用性。

Research on an Importance Resampling Algorithm to Solve Particle Degeneration of Particle Filter

Particle filter implements recursive Bayesian filter based on Monte Carlo simulation and it shows merits in dealing with nonlinear and non-Gaussian models. To combat particle degeneration, a new resampling algorithm, divisional resampling, is proposed. The main idea of divisional resampling is to combine polynomial resampling method and a layered one, divide stochastic set of data into several sets,making sure that each of the sets has stochastic array of data and all the sets have an array according to sort ascending. Compared to other general resampling algorithms, the method proposed improves the average performance of particle filters. Simulation and test verifies validity and applicability of the divisional resampling approach.