Gaussian filters for nonlinear filtering problems
Gaussian filters for nonlinear filtering problems
复制标题
DOI：
10.1109/9.855552
复制
发表时间：
2000-05-01
影响因子：
6.8
通讯作者：
Xiong, KQ
中科院分区：
文献类型：
--
作者：
Ito, K;Xiong, KQ
本文开发并分析了基于高斯分布的非线性滤波问题的实时、精确滤波器。本文给出了高斯滤波器的系统公式，并对最优滤波器进行了高效、精确的数值积分。我们还讨论了用高斯分布的和来近似条件概率密度的混合高斯滤波器。提出了一种新的高斯和滤波器权值更新规则。我们的数值测试表明，新的倾斜器在没有额外成本的情况下显著改善了扩展卡尔曼滤波器，并且新的高斯和滤波器具有接近最优的性能。
In this paper we develop and analyze real-time and accurate filters for nonlinear filtering problems based on the Gaussian distributions. We present the systematic formulation of Gaussian filters and develop efficient and accurate numerical integration of the optimal filter. We also discuss the mixed Gaussian filters in which the conditional probability density is approximated by the sum of Gaussian distributions. A new update rule of weights for Gaussian sum filters is proposed. Our numerical testings demonstrate that new tilters significantly improve the extended Kalman filter with no additional cost and the new Gaussian sum filter has a nearly optimal performance.