作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2011, Vol. 37 ›› Issue (16): 191-193. doi: 10.3969/j.issn.1000-3428.2011.16.065

• 人工智能及识别技术 • 上一篇    下一篇

基于求积分卡尔曼滤波的交互式多模型算法?

马丽丽 1,陈金广 1,2   

  1. (1. 西安工程大学计算机科学学院,西安 710048;2. 西安电子科技大学电子工程学院,西安 710071)
  • 收稿日期:2011-01-21 出版日期:2011-08-20 发布日期:2011-08-20
  • 作者简介:马丽丽(1979-),女,讲师、硕士,主研方向:目标跟踪,信息融合;陈金广,讲师、博士
  • 基金资助:
    陕西省教育厅自然科学专项基金资助项目(2010JK565);西安工程大学基础研究基金资助项目(2010JC03);西安工程大学校管课题基金资助项目(2010XG17)

Interacting Multiple Model Algorithm Based on Quadrature Kalman Filtering

MA Li-li 1, CHEN Jin-guang 1,2   

  1. (1. School of Computer Science, Xi’an Polytechnic University, Xi’an 710048, China; 2. School of Electronic Engineering, Xidian University, Xi’an 710071, China)
  • Received:2011-01-21 Online:2011-08-20 Published:2011-08-20

摘要: 针对非线性系统中的多模型估计问题,将求积分卡尔曼滤波算法应用到交互式多模型算法过程中,提出一种基于求积分卡尔曼滤波的交互式多模型算法。该算法不需要求取非线性方程的雅可比矩阵,且能够获得比基于不敏卡尔曼滤波的交互式多模型方法更高的滤波精度。仿真结果证明了该算法的有效性。

关键词: 交互式多模型, 非线性滤波, 求积分卡尔曼滤波, 目标跟踪, 状态估计

Abstract: Aiming at the problem of multiple model estimation in nonlinear system, the Quadrature Kalman Filtering(QKF) is employed to the process of the Interacting Multiple Model(IMM) algorithm and an interacting multiple model algorithm based on QKF is proposed. The Jacobian matrix of nonlinear equations is unnecessary and a little better error performance can be obtained than that of the interacting multiple model algorithm based on unscented Kalman filtering. Simulation results show the effectiveness of the new algorithm.

Key words: Interacting Multiple Model(IMM), nonlinear filtering, Quadrature Kalman Filtering(QKF), target tracking, state estimation

中图分类号: