J4 ›› 2010, Vol. 37 ›› Issue (5): 862-865+883.doi: 10.3969/j.issn.1001-2400.2010.05.015

• 研究论文 • 上一篇    下一篇

一种新的改进粒子滤波算法

杨璐;李明;张鹏   

  1. (西安电子科技大学 雷达信号处理重点实验室,陕西 西安  710071)
  • 收稿日期:2000-09-13 出版日期:2010-10-20 发布日期:2010-10-11
  • 通讯作者: 杨璐
  • 作者简介:杨璐(1986-),女,西安电子科技大学博士研究生,E-mail: yanglu8642@yahoo.cn.
  • 基金资助:

    国家部委基金资助项目(9140C0103071003);国家自然科学基金资助项目(60872137)

New improved particle filter algorithm

YANG Lu;LI Ming;ZHANG Peng   

  1. (Key Lab. of Radar Signal Processing, Xidian Univ., Xi'an  710071, China)
  • Received:2000-09-13 Online:2010-10-20 Published:2010-10-11
  • Contact: YANG Lu

摘要:

标准粒子滤波算法存在的最大问题是粒子退化,针对这一问题,提出了一种改进的粒子滤波算法,该算法将无迹卡尔曼滤波算法(UKF)、混合遗传模拟退火算法和基本粒子滤波算法相结合,运用无迹卡尔曼滤波算法获得重要性函数,提高了粒子的使用效率; 运用混合遗传模拟退火算法的进化思想,提高了粒子的多样性.仿真结果表明,新算法很好地解决了基本粒子滤波算法存在的粒子退化问题,提高了系统的滤波精度和稳定性(在信噪比为16dB时,精度提高80%以上),较好地抑制了噪声的干扰.

关键词: 粒子滤波, 无迹卡尔曼滤波, 重要性概率密度, 混合遗传模拟退火算法

Abstract:

The sample degeneracy is the critical problem existing in the particle filter. In order to solve this problem, a new combined particle filter algorithm, based on the genetic simulated annealing algorithm and unscented Kalman filter algorithm, is presented in this paper. In the proposed algorithm, unscented Kalman filter algorithm is used to generate the importance proposal distribution which can match the true posterior distribution more closely, and the genetic simulated annealing algorithm based upon the survival-of-the-fitness principle is applied to enhance the diversity of samples. Simulation results indicate the effectiveness and feasibility of the proposed algorithm.

Key words: particle filter, unscented Kalman filter, proposal probability density, genetic annealing simulated algorithm