一种人工物理优化的粒子滤波算法
DOI:
CSTR:
作者:
作者单位:

作者简介:

钱东

通讯作者:

中图分类号:

基金项目:

国家自然科学基金重点资助项目


An artificial physics optimized particle filter
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    为了改善传统粒子滤波中的粒子退化和样本贫化问题, 提出一种人工物理优化的粒子滤波方法. 通过引入
    人工物理优化, 对粒子滤波重采样过程进行了改进. 人工物理优化虚拟力模型规定粒子间存在相互作用的吸引力或
    排斥力, 通过优化可以使粒子集提高对后验概率密度的逼近程度, 克服粒子退化的问题. 同时, 由于粒子在移动过程
    中相互牵制, 优化后粒子集分布性更好, 并避免了粒子重叠或过度拥挤, 从而提高了估计能力, 维持了粒子的多样性.
    仿真实验结果验证了所提出算法的有效性, 同时表明, 该算法具有较好的估计精度和稳定性.

    Abstract:

    In this paper, an artificial physics optimized particle filter(APO-PF) is proposed. Artificial physics optimization
    (APO) is incorpoarted into resampling process to deal with the sample degeneration and impoverishment of generic
    particle filter(PF). Virtual force model of the APO specifies that particles have mutually attractive and repulsive force.
    Through optimization, the APO can distribute particles in high likelihood area, and the sample degeneration is reduced.
    Synchronously, the APO makes particles contain each other in the motion process, ulteriorly formats better coverage to
    posterior probability density, which improves estimation performance, particle overlap is avoided and diversity of particle
    is also maintained. The simulations are performed to show the effectiveness of the algorithm, and the results show that the
    estimation performance and robustness of the proposed algorithm are superior to that of the generic PF.

    参考文献
    相似文献
    引证文献
引用本文

刘繁明, 钱东, 刘超华.一种人工物理优化的粒子滤波算法[J].控制与决策,2012,27(8):1145-1149

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2011-01-17
  • 最后修改日期:2011-05-12
  • 录用日期:
  • 在线发布日期: 2012-08-20
  • 出版日期:
文章二维码