| 基于人工鱼群的无轨迹粒子滤波算法 |
| |
| 引用本文： | 梁磊,逄博,赵丽丽.基于人工鱼群的无轨迹粒子滤波算法[J].计算机应用与软件,2012(1):137-140. |
| |
| 作者姓名： | 梁磊 逄博 赵丽丽 |
| |
| 作者单位： | 兰州理工大学计算机与通信学院;兰州理工大学经济管理学院 |
| |
| 基金项目： | 甘肃省自然科学基金(1014RJZA028) |
| |
| 摘 要： | 针对粒子滤波算法中粒子退化现象及重采样所带来的粒子贫化问题,提出一种基于人工鱼群的无轨迹粒子滤波算法。采用无轨迹变换选取优化的重要性密度函数,将人工鱼群的智能思想引入到粒子滤波中代替重采样过程,通过觅食、聚群和追尾行为找到全局最优位置,驱动粒子向最优点靠近,从而增加粒子多样性。仿真结果表明,与传统的无轨迹粒子滤波和常规粒子滤波相比,该算法在估计精度上有显著的提高。
|
| 关 键 词： | 无轨迹粒子滤波 人工鱼群算法 粒子退化 粒子贫化 |
UNSCENTED PARTICLE FILTER BASED ON ARTIFICIAL FISH SCHOOL ALGORITHM |
| |
| Liang Lei,Pang Bo,Zhao Lili.UNSCENTED PARTICLE FILTER BASED ON ARTIFICIAL FISH SCHOOL ALGORITHM[J].Computer Applications and Software,2012(1):137-140. |
| |
| Authors: | Liang Lei Pang Bo Zhao Lili |
| |
| Affiliation: | 1(School of Computer and Communication,Lanzhou University of Technology,Lanzhou 730050,Gansu,China) 2(School of Economics and Management,Lanzhou University of Technology,Lanzhou 730050,Gansu,China) |
| |
| Abstract: | To overcome the particle impoverishment problem caused by particle degeneracy phenomenon and re-sampling in particle filter algorithms,the paper proposes an unscented particle filter algorithm based on artificial fish school.The algorithm uses unscented transform to select optimized importance density functions,replacing re-sampling by introducing the intelligent thought of artificial fish school to particle filter which,through preying,swarming and following behaviors,finds out a global optimum position and drive particles towards that optimum site.Simulation results show that,compared with the traditional unscented particle filter and conventional particle filter,there is significant improvement on estimation precision with the proposed algorithm. |
| |
| Keywords: | Unscented particle filter Artificial fish school algorithm Particle degeneracy Particle impoverishment |
| 本文献已被 CNKI 等数据库收录！ |
|
