摘要
针对粒子滤波算法重采样导致的样本贫化问题,提出基于鸽群优化(PIO)思想改进的粒子滤波算法。将鸽群不断从较远位置飞向适应度值高的地方的归巢过程引入到粒子滤波中,驱使粒子不断向高似然区域移动,并将自适应交叉操作加入到鸽群优化过程当中,保障样本多样性。通过非线性模型仿真实验表明,所提算法相对于标准粒子滤波算法,精度提高了45%,稳定性提高了72%,同时降低了状态估计所需的粒子数量。
A particle filtering(PF) algorithm based on pigeon-inspired optimization(PIO) is proposed,aiming at problem of sample impoverishment caused by resampling of PF algorithm.When pigeons fly,they usually fly from a far position to high fitness areas constantly.This optimum process is introduced into PF to drive particles moving towards high likelihood areas ceaselessly. And adaptive crossover operation is added to the process of PIO to guarantee the diversity of samples. The nonlinear model simulations experiments show that the precision of the proposed algorithm is improved by 45 % compared with the standard PF algorithm,the stability is improved by72 %,and the number of particles required for the state estimation is reduced at the same time.
引文
[1]Doucte A,de Freitas N,Gordon N.Sequential Monte Carol methods in practice[M].New Work:Springer-Verlag,2001.
[2]王法胜,鲁明羽,赵清杰,等.粒子滤波算法[J].计算机学报,2014,37(8):1679-1694.
[3]Gustafsson F.Particle filter theory and practice with positioning applications[J]. Aerospace&Electronic Systems Magazine,IEEE,2010,25(7):53-82.
[4]李天成,范红旗,孙树栋.粒子滤波理论、方法及其在多目标跟踪中的应用[J].自动化学报,2015,41(12):1981-2002.
[5]Gao M,Zhang H.Sequential Monte Carlo methods for parameter estimation in nonlinear state-space models[J].Computers&Geosciences,2012,44(13):70-77.
[6]Arulampalam M S,Maskell S,Gordon N,et al.A tutorial on particle filters for online nonlinear/nongaussisan Bayesian tracking[J]. IEEE Transactions on Siganl Processing,2002,50(2):174-188.
[7]Foo P H,Ng G W.Combing the interacting multiple model method with particle filters for manoeuvring target tracking[J]. IET Radar,Sonar and Navigation,2011,5(3):234-255.
[8]Thrun S,Langford J,Verma V.Risk sensitive particle filters[J].Adrances in Nearal Information Processing Systems,2001,22(3):961-968.
[9]Li T C,Sattar T P,Sun S D.Deterministic resampling:Unbiased sampling to avoid sample impoverishment in particle filters[J].Signal Processing,2012,92(7):1637-1645.
[10]张光,张英堂,任国全,等.基于正则化粒子滤波的磁梯度张量跟踪方法[J].探测与控制学报,2014(2):0050-0053.
[11]罗颖,谭冠政.基于SSPF算法的移动机器人全局定位研究[J].传感器与微系统,2008,27(5):31-34.
[12]Yu Y,Zheng X.Particle filter with ant colony optimization for frequency offset estimation in OFDM systems with unknown noise distribution[J].Signal Processing,2011,91(5):1339-1342.
[13]田梦楚,薄煜明,陈志敏,等.萤火虫算法智能优化粒子滤波[J].自动化学报,2016,42(1):89-97.
[14]汪荣贵,李孟敏,吴昊,等.一种新型的基于自适应遗传算法的粒子滤波算法[J].中国科学技术大学学报,2011,41(2):134-141.
[15]方正,徐国峰,徐心和.粒子群优化粒子滤波方法[J].控制与决策,2007,27(3):273-277.
[16]Tian Y,Lu C,Wang Z,et al.Artificial fish swarm algorithm-based particle filter for l Li-ion battery life prediction[J]. Mathematical Problems in Engineering,2014(3):1-10.
[17]Duan H,Qiao P.Pigeon-inspired optimization:A new swarm intelligence optimizer for air robot path planning[J]. International Journal of Intelligent Computing&Cybernetics,2014,7(1):24-37.
[18]段海滨,叶飞.鸽群优化算法研究进展[J].北京工业大学学报,2017,43(1):1-7.
[19]朱志宇.粒子滤波算法及其应用[M].北京:科学出版社,2010:27-31.
[20]周雨鹏.基于鸽群算法的函数优化问题求解[D].长春:东北师范大学,2016:6-8.