Author(s)

Daixian Zhu¹, Mingbo Wang¹, Mengyao Su¹, Shulin Liu², Ping Guo¹

Affiliation(s)

¹ College of communication and Information Engineering, Xi'an University of Science and Technology, Xi'an 710054, China;

² College of electrical and control engineering, Xi'an University of Science and Technology, Xi'an 710054, China.

Corresponding Author

ABSTRACT

Aiming at the problem of particle filter weight degradation and loss of diversity resulting in poor filter accuracy, an improved algorithm based on improved gravitational field optimization particle filter (Improved-GFA-PF, I-GFA-PF) was proposed. The resampling process of the particle filter algorithm is optimized by improving the gravitational field, namely using the gravitational field algorithm to optimize the particle set to be concentrated in the high-likelihood area to solve the weight degradation. To ensure particle diversity and filtering accuracy, the evaluation criteria of moving weight and rotation rejection factor were reset on the basis of the original algorithm, so as to increase the particles diversity and improve the filtering accuracy. The simulation results show that the filtering accuracy of the proposed I-GFA-PF is about 12% higher than that of the GFA-PF.

KEYWORDS

Particle filter, weight degradation, particle diversity, gravitational field algorithm, global optimal value.

CITE THIS PAPER

Zhu Daixian, Wang Mingbo, Su Mengyao, Liu Shulin, Guo Ping. An optimized particle filter method based on improved gravitational field algorithm. Eurasia Journal of Science and Technology. 2020, 2(2): 58-63.

REFERENCES

[1]Maroulas V , Stinis P . Improved particle filters for multi-target tracking[J]. Journal of Computational Physics, 2012, 231(2):602-611.

[2] Jiashan Cui,Dongzhu Feng,Yunhui Li,Qichen Tian. Research on simultaneous localization and mapping for AUV by an improved method: Variance reduction FastSLAM with simulated annealing[J]. Defence Technology,2019.

[3] Somayyeh Sadegh Moghaddasi,Neda Faraji. A hybrid algorithm based on particle filter and genetic algorithm for target tracking[J]. Expert Systems With Applications,2020,147.

[4] Wang Guofeng,Dong Yi,Yang Kai,An Hua.Tool life prediction based on deep learning and particle filter[J].Journal of Tianjin University (Natural Science and Engineering Technology Edition), 2019,52(11):1109-1116.

[5] Bi Xiaojun, Hu Songyi. High-precision firefly optimized particle filter algorithm based on hybrid guidance strategy[J]. Journal of Shanghai Jiaotong University, 2019, Volume 53(2):232-238.

[6] Teng Fei,Xue Lei,Li Xiuhe.KLD-based bat algorithm optimization adaptive particle filter[J].Control and Decision,2019,34(03): 561-566.

[7] Li Weigang,Li Yang,Zhao Yuntao,Yan Baokang.Research on Particle Filter Algorithm Based on Improved Grey Wolf Algorithm[J/OL].Journal of System Simulation:1-8[2020-03-24].http://kns.cnki.net/kcms/detail/11.3092.V.20191226.1616.018.html.

[8] Cui Haoyang,Zhang Yu,Zhou Kun,Hu Fengye,Xu Yongpeng.Study on accuracy prediction of SLAM algorithm based on bionic algorithm-improved particle filter[J/OL].Control and Decision: 1-7[2020-03-24].https://doi.org/10.13195/j.kzyjc.2019.0555.

[9] Zhu Zhenshu, Jiang Changhui, Bo Yuming et al. Improved particle filter algorithm for krill swarm optimization[J]. Journal of Harbin Institute of Technology, 2020, (2)

[10] Chen Shiming,Liu Junkai,Xiao Juan.Unscented FastSLAM2.0 Algorithm Based on Gravitational Field Optimization[J].Control Theory and Applications,2018,35(08):1186-1193.

[11] Zheng Ming. Gravitational field algorithm and its application in bioinformatics[D]. Jilin University,2013.

[12] Zan Mengen, Zhou Hang, Han Dan et al. Overview of particle filter target tracking algorithms[J]. Computer Engineering and Applications, 2019, Volume 55(5):8-17，59.

[13] Chen Shiming,Xiao Juan,Li Haiying,Nie Sen.Particle filter algorithm based on gravitational field[J].Control and Decision, 2017,32(04):709-714.

[14]Wu Yali,Fu Yulong,Wang Xinrui,Liu Qing.A Differential Brainstorming Optimization Algorithm for Target Space Clustering[J].Control Theory and Applications,2017,34(12):1583-1593.