|Table of Contents|

Application of relevance vector machine in vehicle state estimation(PDF)

长安大学学报（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

Issue:
2013年03期
Page:
88-93
Research Field:
汽车与机械工程
Publishing date:

Info

Title:
Application of relevance vector machine in vehicle state estimation
Author(s):
LUO Cheng-zhen;  ZHANG Ya-qi;  REN Chao-wei
School of Autombobile, Chang’an University, Xi’an 710064, Shaanxi, China
Keywords:
automobile engineering;  motion state;  estimation;  RVM;  Kalman filtering
PACS:
U461.51; TP206
DOI:
-
Abstract:
Because vehicle movement exists nonlinear characteristics, this paper adopted relevance vector machine(RVM)to estimate the vehicle state. The test time of relevance vector machine is shorter than support vector machine(SVM)and the amount of computation is smaller than SVM. In order to estimate vehicle state accurately, Kalman filter was used to filter yaw rate and velocity data after collecting the test data. The filtered data were regarded as the input of relevance vector machine. Then the maximum likelihood function was established according to Bayesian theory. The difference between the change of yaw rate and velocity data was considered. The optimal number of iterations could be determined by gamma values, values difference and the maximum likelihood values in different iterations so as to guarantee the shorter testing time and higher hit probability of this model. Finally, the validation of the model was proved. The results show that this model can approximate to the true values of the estimated samples more accurately. The yaw rates with greater volatility need more number of iterations, gamma values and values change more rapidly, and the convergence speed is faster. 2 tabs, 9 figs, 11 refs.

References:

[1] Young M S,Stanton N A.Taking the load off: investigations of how adaptive cruise control affects mental workload[J].Ergonomics,2004,47(9):1014-1035.
[2]Maduro C,Batista K,Batista J.Estimating vehicle velocity using image profiles on rectified images[J].Pattern Recognition and Image Analysis,2009(5524):64-71.
[3]Kato J,Watanabe T,Joga S.An Hmm/MRF-based stochastic framework for robust vehicle tracking[J].Intelligent Transportation System,2004,5(3):142-154.
[4]陈 林,施树明,李元芳.车辆操纵稳定性状态估计算法比较研究[J].交通信息与安全,2011,29(5):36-40.CHEN Lin,SHI Shu-ming,LI Yuan-fang.Comparative study of some estimation algorithms for vehicle stability state[J].Traffic Information and Safety,2011,29(5):36-40.(in Chinese)
[5]余卓平,高晓杰.车辆行驶过程中状态估计问题综述[J].机械工程学报,2009,45(5):20-33.YU Zhuo-ping,GAO Xiao-jie.Review of vehicle state estimation problem under driving situation[J].Journal of Mechanical Engineering,2009,45(5):20-33.(in Chinese)
[6]Liu A,Salvucci D.Modeling and prediction of human driver behavior[C]//Lawrence Erlbaum Associates.9th International Conference on Human-Computer Interaction.New Orleans:Lawrence Erlbaum Associates.2001:1542-1547.
[7]Liu W,Wen X Z,Duan B B,et al.Rear vehicle detection and tracking for lane change assist[C]//IEEE.Proceedings of the 2007 IEEE Intelligent Vehicles Symposium.Istanbul:IEEE,2007:252-257.
[8]聂建亮,张双成,徐永胜,等.基于抗差Kalman滤波的精密单点定位[J].地球科学与环境学报,2010,32(2):218-220.NIE Jian-liang,ZHANG Shuang-cheng,XU Yong-sheng,et al.Precise point positioning based on robust Kalman filtering[J].Journal of Earth Sciences and Environment,2010,32(2):218-220.(in Chinese)
[9]周露平,陈会勇,方 伟,等.基于Kalman滤波的特征跟踪[J].建模与仿真技术,2009(9):263-267.ZHOU Lu-ping,CHEN Hui-yong,FANG Wei,et al.Tracking of feature point based on Kalman filter[J].Modeling and Simulation Technology,2009(9):263-267.(in Chinese)
[10]惠文华.基于支持向量机的遥感图像分类方法[J].地球科学与环境学报,2006,28(2):93-95.HUI Wen-hua.TM image classification based on support vector machine[J].Journal of Earth Sciences and Environment,2006,28(2):93-95.(in Chinese)
[11]杨树仁,沈洪远.基于相关向量机的机器学习算法研究与应用[J].计算技术与自动化,2010,29(1):43-47.YANG Shu-ren,SHEN Hong-yuan.Research and application of machine learning algorithm based on relevance vector machine[J].Computing Technology and Automation,2010,29(1):43-47.(in Chinese)

Memo

Memo:
-
Last Update: 2013-05-30