计算机科学 ›› 2020, Vol. 47 ›› Issue (5): 230-235.doi: 10.11896/jsjkx.190300155

• 人工智能 • 上一篇    下一篇

车联网络通过两级量化自适应卡尔曼滤波实现车辆状态预测

冯安琪, 钱丽萍, 欧阳金源, 吴远   

  1. 浙江工业大学信息工程学院 杭州310023
  • 收稿日期:2019-03-29 出版日期:2020-05-15 发布日期:2020-05-19
  • 通讯作者: 钱丽萍(lpqian@zjut.edu.cn)
  • 作者简介:aqfeng_zjut@163.com
  • 基金资助:
    国家自然科学基金(61379122);浙江省自然科学基金(LR16F010003)

Vehicular Networking Enabled Vehicle State Prediction with Two-level Quantized AdaptiveKalman Filtering

FENG An-qi, QIAN Li-ping, OUYANG Jin-yuan, WU Yuan   

  1. College of Information Engineering,Zhejiang University of Technology,Hangzhou 310023,China
  • Received:2019-03-29 Online:2020-05-15 Published:2020-05-19
  • About author:FENG An-qi,born in 1995,postgra-duate.Her main research interests include network and intelligent systems,vehicular networking and Internet of Things technologies.
    QIAN Li-ping,born in 1981,Ph.D,professor,Ph.D supervisor,is a member of China Computer Federation.Her main research interests include wireless communication network,vehicular networking and Internet of Things technologies.
  • Supported by:
    This work was supported by the National Natural Science Foundation of China (61379122) and Natural Science Foundation of Zhejiang Province,China (LR16F010003)

摘要: 随着城市化和机动化的快速发展,交通安全越来越受到人们的关注。利用车载网络系统获取车载数据来预测车辆下一时刻的车载状态,对于提高运输路段的交通安全起着重要作用。文中提出一种基于自回归滑动平均(Auto-Regressice Mo-ving Average,ARMA)模型的两级量化自适应卡尔曼滤波算法,来预测车辆的行车状态(行驶的方向、行驶的车道、车辆的速度和加速度)。首先,开发了一个车载网络系统,通过交换车载单元(On-Board Unit,OBU)和路边单元(Roadside Unit,RSU)之间的交通数据来获取车辆数据;然后,通过配置在路边单元的边缘云服务器来预测车辆状态;最后,边缘服务器把预测到的状态信息广播给其他路边单元,以便交叉口其他车辆获取车辆信息。实验结果验证了用于预测加速度的自回归移动平均模型的有效性。此外,文中还评估了所提算法的有效性。与其他3种预测算法相比,所提算法的速度预测精度分别提高了90.62%,89.81%,82.76%,这说明该算法在车载网络中能有效预测车辆状态。

关键词: 车辆状态预测, 车载网络, 交通安全, 量化自适应卡尔曼滤波, 自回归滑动平均模型

Abstract: With the rapid development of urbanization and motorization,traffic safety issues have been drawing more and more attentions.The accurate prediction of vehicle state based on the data acquired by the vehicular networking system plays an important role in improving the traffic safety in transportation section.This paper proposes a two-level quantized adaptive Kalman filter algorithm (QAKF) based on the auto-regressive moving average (ARMA) model,to predict the vehicle state (i.e.,the moving direction,driving lane,vehicle speed,and acceleration).First of all,a vehicular networking system is developed to acquire the vehicle data by exchanging traffic data among the on-board unit (OBU) and the roadside unit (RST).Then,the vehicle state is predicted at the edge cloud server equipped at the roadside unit.Finally,the edge cloud server broadcasts the predicted state to other roadside units for other vehicles at the intersection to obtain vehicle information.The numerical results verify the effectiveness of the auto-regressive moving average model used for predicting acceleration.And,this paper evaluates the efficiency of the proposed algorithm.Compared with the other three prediction algorithms,the proposed algorithm can improve the speed prediction accuracy by 90.62%,89.81% and 82.76%,respectively,which implies that this algorithm can effectively predict the vehicle state in vehicular networks.

Key words: Auto-regressive moving average model, Quantized adaptive Kalman filter, Traffic safety, Vehicle state predication, Vehicular networks

中图分类号: 

  • TP391
[1]WHO.Deaths on the roads:based on the WHO global status re-port on road safety 2015[M].World Health Organization (WHO),2015.
[2]CHENG N,LYU F,CHEN J Y,et al.Big data driven vehicular networks[J].IEEE Network,2018,32(6):160-167.
[3]QIAN L P,WU Y,ZHOU H B,et al.Dynamic cell association for non-orthogonal multiple-access V2S networks[J].IEEE Journal on Selected Areas in Communications,2017,35(10):2342-2356.
[4]TAKAHASHI Y,KAWAMOTO Y,NISHIYAMA H,et al.A novel radio resource optimization method for relay-based unmanned aerial vehicles[J].IEEE Transactions on Wireless Communications,2018,17(11):7352-7363.
[5]SUN Y L,XU Y,TANG Y L,et al.Traffic offloading for online video service in vehicular networks:a cooperative approach[J].IEEE Transactions on Vehicular Technology,2018,67(8):7630-7642.
[6]BHARATI S,ZHUANG W H,THANAYANKIZIL L V,et al.Link-layer cooperation based on distributed TDMA MAC for vehicular networks[J].IEEE Transactions on Vehicular Technology,2017,66(7):6415-6427.
[7]LIU K,FENG L,DAI P L,et al.Coding-assisted broadcastscheduling via memetic computing in SDN-based vehicular networks[J].IEEE Transactions on Intelligent Transportation Systems,2018,19(8):2420-2431.
[8]RASHDAN L,SCHMIDHAMMER M,MUELLER F P,et al.Performance evaluation of vehicle-to-vehicle communication for cooperative collision avoidance at urban intersections[C]//IEEE 86th Vehicular Technology Conference (VTC-Fall).2017:1-5.
[9]HAFEEZ K A,ANPALAGAN A,ZHAO L.Optimizing thecontrol channel interval of the DSRC for vehicular safety applications[J].IEEE Transactions on Vehicular Technology,2016,65(5):3377-3388.
[10]KIM B,YI K.Probabilistic and holistic prediction of vehiclestates using sensor fusion for application to integrated vehicle safety systems[J].IEEE Transactions on Intelligent Transportation Systems,2014,15(5):2178-2190.
[11]WANG Y,DENG Q X,LIU G H,et al.Dynamic target tracking and predicting algorithm based on combination of motion equation and Kalman filter[J].Computer Science,2015,42(12):76-81.
[12]PARK S,KIM B,KANG C,et al.Sequence-to-sequence prediction of vehicle trajectory via LSTM encoder-decoder architecture[C]//IEEE Intelligent Vehicles Symposium (IV).2018:1672-1678.
[13]FENG A Q,QIAN L P,HUANG Y P,et al.RFID data driven vehicle speed prediction using adaptiveKalman filter [J].Computer Science,2019,46(4):100-105.
[14]BASYONI Y,ABBAS H M,TALAAT H,et al,Speed prediction from mobile sensors using cellular phone-based traffic data[J].IET Intelligent Transport Systems,2017,11(7):387-396.
[15]HU X,BAO M,ZHANG X,et al.Quantized Kalman filtertracking in directional sensor networks[J].IEEE Transactions on Mobile Computing,2018,17(4):871-883.
[16]HU X,BAO M,ZHANG X,et al.Generalized iterated Kalman filter and its performance evaluation[J].IEEE Transactions on Signal Processing,2015,63(12):3204-3217.
[17]RAHIMI A,DUNAGAN B,DARRELL T.Tracking peoplewith a sparse network of bearing sensors[C]//Computer Vision(ECCV 2004).Heidelberg:Springer,2004:507-518.
[18]WANG X W,SHEN X L,LIU X S.Random error analysis of MEMS gyroscope based on adaptive Kalman filter[J].Chinese Journal of Sensors and Actuators,2017,30(11):1666-1670.
[19]LEBRE M,MOUEL F,MENARD E.On the importance of real data for microscopic urban vehicular mobility trace[C]//International Conference on ITS Telecommunications.2015:22-26.
[20]LEBRE M,MOUEL F,MENARD E.Partial and local know-ledge for global efficiency of urban vehicular traffic[C]//IEEE 82nd Vehicular Technology Conference.2015:1-5.
[1] 于天琪, 胡剑凌, 金炯, 羊箭锋.
基于移动边缘计算的车载CAN网络入侵检测方法
Mobile Edge Computing Based In-vehicle CAN Network Intrusion Detection Method
计算机科学, 2021, 48(1): 34-39. https://doi.org/10.11896/jsjkx.200900181
[2] 樊英, 张达敏, 陈忠云, 王依柔, 徐航, 王栎桥.
基于改进乌鸦算法的车载网络频谱分配方案
Spectrum Allocation Scheme of Vehicular Ad Hoc Networks Based on Improved Crow Search Algorithm
计算机科学, 2020, 47(12): 273-278. https://doi.org/10.11896/jsjkx.190900199
[3] 陈杰, 谢显中, 黄倩, 黎佳.
无线车载网络中一种基于跨层优化的网络编码TCP协议
Network Coding TCP Protocol Based on Cross-layer Optimization in Wireless Vehicle Networks
计算机科学, 2019, 46(2): 88-94. https://doi.org/10.11896/j.issn.1002-137X.2019.02.014
[4] 姚宏,白长敏,胡成玉,曾德泽,梁庆中.
移动数据分流研究综述
Survey on Mobile Data Offloading
计算机科学, 2014, 41(Z11): 182-186.
[5] 汪峥,钱焕延,汪婧雅,高德民.
车载物联网中蠕虫传播模型的构建与仿真
Construction and Simulation of Worm Propagation Model in Vehicular Internet of Things
计算机科学, 2012, 39(3): 28-32.
[6] 蔡青松,牛建伟,刘畅.
一种基于车载机会网络的自适应数据分发算法
Adaptive Data Dissemination Algorithm for Vehicular Opportunistic Networks
计算机科学, 2011, 38(6): 58-63.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!