计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (6): 384-390.doi: 10.11896/jsjkx.231000126

• 计算机网络 • 上一篇    下一篇

基于边缘智能的车辆编队协同控制方法研究

李乐1, 刘美芳1, 陈荣1, 魏思雨2   

  1. 1 青岛海信微联信号有限公司 山东 青岛 266400
    2 北京交通大学电子信息工程学院 北京 100044
  • 收稿日期:2023-10-18 修回日期:2024-03-29 出版日期:2024-06-15 发布日期:2024-06-05
  • 通讯作者: 陈荣(chenrong9@hisense.com)
  • 作者简介:(lile5@hisense.com)

Study on Collaborative Control Method of Vehicle Platooning Based on Edge Intelligence

LI Le1, LIU Meifang1, CHEN Rong1, WEI Siyu2   

  1. 1 Qingdao Hisense Microunion Signal Co.,LTD.,Qingdao,Shandong 266400,China
    22 School of Electronic and Information Engineering,Beijing Jiaotong University,Beijing 100044,China
  • Received:2023-10-18 Revised:2024-03-29 Online:2024-06-15 Published:2024-06-05
  • About author:LI Le,born in 1984,master,engineer.His main research interests include railway signal control system and edge computing.
    CHEN Rong,born in 1988,postgra-duate,engineer.His main research interests include railway signal control system and edge intelligence.

PDF (PC)

506

摘要： 随着通信技术及自动化控制技术的发展,智能网联汽车的自主控制方法,特别是混合编队下的控制方法已经成为无人驾驶技术研究的重要方向。由于车载处理器计算能力有限,为了减少控制策略输出的时延,提高车辆跟踪效果,提出了基于边缘智能的车辆编队协同控制方法。利用边缘服务器的强大计算能力和5G通信网络,设计了基于边缘智能的控制系统,将计算任务上传至云端,充分释放车载处理器的计算资源。对混合编队下的跟车场景进行了分析,设计了时空耦合场景下的车辆编队控制模型,利用MPC控制算法,建立了车辆动力学模型,通过模型预测、滚动优化与反馈校正为智能网联汽车提供控制策略计算服务。经MATLAB仿真实验及边缘计算虚拟平台实验验证,所提出的MPC控制算法在轨迹跟踪控制上表现良好,能够实时高效地为车辆提供安全控制策略。

关键词: 边缘智能, 车辆编队, 协同控制, 智能网联汽车

Abstract: With the development of communication technology and automatic control technology,the autonomous control method of intelligent and connected vehicles(ICV),especially the control method under hybrid platooning,has become an important direction of the research of unmanned driving technology.In order to reduce the delay of control strategy output due to the limitation of computing power of on-board processor,and improve vehicle tracking effect,a collaborative control method of vehicle platooning based on edge intelligence is proposed.Using the powerful computing power of edge server and 5G communication network,a control system based on edge intelligence is designed to upload computing tasks to the cloud and release the computing resources of the on-board processor.Based on the analysis of vehicle following scenario in hybrid platooning,a vehicle platooning control model in spatiotemporal coupling scenario is designed,and a vehicle dynamics model is established by using MPC control algorithm.Through model prediction,rolling optimization and feedback correction,control strategy calculation services are provi-ded for intelligent and connected vehicle.The results of MATLAB simulation experiment and edge computing virtual platform experiment show that the proposed MPC control algorithm performs well in trajectory tracking control and can provide safety control strategy for vehicles in real time and efficiently.

Key words: Edge intelligence, Vehicle platooning, Cooperative control, Intelligent and connected vehicle

中图分类号: 

  • U491
[1]LIANG Z C,ZHANG H,ZHAO J,et al.Trajectory trackingcontrol of unmanned vehicles based on adaptive MPC[J].Journal of Northeastern University(Natural Science),2020,41(6):835-840.
[2]MONTEIL J,BOUROCHE M,LEITH D J.L2 and L∞ Stability Analysis of Heterogeneous Traffic With Application to Parameter Optimization for the Control of Automated Vehicles[J].IEEE Transactions on Control Systems Technology,2018,27(3):934-946.
[3]Xinhua,Sadie consultant.The development report of the con-nected vehicle industry[EB/OL].https://max.book118.comhtml201908038116017073002040.shtm.
[4]HUI N,WU J,ZHOU Y Q,et al.Future Vehicular fog computing networks[J].Telecommunications Science,2020,36(6):14-27.
[5]LI X,BAO L Y,DING H W,et al.MAC layer scheduling strategy of roadside units based on MEC server priority service[J/OL].http://www.joca.cn/CN/10.11772/j.issn.1001-9081.2023050556.
[6]LV P,XU J,LI T S,et al.Survey on edge computing technology for autonomous driving[J].Journal on Communications,2021,42(3):190-208.
[7]MA X T.Research on resource allocation and scheduling optimization in vehicle platooning networks[D].Beijing:Beijing Jiaotong University,2022.
[8]LV Z,QIAO L,CAI K,et al.Big data analysis technology forelectric vehicle networks in smart cities[J].IEEE Transactions on Intelligent Transportation Systems,2020,22(3):1807-1816.
[9]LI Q Y,YI HAO.SUN Y X.A 5G intelligent connected vehicle service platform based on mobile edge computing for collaborative driving[J].South Forum,2022,53(11):24-26,32.
[10]SONG I,TAM P,KANG S,et al.DRL-Based Backbone SDN Control Methods in UAV-Assisted Networks for Computational Resource Efficiency[J].Electronics,2023,12(13):2984.
[11]HUANG M T,YI Y H,ZHANG G L.Service Caching and Task Offloading for Mobile Edge Computing-Enabled Intelligent Connected Vehicles[J].Journal of Shanghai Jiaotong University (Science),2021,26(5):670-679.
[12]SUN X,ANSARI N.EdgeIoT:Mobile edge computing for the Internet of Things[J].IEEE Communications Magazine,2016,54(12):22 -29.
[13]SINGH R,SALUJA D,KUMAR S.Graphical approach for V2V connectivity enhancement in clustering-based VANET[J].IEEE Wireless Communications Letters,2021,10(6):1217-1221.
[14]GUO Y,SONG X P,LIANG R L.Simulation analysis on stability of network of connected vehicle platooning under unreliable network environment[J].Electronic Design Engineering,2021,29(15):77-82.
[15]GE L H,ZHAO Y,ZHOU S R,et al.Motion Control of Auto-nomous Vehicles Based on Offset Free Model Predictive Control Methods[J].Journal of Dynamic Systems,Measurement,and Control,2022,144(11):11003.
[16]SEONGHYUN K,TAEHONG K.Local Scheduling in Kube-Edge-Based Edge Computing Environment[J].Sensors,2023,23(3):1522.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发