基于数字孪生的道路交叉口建模与应用

doi:10.3969/j.issn.1674-8484.2023.01.007

汽车安全与节能学报 ›› 2023, Vol. 14 ›› Issue (1): 55-61.DOI: 10.3969/j.issn.1674-8484.2023.01.007

基于数字孪生的道路交叉口建模与应用

张宏¹^,²(), 于海亮¹, 郑赞¹, 袁胜东³, 熊国强³

1.内蒙古大学交通学院，呼和浩特 010020，中国
2.内蒙古自治区城市交通数据科学及应用工程技术研究中心，呼和浩特010020，中国
3.北奔重型汽车集团有限公司创新研究院，包头014032，中国

收稿日期:2022-05-21 修回日期:2022-10-24 出版日期:2023-02-28 发布日期:2023-03-07
作者简介:张宏(1981—），女（汉），内蒙古，副教授。E-mail: zh-hong@foxmail.com。
基金资助:
内蒙古自治区高等学校青年科技英才支持项目(NJYT23060);内蒙古大学研究生科研创新项目

Modeling and application of road intersections based on digital twins

ZHANG Hong¹^,²(), YU Hailiang¹, ZHENG Zan¹, YUAN Shengdong³, XIONG Guoqiang³

1. School of Transportation, Inner Mongolia University, Hohhot 010020, China
2. CInner Mongolia Engineering Research Center for Urban Transportation Data Science and Applications, Hohhot 010020, China
3. Innovation Institute, Beiben Trucks Group Company Limited, Baotou 014032, China

Received:2022-05-21 Revised:2022-10-24 Online:2023-02-28 Published:2023-03-07

摘要/Abstract

摘要：

为有效调控路网交通状态，建立了一种道路交叉口交通数字孪生管理系统。从理论方面和模型的构建、组装、融合、管理、验证及校正等6个方面，阐述了该模型的核心要素及模型构建理论体系；从交通要素管理和运行过程控制2个方面，分析了模型的运行机制和人、车、路、环境的实时交互关键技术；基于机器视觉，实时识别交叉口的交通要素及运行状态；分析“以虚控实”管理系统的构建技术。研究表明：该方法能对道路交叉口的交通要素及运行状态实现精确识别与仿真，可望为相关部门高效调节路网交通状态创建数字化窗口及为自动驾驶提供数据支持。

关键词: 智能交通, 交通管理系统, 数字孪生, 道路交叉口, 以虚控实, 机器视觉

Abstract:

A digital twin traffic management system at road intersection was established to effectively regulate the traffic state of the road network. The core elements and theoretical system of the digital twin model of road intersection were described from six aspects: the theory and the model construction, assembly, integration, management, verification and correction. The operation mechanism of the model and the key technologies of real-time interaction between man, vehicle, road and environment were analyzed from two aspects of the traffic element management and the operation process control. The traffic elements and the intersection operation status were identified in real time based on machine vision; The construction technology was analyzed for the management system based on “virtual control reality”. The results show that this method can accurately identify and simulate the traffic elements and operation state of the road intersection, create a digital window for relevant departments to efficiently adjust the traffic state of the road network, and provide data support for automatic driving.

Key words: intelligent transportation, traffic management system, digital twins, road intersection, virtual control of reality, machine vision

中图分类号:

TP391.9

张宏, 于海亮, 郑赞, 袁胜东, 熊国强. 基于数字孪生的道路交叉口建模与应用[J]. 汽车安全与节能学报, 2023, 14(1): 55-61.

ZHANG Hong, YU Hailiang, ZHENG Zan, YUAN Shengdong, XIONG Guoqiang. Modeling and application of road intersections based on digital twins[J]. Journal of Automotive Safety and Energy, 2023, 14(1): 55-61.

图/表 12

图1 数字孪生模型及相关要素

图2 模型构建理论体系

图3 数字孪生道路交叉口模型校正系统

图4 数字孪生道路交叉口模型运行机制

图5 数字孪生道路交叉口数据交互设计理念

图6 数字孪生道路交叉口模型构建关键技术

图7 道路交叉口交通场景建模

图8 数字化道路交叉口交通状态建模

图9 呼和浩特市某道路交叉口机器视觉技术识别交通状态

测试版本	YOLOv5
网络模型	YOLOv5l.pt
模型深度	1.0
模型广度	1.0
NMS置信度	0.45
置信度	0.15

表1 机器视觉技术测试

图10 激光雷达识别道路交叉口交通状态

图11 数字孪生道路交叉口管理系统

参考文献 14

[1]	陶飞, 刘蔚然, 张萌, 等. 数字孪生五维模型及十大领域应用[J]. 计算机集成制造系统, 2019, 25(1): 1-18.
	TAO Fei, LIU Weiran, ZHANG Meng, et al. Five-dimensional digital twin model and its ten applications[J]. Comput Integr Manuf Syst, 2019, 25(1): 1-18. (in Chinese)
[2]	陶飞, 程颖, 程江峰, 等. 数字孪生车间信息物理融合理论与技术[J]. 计算机集成制造系统, 2017, 23(8): 1603-1611.
	TAO Fei, CHENG Ying, CHENG Jiangfeng, et al. Theories and technologies for cyber-physical fusion in digital twin shopfloor[J]. Comput Integr Manuf Syst, 2017, 23(8): 1603-1611. (in Chinese)
[3]	LU Yuqian, LIU Chao, XU Xun, et al. Digital Twin-driven smart manufacturing: Connotation, reference model, applications and research issues[J]. Robot CIM-INT Manuf, 2020, 61: 101837. doi: 10.1016/j.rcim.2019.101837 URL
[4]	伍朝辉, 刘振正, 石可, 等. 交通场景数字孪生构建与虚实融合应用研究[J]. 系统仿真学报, 2021, 33(2): 295-305. doi: 10.16182/j.issn1004731x.joss.20-0754
	WU Zhaohui, LIU Zhenzheng, SHI Ke, et al. Review on the construction and application of digital twins in transportation scenes[J]. J Syst Simul, 2021, 33(2): 295-305. (in Chinese) doi: 10.16182/j.issn1004731x.joss.20-0754
[5]	Park K T, Nam Y W, Lee H S, et al. Design and implementation of a digital twin application for a connected micro smart factory[J]. Int J Comput Integ M, 2019, 32(6): 596- 614.
[6]	ZHANG Ke, CAO Jiayu, ZHANG Yan. Adaptive digital twin and multiagent deep reinforcement learning for vehicular edge computing and networks[J]. IEEE Trans Indu Info, 2022, 18(2): 1405-1413.
[7]	陶飞, 张贺, 戚庆林, 等. 数字孪生模型构建理论及应用[J]. 计算机集成制造系统, 2021, 27(01): 1-15.
	TAO Fei, ZHANG He, QI Qinglin, et al. Theory of digital twin modeling and its application[J]. Comput Integr Manuf Syst, 2021, 27(1): 1-15. (in Chinese) doi: 10.13196/j.cims.2021.01.001
[8]	Jones D, Snider C, Nassehi A, et al. Characterising the digital twin: A systematic literature review[J]. Cirp J Manuf Sci Tech, 2020, 29: 36-52. doi: 10.1016/j.cirpj.2020.02.002 URL
[9]	LI Guofa, LIN Siyan, LI Shen, et al. Learning automated driving in complex intersection scenarios based on camera sensors: A deep reinforcement learning approach[J]. IEEE Sensors J, 2022, 22(5): 4687-4696. doi: 10.1109/JSEN.2022.3146307 URL
[10]	Jubayer F, Soeb J A, Mojumder A, et al. Detection of mold on the food surface using YOLOv5[J]. Curr Res Food Sci, 2021, 4: 724-728. doi: 10.1016/j.crfs.2021.10.003 URL
[11]	ZHOU Junchi, JIANG Ping, ZOU Airu, et al. Ship target detection algorithm based on improved YOLOv5[J]. J Marine Sci Eng, 2021, 9(8): 908-908. doi: 10.3390/jmse9080908 URL
[12]	XU Xiaowo, ZHANG Xiaoling, ZHANG Tianwen. Lite-YOLOv5: A lightweight deep learning detector for on-board ship detection in large-scene Sentinel-1 SAR images[J]. Remote Sens-Basel, 2022, 14(4): (Paper No)1018.
[13]	LIN Ciyun, GUO Yingzhi, LI Wenjun, et al. An automatic lane marking detection method with low-density roadside LiDAR data[J]. IEEE Sensors J, 2021, 21(8) :10029-10038.
[14]	QIN Fei, BU Xiangxi, ZENG Zhiyuan, et al. Small target detection for FOD millimeter-wave radar based on compressed imaging[J]. IEEE Geosci Remote Sen Lett, 2022, 19: 1-5.

基于数字孪生的道路交叉口建模与应用

Modeling and application of road intersections based on digital twins

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 14

相关文章 6

编辑推荐

Metrics

本文评价

期刊信息

在线期刊

作者中心

审稿中心

联系我们

[1]	韩玲, 张晖, 方若愚, 刘国鹏, 朱长盛, 迟瑞丰. 基于改进深度强化学习的全局路径规划策略[J]. 汽车安全与节能学报, 2023, 14(2): 202-211.
[2]	张希, 廖宇兰, 李沁逸, 陈益庆. 安全行驶下的车用电机轴承的数字孪生故障诊断[J]. 汽车安全与节能学报, 2023, 14(2): 232-238.
[3]	朱淑亮，于涛，李峻. 基于机器视觉与信息共享的交叉路口交通安全预警[J]. JASE, 2018, 9(2): 156-163.
[4]	金立生，程蕾，成波. 基于毫米波雷达和机器视觉的夜间前方车辆检测[J]. JASE, 2016, 07(02): 167-174.
[5]	谢伯元，李克强，王建强，赵树连. “三网融合”的车联网概念及其在汽车工业中的应用[J]. 汽车安全与节能学报, 2013, 4(4): 348-355.
[6]	周晶, 彭晖. 基于伺服环动力学的自适应巡航控制系统串行稳定性研究[J]. 汽车安全与节能学报, 2010, 1(1): 30-39.