面向自动驾驶的边缘计算技术研究综述

doi:10.11959/j.issn.1000-436x.2021045

通信学报 ›› 2021, Vol. 42 ›› Issue (3): 190-208.doi: 10.11959/j.issn.1000-436x.2021045

所属专题：边缘计算

面向自动驾驶的边缘计算技术研究综述

吕品¹^,²^,³, 许嘉¹^,²^,³, 李陶深¹^,³, 徐文彪¹

¹ 广西大学计算机与电子信息学院，广西南宁 530004
² 广西多媒体通信与网络技术重点实验室，广西南宁 530004
³ 广西高校并行分布式计算技术重点实验室，广西南宁 530004

修回日期:2020-12-21 出版日期:2021-03-25 发布日期:2021-03-01
作者简介:吕品（1983- ），男，山东滨州人，博士，广西大学副研究员、硕士生导师，主要研究方向为无线网络、物联网、人工智能等。
许嘉（1984- ），女，山东荣成人，博士，广西大学副教授、硕士生导师，主要研究方向为大数据分析与处理、人工智能等。
李陶深（1957- ），男，广西南宁人，博士，广西大学教授、博士生导师，主要研究方向为无线网络、无线携能通信、网络信息安全、大数据处理等。
徐文彪（1997- ），男，湖南常德人，广西大学硕士生，主要研究方向为边缘计算、自动驾驶等。
基金资助:
国家自然科学基金资助项目(62062008);国家自然科学基金资助项目(61771312);国家自然科学基金资助项目(62062006);广西自然科学基金资助项目(2018JJA170194);广西自然科学基金资助项目(2018JJA170028);广西自然科学基金资助项目(2019JJA170045);广西八桂学者专项经费资助项目

Survey on edge computing technology for autonomous driving

Pin LYU¹^,²^,³, Jia XU¹^,²^,³, Taoshen LI¹^,³, Wenbiao XU¹

¹ School of Computer, Electronics and Information, Guangxi University, Nanning 530004, China
² Guangxi Key Laboratory of Multimedia Communications and Network Technology, Nanning 530004, China
³ Guangxi Colleges and University Key Laboratory of Parallel and Distributed Computing, Nanning 530004, China

Revised:2020-12-21 Online:2021-03-25 Published:2021-03-01
Supported by:
The National Natural Science Foundation of China(62062008);The National Natural Science Foundation of China(61771312);The National Natural Science Foundation of China(62062006);The Guangxi Natural Science Foundation(2018JJA170194);The Guangxi Natural Science Foundation(2018JJA170028);The Guangxi Natural Science Foundation(2019JJA170045);Special Funds for Guangxi BaGui Scholars

摘要/Abstract

摘要：

边缘计算在自动驾驶的环境感知和数据处理方面有着极其重要的应用。自动驾驶汽车可以通过从边缘节点获得环境信息来扩大自身的感知范围，也可以向边缘节点卸载计算任务以解决计算资源不足的问题。相比于云计算，边缘计算避免了长距离数据传输所导致的高时延，能给自动驾驶车辆提供更快速的响应，并且降低了主干网络的负载。基于此，首先介绍了基于边缘计算的自动驾驶汽车协同感知和任务卸载技术及相关挑战性问题，然后对协同感知和任务卸载技术的研究现状进行了分析总结，最后讨论了该领域有待进一步研究的问题。

关键词: 自动驾驶, 边缘计算, 协同感知, 任务卸载

Abstract:

Edge computing plays an extremely important role in the environment perception and data processing of autonomous driving.Autonomous driving vehicles can expand their perception scope by obtaining environmental information from edge nodes, and can also deal with the problem of insufficient computing resources by offloading tasks to edge nodes.Compared with cloud computing, edge computing avoids high latency caused by long-distance data transmission, and provides autonomous driving vehicles with faster responses, and relieves the traffic load of the backbone network.Firstly, the edge computing-based cooperative perception and task offloading technologies for autonomous vehicles were introduced firstly, and related challenging issues were also proposed.Then the state-of-the-art of cooperative perception and task offloading technologies were analyzed and summarized.Finally, the problems need to be further studied in this field were discussed.

Key words: autonomous driving, edge computing, cooperative perception, task offloading

中图分类号:

TP393

吕品, 许嘉, 李陶深, 徐文彪. 面向自动驾驶的边缘计算技术研究综述[J]. 通信学报, 2021, 42(3): 190-208.

Pin LYU, Jia XU, Taoshen LI, Wenbiao XU. Survey on edge computing technology for autonomous driving[J]. Journal on Communications, 2021, 42(3): 190-208.

图/表 10

图1

图2

表1

表2

图3

图4

表3

表4

任务卸载算法研究分类总结"

算法类型	优化指标	文献	主要研究点
	时延	文献[74-77]	有执行顺序约束的部分卸载
		文献[78]	考虑多种因素找到任务卸载时延最短的节点
		文献[79]	将任务卸载系统分为前端和后端，采用不同的方式减少能耗
		文献[80]	根据边缘服务器的负载和预测成本决定卸载位置
		文献[81]	根据任务的特性，将整体卸载和部分卸载相结合
	能耗	文献[82]	保护车辆隐私的任务卸载
任务调度		文献[83]	基于不完全信道状态信息的卸载
		文献[84]	基于博弈论的任务卸载，每个车辆会考虑其他车辆的决策来制定自身的卸载决策
		文献[85]	在RSU之间调度任务，考虑RSU下行链路能耗
	负载平衡	文献[86]	采用V2X通信在车辆之间传递数据，找到目标RSU进行卸载
		文献[87]	联合优化节点选择方案和卸载比例
		文献[88]	在RSU之间替换等待队列中的任务，提高任务完成率
	任务完成率	文献[89]	根据任务优先级调度任务
		文献[90]	通过预测每个节点在时延约束下完成任务的概率来选择卸载位置
	时延	文献[91]	基于匹配理论分配V2I带宽
		文献[92]	采用随机公平分配算法分配通信资源
资源分配	能耗	文献[93]	考虑异构车辆的计算资源分配模型
		文献[94]	联合分配计算和通信资源
	系统吞吐量	文献[95]	通过信道复用来增加系统吞吐量
任务调度和资源分配联合优化	任务完成率	文献[96]	联合优化资源分配和任务调度，给出了基于拉格朗日松弛的有效解
任务调度和资源分配联合优化	用户体验质量	文献[97]	将任务调度和资源分配策略转化为联合优化问题，使用户体验质量的最大化
数据传输优化	能耗	文献[98]	自动驾驶汽车选择部分传感器数据以特定的频率发送
	网络负载	文献[99]	根据感知范围的相似性，减少上传到边缘服务器的图像数量
	数据传输成功率	文献[100]	根据信道状态在每个时隙中传输不同大小的数据

表4

图5

表5

参考文献 92

[93]	LIN C C , DENG D J , YAO C C . Resource allocation in vehicular cloud computing systems with heterogeneous vehicles and roadside units[J]. IEEE Internet of Things Journal, 2017,5(5): 3692-3700.
[94]	LI S C , ZHU G , LIN S Y . Joint radio and computation resource allocation with predictable channel in vehicular edge computing[C]// The 21st International Conference on Intelligent Transportation Systems. Piscataway:IEEE Press, 2018: 3736-3741.
[95]	BAI B , XU F L , CAO Y Y ,et al. Hybrid sensing data fusion of cooperative perception for autonomous driving with augmented vehicular reality[J]. IEEE Systems Journal, 2020,doi:10.1109/JSYST.2020.3007202.
[96]	SORKHOH I , EBRAHIMI D , ATALLAH R ,et al. Workload scheduling in vehicular networks with edge cloud capabilities[J]. IEEE Transactions on Vehicular Technology, 2019,68(9): 8472-8486.
[97]	NING Z L , DONG P R , WANG X J ,et al. Deep reinforcement learning for vehicular edge computing:an intelligent offloading system[J]. ACM Transactions on Intelligent Systems and Technology, 2019,10(6): 1-24.
[98]	WANG C W , CHEN X Z , LIU D ,et al. Optimizing the data transmission scheme for edge-based automatic driving[C]// IEEE International Conference on Embedded Software and Systems. Piscataway:IEEE Press, 2019: 1-8.
[99]	NGUYEN T D T , NGUYEN V D , PHAM V-N ,et al. Modeling data redundancy and cost-aware task allocation in MEC-enabled internet-of-vehicles applications[J]. IEEE Internet of Things Journal, 2020,doi:10.1109/JIOT.2020.3015534.
[100]	ZHOU J S , TIAN D X , WANG Y P ,et al. Reliability-oriented optimization of computation offloading for cooperative vehicle-infrastructure systems[J]. IEEE Signal Processing Letters, 2019,26(1): 104-108.
[1]	LIU S S , TANG J , ZHANG Z ,et al. Computer architectures for autonomous driving[J]. Computer, 2017,50(8): 18-25.
[2]	ASHWIN A , PETER S , FAN B . Adaptive cloud offloading for vehicular applications[C]// IEEE Vehicular Networking Conference. Piscataway:IEEE Press, 2016: 1-8.
[3]	MA B J , XIU L Y , ZHU K L ,et al. An intelligent cooperative vision perception system for connected vehicles via IPv6[C]// IEEE/CIC International Conference on Communications in China. Piscataway:IEEE Press, 2018: 485-489.
[4]	施巍松, 张星洲, 王一帆 ,等. 边缘计算:现状与展望[J]. 计算机研究与发展, 2019,56(1): 69-89.
	SHI W S , ZHANG X Z , WANG Y F ,et al. Edge computing:state-of-the-art and future directions[J]. Journal of Computer Research and Development, 2019,56(1): 69-89.
[5]	ABBOUD K , OMAR H A , ZHUANG W H . Interworking of DSRC and cellular network technologies for V2X communications:a survey[J]. IEEE Transactions on Vehicular Technology, 2016,65(12): 9457-9470.
[6]	任开明, 李纪舟, 刘玲艳 ,等. 车联网通信技术发展现状及趋势研究[J]. 通信技术, 2015,48(5): 507-513.
	REN K M , LI J Z , LIU L Y ,et al. Development status and tendency of IoV communication technology[J]. Communications Technology, 2015,48(5): 507-513
[7]	张燕咏, 张莎, 张昱 ,等. 基于多模态融合的自动驾驶感知及计算[J]. 计算机研究与发展, 2020,57(9): 1781-1799.
	ZHANG Y Y , ZHANG S , ZHANG Y ,et al. Multi-modality fusion perception and computing in autonomous driving[J]. Journal of Computer Research and Development, 2020,57(9): 1781-1799.
[8]	KIM S W , QIN B X , CHONG Z J ,et al. Multivehicle cooperative driving using cooperative perception:design and experimental validation[J]. IEEE Transactions on Intelligent Transportation Systems, 2015,16(2): 663-680.
[9]	KIM S W , LIU W , ANG M H ,et al. The impact of cooperative perception on decision making and planning of autonomous vehicles[J]. IEEE Intelligent Transportation Systems Magazine, 2015,7(3): 39-50.
[10]	GUNTHER H J , MENNENGA B , TRAUER O ,et al. Realizing collective perception in a vehicle[C]// IEEE Vehicular Networking Conference. Piscataway:IEEE Press, 2016: 1-8.
[11]	GUNTHER H J , TRAUER O , WOLF L . The potential of collective perception in vehicular ad-hoc networks[C]// The 14th International Conference on ITS Telecommunications. Piscataway:IEEE Press, 2015: 1-5.
[12]	CALVO J A L , MATHAR R . A multi-level cooperative perception scheme for autonomous vehicles[C]// The 15th International Conference on ITS Telecommunications. Piscataway:IEEE Press, 2017: 1-5.
[13]	WANG Y C , VECIANA G D , SHIMIZU T ,et al. Deployment and performance of infrastructure to assist vehicular collaborative sensing[C]// The 87th Vehicular Technology Conference. Piscataway:IEEE Press, 2018: 1-5.
[14]	WEN T P , XIAO Z Y , JIANG K ,et al. High precision target positioning method for RSU in cooperative perception[C]// The 21st International Workshop on Multimedia Signal Processing. Piscataway:IEEE Press, 2019: 1-6.
[15]	LIN S C , ZHANG Y Q , HSU C H ,et al. The architectural implications of autonomous driving:constraints and acceleration[J]. ACM Sigplan Notices, 2018,53(2): 751-766.
[16]	WEI S G , YU D , GUO C L ,et al. Survey of connected automated vehicle perception mode:from autonomy to interaction[J]. IET Intelligent Transport System, 2019,13(3): 495-505.
[17]	FUKATSU R , SAKAGUCHI K . Millimeter-wave V2V communications with cooperative perception for automated driving[C]// The 89th Vehicular Technology Conference. Piscataway:IEEE Press, 2019: 1-5.
[18]	SAKAGUCHI K , FUKATSU R . Cooperative perception realized by millimeter-wave V2V for safe automated driving[C]// Asia-Pacific Microwave Conference. Piscataway:IEEE Press, 2018: 180-182.
[19]	WANG Y C , VECIANA G D , SHIMIZU T ,et al. Performance and scaling of collaborative sensing and networking for automated driving applications[C]// International Conference on Communications Workshops. Piscataway:IEEE Press, 2018: 1-6.
[20]	THANDAVARAYAN G , SEPULCRE M , GOZALVEZ J . Analysis of message generation rules for collective perception in connected and automated driving[C]// Intelligent Vehicles Symposium. Piscataway:IEEE Press, 2019: 134-139.
[21]	THANDAVARAYAN G , SEPULCRE M , GOZALVEZ J . Redundancy mitigation in cooperative perception for connected and automated vehicles[C]// The 91st Vehicular Technology Conference. Piscataway:IEEE Press, 2020: 1-5.
[22]	HIGUCHI T , GIORDANI M , ZANELLA A ,et al. Value-anticipating V2V communications for cooperative perception[C]// Intelligent Vehicles Symposium. Piscataway:IEEE Press, 2019: 1947-1952.
[23]	TAYA A , NISHIO T , MORIKURA M ,et al. Concurrent data dissemination at intersections in mmWave for cooperative perceptions[C]// The 88th Vehicular Technology Conference. Piscataway:IEEE Press, 2018: 1-5.
[24]	RAHAL J A , VECIANA G D , SHIMIZU T ,et al. Optimizing timely coverage in communication constrained collaborative sensing systems[C]// The 18th International Symposium on Modeling and Optimization in Mobile,Ad Hoc,and Wireless Networks. Piscataway:IEEE Press, 2020: 1-8.
[25]	NOH S , AN K , HAN W . Toward highly automated driving by vehicle-to-infrastructure communications[C]// The 15th International Conference on Control,Automation and Systems. Piscataway:IEEE Press, 2015: 2016-2021.
[26]	REBSAMEN B , BANDYOPADHYAY T , WONGPIROMSARN T ,et al. Utilizing the infrastructure to assist autonomous vehicles in a mobility on demand context[C]// TENCON 2012 IEEE Region 10 Conference. Piscataway:IEEE Press, 2012: 1-5.
[27]	LIU W J , MURAMATSU S , OKUBO Y . Cooperation of V2I/P2I communication and roadside radar perception for the safety of vulnerable road users[C]// The 16th International Conference on Intelligent Transportation Systems Telecommunications. Piscataway:IEEE Press, 2018: 1-7.
[28]	RAUCH A , KLANNER F , RASSHOFER R ,et al. Car2X-based perception in a high-level fusion architecture for cooperative perception systems[C]// IEEE Intelligent Vehicles Symposium. Piscataway:IEEE Press, 2012: 270-275.
[29]	SRIDHAR S , ESKANDARIAN A . Cooperative perception in autonomous ground vehicles using a mobile-robot testbed[J]. IET Intelligent Transport Systems, 2019,13(10): 1545-1556.
[30]	XIAO Z Y , MO Z B , JIANG K ,et al. Multimedia fusion at semantic level in vehicle cooperative perception[C]// International Conference on Multimedia ＆ Expo Workshops. Piscataway:IEEE Press, 2018: 1-6.
[31]	LIAN Y X , QIAN L , DING L H ,et al. Semantic fusion infrastructure for unmanned vehicle system based on cooperative 5G MEC[C]// IEEE/CIC International Conference on Communications in China. Piscataway:IEEE Press, 2020: 202-207.
[32]	CHEN Q , TANG S H , YANG Q ,et al. Cooper:cooperative perception for connected autonomous vehicles based on 3D point clouds[C]// The 39th International Conference on Distributed Computing Systems. Piscataway:IEEE Press, 2019: 514-524.
[33]	RAUCH A , MAIER S , KLANNER F ,et al. Inter-vehicle object association for cooperative perception systems[C]// The 16th International Conference on Intelligent Transportation Systems. Piscataway:IEEE Press, 2013: 893-898.
[34]	WEI S G , YU D , LIN G C . Interactive perception-based multiple object tracking via CVIS and AV[J]. IEEE Access, 2019,7: 1907-1921.
[35]	ARNOLD E , DIANATI M , TEMPLE R D ,et al. Cooperative perception for 3D object detection in driving scenarios using infrastructure sensors[J]. IEEE Transactions on Intelligent Transportation Systems, 2020,doi:10.1109/TITS.2020.3028424.
[36]	LI H , NASHASHIBI F . A new method for occupancy grid maps merging:application to multi-vehicle cooperative local mapping and moving object detection in outdoor environment[C]// The 12th International Conference on Control Automation Robotics ＆ Vision. Piscataway:IEEE Press, 2012: 632-637.
[37]	LI H , TSUKADA M , NASHASHIBI F ,et al. Multivehicle cooperative local mapping:a methodology based on occupancy grid map merging[J]. IEEE Transactions on Intelligent Transportation Systems, 2014,15(5): 2089-2100.
[38]	CAMARDA F , DAVOINE F , CHERFAOUI V . Fusion of evidential occupancy grids for cooperative perception[C]// The 13th Annual Conference on System of Systems Engineering. Piscataway:IEEE Press, 2018: 284-290.
[39]	AMBROSIN M , ALVAREZ I J , BUERKLE C ,et al. Object-level perception sharing among connected vehicles[C]// IEEE Intelligent Transportation Systems Conference. Piscataway:IEEE Press, 2019: 1566-1573.
[40]	VASIC M , MARTINOLI A . A Collaborative sensor fusion algorithm for multi-object tracking using a Gaussian mixture probability hypothesis density filter[C]// The 18th International Conference on Intelligent Transportation Systems. Piscataway:IEEE Press, 2015: 491-498.
[41]	YUAN T , KRISHNAN K , Chen Q ,et al. Object matching for inter-vehicle communication systems—an IMM-based track association approach with sequential multiple hypothesis test[J]. IEEE Transactions on Intelligent Transportation Systems, 2017,18(12): 3501-3512.
[42]	KIM S W , LIU W . Cooperative autonomous driving:a mirror neuron inspired intention awareness and cooperative perception approach[J]. IEEE Intelligent Transportation Systems Magazine, 2016,8(3): 23-32.
[43]	KIM S W , LIU W , ANG M H ,et al. Cooperative autonomous driving using cooperative perception and mirror neuron inspired intention awareness[C]// International Conference on Connected Vehicles and Expo. Piscataway:IEEE Press, 2014: 369-376.
[44]	LIU W , KIM S W , MARCZUK K ,et al. Vehicle motion intention reasoning using cooperative perception on urban road[C]// The 17th International Conference on Intelligent Transportation Systems. Piscataway:IEEE Press, 2014: 424-430.
[45]	LIU W , KIM S W , CHONG Z J ,et al. Motion planning using cooperative perception on urban road[C]// The 6th IEEE Conference on Robotics,Automation and Mechatronics. Piscataway:IEEE Press, 2013: 130-137.
[46]	XIAO Z Y , YANG D G , WEN F X ,et al. A unified multiple-target positioning framework for intelligent connected vehicles[J]. Sensors, 2019,19(9): 1-22.
[47]	MILLER A , RIM K , CHOPRA P ,et al. Cooperative perception and localization for cooperative driving[C]// IEEE International Conference on Robotics and Automation. Piscataway:IEEE Press, 2020: 1256-1262.
[48]	AN K , HAN W . Cooperative vehicle control system based on fusion map[C]// The 7th International Conference on Computing and Convergence Technology. Piscataway:IEEE Press, 2012: 94-97.
[49]	FENG J Y , LIU Z , WU C ,et al. AVE:autonomous vehicular edge computing framework with ACO-based scheduling[J]. IEEE Transactions on Vehicular Technology, 2017,66(12): 10660-10675.
[50]	SUN J N , GU Q , ZHENG T ,et al. Joint communication and computing resource allocation in vehicular edge computing[J]. International Journal of Distributed Sensor Networks, 2019,15(3): 1-13.
[51]	MATSUMOTO H , GU B , MIZUNO O . A V2X task offloading method considering automobiles’ behavior in urban area[C]// The 20th Asia-Pacific Network Operations and Management Symposium. Piscataway:IEEE Press, 2019: 1-4.
[52]	ZHANG K , MAO Y M , LENG S P ,et al. Mobile-edge computing for vehicular networks:a promising network paradigm with predictive off-loading[J]. IEEE Vehicular Technology Magazine, 2017,12(2): 36-44.
[53]	WANG H S , LI X , JI H ,et al. Dynamic offloading scheduling scheme for MEC-enabled vehicular networks[C]// IEEE/CIC International Conference on Communications in China. Piscataway:IEEE Press, 2018: 206-210.
[54]	CHEN C , CHEN L L , LIU L ,et al. Delay-optimized V2V-based computation offloading in urban vehicular edge computing and networks[J]. IEEE Access, 2020,8: 18863-18873.
[55]	YANG C , LIU Y , CHEN X ,et al. Efficient mobility-aware task offloading for vehicular edge computing networks[J]. IEEE Access, 2019,7: 26652-26664.
[56]	PACHECO L , OLIVEIRA H , ROSARIO D ,et al. Service migration for connected autonomous vehicles[C]// IEEE Symposium on Computers and Communications. Piscataway:IEEE Press, 2020: 1-6.
[57]	ZHAO H T , DING Y , ZHANG M K ,et al. Multipath transmission workload balancing optimization scheme based on mobile edge computing in vehicular heterogeneous network[J]. IEEE Access, 2019,7: 116047-116055.
[58]	TANG J , YU R , LIU S S ,et al. A container based edge offloading framework for autonomous driving[J]. IEEE Access, 2020,8: 33713-33726.
[59]	ZHOU Z Y , LIAO H J , WANG X Y ,et al. When vehicular fog computing meets autonomous driving:computational resource management and task offloading[J]. IEEE Network, 2020,34(6): 1-8.
[60]	WANG H S , LI X , JI H ,et al. Federated offloading scheme to minimize latency in MEC-enabled vehicular networks[C]// IEEE Globecom Workshops. Piscataway:IEEE Press, 2018: 1-6.
[61]	XIE R C , TANG Q Q , WANG Q N ,et al. Collaborative vehicular edge computing networks:architecture design and research challenges[J]. IEEE Access, 2019,7: 178942-178952.
[62]	WANG L , ZHANG Q Y , LI Y H Z ,et al. MobileEdge:enhancing on-board vehicle computing units using mobile edges for CAVs[C]// The 25th International Conference on Parallel and Distributed Systems. Piscataway:IEEE Press, 2019: 470-479.
[63]	VLADYKO A , KHAKIMOV A , MUTHANNA A ,et al. Distributed edge computing to assist ultra-low-latency VANET applications[J]. Future Internet, 2019,11(6): 1-22.
[64]	ZHANG J , GUO H Z , LIU J J ,et al. Task offloading in vehicular edge computing networks:a load-balancing solution[J]. IEEE Transactions on Vehicular Technology, 2019,69(2): 2092-2104.
[65]	CORONADO E , CEBRIAN-MARQUEZ G , RIGGIO R . Enabling computation offloading for autonomous and assisted driving in 5G networks[C]// IEEE Global Communications Conference. Piscataway:IEEE Press, 2019: 1-6.
[66]	GUO H Z , ZHANG J , LIU J J . FiWi-enhanced vehicular edge computing networks:collaborative task offloading[J]. IEEE Vehicular Technology Magazine, 2019,14(1): 45-53.
[67]	QIAO G H , LENG S P , ZHANG K ,et al. Collaborative task offloading in vehicular edge multi-access networks[J]. IEEE Communications Magazine, 2018,56(8): 48-54.
[68]	FENG J Y , LIU Z , WU C ,et al. HVC:a hybrid cloud computing framework in vehicular environments[C]// The 5th IEEE International Conference on Mobile Cloud Computing,Services,and Engineering. Piscataway:IEEE Press, 2017: 9-16.
[69]	SASAKI K , SUZUKI N , MAKIDO S ,et al. Vehicle control system coordinated between cloud and mobile edge computing[C]// The 55th Annual Conference of the Society of Instrument and Control Engineers of Japan. Piscataway:IEEE Press, 2016: 1122-1127.
[70]	SASAKI K , SUZUKI N , MAKIDO S ,et al. Layered vehicle control system coordinated between multiple edge servers[C]// IEEE Conference on Network Softwarization. Piscataway:IEEE Press, 2017: 1-5.
[71]	SASAKI K , MAKIDO S , NAKAO A . Vehicle control system for cooperative driving coordinated multi-layered edge servers[C]// IEEE 7th International Conference on Cloud Networking. Piscataway:IEEE Press, 2018: 1-7.
[72]	KREUTZ D , RAMOS F M V , VERISSIMO P E ,et al. Software-defined networking:a comprehensive survey[J]. Proceedings of the IEEE, 2014,103(1): 14-76.
[73]	郭金林, 武继刚, 陈龙 ,等. 基于光纤?无线网络的协同计算卸载算法[J]. 计算机工程与科学, 2019,41(1): 31-40.
	GUO J L , WU J G , CHEN L ,et al. A collaborative computation offloading algorithm based on fiber-wireless networks[J]. Computer Engineering and Science, 2019,41(1): 31-40.
[74]	SUN F , HOU F , CHENG N ,et al. Cooperative task scheduling for computation offloading in vehicular cloud[J]. IEEE Transactions on Vehicular Technology, 2018,67(11): 11049-11061.
[75]	LIN K , LIN B , CHEN X ,et al. A time-driven workflow scheduling strategy for reasoning tasks of autonomous driving in edge environment[C]// IEEE International Conference on Parallel ＆ Distributed Processing with Applications,Big Data ＆ Cloud Computing,Sustainable Computing ＆ Communications,Social Computing ＆ Networking. Piscataway:IEEE Press, 2019: 124-131.
[76]	WANG J F , LYU T J , HUANG P M ,et al. Mobility-aware partial computation offloading in vehicular networks:a deep reinforcement learning based scheme[J]. China Communications, 2020,17(10): 31-49.
[101]	MENDKI P , . Blockchain enabled IoT edge computing[C]// International Conference on Blockchain Technology. New York:ACM Press, 2019: 66-69.
[77]	CUI M Y , ZHONG S P , LI B Y ,et al. Offloading autonomous driving services via edge computing[J]. IEEE Internet of Things Journal, 2020,7(10): 10535-10547.
[78]	LAMB Z , AGRAWAL D . Context-aware mobile edge computing in vehicular ad-hoc networks[C]// The 28th International Telecommunication Networks and Applications Conference. Piscataway:IEEE Press, 2018: 1-7.
[79]	WANG X J , WEI X , WANG L . A deep learning based energy-efficient computational offloading method in Internet of vehicles[J]. China Communications, 2019,16(3): 81-91.
[80]	LI L J , ZHOU H M , SHAWN X X ,et al. Compound model of task arrivals and load-aware offloading for vehicular mobile edge computing networks[J]. IEEE Access, 2019,7: 26631-26640.
[81]	LIU J , WANG S B , WANG J T ,et al. A task oriented computation offloading algorithm for intelligent vehicle network with mobile edge computing[J]. IEEE Access, 2019,7: 180491-180502.
[82]	XU X L , XUE Y , QI L Y ,et al. An edge computing-enabled computation offloading method with privacy preservation for Internet of connected vehicles[J]. Future Generation Computer Systems, 2019,96: 89-100.
[83]	SHANG L C , WANG X H , WANG P ,et al. Computation offloading management in vehicular edge network under imperfect CSI[C]// The 2nd IEEE International Conference on Information Communication and Signal Processing. Piscataway:IEEE Press, 2019: 199-203.
[84]	LIU Y J , WANG S G , HUANG J ,et al. A computation offloading algorithm based on game theory for vehicular edge networks[C]// IEEE International Conference on Communications. Piscataway:IEEE Press, 2018: 1-6.
[85]	NING Z L , HUANG J , WANG X J ,et al. Mobile edge computing-enabled Internet of vehicles:toward energy-efficient scheduling[J]. IEEE Network, 2019,33(5): 198-205.
[86]	XU X L , XUE Y , LI X ,et al. A computation offloading method for edge computing with vehicle-to-everything[J]. IEEE Access, 2019,7: 131068-131077.
[87]	DAI Y Y , XU D , MAHARJAN S ,et al. Joint load balancing and offloading in vehicular edge computing and networks[J]. IEEE Internet of Things Journal, 2018,6(3): 4377-4387.
[88]	DAI H J , ZENG X Y , YU Z L ,et al. A scheduling algorithm for autonomous driving tasks on mobile edge computing servers[J]. Journal of Systems Architecture, 2019,94: 14-23.
[89]	LIU Q , CHEN Z G , WU J ,et al. An efficient task scheduling strategy utilizing mobile edge computing in autonomous driving environment[J]. Electronics, 2019,8(11): 1-19.
[90]	KOVALENKO A , HUSSAIN R F , SEMIARI O ,et al. Robust resource allocation using edge computing for vehicle to infrastructure (V2I) networks[C]// IEEE 3rd International Conference on Fog and Edge Computing. Piscataway:IEEE Press, 2019: 1-6.
[91]	TAREQ M M K , SEMIARI O , AMINI M S ,et al. Ultra reliable,low latency vehicle-to-infrastructure wireless communications with edge computing[C]// IEEE Global Communications Conference. Piscataway:IEEE Press, 2018: 1-7.
[92]	LI X , DANG Y F , CHEN T F . Vehicular edge cloud computing:depressurize the intelligent vehicles onboard computational power[C]// The 21st International Conference on Intelligent Transportation Systems. Piscataway:IEEE Press, 2018: 3421-3426.

研究问题	相关文献	关键研究点
	文献[16]	利用神经网络模型，根据车辆密度、速度和数据传输量决定使用哪种通信网络进行通信
支持共享CPM的网络架构	文献[17]	分析不同行驶速度下进行协同感知所需的动态信息交换量
	文献[18]	探究不同行驶速度下的自动驾驶汽车实现协同感知需要的数据率
	文献[19]	分析不同交通密度和不同渗透率下实现协同感知对V2V和V2I网络容量的需求
	文献[20]	对比ETSI制定的动态CPM生成策略和周期性生成策略的性能
	文献[21]	通过减少数据冗余优化ETSI制定的动态CPM生成策略
	文献[22]	预测信息对接收车辆的潜在价值，衡量网络情况决定是否发送该信息
CPM共享策略	文献[23]	优先广播重要地理位置的感知信息使车辆获得更大的感知范围
	文献[24]	提高大多数车辆感兴趣区域的感知信息的广播频率，提高感知范围，降低信息年龄
	文献[25]	利用RSU的感知信息为自动驾驶汽车提供危险警告和驾驶建议
	文献[26]	在先验环境下，利用RSU的感知信息扩大感知范围，减少车载传感器成本
	文献[27]	RSU将感知到的非自动驾驶汽车或行人信息发送给自动驾驶汽车，扩大车辆感知范围

数据融合方式	相关文献	关键研究点
	文献[29]	通过匹配图像中的特征点进行数据融合，用于有共同视野车辆之间的数据融合
图像融合	文献[30]	通过特征点匹配或坐标转换融合其他车辆生成的鸟瞰图
	文献[31]	融合多个RSU摄像头的数据来扩大协同感知系统的感知范围并提高感知精度
	文献[32]	将其他车辆的点云数据映射到主车辆的位置，然后合并、对齐从附近车辆收集的共享数据
点云融合	文献[33]	利用点匹配算法消除接收到的目标与本身所探测到的目标之间的偏差
	文献[34]	通过节点间激光雷达数据的融合来提升目标跟踪精度
	文献[35]	融合多个方位RSU的点云数据，提高目标检测精度
占用栅格地图融合	文献[36-37]	引入基于占用概率的目标函数来度量地图对齐的一致性程度，采用遗传算法对目标函数进行动态优化
	文献[38]	利用信任函数理论对车辆的相对位置和交换的传感器数据进行不确定性推理
	文献[28]	数据的时间对齐和空间对齐
对象匹配	文献[39]	主车辆接收其他车辆发送的对象列表，丢弃感兴趣范围外的对象，持续跟踪感兴趣范围内的对象
	文献[40]	用高斯混合概率假设密度协同融合方法进行不同车辆间的对象数据融合
	文献[41]	关联对象的轨迹，仅利用车辆的位置信息进行目标匹配

架构类型	解决的问题	文献	主要研究点
	车辆之间的合作方式	文献[49]	分布式任务卸载架构
车群架构		文献[50]	中心式的任务卸载架构，以更好地分配通信和计算资源
车群架构	车辆的移动性	文献[51]	考虑到车辆转弯行为的车辆间任务卸载
		文献[52]	预测任务完成时车辆的位置，提出2种不同的任务卸载方式
		文献[53]	将任务划分为多个部分，分配给多个车辆将要到达的RSU执行
	车辆的移动性	文献[54]	RSU根据车辆最大服务时间管理车群的任务卸载
		文献[55]	根据车辆移动过程中与RSU通信距离的变化选择最佳卸载时间点
		文献[56]	根据车辆的移动，在边缘服务器之间进行服务迁移
车-边架构		文献[57]	采用多路径传输建立车辆与基站之间的连接减少车辆与RSU之间建立连接的时延
	隔离任务执行环境	文献[58]	基于容器的任务卸载架构
		文献[59]	基于契约理论和匹配学习的任务卸载
	充分利用车群计算能力	文献[60]	将任务分为3个部分，分别由主车辆、其他车辆和RSU执行
		文献[61]	RSU根据自身计算能力、车群计算能力以及网络状况做出任务卸载决策
	利用移动设备的计算能力	文献[62]	使用乘客的移动设备进行任务卸载
车-边-云架构	使用SDN或Fi-Wi网络增强系统性能	文献[63,64,65,66]	使用SDN管理任务卸载，使用Fi-Wi网络增加数据传输速度
	实现车、边、云深度合作	文献[67]	云端进行全局协调，多个RSU形成边缘云，车辆之间共享计算任务。
	通用卸载架构	文献[68]	支持多种应用的任务卸载框架
	使用外部服务器控制车辆	文献[69,70,71]	使用云和边缘服务器控制车辆，优化云边控制比例

所面临的挑战	解决的主要问题	相关研究
	合理分配通信或计算资源	文献[83, 91-97]
资源有限	通过合理的任务调度提高系统吞吐量	文献[86-90]
	数据传输优化	文献[3, 98-100]
	车辆之间通信距离的快速变化	文献[49, 51, 54, 74-75]
车辆移动性	车辆频繁切换为其服务的RSU	文献[52-53, 55-57]
	寻找动态车辆网络数据传输路由	文献[82, 86]
任务执行环境的隔离性	基于容器的任务卸载	文献[58]

面向自动驾驶的边缘计算技术研究综述

Survey on edge computing technology for autonomous driving

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 92

相关文章 15

Metrics

推荐阅读 0

[1]	鲁蔚锋, 李宁, 徐佳, 徐力杰, 徐建. 多接入边缘计算中相关性任务的联合调度算法[J]. 通信学报, 2023, 44(4): 87-98.
[2]	苏新, 张桂福, 行鸿彦, Zenghui Wang. 基于平衡生成对抗网络的海洋气象传感网入侵检测研究[J]. 通信学报, 2023, 44(4): 124-136.
[3]	谢人超, 文雯, 唐琴琴, 刘云龙, 谢高畅, 黄韬. 轨道交通移动边缘计算网络安全综述[J]. 通信学报, 2023, 44(4): 201-215.
[4]	余雪勇, 邱礼翔, 宋家宁, 朱洪波. 无人机辅助边缘计算中安全通信与能效优化策略[J]. 通信学报, 2023, 44(3): 45-54.
[5]	范伟, 彭诚, 朱大立, 王雨晴. 移动边缘计算网络下基于静态贝叶斯博弈的入侵响应策略研究[J]. 通信学报, 2023, 44(2): 70-81.
[6]	赵庶旭, 韦萍, 王小龙. 多任务并发边缘计算环境中最优联盟结构生成策略[J]. 通信学报, 2023, 44(2): 172-184.
[7]	夏景明, 刘玉风, 谈玲. 基于蜂窝网络的多无人机能量消耗最优化算法研究[J]. 通信学报, 2023, 44(2): 185-197.
[8]	龙隆, 刘子辰, 陆在旺, 张玉成, 李蕾. 移动边缘网络下服务缓存与资源分配联合优化策略[J]. 通信学报, 2023, 44(1): 64-74.
[9]	张宇, 程旻. NDN中边缘计算与缓存的联合优化[J]. 通信学报, 2022, 43(8): 164-175.
[10]	王子园, 杜瑞忠. 边缘环境下基于无证书公钥密码的数据完整性审计方案[J]. 通信学报, 2022, 43(7): 62-72.
[11]	莫梓嘉, 高志鹏, 杨杨, 林怡静, 孙山, 赵晨. 面向车联网数据隐私保护的高效分布式模型共享策略[J]. 通信学报, 2022, 43(4): 83-94.
[12]	杨力, 潘成胜, 孔相广, 黄琦龙, 戚耀文. 5G融合卫星网络研究综述[J]. 通信学报, 2022, 43(4): 202-215.
[13]	王继锋, 王国峰. 边缘计算模式下密文搜索与共享技术研究[J]. 通信学报, 2022, 43(4): 227-238.
[14]	曹敦, 张应宝, 邹电, 王进, 汤强, 冀保峰. V2X多节点协同分布式卸载策略[J]. 通信学报, 2022, 43(2): 185-195.
[15]	孙俨, 熊翱, 蒋承伶, 王威, 于东晓, 郭少勇. 基于区块链的计算与无线通信资源联合管理双向拍卖模型[J]. 通信学报, 2022, 43(11): 14-25.