电信科学 ›› 2023, Vol. 39 ›› Issue (3): 45-60.doi: 10.11959/j.issn.1000-0801.2023048

• 专题:智能网联汽车与车联网 • 上一篇    下一篇

基于C-V2X的车路协同自动驾驶关键技术与应用

王鲲1, 董振江2, 杨凡1, 周谷越3   

  1. 1 北京百度智行科技有限公司,北京 100193
    2 南京邮电大学,江苏 南京 210023
    3 清华大学人工智能产业研究院,北京 100084
  • 修回日期:2023-03-16 出版日期:2023-03-20 发布日期:2023-03-01
  • 作者简介:王鲲(1987- ),男,北京百度智行科技有限公司车路协同技术战略专家,主要研究方向为C-V2X、车路协同自动驾驶
    董振江(1970- ),男,博士,南京邮电大学教授、博士生导师,国务院政府特殊津贴专家,中国人工智能学会常务理事,主要研究方向为人工智能与车联网
    杨凡(1976- ),男,博士,北京百度智行科技有限公司智能交通资深工程师,主要研究方向为智能交通与自动驾驶的协同研究和开发
    周谷越(1977- ),男,博士,清华大学人工智能产业研究院副研究员、副教授,协同视觉与机器人实验室(DISCOVER Lab)主任,主要研究方向为先进制造、智能机器人、计算机视觉与人机交互等
  • 基金资助:
    科技创新2030——“新一代人工智能”重大项目(2022ZD0115504)

Key technologies and applications of C-V2X based vehicle-infrastructure cooperative autonomous driving

Kun WANG1, Zhenjiang DONG2, Fan YANG1, Guyue ZHOU3   

  1. 1 Beijing Baidu Apollo Mobility Technology Co., Ltd., Beijing 100193, China
    2 Nanjing University of Posts and Telecommunications, Nanjing 210023, China
    3 Institute for AI Industry Research, Tsinghua University, Beijing 100084, China
  • Revised:2023-03-16 Online:2023-03-20 Published:2023-03-01
  • Supported by:
    Technological Innovation 2030 — “New Generation Artificial Intelligence” Major Project(2022ZD0115504)

摘要:

随着车联网技术的演进,自动驾驶在单车智能的基础上,又有了新的发展形态——车路协同自动驾驶。通过“人-车-路-云”深度融合形成的一体化复杂信息物理系统(cyber physical system,CPS),可以与自动驾驶车辆实现协同感知、协同决策规划甚至协同控制,提升自动驾驶安全性,帮助克服各类复杂交通环境。首先介绍了车路协同的复杂信息物理系统的概念内涵和总体架构,并提出了车路协同自动驾驶的一系列典型应用场景、技术原理、C-V2X(cellular vehicle-to-everything)性能要求、车路协同系统功能与性能要求,可以为下一阶段智能网联汽车与智能交通的深度融合发展提供参考和解决思路。

关键词: 自动驾驶, 蜂窝车联网, 网联自动驾驶车辆, 车路协同自动驾驶

Abstract:

With the evolution of vehicle-to-everything (V2X) technology, autonomous driving (AD) has entered a new stage of development, called vehicle-infrastructure cooperative autonomous driving (VICAD).Through the integrated complex cyber-physical system formed by the deep integration of “human-vehicle-road-cloud”, cooperative perception, cooperative decision-making and planning, and even cooperative control can be achieved with autonomous vehicles (AV), enhancing the safety of autonomous driving and helping to overcome various complex traffic environments.The concept and overall architecture of the complex cyber-physical system of VICAD was firstly introduced, and a series of typical application scenarios, technical principles, C-V2X performance requirements, and functional and performance requirements of the VICAD system were proposed.It can provide a reference and solution for the deep integration development of intelligent networked vehicles and intelligent transportation in the next stage.

Key words: autonomous driving, C-V2X, connected and automated vehicle, VICAD

No Suggested Reading articles found!