摘要
智能汽车的人机共驾技术(HMIoIV)是解决其智能化级别难以快速跨越至高度自动化水平的有效过渡手段。HMIoIV涉及了L0~L3级别的智能汽车的多种自动化技术,包括先进辅助驾驶系统。针对当前国内外智能汽车人机共驾技术的研究现状,对其概念、结构和研究内容进行总结,根据独立驾驶人参与的数量和驾驶操作方参与的数量将现有的人机共驾技术分成3类:单驾双控结构、串联型双驾单控结构(Traded Control)和并联型双驾双控结构(Shared Control);并对驾驶人为因素、驾驶人模型、自然驾驶人状态监测和驾驶意图识别、串联型双驾单控结构和并联型双驾双控结构的研究方法以及权限与责任的关系进行全面综述。最后,分析总结当前智能汽车的人机共驾技术所面临的问题和挑战,并对该技术的发展趋势做出展望。
Human-machine interaction technology of intelligent vehicles(HMIoIVs) is an effective transition method for improving the intelligence level of autonomous vehicles to leap to high automation levels rapidly. It involves different automation techniques of L0-L3 intelligent vehicles, including the advanced driving assistance system(ADAS). This paper presents a review of the concept, structure, and research content of HMIoIVs. Based on the quantity of independent drivers and the number of driving operation involved, existing HMIoIVs can be divided into three categories: the single-driving dual-control structure, serial dual-driving single-control structure(traded control), and parallel dual-driving dual-control structure(shared control). Human driver factors, the driver model, human driver condition monitoring, and driving intention recognition, research methods of traded control and shared control, and the relationship between authority and responsibility are reviewed comprehensively. Finally, the challenges faced by the current HMIoIVs are analyzed and summarized, and prospects for the technological development of HMIoIVs are highlighted.
作者
宗长富
代昌华
张东
ZONG Chang-fu;DAI Chang-hua;ZHANG Dong(State Key Laboratory of Automotive Simulation and Control,Jilin University,Changchun 130022,Jilin,China;School of Electrical and Electronic Engineering,Nanyang Technological University,Singapore 639798,Singapore)
出处
《中国公路学报》
EI
CAS
CSCD
北大核心
2021年第6期214-237,共24页
China Journal of Highway and Transport
基金
汽车仿真与控制国家重点实验室开放基金项目(20201111)。
关键词
汽车工程
人机共驾
综述
串联型双驾单控结构
并联型双驾双控结构
驾驶人模型
自然驾驶人状态监测
驾驶意图识别
automotive engineering
human-machine interaction technology of autonomous vehicles
review
traded control
shared control
driver model
human driver condition monitoring
driving intention recognition