Human-Machine Shared Lateral Control Strategy for Intelligent Vehicles Based on Human Driver Risk Perception Reliability  

作　　者：Dongjian Song Bing Zhu Jian Zhao Jiayi Han 

机构地区：[1]State Key Laboratory of Automotive Simulation and Control,Jilin University,Changchun 130022,China

出　　处：《Automotive Innovation》2024年第1期102-120,共19页汽车创新工程（英文）

基　　金：supported by the National Natural Science Foundation of China under Grant 52172386;the National Natural Science Foundation of China under Grant U22A20247;the Jilin Province Science and Technology Development Plan Projects under Grant 20210101057JC;the Jilin Provincial Department of Science and Technology under Grant 20220301009GX.

摘　　要：Intelligent vehicle(Ⅳ)technology has developed rapidly in recent years.However,achieving fully unmanned driving still presents numerous challenges,which means that human drivers will continue to play a vital role in vehicle operation for the foreseeable future.Human-machine shared driving,involving cooperation between a human driver and an automated driving system(AVS),has been widely regarded as a necessary stage for the development of IVs.Focusing onⅣdriving safety,this study proposed a human-machine shared lateral control strategy(HSLCS)based on the reliability of driver risk perception.The HSLCS starts by identifying the effective areas of driver risk perception based on eye movements.It establishes an anisotropic driving risk field,which serves as the foundation for the AVS to assess risk levels.Building upon the cumulative and diminishing effects of risk perception,the proposed approach leverages the driver's risk perception effective area and converts the risk field into a representation aligned with the driver's perspective.Subsequently,it quantifies the reliability of the driver's risk perception by using area-matching rules.Finally,based on the driver’s risk perception reliability and dif-ferences in lateral driving operation between the human driver and the AVS,the dynamic distribution of driving authority is achieved through a fuzzy rule-based system,and the human-machine shared lateral control is completed by using model predictive control.The HSLCS was tested across various scenarios on a driver-in-the-loop test platform.The results show that the HSLCS can realize the synergy and complementarity of human and machine intelligence,effectively ensuring the safety ofⅣoperation.

关 键 词：Intelligent vehicle Human-machine shared driving Risk perception Driving authority distribution 

分 类 号：TN9[电子电信—信息与通信工程]