基于ERP的草原公路自动驾驶接管认知特性研究  

Cognitive Characterization of Automatic Takeover of Driving on Grassland Roads Based on ERP

作　　者：高明星[1] 岳晶晶 李鹏飞 马东梅 GAO Mingxing;YUE Jingjing;LI Pengfei;MA Dongmei(College of Energy and Traffic Engineering,Inner Mongolia Agricultural University,Hohhot 010018,China;Inner Mongolia Jiaoke Road and Bridge Construction CO.Ltd.,Hohhot 010070,China)

机构地区：[1]内蒙古农业大学能源与交通工程学院,呼和浩特010018 [2]内蒙古交科路桥建设有限公司,呼和浩特010070

出　　处：《内蒙古农业大学学报（自然科学版）》2024年第6期69-75,共7页Journal of Inner Mongolia Agricultural University(Natural Science Edition)

基　　金：内蒙古自治区高等学校青年科技人才发展项目(NMGIRT2304)。

摘　　要：探究草原公路L3级有条件自动驾驶接管过程中驾驶员的认知特性,对提升自动驾驶技术的普适性和安全性有重要意义。根据感官参与维度负荷等级评价法,设计4种不同负荷等级的非驾驶相关任务(NDRTs):0级负荷-无NDRTs、1级负荷-听新闻、2级负荷-看视频、3级负荷-玩游戏,并结合草原公路典型风险接管场景(牲畜占道)开展模拟驾驶实验。利用事件相关电位(ERP)分析不同NDRTs下驾驶员的P300与N2b的脑地形图、潜伏期和波幅值变化规律,综合NASA-TLX量表进行接管认知主客观评价。结果表明:(1)参与认知资源分配和注意力调控的额区和顶区中P300、N2b成分变化最为明显;(2)P300波幅值和N2b潜伏期均在1级负荷NDRTs下达到最小值,而在3级负荷NDRTs下P300潜伏期和N2b波幅值出现显著下降;(3)在草原公路自动驾驶过程中,建议驾驶人执行涉及听觉和认知资源的1级负荷NDRTs,尽量避免执行占用多种感官参与维度的3级负荷NDRTs。Exploring the cognitive characteristics of drivers during L3-level conditional autonomous driving takeovers on grassland roads is important for enhancing the universality and safety of autonomous driving technology.Utilizing a load level evaluation meth⁃od based on sensory engagement dimensions,four kinds of non-driving related tasks(NDRTs)with varying load levels,i.e.,level 0 load(no NDRTs),level 1 load(listening to news),level 2 load(watching videos),and level 3 load(playing games),were de⁃signed.Simulated driving experiments were also conducted in conjunction with a typical risk takeover scenario(livestock occupying the road)on a grassland road.Event-related potential(ERP)was used to assess the changes in brain topography,latency and wave amplitude values of P300 and N2b in drivers under different NDRTs.Additionally,the comprehensive NASA-TLX scale was em⁃ployed for both subjective and objective evaluations of takeover cognition.The results showed that,the changes of P300 and N2b components in the frontal and parietal regions,which are involved in cognitive resource allocation and attention regulation,were most pronounced.Both the P300 wave amplitude and N2b latency reached their minimum values under level 1 loading NDRTs,while level 3 loading NDRTs resulted in a significant decrease in P300 latency and N2b wave amplitude.During the grassland high⁃way autopilot,it was recommended that the driver engaged in level 1 loading NDRTs that utilized auditory and cognitive resources,while avoiding level 3 loading NDRTs that demanded multiple sensory engagement dimensions.

关 键 词：草原公路 自动驾驶 接管认知 非驾驶相关任务(NDRTs) 事件相关电位(ERP) 

分 类 号：U491.2*54[交通运输工程—交通运输规划与管理]