基于驾驶模拟的自动驾驶接管行为研究*

为探索有条件自动驾驶对非驾驶相关任务的允准边界,基于实车驾驶模拟器,设计自动驾驶接管试验典型场景,招募30名被试者开展驾驶模拟试验;要求驾驶人执行3种分心形式的驾驶次任务,系统发出接管请求提示后,驾驶人接管车辆控制权以避免险情发生,并分析驾驶人接管反应时间、驾驶负荷以及驾驶绩效等相关数据。结果表明:驾驶次任务涉及的分心形式越复杂,接管过程安全性越差,视觉分心任务与操作分心任务对接管行为影响显著;驾驶人更倾向于选择制动操作接管车辆,次任务分心程度越高,制动接管比例越大;与乘客聊天对接管行为影响不显著,看视频和玩手机游戏均会显著延长接管反应时间,增加工作负荷与车辆纵向减速度,玩手机游戏还会显著提升车辆横向加速度。     

认知分心时驾驶人应激反应特征分析

为预防由认知分心影响驾驶人应激反应能力引发的交通事故,开展试验,在驾驶模拟器平台上模拟城市、乡镇、山区和高速公路等应激场景,测试有无分心任务2种条件下驾驶人的应激反应,采集驾驶人操作数据和车辆行驶数据,并利用Facelab5型眼动仪记录驾驶人眼动数据;选取相关表征指标并分析试验数据。结果表明:相比于正常驾驶,认知分心驾驶导致驾驶人视觉搜索范围变窄;无论正常驾驶还是认知分心驾驶,扫视行为均以中、低幅度为主;认知分心导致驾驶人对加速踏板的控制能力减弱;与正常驾驶相比,认知分心时驾驶人的应激反应时间明显增加。     

城市道路下分心行为对驾驶员驾驶绩效的影响

为探究城市道路条件下常见驾驶分心行为对驾驶绩效的影响,以16名青年志愿者为被试,开展实车驾驶试验,测量车辆纵向和横向行驶参数,对比分析正常驾驶和分心驾驶状态下的驾驶绩效,并探讨驾驶经验的影响。结果表明：3种分心行为均使横向加速度标准差和纵向加速度标准差增加,而使速度均值降低,说明驾驶员通过速度和转向控制补偿分心状态下的驾驶绩效;交谈对速度均值和纵向加速度均值、阅读广告对速度标准差和横向加速度均值具有显著性影响(p<0.05);接听电话时,经验驾驶员速度标准差明显高于新手(p=0.021);接听电话和阅读广告次任务下,经验驾驶员的横向加速度均值均明显较高(p=0.003,p=0.004),说明经验丰富的驾驶员受分心行为的影响程度更低。     

手机导航方式对驾驶行为的影响研究

为研究驾驶员驾驶时使用不同手机导航方式对驾驶行为的影响,开展模拟驾驶试验,利用眼动仪获取4个场景下车辆行驶状态和驾驶人视觉参数;通过均值比较,方差和显著性分析,探究不同手机导航方式下驾驶行为存在的差异。结果表明:不同手机导航方式均造成驾驶分心,但分心程度不同;手持手机导航使驾驶人对前方和左侧区域的关注下降最为显著;使用导航时,驾驶人一般通过降低车速来减少分心带来的潜在风险,其中手持手机导航降低幅度最大;使用手机导航时,车辆纵向速度标准差更加集中,说明此时驾驶人对于车辆的控制变强。     

驾驶人视觉分心与认知分心研究综述

驾驶分心与交通事故有高度相关性。为探索驾驶分心对驾驶行为的影响及其影响方式,系统梳理国内外相关研究内容。首先介绍视觉分心和认知分心对驾驶行为影响方式的区别,归纳分心时视觉行为与操作行为的相关性;然后对比分析视觉分心、认知分心和结合分心对驾驶安全性的作用强度;最后论述驾驶分心研究目前存在的问题以及今后的研究方向。分析结果表明,驾驶分心严重威胁驾驶安全。视觉和操作行为特性是研究分心的主要对象,而不同类型驾驶分心的视觉和操作行为敏感度指标研究还处于初级阶段。3类驾驶分心的区别可为分心的检测和识别提供理论依据,目前对3类分心任务的评级尚未完善,大多数研究采取的强制分心任务与实际驾驶过程之间是否存在差异,能否得出理想的结论仍有待深入研究。     

基于换道行为的驾驶分心识别方法

为预防驾驶分心导致的交通事故,利用径向基函数(RBF)神经网络模型,研究驾驶分心识别方法。通过驾驶模拟试验,分析驾驶人分别在正常驾驶、手持接听电话和免提接听电话等3种状态下执行车辆换道操作时的驾驶行为,构建基于最小正交二乘法(OLS)的RBF神经网络驾驶分心识别模型,用于判定驾驶人是否处于分心状态。研究表明:驾驶分心对换道过程中车辆的纵向速度、横向速度、横向加速度、方向盘转角、方向盘转速和油门开度等6项驾驶绩效参数有显著影响,所构建模型的平均识别正确率达到88. 7%,可准确识别驾驶人的分心状态,为分心事故预防提供理论支撑。     

驾驶分心对隧道段行车安全影响分析

为研究驾驶分心对隧道段行车安全的影响,在虚拟驾驶环境下设计次任务试验,要求被试驾驶人执行多组不同类型、难度的手动与无手动次任务,同时利用眼动追踪装置采集驾驶人视觉特征参数。在筛选有效数据的基础上,运用统计学与数据挖掘方法比较驾驶人在隧道内执行不同次任务时,车辆运行速度离散性、视觉搜索区域面积、瞳孔面积变化率和次任务持续时间的差异,并分析统计显著性。结果表明,驾驶人在执行手动次任务、无手动次任务、无次任务3种状态下,执行手动次任务时车辆运行速度离散性最大、视觉搜索区域面积最小、瞳孔面积变化率最大,次任务持续时间最长;无次任务时车辆运行速度离散性最小、视觉搜索区域面积最大、瞳孔面积变化率最小;无手动次任务的试验结果居于两者之间,次任务持续时间最短。上述差异具有统计学显著性,主观感知评价与客观数据具有一致性。研究表明,手动与无手动次任务使驾驶人心理负荷明显增大,手动次任务对驾驶人的影响最为明显,因此驾驶分心次任务对隧道段行车安全影响较大。     

驾驶人认知分心识别随机森林模型研究

为识别驾驶人认知分心状态,招募13名驾驶人参与驾驶模拟器试验。通过眼动仪采集被试正常驾驶及认知分心状态下的眼动数据,提取5 s时间窗口内的眼动特征。运用随机森林方法构建认知分心识别模型,应用网格搜索确定最优模型参数,并采用100次留出法评估模型性能。根据随机森林模型特征重要性度量结果,进一步分析认知负荷对驾驶人注视及眨眼持续时间的影响。结果表明:当决策树数量为125、最大特征数为5时,模型识别平均准确率为83.69%;注视持续时间及噪声持续时间是认知分心识别的2个关键特征,随着认知负荷的提高,驾驶人注视持续时间减少、眨眼时间增加。     

城市道路环境下新老驾驶人视觉特性研究

为研究新老驾驶人在城市道路环境下的视觉特性,以开发型汽车驾驶模拟器为试验平台,选用12名被试人员,用眼动仪对被试人员进行生理指标测试。运用统计学和数据挖掘方法对新老驾驶人的瞳孔面积、注视特性、扫视特性和回视特性进行了分析。结果表明:在城市道路环境下,新驾驶人的瞳孔面积变化剧烈;老驾驶人前瞻性机制和反馈机制表现明显,而新驾驶人只表现出具有反馈机制;新驾驶人对仪表盘、前方车辆的注视次数和注视时间较多,老驾驶人更倾向于对后视镜、标志牌、行人等信息的关注;新驾驶人的回视次数多,而老驾驶人回视次数少。在城市道路环境中新驾驶人与老驾驶人相比,视觉特性不稳定,受道路环境的影响较大。     

使用车载信息装置对驾驶行为的影响研究

为研究使用车载信息装置对驾驶行为的影响,基于虚拟驾驶仿真平台,开展正常驾驶、操作按键式和触摸屏式收音机驾驶分心试验;应用外周视觉检测任务法(PDT)测量驾驶人反应时间、PDT目标命中率以及车速和跟驰距离等参数,以评估分心行为的心理资源需求及其对驾驶绩效的影响。试验结果表明:使用车载信息装置会降低驾驶人反应能力和驾驶绩效,操作触摸屏分心与操作按键分心相比,驾驶人反应时间延长了167 ms,PDT目标命中率降低了10%,速度保持和车距保持能力下降,使用触摸屏式车载信息装置需要更多的心理资源,对两侧视野内的信息刺激反应明显迟钝,对行车安全有较大影响。     

驾驶中使用手机对驾驶员行为安全绩效影响综述

驾驶中使用手机与交通事故之间存在着高度相关性。为揭示使用手机对驾驶行为安全绩效的影响,探索影响驾驶安全的理论机制,采取更有效的干预措施,结合近10 a来相关研究,综述了与驾驶安全密切相关的驾驶分心问题,主要包括:驾驶员分心的定义及其分类;使用手机对驾驶行为安全绩效的影响,如反应时(RT)、行车速度、路线保持和跟车距离;手机使用对驾驶员分心影响的理论机制,如信息加工理论和计划行为理论(TPB)。分析表明,使用手机会导致驾驶员的反应时延长15%～40%,驾驶路线发生明显偏移,对于行车速度减缓和跟车距离延长的假设需结合驾驶员主客观数据进行比较做进一步验证;驾驶过程中使用手机会增加驾驶员的认知负荷,TPB能够对使用手机行为进行有效的解释和预测,但对该理论中基于信念测量的研究还很少;除手机操作任务,影响驾驶员分心的其他操作任务还需做进一步的研究。     

Fleet analysis of headway distance for autonomous driving

IntroductionModern automobiles are going through a paradigm shift, where the driver may no longer be needed to drive the vehicle. As the self-driving vehicles are making their way to public roads the automakers have to ensure the naturalistic driving feel to gain drivers’ confidence and accelerate adoption rates.MethodThis paper filters and analyzes a subset of radar data collected from SHRP2 with focus on characterizing the naturalistic headway distance with respect to the vehicle speed.ResultsThe paper identifies naturalistic headway distance and compares it with the previous findings from the literature.ConclusionA clear relation between time headway and speed was confirmed and quantified. A significant difference exists among individual drivers which supports a need to further refine the analysis.Practical applicationsBy understanding the relationship between human driving and their surroundings, the naturalistic driving behavior can be quantified and used to increase the adoption rates of autonomous driving. Dangerous and safety-compromising driving can be identified as well in order to avoid its replication in the control algorithms.     

生态驾驶行为对单个小汽车运行状态的综合影响分析

为了进一步明确我国实际道路交通条件下生态驾驶行为对车辆运行状态的综合影响,助力生态驾驶行为推广应用策略,结合驾驶模拟和实车驾驶试验,重点分析了生态驾驶行为对单个小汽车能耗、排放及运行效率的影响。结果表明:生态驾驶行为能有效降低机动车能耗和尾气排放;同时,相同条件下,生态驾驶行为降低车辆能耗的比例远大于车辆行驶时间增加的比例。因此,对单个小汽车而言,生态驾驶行为的节能效益大于其对车辆运行效率的影响。     

Assessing drivers' response during automated driver support system failures with non-driving tasks

IntroductionWith the increase in automated driver support systems, drivers are shifting from operating their vehicles to supervising their automation. As a result, it is important to understand how drivers interact with these automated systems and evaluate their effect on driver responses to safety critical events. This study aimed to identify how drivers responded when experiencing a safety critical event in automated vehicles while also engaged in non-driving tasks.MethodIn total 48 participants were included in this driving simulator study with two levels of automated driving: (a) driving with no automation and (b) driving with adaptive cruise control (ACC) and lane keeping (LK) systems engaged; and also two levels of a non-driving task (a) watching a movie or (b) no non-driving task. In addition to driving performance measures, non-driving task performance and the mean glance duration for the non-driving task were compared between the two levels of automated driving.ResultsDrivers using the automated systems responded worse than those manually driving in terms of reaction time, lane departure duration, and maximum steering wheel angle to an induced lane departure event. These results also found that non-driving tasks further impaired driver responses to a safety critical event in the automated system condition.ConclusionIn the automated driving condition, driver responses to the safety critical events were slower, especially when engaged in a non-driving task.Practical applicationTraditional driver performance variables may not necessarily effectively and accurately evaluate driver responses to events when supervising autonomous vehicle systems. Thus, it is important to develop and use appropriate variables to quantify drivers' performance under these conditions.     

Driving context influences drivers' decision to engage in visual–manual phone tasks: Evidence from a naturalistic driving study

IntroductionVisual–manual (VM) phone tasks (i.e., texting, dialing, reading) are associated with an increased crash/near-crash risk. This study investigated how the driving context influences drivers' decisions to engage in VM phone tasks in naturalistic driving.MethodVideo-recordings of 1,432 car trips were viewed to identify VM phone tasks and passenger presence. Video, vehicle signals, and map data were used to classify driving context (i.e., curvature, other vehicles) before and during the VM phone tasks (N = 374). Vehicle signals (i.e., speed, yaw rate, forward radar) were available for all driving.ResultsVM phone tasks were more likely to be initiated while standing still, and less likely while driving at high speeds, or when a passenger was present. Lead vehicle presence did not influence how likely it was that a VM phone task was initiated, but the drivers adjusted their task timing to situations when the lead vehicle was increasing speed, resulting in increasing time headway. The drivers adjusted task timing until after making sharp turns and lane change maneuvers. In contrast to previous driving simulator studies, there was no evidence of drivers reducing speed as a consequence of VM phone task engagement.ConclusionsThe results show that experienced drivers use information about current and upcoming driving context to decide when to engage in VM phone tasks. However, drivers may fail to sufficiently increase safety margins to allow time to respond to possible unpredictable events (e.g., lead vehicle braking).Practical applicationsAdvanced driver assistance systems should facilitate and possibly boost drivers' self-regulating behavior. For instance, they might recognize when appropriate adaptive behavior is missing and advise or alert accordingly. The results from this study could also inspire training programs for novice drivers, or locally classify roads in terms of the risk associated with secondary task engagement while driving.     

基于多信息检测的车辆智能防撞预警技术研究

运用多源信息检测技术对驾驶状态进行综合检测,利用架设在车辆外部的摄像机获取本车与前方车辆之间的相对距离、相对速度信息,利用架设在车辆内部的摄像机获取驾驶人状态信息,通过综合判断降低车辆防撞检测的漏警率、误警率以及冗余报警率;构建车辆行驶安全判定规则,对行车实时危险和潜在危险进行检测、分析与判断,获取可靠的防撞警示提醒;使反应时间、相对距离、相对速度3个方面都能得到优化控制,从而避免车辆碰撞事故;同时也为提高车速、增加道路通行能力、实现自动驾驶等奠定良好的基础。     

Emotions drive attention: Effects on driver’s behaviour

Music is the favourite activity while driving. However, very few studies have investigated its impact on driving performances. This study was designed to assess the effect of music’s emotional valence on driving behaviour. Happy, sad and neutral music excerpts were alternated with no-music phases while driving in a simulator. Results showed that happy music distracted drivers the most as their mean speed unexpectedly decreased and their lateral control deteriorated. Sad music influenced drivers in a different way as they drove slowly and kept their vehicle in its lane. These findings were discussed within the framework of attentional orienting and emotions.     

Driver's behavioral adaptation to Adaptive Cruise Control (ACC): The case of speed and time headway

ProblemThe Adaptive Cruise Control is an Advanced Driver Assistance System (ADAS) that allows maintaining given headway and speed, according to settings pre-defined by the users. Despite the potential benefits associated to the utilization of ACC, previous studies warned against negative behavioral adaptations that might occur while driving with the system activated. Unfortunately, up to now, there are no unanimous results about the effects induced by the usage of ACC on speed and time headway to the vehicle in front. Also, few studies were performed including actual users of ACC among the subjects.ObjectivesThis research aimed to investigate the effect of the experience gained with ACC on speed and time headway for a group of users of the system. In addition, it explored the impact of ACC usage on speed and time headway for ACC users and regular drivers.MethodA matched sample driving simulator study was planned as a two-way (2 × 2) repeated measures mixed design, with the experience with ACC as between-subjects factor and the driving condition (with ACC and manually) as within-subjects factor.ResultsThe results show that the usage of ACC brought a small but not significant reduction of speed and, especially, the maintenance of safer time headways, being the latter result greater for ACC users, probably as a consequence of their experience in using the system.SummaryThe usage of ACC did not cause any negative behavioral adaptations to the system regarding speed and time headway.Practical applicationsBased on this research work, the Adaptive Cruise Control showed the potential to improve road safety for what concerns the speed and the time headway maintained by the drivers. The speed of the surrounding traffic and the minimum time headway settable through the ACC seem to have an important effect on the road safety improvement achievable with the system.     

三岔型枢纽互通事故高发匝道的形成机制与安全提升研究*

为研究高速公路三岔型互通右转匝道车辆事故的发生机制,以宜宾至叙永高速公路双桥枢纽互通为对象,运用Carsim/trucksim软件建立事故匝道的三维数字模型,模拟小客车和货柜车的运行过程,设置3种不同工况,对车辆在匝道上的动力学特性进行分析。结果表明:行驶速度升高会导致匝道路段的车辆横向偏离增大,发生侧滑或侧翻的几率增加;充分制动距离是保证车辆安全通过匝道受限路段的重要因素,货车需要更长的制动距离;道路视觉环境是影响驾驶人速度选择行为的重要因素,匝道路段与高速公路主线行驶环境的高度近似,导致驾驶人选择较高的速度进入匝道,部分车辆在小半径弯道之前无法将速度降低至安全速度,进而发生事故。本文运用行车动力学仿真和驾驶人视觉手段,在驾驶行为层面分析事故的形成机制,进而提出安全提升措施,可为匝道线形设计和交通运行管理提供科学依据。