山区高速公路驾驶人加减速行为建模

山区地形地质条件复杂,各类复杂的组合线形设计更为常见,例如直线与平曲线间组合或不同平曲线间组合。驾驶人在相邻组合路段行驶时会感知到线形的变化,引起驾驶行为的改变,最终车辆的纵向加速度也会随之改变。频繁的加减速行为会引起驾驶人不适,甚至形成安全隐患。目前针对相邻组合路段驾驶行为的研究中,关于加速度的研究主要基于路段特殊点进行计算。随着驾驶模拟技术的发展,高仿真驾驶模拟器为高速公路的设计评估提供了更好的数据及试验条件支撑。在高仿真驾驶模拟器中,基于湖南省永吉高速公路道路设计参数及周边地形环境参数,构建山区高速公路的三维虚拟模型,以山区高速公路中的相邻组合路段为研究对象,获取山区高速公路组合线形路段的车辆纵向加速度数据,提取加减速事件后,基于驾驶人的加减速行为,采用混合Logit模型,分别判定道路线形层和驾驶人层的影响,研究组合线形对驾驶人纵向加减速选择的具体影响变量以及变量的影响范围。研究结果表明：下游路段最大曲率、上游路段圆曲线段比例、下游路段变坡点数量、下游路段曲线数量、上游路段平均曲率和当前位置曲率等对驾驶人加减速行为有显著影响;通过对比混合Logit模型和多元Logit模型,指出驾驶人层面对模型结果的影响显著。研究结果提供了一种山区高速公路连续纵向加减速行为的建模方案,并可为研究驾驶人在复杂线形条件下的纵向加速度选择行为提供基础。     

基于实车数据的高速公路行驶轨迹偏移和车道侧向余宽

为明确高速公路行驶环境下车辆在车道保持阶段的行驶轨迹特征，给车道宽度值确定提供参考，在重庆市主城区2段高速公路上开展了38名驾驶人的实车驾驶试验。使用车载设备采集自然驾驶状态下的车辆行驶速度、行驶轨迹和“车辆中心点-车道线”横向距离。基于以上数据，计算轨迹横向偏移值和“车身轮廓-车道线”侧向余宽等参数，分析高速公路直线/曲线路段的车辆轨迹横向偏移和侧向余宽变化特征及其影响因素。结果表明：曲线路段和直线路段的期望轨迹横向偏移存在差异，曲线路段行驶轨迹的本质特征是轨迹往曲线内侧偏移，而直线路段的车辆轨迹是倾向于往车道左侧偏移，但曲线路段紧贴车道线行驶的车辆占比要低于直线路段。直线路段车道左侧余宽最小值、期望值分别集中于[0.2 m, 0.6 m]和[0.3 m, 0.9 m],曲线路段车道左侧余宽的最小值和期望值主要分布在[0.2 m, 0.7 m]和[0.5 m, 0.9 m]范围内；车道位置对期望轨迹横向偏移和车道侧向余宽均有影响，左转弯路段的左侧余宽要低于直线路段和右转弯路段；在左转弯路段内侧车道行驶时车辆与中分带的距离更近，因此左转弯的事故风险更高；行驶速度增加时，内侧车道的车辆有...     

考虑道路平曲线设计的驾驶疲劳对车道保持能力影响研究

不同的道路平面线形几何设计对于驾驶人车道保持能力的需求是有差异的,驾驶人受疲劳程度影响也会呈现车道保持能力下降的趋势,当前的研究未综合考虑以上2个因素:线形和疲劳程度对驾驶横向表现的交互影响.邀请41位被试者分别开展550 km的实车实验,获取车辆位置信息GPS以匹配道路线形类型,基于问卷调查方法获取驾驶过程疲劳等级.分析不同疲劳程度、不同平面线形类型以及弯道半径条件下的车道偏离标准差参数,构建了多元线性回归模型.数据分析结果表明,相同疲劳程度下驾驶人在圆曲线段驾驶的偏离值要超过直线段以及缓和曲线段;当弯道半径超过5 500 m时,曲线段弯道半径越大,车道偏离差值越高.同时,考虑了线形影响的多元线性回归模型对疲劳程度的预测精度要高于未考虑线形因素的模型,进一步说明在针对驾驶疲劳行为表现开展研究时,有必要对道路设计参数加以考虑以提高疲劳辨识精度.      

基于视觉特性的驾驶人预瞄时间建模

针对固定时长的预瞄时间无法真实反映驾驶人预瞄行为的问题,首先对自由流条件下的驾驶人视觉特性进行研究,得到直行路段驾驶人注视点多分布在车道中央、弯道路段驾驶人注视点多分布在内侧边缘线附近且视线近似与内侧边缘线相切的结论;在此基础上,探究直行和弯道路段驾驶人预瞄时间的求解方法,并借助驾驶模拟器进行试验,获得了17位驾驶人的预瞄时间。由于预瞄时间的原始数据分布离散程度高,难以直观地体现其随道路线形的变化规律,因而对预瞄时间随道路线形的分布特征进行研究,利用分组求中位数的方法进行数据处理,最终构建预瞄时间关于道路线形的分段线性函数和非线性指数函数。最后,通过数值仿真研究不同类型的预瞄时间（固定时长的预瞄时间、分段线性函数预瞄时间及指数函数预瞄时间）对人-车-路闭环系统动力学特性的影响。研究结果表明：驾驶人预瞄特性会对车辆的轨迹跟随和车道保持绩效产生重要影响;在闭环系统中使用随道路线形变化的预瞄时间可以显著提高车辆的轨迹跟随绩效,确保车辆在指定车道内行驶;驾驶人对道路环境的感知具有自适应性,通过其视觉特性可准确感知环境变化,并据此调整决策目标及其操纵特性。     

驾驶模拟条件下高速公路线形指标对驾驶绩效影响特征分析

驾驶绩效是衡量驾驶员维持正常驾驶能力的重要指标。为研究高速公路平、纵线形指标对驾驶员行车过程中纵向和横向驾驶绩效的影响,利用模拟驾驶实验平台开展了模拟驾驶实验。按照几何线形对实验场景进行路段划分,统计分析了不同线形指标路段单元上车辆速度、车道偏移量等驾驶绩效指标的变化规律。实验结果表明,车辆运行速度随着平曲线半径增大而上升;下坡路段车速随着纵坡坡度的增大出现先上升后下降的小幅度变化;车辆横向偏移量随道路线形指标无明显变化规律,其变化受驾驶经验、车速、线形指标等多因素影响。这一研究可为高速公路人性化道路线形设计提供参考。     

基于自然驾驶数据的高密度立交出入口车辆轨迹特征研究

互通式立体交叉是道路交通网络重要的节点,而随着相邻立交之间的间距不断缩小,逐渐形成了高密度立交群,容易造成交通拥堵,加大驾驶负荷和事故风险。为明确在高密度立交群出入口区段的运行风险和安全隐患,在重庆内环路选取了1簇高密度立交群作为研究对象,开展了实车驾驶实验。使用车载仪器采集自然驾驶状态下车辆轨迹数据,包含速度、实时行驶位置以及车辆中心与两侧车道线之间的横向距离;基于对实测数据的深度分析,明确立交出入口的车辆轨迹形态以及车道选择行为特征和驾驶人性别对轨迹形态的影响关系,挖掘车辆驶离（汇入）主线过程中的换道行为特征和驾驶风险影响因素。结果表明：(1)出入口类型对车道选择和轨迹形态有明显影响,相比于平行式出口,直接式出口的轨迹更顺畅,换道次数更少;(2)驾驶人在净距较近的2座立交驶入驶出时,进入主线路段更倾向选择辅助车道或者最外侧车道行驶,以减少换道次数;(3)出入口附近的主线车道数变化会影响驾驶人的车道选择行为;(4)驶离主线时,平行式出口的换道持续时间要高于直接式出口,而入口类型对于换道时间没有显著影响,78%驾驶人的换道时间为5～10 s;(5)出口区段的运行风险高于入口区段,可在出...     

重载货车长下坡挂挡决策行驶安全仿真

长大下坡是大型车辆事故多发的典型路段,现有仿真模式多适用于宏观评价道路平面线形安全,无法反映驾驶人不同挂档决策对长下坡行车安全的影响。建立了重载货车整车模型、转向控制器和踏板控制器。根据重载货车自然驾驶数据,引入驾驶人控制边界约束,通过联合TruckSim和Simulink软件,设计了基于挂档加速、挂档滑行、挂档制动的长下坡行驶控制策略。提出了在车辆速度层面引入驾驶人操纵行为特征谱的虚拟仿真试验。根据当前路段驾驶人挂挡问卷调查信息,以1条实际长下坡道路作为算例,研究了不同驾驶模式下重载货车长下坡行驶特性。仿真结果表明:预瞄定速模式控制下的车辆节气门开度和车轮制动压力呈现相互交替态势,与车辆真实长下坡行驶特性不符,难以为长下坡道路安全改善提供客观依据,而挂挡下坡行驶控制模式能够反映重载货车在不同挂挡决策下的行驶特性;以车辆行车速度和单轮制动压力为评价参数,在当前仿真路段行驶过程中,重载货车7档位挂挡下行安全性能最优,8档位挂挡下行综合性能最优,其单轮制动压力高幅值波动区域主要集中于28.3～35.5 km路段,从而可为该路段驾驶人挂档决策优化、道路纵断面及避险车道位置设计提供一种新的思路。     

高速公路不同线形组合路段划分研究

通过对27名典型车型驾驶员在高速公路不同线形条件下的运行速度、生理和心理变化等现场试验数据采集、分析,得到驾驶员安全舒适性评价指标(驾驶工作负荷度)在高速公路不同线形组合路段的变化规律;提出高速公路线形变化引起的车辆运行速度和驾驶工作负荷度变化具有提前性,而并非在道路线形变化点同时发生变化,这种提前现象反映出驾驶员对道路线形条件变化认知和决策的适应特性;提出了基于驾驶工作负荷度变化特性的高速公路不同线形组合路段划分标准。研究结论对道路设计、交通安全设施布设和道路运营管理等理论和实践具有一定的参考价值。     

自然驾驶状态下重型工程车驾驶人驾驶稳定性分析

重型工程车行驶过程中事故风险大,发生恶性事故的概率高,易造成重大生命和经济损失,其运输安全管理问题面临挑战.为探究重型工程车驾驶人驾驶稳定性与相关影响因素之间的关系,开展重型工程车自然驾驶试验,提取车辆运动学、道路条件、驾驶人状态和工作时间等数据;采用速度均值和速度标准差表征驾驶人驾驶稳定性,以睡眠模式、道路线形、道路...     

线形空间几何突变对曲线路段车道偏移的影响

为了探讨道路线形变化对侧碰、刮擦等侧向安全事故的影响，以三维空间线形的曲率和挠率作为公路线形几何特征描述参数，以车道偏移量作为侧向行车安全的表征指标，剖析了线形在空间层面发生的几何突变对车道偏离的影响。在山区高速公路开展实车试验，采用侧向行车视频记录连续的车道偏移，进行图像距离与实际距离的标定，并通过图像识别技术自动读取连续的车道偏移曲线，从中获取最大车道偏移作为分析变量。采用单因素方差分析方法，对新手驾驶人和熟练驾驶人在线形空间几何特征不同的曲线路段所表现的最大车道偏移结果展开统计分析和检验。分析结果表明：当空间曲率突变超过一定的临界值时，空间曲率突变与最大车道偏移显著正相关；挠率突变对车道偏移产生的影响主要取决于线形扭转的方向，当线形扭转方向与路拱横坡反向时，会明显加剧最大车道偏移；而线形扭转方向与路拱横坡同向时，会降低最大车道偏移但降低效果不明显；熟练驾驶人的最大车道偏移小于新手驾驶人，这种现象在空间曲率突变较大和挠率突变不利的路段尤为明显。研究结论可为公路线形安全性评价、线形设计优化和路侧安全改善提供参考。     

A two-stage-training support vector machine approach to predicting unintentional vehicle lane departure

Advanced driver assistance systems, such as unintentional lane departure warning systems, have recently drawn much attention and efforts. In this study, we explored utilizing the nonlinear binary support vector machine (SVM) technique to predict unintentional lane departure, which is innovative, as the SVM methodology has not previously been attempted for this purpose in the literature. Furthermore, we developed a two-stage training scheme to improve SVM's prediction performance in terms of minimization of the number of false positive prediction errors. Experiment data generated by VIRTTEX, a hydraulically powered, 6-degrees-of-freedom moving base driving simulator at Ford Motor Company, were used. All the vehicle variables were sampled at 50 Hz and there were 16 drowsy drivers (about 3 hours of driving per subject) and six control drivers (approximately 20 minutes f driving each). In total, 3,508 unintentional lane departures occurred for the drowsy drivers and 23 for the control drivers. Our study involving these 22 drivers with a total of more than 7.5 million prediction decisions demonstrates that (a) excellent SVM prediction performance, measured by numbers of false positives (i.e., falsely predicted lane departures) and false negatives (i.e., lane departures failed to be predicted), was achieved when the prediction horizon was 0.6 seconds or less, (b) lateral position and lateral velocity worked the best as SVM input variables among the nine variable sets that we explored, and (c) the radial basis function performed the best as the SVM kernel function.     

Vehicle dynamics and road curvature estimation for lane departure warning system using robust fuzzy observers: experimental validation

This paper describes a new approach to estimate vehicle dynamics and the road curvature in order to detect vehicle lane departures. This method has been evaluated through an experimental set-up using a real test vehicle equipped with the RT2500 inertial measurement unit. Based on a robust unknown input fuzzy observer, the road curvature is estimated and compared to the vehicle trajectory curvature. The difference between the two curvatures is used by the proposed lane departure detection algorithm as the first driving risk indicator. To reduce false alarms and take into account driver corrections, a second driving risk indicator based on the steering dynamics is considered. The vehicle nonlinear model is deduced from the vehicle lateral dynamics and road geometry and then represented by an uncertain Takagi–Sugeno fuzzy model. Taking into account the unmeasured variables, an unknown input fuzzy observer is proposed. Synthesis conditions of the proposed fuzzy observer are formulated in terms of linear matrix inequalities using the Lyapunov method.     

Driver models for personalised driving assistance

We propose a learning-based driver modelling approach which can identify manoeuvres performed by drivers on the highway and predict the future driver inputs. We show how this approach can be applied to provide personalised driving assistance. In a first example, the driver model is used to predict unintentional lane departures and a model predictive controller is used to keep the car in the lane. In a second example, the driver model estimates the preferred acceleration of the driver during lane keeping, and a model predictive controller is implemented to provide a personalised adaptive cruise control. For both applications, we use a combination of real data and simulation to evaluate the proposed approaches.     

Factors affecting lane change crashes

This study aims to investigate the contributing factors affecting the occurrence of crashes while lane-changing maneuvers of drivers. Two different data sets were used from the same drivers' population. The first data set was collected from the traffic police crash reports and the second data set was collected through a questionnaire survey that was conducted among 429 drivers. Two different logistic regression models were developed by employing the two sets of the collected data. The results of the crash occurrence model showed that the drivers' factors (gender, nationality and years of experience in driving), location and surrounding condition factors (non-junction locations, light and road surface conditions) and roads feature (road type, number of lanes and speed limit value) are the significant variables that affected the occurrence of lane-change crashes. About 57.2% of the survey responders committed that different sources of distractions were the main reason for their sudden or unsafe lane change including 21.2% was due to mobile usage. The drivers' behavior model results showed that drivers who did sudden lane change are more likely to be involved in traffic crashes with 2.53 times than others. The drivers who look towards the side mirrors and who look out the windows before lane-change intention have less probability to be involved in crashes by 4.61 and 3.85 times than others, respectively. Another interesting finding is that drivers who reported that they received enough training about safe lane change maneuvering during issuing the driving licenses are less likely to be involved in crashes by 2.06 times than other drivers.     

老年驾驶人在交叉口的视觉特性（双语出版）

机动车驾驶人主要通过视觉搜索行为获取交通信息,为了分析老年驾驶人进入道路交叉口的视觉特性,建立了5个道路交叉口的虚拟场景,并进行了驾驶模拟试验,采集了21名老年驾驶人和17名中青年驾驶人进入交叉口的眼动数据。应用动态聚类法将驾驶人的视野平面划分为5个注视区域;在此基础上对比分析了2组驾驶人进入交叉口的注视特性、扫视特性、注视转移概率和注视平稳分布概率;并通过灰色关联度矩阵分析了影响注意转移行为的因素。分析结果表明：老年驾驶人对非行驶方向上的注视区域的注意都相对较差,2组驾驶人的注视持续时间、扫视幅度和扫视平均速度存在较大的差异,其中老年驾驶人的扫视幅度和扫视速度明显低于中青年驾驶人,而且老年驾驶人的注视点分布在车辆正前方区域的平稳分布概率为80.7%,比中青年驾驶人的69.3%高11.4%,并且具有显著性差异,说明老年驾驶人注视转移模式的灵活性相对中青年驾驶人较差。     

Analysis of driver response to collision warning during car following

This paper describes research on drivers’ responses to a forward vehicle collision warning by driving simulator experiments in which 36 subjects were disposed randomly to the following three kinds of dangerous scenes while the subjects were intentionally distracted: closing to a preceding vehicle, sudden cut-in of a vehicle from an adjacent lane, and lane departure of own vehicle. The responses of the subjects to the warning against cut-in vehicles were analyzed. It is shown that the subjects could take proper evasive action, but the average brake response time was longer than those for simpler scenario tests. It is also verified that there were statistically significant effects of warning sound on the subjects’ response times.