山区高速公路组合线形路段车道偏移行为

为在道路设计阶段确定平纵组合与相邻路段线形对车道偏离的影响,并为减少因道路线形因素引发的侧碰、追尾甚至车辆驶出路外事故提供改善依据,基于真实的山区高速公路道路设计参数及周边地形,搭建驾驶模拟场景,利用驾驶模拟试验获取小客车车道偏离数据,并对应获取车辆当前所在路段及上、下游路段的线形参数。以车辆车道内行驶为参照,沿道路行进方向,将车道偏离行为分为左偏驶离车道与右偏驶离车道。因车道偏离受驾驶人影响,采用双层Logit模型,分别判定道路线形及驾驶人层的影响。研究结果表明：相比直线路段,曲线更易引发车道偏离行为,驾驶人易偏向于曲线内侧行驶;上游300 m路段曲率差越大、平均车速越大,则车道偏离的概率增大;相对于缓坡（-2%≤坡度S≤2%）,行驶于上坡（S>2%）或下坡（S<2%）路段时,车辆车道偏离概率减小;车辆行驶于外侧车道的左偏驶离车道概率大于行驶于内侧车道;驾驶人因素对左偏驶离车道的影响比例为8.8%,对右偏驶离车道的影响比例为25.6%。研究结论可从组合线形角度帮助工程师设计更安全的山区高速公路。     

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。     

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.     

Drowsy behavior detection based on driving information

Drowsy behavior is more likely to occur in sleep-deprived drivers. Individuals’ drowsy behavior detection technology should be developed to prevent drowsiness related crashes. Driving information such as acceleration, steering angle and velocity, and physiological signals of drivers such as electroencephalogram (EEG), and eye tracking are adopted in present drowsy behavior detection technologies. However, it is difficult to measure physiological signal, and eye tracking requires complex experiment equipment. As a result, driving information is adopted for drowsy driving detection. In order to achieve this purpose, driving experiment is performed for obtaining driving information through driving simulator. Moreover, this paper investigates effects of using different input parameter combinations, which is consisted of lateral acceleration, longitudinal acceleration, and steering angles with different time window sizes (i.e. 4 s, 10 s, 20 s, 30 s, 60 s), on drowsy driving detection using random forest algorithm. 20 s-size datasets using parameter combination of accelerations in lateral and longitudinal directions, compared to the other combination cases of driving information such as steering angles combined with lateral and longitudinal acceleration, steering angles only, longitudinal acceleration only, and lateral acceleration only, is considered the most effective information for drivers’ drowsy behavior detection. Moreover, comparing to ANN algorithm, RF algorithm performs better on processing complex input data for drowsy behavior detection. The results, which reveal high accuracy 84.8 % on drowsy driving behavior detection, can be applied on condition of operating real vehicles.     

人机共驾智能车驾驶模式决策属性析取研究

为了深入分析驾驶模式决策影响因子,通过实车试验采集了人-车-路多源特征信息。用驾驶人主观经验将驾驶模式划分为人工驾驶、警示辅助、自动驾驶3种状态,并利用采集的驾驶人血流量脉冲（BVP）和皮肤电导（SC）值进行K均值聚类,将驾驶人当前合适的驾驶模式自动聚类为3级。通过融合驾驶人自汇报结果和聚类结果对驾驶模式进行准确标定。采用以信息增益为依据的Ranker算法对多特征进行排序,并在此基础上,根据多分类器分级结果确定最优特征属性集合。研究结果表明：当选取车速、车头时距、车道中心距离、前轮转角标准差、驾驶经验5个指标为特征子集时,支持向量机、朴素贝叶斯及K近邻这3种分类器的识别准确率都超过90%;除警示辅助模式与自动驾驶模式下的车速值和车道中心距之外,其余所有不同模式决策属性值均呈显著性差异;研究结果可为人机共驾智能车驾驶模式决策提供依据。     

Road curvature estimation for vehicle lane departure detection using a robust Takagi–Sugeno fuzzy observer

In this paper, a lane departure detection method is studied and evaluated via a professional vehicle dynamics software. Based on a robust fuzzy observer designed with unmeasurable premise variables with unknown inputs, the road curvature is estimated and compared with the vehicle trajectory curvature. The difference between the two curvatures is used by the proposed algorithm as the first driving risk indicator. To reduce false alarms and take into account the driver corrections, a second driving risk indicator is considered, which is based on the steering dynamics, and it gives the time to the lane keeping. The used nonlinear model deduced from the vehicle lateral dynamics and a vision system is represented by an uncertain Takagi–Sugeno fuzzy model. Taking into account the unmeasured variables, an unknown input fuzzy observer is then proposed. Synthesis conditions of the proposed fuzzy observer are formulated in terms of linear matrix inequalities using Lyapunov method. The proposed approach is evaluated under different driving scenarios using a software simulator. Simulation results show good efficiency of the proposed method.     

A new shared control for lane keeping and road departure prevention

In recent years, the driver's active assistances have become important features in commercialised vehicles. In this paper, we present one of these features which consists of an advanced driver assistance system for lane keeping. A thorough analysis of its performance and stability with respect to variations in driver behaviour will be given. Firstly, the lateral control model based on visual preview is established and the kinematics model based on visual preview, including speed and other factors, is used to calculate the lateral error and direction error. Secondly, and according to the characteristics of the lateral control, an efficient strategy of intelligent electric vehicle lateral mode is proposed. The integration of the vehicle current lateral error and direction error is chosen as the parameter of the sliding mode switching function to design the sliding surface. The control variables are adjusted according to the fuzzy control rules to ensure that they meet the existence and reaching condition. A new fuzzy logic-based switching strategy with an efficient control law is also proposed to ensure a level of continuous and variable sharing according to the state of the driver and the vehicle positioning on the roadway. The proposed control law acts either at the centre of the lane, as a lane keeping assistance system to reduce the driver's workload for long trips, or as a lane departure avoidance system that intervenes for unintended lane departures. Simulation results are included in this paper to explain this concept.     

Driving environment assessment using fusion of in- and out-of-vehicle vision systems

Because the overall driving environment consists of a complex combination of the traffic Environment, Vehicle, and Driver (EVD), Advanced Driver Assistance Systems (ADAS) must consider not only events from each component of the EVD but also the interactions between them. Although previous researchers focused on the fusion of the states from the EVD (EVD states), they estimated and fused the simple EVD states for a single function system such as the lane change intent analysis. To overcome the current limitations, first, this paper defines the EVD states as driver’s gazing region, time to lane crossing, and time to collision. These states are estimated by enhanced detection and tracking methods from in- and out-of-vehicle vision systems. Second, it proposes a long-term prediction method of the EVD states using a time delayed neural network to fuse these states and a fuzzy inference system to assess the driving situation. When tested with real driving data, our system reduced false environment assessments and provided accurate lane departure, vehicle collision, and visual inattention warning signals.     

Optimal Control Model Applications and Field Measurements with Respect to Car Driving

The well-known optimal control model has been applied only rarely to car driving, although its structure suits the modelling demands of driving by allowing for a multitask application and providing possibilities for the evaluation of driving in terms of supervisory control. Two series of Supervisory Driver Model predictions are stated for lateral position control in a straight driving scenario with disturbances generated internally by the driver. The first series of model calculations predicts lateral position variations and the time that a driver's vision can be occluded during the observation and control of different combinations of display variables (lateral position, lateral speed, yaw rate, lateral acceleration and yaw acceleration). The second series of predictions concerns two extreme sets of display variables in relation to driving speed and driving experience. Model predictions for the observation and control of all display variables give occlusion times which correspond with data from instrumented car studies with experienced drivers. However, with exclusive observation and control of the lateral position cue, predicted occlusion times are less than found in experimental results of inexperienced drivers. It is suggested that inexperienced drivers are also controlling yaw rate and/or both acceleration cues.     

Effect of drowsiness on driving performance variables of commercial vehicle drivers

Driver drowsiness is a major safety concern, especially among commercial vehicle drivers, and is responsible for thousands of accidents and numerous fatalities every year. The design of a drowsiness detection system is based on identifying suitable driver-related and/or vehicle-related variables that are correlated to the driver’s level of drowsiness. Among different candidates, vehicle control variables seem to be more promising since they are unobtrusive, easy to implement, and cost effective. This paper focuses on in-depth analysis of different driver-vehicle control variables, e.g., steering angle, lane keeping, etc. that are correlated with the level of drowsiness. The goal is to find relationships and to characterize the effect of a driver’s drowsiness on measurable vehicle or driving variables and set up a framework for developing a drowsiness detection system. Several commercial drivers were tested in a simulated environment and different variables were recorded. This study shows that drowsiness has a major impact on lane keeping and steering control behavior. The correlation of the number and type of accidents with the level of drowsiness was also examined. Significant patterns in lateral position variations and steering corrections were observed, and two phases of drowsiness-related degradation in steering control were identified. The two steering degradation phases examined are suitable features for use in drowsiness detection systems.     

Driver behavior formulation in intersection dilemma zones with phone use distraction via a logit-Bayesian network hybrid approach

Use of cellular phone while driving is one of the top contributing factors that induce traffic crashes, resulting in significant loss of life and property. A dilemma zone is a circumstance near signalized intersections where drivers hesitate when making decisions related to their driving behaviors. Therefore, the dilemma zone has been identified as an area with high crash potential. This article utilizes a logit-based Bayesian network (BN) hybrid approach to investigate drivers' decision patterns in a dilemma zone with phone use, based on experimental data from driving simulations from the National Advanced Driving Simulator (NADS). Using a logit regression model, five variables were found to be significant in predicting drivers' decisions in a dilemma zone with distractive phone tasks: older drivers (50–60 years old), yellow signal length, time to stop line, handheld phone tasks, and driver gender. The identified significant variables were then used to train a BN model to predict drivers' decisions at a dilemma zone and examine probabilistic impacts of these variables on drivers' decisions. The analysis results indicate that the trained BN model was effective in driver decision prediction and variable influence extraction. It was found that older drivers, a short yellow signal, a short time to stop line, nonhandheld phone tasks, and female drivers are factors that tend to result in drivers proceeding through intersections in a dilemma zone with phone use distraction. These research findings provide insight in understanding driver behavior patterns in a dilemma zone with distractive phone tasks.     

基于注意力Seq2Seq网络的高速公路交织区车辆变道轨迹预测

针对交通状态复杂的高速公路交织区域,经验丰富的驾驶人能够通过正确地推断周围车辆的未来运动进行及时的车道变换,这对于实现安全高效的自动驾驶至关重要,然而目前的自动驾驶车辆往往缺乏这种预测能力。为此,基于深度学习理论,提出了一种结合注意力机制和编-解码器结构的交织区车辆强制性变道轨迹预测方法,利用Next Generation Simulation（NGSIM）数据集提取车辆变道过程中的关键特征,并引入碰撞时间（Time to Collision,TTC）和避免碰撞减速度（Deceleration Rate to Avoid a Crash,DRAC）2种风险指标,将变道车辆及其周围车辆视为一个整体状态单元,同时补全状态单元内部不同车辆在横向和纵向上的时空状态特征,从而更有效地刻画车辆间的动态交互行为;然后将不同观测车辆的连续窗口序列输入基于长短期记忆网络（Long Short-term Memory,LSTM）的编-解码器,预测交织区车辆变道的未来运动轨迹,通过添加软注意力模块,使模型能够集中聚焦于影响车辆在不同时刻下位置变化的关键信息,再现了真实交通场景下车辆的变道行为。试验验证表明：基于注意力机制的编-解码器模型与当前流行的卷积长短期记忆网络、极限梯度提升树等模型相比具有更高的轨迹预测精度,在长时域的变道轨迹拟合上有显著的优越性,为辅助和自动驾驶领域的发展提供了新思路。     

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.      

驾驶风格对驾驶行为的影响

为了揭示驾驶风格对驾驶行为的影响规律,进而提取表征驾驶风格的特征参数,对不同风格驾驶人在感知层和操作层的驾驶行为数据进行了量化分析。首先,基于驾驶行为问卷对18名中国非职业驾驶人进行了驾驶风格问卷调查,并采用主成分分析、K-均值聚类等方法将被试驾驶人分为谨慎型、正常型和激进型3种类型。接着,被试驾驶人在搭载了SmartEye眼动仪的驾驶模拟器上开展了高速公路行车环境下的驾驶试验,同步采集了感知层的视觉特性参数和操作层的驾驶绩效参数,并采用判断抽样的方式将驾驶样本按照驾驶风格和驾驶模式（换道意图和车道保持）进行了划分,共选取了810组有效样本。最后,采用方差分析法分析了不同风格驾驶人在不同驾驶模式下的注视行为、扫视行为、横向控制特性、纵向控制特性方面相关参数的差异显著性,并提取了不同风格间存在显著差异的参数作为表征驾驶风格的特征参数。研究结果表明：驾驶风格越激进,驾驶人对周围环境关注越少,对车辆的横向控制稳定性越差,急加速和急减速行为发生的频次越高;不同风格驾驶人在意图时窗内对后视镜的注视次数（p=0.002）、方向盘转角熵值（p=0.04）、加速踏板开度（p=0.01）、制动踏板开度（p=0.02）这4个参数的差异均较为显著,因此可作为表征驾驶风格的特征参数。     

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.     

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.     

识别驾驶人意图的车道偏离防避有界控制

为了防止车辆偏离车道导致交通事故的发生和避免车道偏离防避系统（Lane Departure Avoidance Systems,LDAS）对驾驶人行为不必要的干预,提出基于中心区操纵特性阈值法和基于D-S（Dempster-Shafer）证据理论的车辆偏离车道驾驶人意图识别准则,并运用CarSim/Simulink联合仿真对比2种识别准则的有效性。建立转向盘角速度为输入的车路模型,设计LDAS滑模转向控制器,基于预瞄点的侧向偏移量和横摆角速度设计LDAS的期望横摆角速度观测器,并与基于道路曲率和预瞄点侧向偏移量的期望横摆角速度的LDAS进行性能对比。运用相平面法确定保证LDAS车辆稳定性的前轮转向角最大值,并基于CarSim/LabVIEW RT硬件在环试验平台验证基于BP神经网络训练获得D-S证据理论的初始概率赋值的驾驶人意图决策算法的有效性。结果表明：所提出的识别准则能够及时识别车辆偏离车道时的驾驶人意图,为LDAS控制器介入赢得了宝贵的时间,所设计的期望横摆角速度观测器具有很好的稳定性,所提出的方法能够有效避免车辆偏离车道。     

基于脉搏波特征融合的驾驶疲劳检测方法

疲劳驾驶是交通事故的主要诱因之一,精确检测驾驶人的疲劳程度是主动预防疲劳驾驶事故的核心内容之一。通过开展自然驾驶试验,以驾驶人的生物信号脉搏波（Blood Pressure Waveform,BPW）为数据源,使用脉搏波波形分析方法从中提取有效表征驾驶疲劳的特征指标,构建用于检测驾驶疲劳等级的BPW特征指标集,在此基础上引入D-S证据理论建立了基于BPW特征融合的驾驶疲劳检测模型。结果表明：该模型对测试数据的疲劳驾驶理论检测精度达到了91.8%,优于贝叶斯网络模型的81.4%和支持向量机模型的84.3%,能够满足实际应用的需求,但与决策回归树检测模型99.7%的精度相比较还有差距。研究获得的基于生物信息融合的驾驶疲劳检查模型和方法在驾驶疲劳检测与监测中具有很好的应用前景,可为辅助安全驾驶和疲劳预警及主动干预提供新的技术方案。     

应急车辆延误情况调查及应对措施研究

因交通拥堵而造成的应急车辆救援延误导致悲剧事件频发。为了解应急车辆救援延误的情况并研究应对措施,以普通机动车驾驶者为对象进行问卷调查,针对驾驶者对应急车辆的认识和对应急车道的占用情况,驾驶者在驾驶过程中对应急车辆是否避让,以及避让方法进行调查。然后利用SPSS数据统计软件筛选出对驾驶者驾驶行为影响权重较大的特征变量,并基于Logistic模型建立了驾驶者特征与占用应急车道和避让应急车辆行为的模型。在此基础上提出相应的应对方案,利用Vissim仿真软件对解决方案进行仿真。结果显示:对有一定驾驶年龄并有本科以上学历的青壮年的驾驶行为对应急车辆延误有较大影响,且正确的避让方法能明显地减少应急车辆的行程时间。