Investigating fatal and injury crash patterns of teen drivers with unsupervised learning algorithms

Teenagers have been emphasized as a critical driver population class because of their overrepresentation in fatal and injury crashes. The conventional parametric approaches rest on few predefined assumptions, which might not always be valid considering the complicated nature of teen drivers' crash characteristics that are reflected by multidimensional crash datasets. Also, individual attributes may be more speculative when combined with other factors. This research employed joint correspondence analysis (JCA) and association rule mining (ARM) to investigate the fatal and injury crash patterns of at-fault teen drivers (aged 15 to 19 years) in Louisiana. The unsupervised learning algorithms can explore meaningful associations among crash categories without restricting the nature of variables. The analyses discover intriguing associations to understand the potential causes and effects of crashes. For example, alcohol impairment results in fatal crashes with passengers, daytimes severe collisions occur to unrestrained drivers who have exceeded the posted speed limits, and adverse weather conditions are associated with moderate injury crashes. The findings also reveal how the behavior patterns connected with teen driver crashes, such as distracted driving in the morning hours, alcohol intoxication or using cellphone in pickup trucks, and so on. The research results can lead to effectively targeted teen driver education programs to mitigate risky driving maneuvers. Also, prioritizing crash attributes of key interconnections can help to develop practical safety countermeasures. Strategy that covers multiple interventions could be more effective in curtailing teenagers' crash risk.     

考虑高速公路运行风险的雨天可变限速方法

为保证雨天环境下高速公路行驶安全，降低道路整体运行风险，结合雨天风险特征，开展考虑运行风险的雨天可变限速研究。首先应用随机森林模型，标定雨天环境下高速公路动静态风险因素的特征重要度，并结合熵值理论，建立高速公路风险模型、计算风险系数、划分风险等级;之后，以空域自适应算法中可变限速推演变化规律为基础，考虑大、小型车的行驶特征，结合预期风险、雨天停车视距、水膜厚度等因素，优化可变限速模型，细化大、小型车辆的初始控制值，进而提出不同降雨强度、不同能见度下的可变限速推荐值；在此基础上，利用驾驶模拟实景仿真系统、心理生理检测设备、微观交通流仿真软件，开展可变限速系统控制值合理性及驾驶人行车适应性与交通流运行状态的实证分析。研究结果表明：随着能见度降低和降雨量增大，在可变限速控制下，驾驶人呈现出交感神经兴奋性减弱、副交感神经兴奋性增强、心理紧张度降低的状态，其平均心率、心率变异性高频值、心率变异性低频值、心率变异性差异值分别由74.13、0.121、0.643、2.37变为78.23、0.192、0.567、2.01，驾驶人对限速方案的适应性良好；同时，可变限速可保证道路整体通行效率，不会造成交通流风险震动，在小型车、大型车限速分别为80、60 km·h^-1和小型车限速60 km·h^-1、大型车禁止驶入场景下，碰撞时间均值、中值大于未限速场景，各车道的行车安全性均能得到保障;提出的雨天可变限速控制方法合理，且具有一定工程适应性，能为异常天气高速公路宏观车流主动防控提供理论支撑。     

基于轨迹数据的危险驾驶行为识别方法

连续的跟驰行为和换道行为是驾驶行为的主要构成部分,对交通拥挤和交通事故有着重要影响。通过无人机视频拍摄和图像处理方式,提取了曹安公路沿线的2个交叉路口间正常交通流状态下共600条多车高精度轨迹数据。首先,考虑车辆类型对驾驶行为产生直接的影响,分析了大车和小车的车辆轨迹特征变量分布的差异性,包括速度、加速度、碰撞时间倒数、车头时距等,在标记危险驾驶行为的过程中考虑车辆类型的影响。其次,针对不同的车辆类型,利用修正碰撞裕度对跟驰行为和换道行为进行风险性评估,将其划分为安全型和风险型。根据风险型行为发生的顺序以及持续时间,评估驾驶人的整体驾驶状态是否危险,作为危险驾驶行为识别的样本标记。分别利用离散小波变换和统计方法提取车辆轨迹的关键特征参数,为了提高模型识别效率,将关键特征参数进行排序,从而确定最优判别指标;最后,利用轻量梯度提升机（LGBM）算法对危险驾驶行为进行识别,并与随机森林、多层感知器、支持向量机等算法在精度上进行比较。研究结果表明：在上述研究条件下,LGBM算法对危险驾驶行为的理论识别率最高可达93.62%,可以实现基于机器学习算法的危险驾驶行为的高精度自动识别,该结果对于智能驾驶辅助系统的设计、道路交通安全决策的制定具有显著的意义。     

基于轨迹数据的交叉口相位切换期间危险驾驶行为实证分析

基于交叉口相位切换期间的车辆轨迹数据,分别根据单车和跟车行驶状态,识别和分析了相位切换期间可能发生的危险驾驶行为。通过视频拍摄和图像处理的方式,提取了曹安公路沿线3个交叉口共312条单车状态和四平路-大连路交叉口共449条跟车状态的高精度车辆轨迹数据。针对交叉口相位切换期间的危险驾驶行为特征,利用速度、加减速度、减速度变化率、潜在碰撞时间（TTC）等指标,研究在此期间车辆发生危险驾驶行为的特点和类型。对于单车状态下行驶的车辆,按停止、通过分类,依据减速度、减速度变化率、减速度变化率的峰值差等指标将停止车辆的危险驾驶行为分为紧急减速型、增强减速型和持续急减型,依据过停车线时间、速度、加速度等指标将通过车辆分为闯红灯型、超速过线型、激进加速型和持续高速型。对于在跟车状态下行驶的车辆,按前、后车不同的停止、通过决策组合分类,依据连续5个时间间隔（0.12 s）的TTC分析前、后车的危险驾驶行为及发生追尾事故的危险程度。针对识别出的危险驾驶行为类型,讨论车辆的关键行为参数与危险驾驶行为之间的内在关联。研究结果表明：单车状态下有17%的车辆存在危险驾驶行为,其中53%为紧急减速行为;跟车状态下有19%的跟车行为是危险的,其中停止车辆的比例是通过车辆的2倍以上。研究成果可进一步应用于驾驶行为模型的参数标定、基于车辆轨迹的交叉口安全评价以及预防危险驾驶行为的主动安全控制策略等。     

山区高速公路隧道路段与开放路段的事故影响因素分析

高速公路隧道构造特殊且通行环境复杂,因而通常事故多发。为探究高速公路隧道路段与开放路段事故影响因素和严重程度致因机理的差异,采集沪昆高速邵怀段2011—2016年期间1 537起事故为研究样本;以事故发生路段为响应变量构建逻辑回归模型,解释各种风险因素对事故发生路段倾向性的影响差异;分别针对隧道路段与开放路段建立模型研究事故伤害严重程度的影响因素。建立二元Logit回归模型分析事故的发生倾向性和2类路段的事故严重程度的影响因素;采用随机参数Logit模型以反映异质性条件对参数的影响。统计表明:与疲劳驾驶、未保持安全距离相关的事故发生在隧道路段的概率更高,其事故发生概率分别是开放路段的2.373和2.482倍;与隧道路段事故严重程度正相关的因素包括下坡（坡度2%以上）、夏季和超速行驶,其中下坡（坡度2%以上）段的严重事故发生的概率为上坡（坡度2%以上）的3.397倍,夏季的严重事故发生概率为秋季的3.951倍,超速行驶相关的严重事故发生概率为其他不当驾驶行为的4.242倍;与开放路段事故严重程度正相关的因素包括超速行驶和疲劳驾驶,其中超速行驶相关的严重事故概率是其他不当驾驶行为的2.713倍,疲劳驾驶相关的严重事故概率是其他不当驾驶行为的4.802倍。研究表明,山区高速公路隧道路段与开放路段的事故发生概率及其严重程度的影响因素存在一定的差异性,研究结论可为山区高速公路差异管理方案制定提供依据。      

Employment of instrumented vehicles to identify real-time snowy weather conditions on freeways using supervised machine learning techniques – A naturalistic driving study

This study introduces the idea of using vehicles as weather sensors to identify real-time weather on freeways in the same context as Road Weather Information System (RWIS) but in a continuous, trajectory-level, and for road segments allocated in the vehicles paths. The study developed a novel approach to detect snowy and clear weather conditions by utilizing real-time data collected from vehicles' external sensors and CANbus. The proposed approach used time series datasets from the SHRP2 Naturalistic Driving Study (NDS), collected during normal driving conditions on freeways. Trips occurring in snowy weather alongside matched trips in clear weather were segmented into time- and distance-based segments such as a one-minute, one-mile, and half a mile. Three assemblies of the input data are considered in the modeling step: data collected from external sensors, CANbus data, and these two data combined. Data analysis was implemented using the Deep Learning Artificial Neural Network, Decision Tree, Random Forest, and Gradient Boosted Trees models. The results indicate that using different segmentation levels provides decent results in detecting snowy weather. The accuracy in estimating the real-time snowy weather was in ranges of 80% to 85%, 71% to 79%, and 73% to 83% for the one-minute, one-mile, and half mile segmentation types, respectively. The GBT model performed the best among all models based on the area under the Receiver Operating Characteristics (ROC) curve, the highest cumulative percentage in estimating the snowy weather using the lower portion of the population, and the highest overall accuracy. Results indicated that an accuracy of 83% in estimating snowy weather conditions could be accomplished using the data collected from external sensors only without accessing CANbus data.     

Assessment of the effectiveness of connected vehicle weather and work zone warnings in improving truck driver safety

Improving work zone safety remains a prime challenge for the transportation sector in the United States. In particular, the frequency and severity of work zone crashes involving large trucks in rural freeways are alarming. Lack of compliance with the instructions provided at work zones results in increased crash risk. In-vehicle advanced warning systems enabled by Connected Vehicle (CV) technology have the potential to prompt appropriate driver response, make navigation more predictable, and improve overall work zone safety. This study falls under the umbrella of the WYDOT Connected Vehicle Pilot Program and seeks to investigate the impacts of the Pilot's real-time weather and work zone notifications on the behavior of truck drivers in rural freeway work zone settings under poor visibility. Twenty professional truck drivers participated in this simulator study. The driving scenarios were designed to mimic the driving conditions experienced on Wyoming Interstate 80. Findings suggest that exposure to the CV notifications has promising safety benefits manifested in improved driver behavior and response. Furthermore, both the weather and work zone notifications acquired high approval from the participants in terms of usefulness and ease of understanding. Nonetheless, the display of multiple work zone warnings on the Human Machine Interface may had introduced little to moderate distraction for some participants. Overall, this study brings forth valuable lessons that are being funneled to support informed decision making to enhance the Pilot's existing Human Machine Interface design.     

Inclusion of speed and weather measures in safety performance functions for rural roadways

The research on relationships among vehicle operating speed, roadway design elements, weather, and traffic volume on crash outcomes will greatly benefit the road safety profession in general. If these relationships are well understood and characterized, existing techniques and countermeasures for reducing crash frequencies and crash severities could potentially improve, and the opportunity for new methodologies addressing and anticipating crash occurrence would naturally ensue. This study examines the prevailing operating speeds on a large scale and determines how traffic speeds and different speed measures interact with roadway characteristics and weather condition to influence the likelihood of crashes. This study used three datasets from Washington and Ohio: 1) Highway Safety Information System (HSIS), 2) the National Performance Management Research Dataset (NPMRDS), and 3) National Oceanic and Atmospheric Administration (NOAA) weather data. State-based conflated databases were developed using the linear conflation of HSIS and NPMRDS. The results show that certain speed measures were found to be beneficial in quantifying safety risk. Annual-level crash prediction models show that increased variability in hourly operating speed within a day and an increase in monthly operating speeds within a year are both associated with a higher number of crashes. Safety practitioners can benefit from the current study in addressing the issue of speed and weather in crash outcomes.     

Integrated fuzzy/optimal vehicle dynamic control

There are basically two methods to control yaw moment which is the most efficient way to improve vehicle stability and handling. The first method is indirect yaw moment control, which works based on control of the lateral tire force through steering angle control. It is mainly known as active steering control (ASC). Nowadays, the most practical approach to steering control is active front steering (AFS). The other method is direct yaw moment control (DYC), in which an unequal distribution of longitudinal tire forces (mainly braking forces) produces a compensating external yaw moment. It is well known that the AFS performance is limited in the non-linear vehicle handling region. On the other hand, in spite of a good performance of DYC in both the linear and non-linear vehicle handling regions, continued DYC activation could lead to uncomfortable driving conditions and an increase in the stopping distance in the case of emergency braking. It is recommended that DYC be used only in high-g critical maneuvers. In this paper, an integrated fuzzy/optimal AFS/DYC controller has been designed. The control system includes five individual optimal LQR control strategies; each one, has been designed for a specific driving condition. The strategies can cover low, medium, and high lateral acceleration maneuvers on high-μ or low-μ roads. A fuzzy blending logic also has been utilized to mange each LQR control strategy contribution level in the final control action. The simulation results show the advantages of the proposed control system over the individual AFS or DYC controllers.     

Factors influencing crash involvement during early years of owning a new vehicle

Though automobile manufacturers are investing efforts to make newer vehicles safer to drive, an element of uncertainty with the new vehicle seems to persist with the drivers during the early years of ownership. This could be due to a lack of familiarity of the vehicle's power, dimensions or available technologies/features. While the uncertainty in itself is a potential cause of a crash, it is important for the policy-makers, practitioners, and automobile manufacturers to understand the factors that could further aggravate the problem. This research focuses on identifying the factors influencing the likelihood of getting involved in a crash and its severity when driving a new vehicle. Crash data for North Carolina for the years 2013 to 2018 (six years) was used develop partial proportionality odds models, compute the odds ratios, analyze the effects of explanatory variables, and identify factors influencing crashes by the age of the vehicle. The likelihood of getting involved in a severe or moderate injury crash when driving a new vehicle is less for drivers in the age group ≤19 years. Erratic driving behavior (like making wide turns, weaving and swerving in traffic, driving with headlights off, driving on center-line or lane-line, etc.) and speeding increase the risk of getting involved in a moderate injury crash when driving a new vehicle. Likewise, the odds of getting involved in a crash are high on weekends and in adverse weather conditions when driving a new vehicle. They are higher when driving a new motorcycle, heavy vehicle or farm machinery. The findings help policy-makers and practitioners formulate strategies to educate drivers on factors influencing crash risk when driving a new vehicle. Further, automobile manufacturers can establish guidance programs and documentation that explain what to expect when buying and driving a new vehicle.     

高速公路互通立交安全性评价研究综述

高速公路互通立交区道路、交通和行车环境条件的复杂程度远高于基本路段，是制约高速公路运行安全和通行效率的瓶颈路段。互通立交安全性评价研究虽取得了一系列成果，但离实际应用仍有一定差距，有必要对其研究现状进行回顾、总结与展望。为此，针对互通立交安全性评价研究进行系统梳理和总体框架搭建，将其具体分为人因工程理论、交通冲突理论、运行速度协调理论三大理论，事故统计法和层次分析法两大方法，并对其进行综合评述。研究结果表明：人因工程理论适用于主线和匝道的安全性评价，能更准确排查行车安全隐患点、段，但应考虑车辆类型和合理的试验样本量，提高评测指标的稳定性；交通冲突理论适用于主线上存在明显交通冲突区域的安全性评价，但未考虑道路条件对安全性的影响，且应进一步完善交通冲突评价指标体系、划分阈值以及分、合流形式的研究；运行速度协调理论较为成熟，已应用于高速公路基本路段的安全性评价，但主线和匝道的运行速度段落划分和预测模型精度均有待进一步提高；事故统计法的结论客观可靠，但事故数据统计和共享难度大，层次分析法可确定安全性评价的重点内容和关键影响因素，但评价结果主观性较强，2种方法的适用性均存在较大限制。未来研究应针对主线和匝道两大区域系统展开，评价对象应包括分流影响区、合流影响区和衔接过渡区三大路段，建议聚焦人因工程开展深入研究，以最小的代价创建符合人机功效学的互通立交安全运行环境条件。     

A similarity-based neuro-fuzzy modeling for driving behavior recognition applying fusion of smartphone sensors

Drivers’ behavior evaluation is one of the most important problems in intelligent transportation systems and driver assistant systems. It has a great influence on driving safety and fuel consumption. One of the challenges in this regard is the modeling perspective to treat with uncertainty in judgments about driving behaviors. Really, assessing a single maneuver with a rigid threshold leads to a weak judgment for driving evaluation. To fill this gap, a novel neuro-fuzzy system is proposed to classify the driving behaviors based on their similarities to fuzzy patterns when all of the various maneuvers are stated with some fuzzy numbers. These patterns are also fuzzy numbers and they are extracted from statistical analysis on the smartphone sensors data. Our driving evaluation system consists of three processes. Firstly, it detects the type of all of the maneuvers through the driving period, by using a multi-layer perceptron neural network. Secondly, it extracts a new feature based on the acceleration and assigns three fuzzy numbers to driver’s lane change, turn and U-turn maneuvers. Thirdly, it determines the similarity between these three fuzzy numbers and the fuzzy patterns to evaluate the safe and the aggressive driving scores. To validate this model, Driver’s Angry Score (DAS) questionnaires are used. Results show that the fusion of Inertial Measurement Unit (IMU) sensors of smartphones is enough for the proposed driving evaluation system. Accuracy of this system is 87% without using GPS and GIS data and this system is independent of smartphones and vehicles types.     

Crash risk factors associated with injury severity of teen drivers

This paper focuses on identifying crash risk factors associated with injury severity of teen drivers. Crash data obtained from the Highway Safety and Information System (HSIS) for the entire state of North Carolina, for years 2011 to 2013, was used for analysis and modeling. Among all the crashes during the study period, a total of 62,990 crashes involving teen drivers (15 to 19?years) were analyzed. A partial proportionality odds model was developed to identify factors contributing to injury severity of teen drivers. The results obtained indicate that teen drivers driving sports utility vehicles and pickup trucks are more likely to be severely injured when compared to teen drivers driving passenger cars. Teen drivers are more likely to be severely injured on weekdays, particularly during peak hours. The chances of teen drivers getting involved in severe injury crashes on Tuesdays and Fridays is higher when compared to Sundays. Age, gender, road configuration, terrain, adverse weather condition, and access control are observed to have a significant effect on teen driver's injury severity.     

Age and road safety performance: Focusing on elderly and young drivers

The existing literature on young and elderly drivers indicates that they have the highest crash risks compared to other age groups of drivers. This study improves our understanding of the risk factors contributing to young and elderly drivers' elevated crash risk by examining self-report data from the E-Survey of Road User's Safety Attitudes (ESRA). The primary objective of this study is to compare the attitudes and behaviours of young, elderly, and middle-age drivers in Canada, the United States, and Europe. The main focus is on the practice of driving while distracted by mobile phones and driving while fatigued, as these are two dangerous behaviours that demonstrate the impact age may have. The analyses consistently showed that there are differences in the responses attributable to age. In all regions, drivers aged 18–21 years consistently reported higher rates of distracted and fatigued driving and higher rates of perceived social and personal acceptability of these behaviours than drivers aged 35–54 years. Elderly drivers aged 65+ years reported even lower rates of these behaviours and acceptability. Young drivers were also the least likely to believe that distraction and fatigue are frequent causes of road crashes, while elderly drivers were the most likely to believe this. This pattern with respect to age repeats in the support for policy measures as well; young drivers are least likely to support zero tolerance policies for mobile phone use when driving, while elderly drivers are the most likely to support this measure. Multivariate logistic regression modeling confirmed that elderly drivers were the least likely to engage in the use of mobile phones while driving or driving while fatigued. Statistically significant results showed that the middle-age group was less likely than young drivers to read a text message/email or check social media while driving and driving while fatigued.     

Modeling wrong-way crashes and fatalities on arterials and freeways

Wrong way driving (WWD) research and mitigation measures have primarily focused on limited access facilities. This is most likely due to the higher incidence of fatal WWD crashes with dramatic consequences on freeways, media attention, and a call for innovative solutions to address the problem. While public agencies and published literature address WWD incidence on freeway systems, the crash analyses on non-limited access facilities, i.e., arterial corridors, remains untouched. This research extends previous works and attempts to provide many new perspectives on arterial WWD incidence. In particular, one work showed that while WWD fatalities are more likely to occur on freeways, the likelihood of these crashes is higher on arterials. Hence this work with univariate and multivariate analyses of WWD and non-WWD crashes, and fatal and non-fatal WWD incidents. Results show the impressive negative impacts of alcohol use, driver defect, nighttime and weekend incidence, poor street lighting, low traffic volumes, rural geography, and median and shoulder widths. The objective here is to highlight the need for paying greater attention to WWD crashes on arterial corridors as is done with fatal WWD incidents on freeway systems. It suffices to say that while engineering countermeasures should evolve from the traditional signing and pavement markings to connected vehicle technology applications, there is a clear and compelling need to focus on educational campaigns specifically targeting drunken driving, and enforcement initiatives with an objective to mitigate WWD in the most efficient manner possible.     

高速公路平纵线形与事故率的关系及其安全性评价

通过分析高速公路平纵线形指标与事故率的关系,引入线形影响因子,提出了基于线形影响因子的高速公路基本路段安全评价方法。首先,应用回归分析的方法,确定了平曲线半径、平曲线偏角、直线段长度、竖曲线半径及纵坡坡度与事故率的关系,在此基础上分析了弯坡组合、平竖曲线组合以及长大坡组合路段上的事故率。进而,结合事故率与线形的关系,以线形影响因子表征几何线形指标对高速公路事故率的影响,据此评价高速公路的行车安全性。案例分析结果表明,基于线形影响因子确定的危险路段与由实际事故率确定的危险路段具有极高的一致性,达到了81%。      

雨天高速公路纵坡对驾驶员心率及行车速度影响

为了探究降雨时高速公路纵向坡度对行车安全的影响, 以驾驶员的心率增长率(HRGR)和行车速度做为特征参数, 量化分析晴朗和降雨天气下行车速度与驾驶员心率和纵向坡度之间的关系。开展实地驾驶试验采集基础数据, 提取特征参数进行数据融合, 在控制其他因素不变的情况下, 对比晴天和雨天驾驶员HRGR和车辆行驶速度表现的异同, 并确定纵坡路段的研究特征点; 分析晴天和雨天行车速度表现与驾驶员HRGR变化规律, 建立晴天和雨天驾驶员HRGR和行车速度与道路纵向坡度之间的量化关系模型。结果表明: 道路条件相同时, 驾驶员HRGR与行车速度在晴天和雨天的变化规律是分别一致的, 但雨天驾驶员HRGR变化幅度更大, 减速次数更多; 随坡度增大(坡度区间为[1.0%, 4.0%]), 驾驶员HRGR在下坡路段满足指数增长模型, 在上坡路段满足对数增长模型; 行车速度在上坡路段是呈负指数下降趋势, 但在下坡路段, 行车速度在晴天呈指数型增长, 在雨天却呈现出二次多项式先增长再下降的变化规律。      

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.     

Vehicle stability control system for enhancing steerabilty,lateral stability,and roll stability

The Vehicle stability control system is an active safety system designed to prevent accidents from occurring and to stabilize dynamic maneuvers of a vehicle by generating an artificial yaw moment using differential brakes. In this paper, in order to enhance vehicle steerability, lateral stability, and roll stability, each reference yaw rate is designed and combined into a target yaw rate depending on the driving situation. A yaw rate controller is designed to track the target yaw rate based on sliding mode control theory. To generate the total yaw moment required from the proposed yaw rate controller, each brake pressure is properly distributed with effective control wheel decision. Estimators are developed to identify the roll angle and body sideslip angle of a vehicle based on the simplified roll dynamics model and parameter adaptation approach. The performance of the proposed vehicle stability control system and estimation algorithms is verified with simulation results and experimental results.     

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。