Vehicle Occupants and Driver Behavior: A Novel Data Approach to Assessing Speeding (02-009)

Project Description: The question of whether driver behavior, and speeding in particular, differs based on vehicle occupancy requires the use of large amounts of data—some of which may be difficult to accurately obtain. Traditional methods of obtaining information on driver behavior either lack passenger information altogether (i.e., insurance companies using telematics) or rely on rough estimates of passenger age and gender obtained from blurred photos (i.e., naturalistic driving studies like State Highway Research Program 2 (SHRP 2)). This research project represents a novel, data-driven approach to this topic. Household travel survey demographic information and global positioning system (GPS) traces were linked to HERE network speed limit to study the impact of vehicle occupancy on speeding. Survey responses from 11 study areas were cleaned, merged, and ultimately used in developing binomial logistic regression models. Of particular interest were the driver groups of teenagers, adults driving with children, and older drivers. The models suggest that drivers speed less when there is a passenger in the vehicle, especially adults with a child passenger. These data represent the trip summary model inputs for determining the influence that passengers may have on the following driver groups’ speeding behavior: younger drivers (16-years-old to 24-years-old), older drivers (65+ years old), and all drivers 16-years-old to 55-years-old with a child passenger (0-years-old to 15-years-old). The original trip data came from the Texas Department of Transportation Travel Survey Program’s household travel surveys from eleven urban areas around the state. Each trip was matched with its corresponding GPS trace data to determine the travel route. The route was then assigned posted speed limits from the HERE streets network. Each was trip were was coded as a speeding trip if at least 20% of the trip free-flow (any traveling speed that ranged from 5 miles per hour below the posted speed limit or greater) duration was comprised of driving speeds greater than the posted speed limit. All trips were included in the data set irrespective of travel speed. Driver and passenger demographic characteristics were gathered from the household travel surveys. Data Scope: Trip summaries in tabular format (three Excel CSV files): younger_driver_data_public.csv older_driver_data_public.csv all_drivers_data_public.csv 11 cities across Texas: Abilene Bryan-College Station Corpus Christi El Paso Houston Midland-Odessa San Angelo Sherman-Denison Texarkana Victoria Wichita Falls Trips per driver group: Younger drivers – 825 Older drivers – 2,654 All drivers with child passenger – 6,106 Data Specifcation: Data specification is included in a file attached

项目描述：驾驶员行为（尤其是超速行为）是否因车辆载客量不同而存在差异这一问题，需要依托大量数据开展研究，其中部分数据难以精准获取。传统的驾驶员行为信息采集方式要么完全缺失乘客相关信息（如保险公司采用的车载远程信息处理（telematics）系统），要么依赖模糊照片对乘客年龄与性别进行粗略估算（如公路合作研究计划2（State Highway Research Program 2, SHRP 2）这类自然驾驶研究）。本研究项目针对该主题提出了一种新颖的数据驱动研究方法。研究人员将家庭出行调查的人口统计信息与全球定位系统（Global Positioning System, GPS）轨迹数据和HERE地图网络的限速信息进行关联，以分析车辆载客量对驾驶员超速行为的影响。研究对来自11个研究区域的调查结果进行了清洗与合并，最终用于构建二元逻辑回归模型。本次研究重点关注三类驾驶员群体：青少年驾驶员、搭载儿童的成年驾驶员以及老年驾驶员。模型结果显示，当车辆搭载乘客时，驾驶员的超速行为会有所减少，尤其是搭载儿童乘客的成年驾驶员。
本数据集作为行程摘要模型输入数据，用于评估乘客对以下三类驾驶员群体超速行为的影响：16~24岁年轻驾驶员、65岁及以上老年驾驶员，以及所有搭载0~15岁儿童乘客的16~55岁驾驶员。原始行程数据来自得克萨斯州交通运输部出行调查项目针对全州11个城区开展的家庭出行调查。每条行程均匹配了对应的GPS轨迹数据以确定行驶路线，随后从HERE街道网络中获取该路线的法定限速值。若某条行程的自由流时段（指行驶速度不低于法定限速减5英里/小时的时段）中，有20%及以上的时长是以高于法定限速的速度行驶，则该行程被标记为超速行程。本数据集纳入了所有行程，无论其行驶速度如何。驾驶员与乘客的人口统计特征均来自家庭出行调查。
数据范围：以表格格式存储的行程摘要数据（共3个Excel兼容CSV文件）：younger_driver_data_public.csv、older_driver_data_public.csv、all_drivers_data_public.csv。覆盖得克萨斯州11个城市：阿比林（Abilene）、布莱恩-大学城（Bryan-College Station）、科珀斯克里斯蒂（Corpus Christi）、埃尔帕索（El Paso）、休斯敦（Houston）、米德兰-敖德萨（Midland-Odessa）、圣安吉洛（San Angelo）、谢尔曼-丹尼森（Sherman-Denison）、特克萨卡纳（Texarkana）、维多利亚（Victoria）、威奇托福尔斯（Wichita Falls）。各驾驶员群体的行程数量：年轻驾驶员——825条；老年驾驶员——2654条；搭载儿童乘客的全体驾驶员——6106条。
数据规范：数据规范详见附件文件。