Third Generation Simulation Data (TGSIM) I-90/I-94 Moving Trajectories

The main dataset is a 130 MB file of trajectory data (I90_94_moving_final.csv) that contains position, speed, and acceleration data for small and large automated (L2) and non-automated vehicles on a highway in an urban environment. Supporting files include aerial reference images for four distinct data collection “Runs” (I90_94_moving_RunX_with_lanes.png, where X equals 1, 2, 3, and 4). Associated centerline files are also provided for each “Run” (I-90-moving-Run_X-geometry-with-ramps.csv). In each centerline file, x and y coordinates (in meters) marking each lane centerline are provided. The origin point of the reference image is located at the top left corner. Additionally, in each centerline file, an indicator variable is used for each lane to define the following types of road sections: 0=no ramp, 1=on-ramps, 2=off-ramps, and 3=weaving segments. The number attached to each column header is the numerical ID assigned for the specific lane (see “TGSIM – Centerline Data Dictionary – I90_94moving.csv” for more details). The dataset defines six northbound lanes using these centerline files. Images that map the lanes of interest to the numerical lane IDs referenced in the trajectory dataset are stored in the folder titled “Annotation on Regions.zip”. The northbound lanes are shown visually from left to right in I90_94_moving_lane1.png through I90_94_moving_lane6.png. This dataset was collected as part of the Third Generation Simulation Data (TGSIM): A Closer Look at the Impacts of Automated Driving Systems on Human Behavior project. During the project, six trajectory datasets capable of characterizing human-automated vehicle interactions under a diverse set of scenarios in highway and city environments were collected and processed. For more information, see the project report found here: https://rosap.ntl.bts.gov/view/dot/74647. This dataset, which is one of the six collected as part of the TGSIM project, contains data collected using one high-resolution 8K camera mounted on a helicopter that followed three SAE Level 2 ADAS-equipped vehicles (one at a time) northbound through the 4 km long segment at an altitude of 200 meters. Once a vehicle finished the segment, the helicopter would return to the beginning of the segment to follow the next SAE Level 2 ADAS-equipped vehicle to ensure continuous data collection. The segment was selected to study mandatory and discretionary lane changing and last-minute, forced lane-changing maneuvers. The segment has five off-ramps and three on-ramps to the right and one off-ramp and one on-ramp to the left. All roads have 88 kph (55 mph) speed limits. The camera captured footage during the evening rush hour (3:00 PM-5:00 PM CT) on a cloudy day. As part of this dataset, the following files were provided: <ul><li>I90_94_moving_final.csv contains the numerical data to be used for analysis that includes vehicle level trajectory data at every 0.1 second. Vehicle size (small or large), width, length, and whether the vehicle was one of the automated test vehicles ("yes" or "no") are provided with instantaneous location, speed, and acceleration data. All distance measurements (width, length, location) were converted from pixels to meters using the following conversion factor: 1 pixel = 0.3-meter conversion.</li> <li>I90_94_moving_RunX_with_lanes.png are the aerial reference images that define the geographic region and associated roadway segments of interest (see bounding boxes on northbound lanes) for each run X.</li> <li>I-90-moving-Run_X-geometry-with-ramps.csv contain the coordinates that define the lane centerlines for each Run X. The "x" and "y" columns represent the horizontal and vertical locations in the reference image, respectively. The "ramp" columns define the type of roadway segment (0=no ramp, 1=on-ramps, 2=off-ramps, and 3=weaving segments). In total, the centerline files define six northbound lanes.</li> <li>Annotation on Regions.zip, which includes images that visually map lanes (I90_9

主数据集为130 MB的轨迹数据文件（I90_94_moving_final.csv），包含城市环境高速公路上小型、大型自动化（L2级）及非自动化车辆的位置、速度与加速度数据。配套辅助文件包括四个独立数据采集“Run”的航拍参考图像（I90_94_moving_RunX_with_lanes.png，其中X取值为1、2、3、4），同时为每个“Run”配套提供了中心线文件（I-90-moving-Run_X-geometry-with-ramps.csv）。每个中心线文件中包含以米为单位的x、y坐标，用于标记各车道中心线。参考图像的原点位于左上角。此外，每个中心线文件中为每条车道设置了指示变量，用于定义以下路段类型：0=无匝道，1=驶入匝道，2=驶出匝道，3=交织路段。每个列标题附带的数字为对应车道的专属编号（详细信息请参阅"TGSIM – Centerline Data Dictionary – I90_94moving.csv"）。本数据集通过上述中心线文件定义了6条北行车道。用于将目标车道与轨迹数据集中的数字车道ID相对应的图像，存储在名为"Annotation on Regions.zip"的文件夹中。北行车道按从左到右的顺序，分别对应I90_94_moving_lane1.png至I90_94_moving_lane6.png。

本数据集隶属于"第三代仿真数据（Third Generation Simulation Data，简称TGSIM）：深入探究自动驾驶系统对人类驾驶行为的影响"项目。该项目共采集并处理了6套轨迹数据集，用于表征高速公路与城市环境中多样化场景下的人机共驾车辆交互行为。更多信息可查阅项目报告：https://rosap.ntl.bts.gov/view/dot/74647。

本数据集作为TGSIM项目6套采集数据之一，其采集方式为：在4公里长的路段上空200米高度处，使用搭载于直升机的高分辨率8K摄像机，依次跟随3台搭载SAE L2级高级驾驶辅助系统（ADAS）的北行测试车辆。当一台车辆完成该路段行驶后，直升机将返回路段起点，跟随下一台测试车辆以保证数据采集的连续性。该路段被选为研究强制性变道、自主变道及临时强制变道操作的实验场景。路段右侧设有5处驶出匝道与3处驶入匝道，左侧设有1处驶出匝道与1处驶入匝道。全线限速88公里/小时（55英里/小时）。拍摄时段为阴天的晚高峰时段（美国中部时间下午3:00至5:00）。

本数据集包含以下配套文件：
1. I90_94_moving_final.csv：用于分析的数值数据集，以0.1秒为间隔记录车辆级轨迹数据。数据包含车辆尺寸（小型/大型）、宽度、长度、是否为自动化测试车辆（"是"或"否"），以及瞬时位置、速度与加速度数据。所有距离度量（宽度、长度、位置）均通过1像素=0.3米的转换系数，从像素单位转换为米。
2. I90_94_moving_RunX_with_lanes.png：各Run的航拍参考图像，用于划定目标地理区域与道路路段（详见北行车道的边界框标注）。
3. I-90-moving-Run_X-geometry-with-ramps.csv：定义各Run车道中心线的坐标文件。其中"x"与"y"列分别代表参考图像中的水平与垂直位置；"ramp"列用于定义路段类型（0=无匝道，1=驶入匝道，2=驶出匝道，3=交织路段）。所有中心线文件共定义6条北行车道。
4. Annotation on Regions.zip：包含用于可视化匹配车道与轨迹数据集中数字车道ID的图像文件（I90_9