主数据集为一个9 MB的轨迹数据文件（I294_L2_final.csv），包含郊区高速公路环境下小型与大型L2级自动驾驶车辆及非自动驾驶车辆的位置、速度与加速度数据。配套文件包括十二次独立数据采集‘运行’（Runs）的航拍参考图像（文件名格式为I294_L2_Run_X_ref_image_with_lanes.png，其中X分别对应南向运行的5、28、30、36、38、42，以及北向运行的23、29、31、33、35、41）。每条‘运行’还附有对应的中心线文件（I-294-L2-Run_X-geometry-with-ramps.csv），其中以米为单位提供各车道中心线的x、y坐标；参考图像原点位于左上角。每个中心线文件中均设有一个指示变量，用于标识各车道所属路段类型：0=无匝道段，1=入口匝道段，2=出口匝道段，3=交织段。各列标题末尾所附数字为对应车道的数值ID（详见《TGSIM – 中心线数据字典 – I294 L2.csv》）。该数据集通过上述中心线文件定义了八条车道（双向各四条）。将感兴趣车道与轨迹数据集中所引用的数值车道ID进行映射的图像存于压缩包‘Annotation on Regions.zip’中：南向车道可视化图示为I294_L2_lane-2.png至I294_L2_lane-5.png，北向车道为I294_L2_lane2.png至I294_L2_lane5.png。本数据集系‘第三代仿真数据（TGSIM）：自动驾驶系统对人类行为影响的深入研究’项目的一部分；该项目共采集了六组可表征人机交互行为的轨迹数据。

The main dataset is a 9 MB file of trajectory data (I294_L2_final.csv) that contains position, speed, and acceleration data for small and large automated (L2) and non-automated vehicles on a highway in a suburban environment. Supporting files include aerial reference images for twelve distinct data collection “Runs” (I294_L2_Run_X_ref_image_with_lanes.png, where X equals 5, 28, 30, 36, 38, and 42 for southbound runs and 23, 29, 31, 33, 35, and 41 for northbound runs). Associated centerline files are also provided for each “Run” (I-294-L2-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 – I294 L2.csv” for more details). The dataset defines eight lanes (four lanes in each direction) 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 southbound lanes are shown visually in I294_L2_lane-2.png through I294_L2_lane-5.png and the northbound lanes are shown visually in I294_L2_lane2.png through I294_L2_lane5.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 two SAE Level 2 ADAS-equipped vehicles through automated lane change maneuvers and as part of a string once the desired lane was achieved and ACC was enabled. The helicopter then followed the string of vehicles (which sometimes broke from the sting due to large following distances) northbound through the 4.8 km section of highway at an altitude of 300 meters. The goal of the data collection effort was to collect data related to human drivers' responses to automated lane changes and as part of a string. The road segment has four lanes in each direction and covers a major on-ramp and one off-ramp in the southbound direction and one on-ramp as well as two off-ramps in the northbound direction. The segment of highway is operated by Illinois Tollway and contains a high percentage of heavy vehicles. 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>I294_L2_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 L2 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>I294_L2_Run_X_ref_image_with_lanes.png are the aerial reference images that define the geographic region and associated roadway segments of interest (see bounding boxes on northbound and southbound lanes) for each run X.</li> <li>I294_L2_Run_X-geometry-with-ramps.csv contain the coordinates that define the lane centerlines for each Run X. T