The main dataset is a 350 MB file of trajectory data (TGSIM-Foggy Bottom-Data.csv) that contains position, speed, and acceleration data for pedestrians, bicycles, scooters, non-automated passenger cars, automated vehicles, motorcycles, buses, and trucks in an urban environment. Supporting files include an aerial reference image (Reference_Image_Foggy Bottom.png) and a list of polygon boundaries (Foggy_Bottom_boundaries.txt) and associated images (i1.png, i2.png, …, i49.png stored in the folder titled “Annotation on Regions.zip”) to map physical roadway segments to numerical IDs (as referenced in the trajectory dataset).
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 from twelve 4K stationary infrastructure cameras installed in the Foggy Bottom neighborhood of Washington, D.C. The cameras captured four intersections, adjacent crosswalks, road segments between the intersections, and partial road segments extending out from the intersections totaling more than one full block of coverage. These segments are represented by polygons to bound travel lanes, parking lanes, crosswalks, and intersections for detection and analysis purposes (see Reference_Image_Foggy Bottom.png for details). The cameras captured continuous footage during a weekday commute between 3:00PM-5:00PM ET on a sunny day. During this period, one test vehicle equipped with SAE Level 3 automation was deployed to perform various complex maneuvers at both stop signs and traffic signals, including both protected and permitted left turns, to capture human driving behaviors when interacting with automated vehicles. The automated vehicles are indicated in the dataset.
As part of this dataset, the following files were provided:
TGSIM-Foggy Bottom-Data.csv contains the numerical data to be used for analysis that includes vehicle/bicycle/pedestrian trajectory data at every 0.1 second. Road user type, width, and length 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 = 0.0186613838586-meter conversion.
Reference_Image_Foggy Bottom.png is the aerial reference image that defines the geographic region and the associated roadway segments.
Foggy_Bottom_boundaries.txt contains the coordinates that define the roadway segments (n = 49). Each polygon is a list of four to six coordinate pairs measured in pixels (which can be converted to meters using the provided 1 pixel = 0.0186613838586-meter conversion), with (0,0) global reference coordinates at the top-left of the reference image.
Annotation on Regions.zip, which includes i1.png, i2.png,..., i49.png, are images that visually map the road segment IDs (indicated by the number following the i in the file name) to the reference image.