FordMultiAV 福特多季节性自动驾驶数据集

We present a challenging multi-agent seasonal dataset collected by a fleet of Ford autonomous vehicles at different days and times during 2017-18. The vehicles were manually driven on a route in Michigan that included a mix of driving scenarios including the Detroit Airport, freeways, city-centers, university campus and suburban neighborhood. We present the seasonal variation in weather, lighting, construction and traffic conditions experienced in dynamic urban environments. This dataset can help design robust algorithms for autonomous vehicles and multi-agent systems. Each log in the dataset is time-stamped and contains raw data from all the sensors, calibration values, pose trajectory, ground truth pose, and 3D maps. All data is available in Rosbag format that can be visualized, modified and applied using the open source Robot Operating System (ROS). The Ford vehicles traversed an average route of 66km through the Greater Detroit Area. Each drive includes the DTW airport, University of Michigan Dearborn campus and residential communities as shown in the image. Each run has minor variations in the route to capture the diverse features in urban environments, providing useful data to the research community. The data is organized on the basis of dates. Each of these directories contain subfolders for each Vehicle and Maps. Each Vehicle sub-directory contains all the logs in rosbag format, PNG Images and calibration files for each sensor. Calibration data for each Vehicle is provided separately. The directory structure is: The Images are orgainzed as: