Autonomous Vehicle Rural Road Dataset (06-004)

Project Description: A large number of rural roads in the U.S. do not have lane markings and have irregular boundaries. This trait is common to many small and rural communities (SRCs). The goal of this project is to develop and test efficient algorithms to enable the deployment of Autonomous Vehicles (AV's) in SRC's by leveraging crowd sourced topological maps such as the Open Street Maps that provides high level road network information in concert with onboard sensing systems that include LIDAR and cameras to localize and navigate an autonomous vehicle. Data Scope: The dataset contains: LIDAR Intensity Images: 2818 LIDAR Intensity Images LIDAR Multi-channel Images: 2818 Images with 3 channels- Signal, Range and Reflectivity Road Segmentation Masks: 2818 Segmentation masks of road surfaces for Intensity and Multi-channel images. Annotated LIDAR Point-Clouds: 2577 Point-Clouds with road point labelling. Bag Files: Bag files with 10 minutes of driving data including data from IMU, GPS, and wheel speed sensors. Data Specification: Please refer attached file "Rural_Road_Dataset_Specifications.pdf"