Boreas: A multi-season autonomous driving dataset

Keenan Burnett(University of Toronto), David J. Yoon(University of Toronto), Yuchen Wu(University of Toronto), Andrew Z. Li(University of Toronto), Haowei Zhang(University of Toronto), Shichen Lu(University of Toronto), Jingxing Qian(University of Toronto), Wei-Kang Tseng(University of Toronto), Andrew Lambert, Keith YK Leung, Angela P. Schoellig(University of Toronto), Timothy D. Barfoot(University of Toronto)
The International Journal of Robotics Research
January 1, 2023
Cited by 134Open Access
Full Text

Abstract

The Boreas dataset was collected by driving a repeated route over the course of 1 year, resulting in stark seasonal variations and adverse weather conditions such as rain and falling snow. In total, the Boreas dataset includes over 350 km of driving data featuring a 128-channel Velodyne Alpha-Prime lidar, a 360° Navtech CIR304-H scanning radar, a 5MP FLIR Blackfly S camera, and centimetre-accurate post-processed ground truth poses. Our dataset will support live leaderboards for odometry, metric localization, and 3D object detection. The dataset and development kit are available at boreas.utias.utoronto.ca.


Related Papers

No related papers found

Powered by citation graph analysis