Boreas: A multi-season autonomous driving dataset. (February 2023)

• Record Type: Journal Article
• Authors: Burnett, Keenan; Yoon, David J; Wu, Yuchen; Li, Andrew Z; Zhang, Haowei; Lu, Shichen; Qian, Jingxing; Tseng, Wei-Kang; Lambert, Andrew; Leung, Keith YK; Schoellig, Angela P; Barfoot, Timothy D
• Is Part Of: International journal of robotics research. Volume 42:Number 1/2(2023)
• Page Start: 33
• Page End: 42
• Publication Date: 2023-02
• Subjects: Autonomous vehicle -- camera -- dataset -- GPS -- IMU -- lidar -- radar -- snow -- winter; Robots -- Periodicals; Robots, Industrial -- Periodicals; 629.89205
• DOI: 10.1177/02783649231160195
• Languages: English
• ISSNs: 0278-3649

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.