Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Boreas Road Trip: A Multi-Sensor Autonomous Driving Dataset on Challenging Roads

Daniil Lisus, Katya M. Papais, Cedric Le Gentil, Elliot Preston-Krebs, Andrew Lambert, Keith Y. K. Leung, Timothy D. Barfoot

TL;DR

Boreas-RT introduces a large, multi-sensor autonomous driving dataset designed to evaluate odometry, mapping, and localization across diverse road types. It extends the Boreas platform with nine routes, 60 sequences totaling 643 km, and a full sensor stack including camera, radar, Velodyne lidar, FMCW Aeva lidar, multiple IMUs, and a wheel encoder, all with centimeter-level RTX ground truth. Ground truth poses are generated independently via RTX post-processing, allowing objective, cross-sensor benchmarking, while a public leaderboard and development kit enable reproducible, fair comparisons. Benchmark results reveal overfitting tendencies in state-of-the-art methods to simple environments and highlight significant challenges on rural and highway routes, underscoring the need for robust, cross-condition evaluation and multi-modal fusion.

Abstract

The Boreas Road Trip (Boreas-RT) dataset extends the multi-season Boreas dataset to new and diverse locations that pose challenges for modern autonomous driving algorithms. Boreas-RT comprises 60 sequences collected over 9 real-world routes, totalling 643 km of driving. Each route is traversed multiple times, enabling evaluation in identical environments under varying traffic and, in some cases, weather conditions. The data collection platform includes a 5MP FLIR Blackfly S camera, a 360 degree Navtech RAS6 Doppler-enabled spinning radar, a 128-channel 360 degree Velodyne Alpha Prime lidar, an Aeva Aeries II FMCW Doppler-enabled lidar, a Silicon Sensing DMU41 inertial measurement unit, and a Dynapar wheel encoder. Centimetre-level ground truth is provided via post-processed Applanix POS LV GNSS-INS data. The dataset includes precise extrinsic and intrinsic calibrations, a publicly available development kit, and a live leaderboard for odometry and metric localization. Benchmark results show that many state-of-the-art odometry and localization algorithms overfit to simple driving environments and degrade significantly on the more challenging Boreas-RT routes. Boreas-RT provides a unified dataset for evaluating multi-modal algorithms across diverse road conditions. The dataset, leaderboard, and development kit are available at www.boreas.utias.utoronto.ca.

Boreas Road Trip: A Multi-Sensor Autonomous Driving Dataset on Challenging Roads

TL;DR

Boreas-RT introduces a large, multi-sensor autonomous driving dataset designed to evaluate odometry, mapping, and localization across diverse road types. It extends the Boreas platform with nine routes, 60 sequences totaling 643 km, and a full sensor stack including camera, radar, Velodyne lidar, FMCW Aeva lidar, multiple IMUs, and a wheel encoder, all with centimeter-level RTX ground truth. Ground truth poses are generated independently via RTX post-processing, allowing objective, cross-sensor benchmarking, while a public leaderboard and development kit enable reproducible, fair comparisons. Benchmark results reveal overfitting tendencies in state-of-the-art methods to simple environments and highlight significant challenges on rural and highway routes, underscoring the need for robust, cross-condition evaluation and multi-modal fusion.

Abstract

The Boreas Road Trip (Boreas-RT) dataset extends the multi-season Boreas dataset to new and diverse locations that pose challenges for modern autonomous driving algorithms. Boreas-RT comprises 60 sequences collected over 9 real-world routes, totalling 643 km of driving. Each route is traversed multiple times, enabling evaluation in identical environments under varying traffic and, in some cases, weather conditions. The data collection platform includes a 5MP FLIR Blackfly S camera, a 360 degree Navtech RAS6 Doppler-enabled spinning radar, a 128-channel 360 degree Velodyne Alpha Prime lidar, an Aeva Aeries II FMCW Doppler-enabled lidar, a Silicon Sensing DMU41 inertial measurement unit, and a Dynapar wheel encoder. Centimetre-level ground truth is provided via post-processed Applanix POS LV GNSS-INS data. The dataset includes precise extrinsic and intrinsic calibrations, a publicly available development kit, and a live leaderboard for odometry and metric localization. Benchmark results show that many state-of-the-art odometry and localization algorithms overfit to simple driving environments and degrade significantly on the more challenging Boreas-RT routes. Boreas-RT provides a unified dataset for evaluating multi-modal algorithms across diverse road conditions. The dataset, leaderboard, and development kit are available at www.boreas.utias.utoronto.ca.
Paper Structure (41 sections, 2 equations, 15 figures, 8 tables)

This paper contains 41 sections, 2 equations, 15 figures, 8 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. Sensors
  4. Sequences
  5. Structured routes
  6. Rural routes
  7. Highway routes
  8. Data format
  9. Data organization
  10. File formats
  11. Camera:
  12. Lidar:
  13. Aeva:
  14. Radar:
  15. IMU:
  16. ...and 26 more sections

Figures (15)

  • Figure 1: Our data collection platform, Boreas, is equipped with a 5MP FLIR Blackfly S camera, a 360° Navtech RAS6 Doppler-enabled spinning radar, a 360° Velodyne Alpha Prime lidar, an Aeva Aeries II FMCW Doppler-enabled lidar, a Silicon Sensing DMU41 IMU, and a Dynapar wheel encoder.
  • Figure 2: Boreas-RT sensor placements. All distances are given in metres, with exact values provided in the calibration folder. 'Lidar' refers to the $360\;°$ Velodyne Alpha-Prime lidar, whereas 'Aeva' refers to the Aeva Aeries II FMCW lidar.
  • Figure 3: Two overlaid lidar maps of the tunnel route, aligned using ground-truth poses, constructed from sequences driven in opposite directions (red and blue).
  • Figure 4: The 'structured' data routes. Top to bottom: suburbs, industrial, urban. Left to right: camera image, radar scan, lidar scan (aligned to radar scan and with ground plane removed), OpenStreetMap route overview. Note the high level of structure and clear geometric features. The 'urban' sequences feature extensive cars, pedestrians, cyclists, trams, and other dynamic urban objects.
  • Figure 5: The 'rural' data routes. Top to bottom: forest, farm. Left to right: camera image, radar scan, lidar scan (aligned to radar scan and with ground plane removed), OpenStreetMap route overview. Note the lack of any structure. The farm sequence has a car in front of the data collection platform that is raising a dust cloud and consequently obscuring it in both the camera and lidar data.
  • ...and 10 more figures