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

2026-02-18

AI Summary

This work addresses the limited generalization of current autonomous driving algorithms in complex road scenarios, primarily due to the absence of multi-sensor benchmark datasets encompassing diverse and challenging conditions. To this end, we introduce the Boreas-RT dataset, which spans 643 kilometers across nine real-world, complex routes, each traversed multiple times to enable evaluation under varying traffic and weather conditions. Boreas-RT is the first to integrate FMCW LiDAR, Doppler radar, 5MP cameras, 360° Navtech radar, Velodyne Alpha Prime LiDAR, IMU, and wheel encoders, accompanied by centimeter-accurate GNSS-INS ground truth, full calibration parameters, and a public evaluation platform. Benchmarking reveals that state-of-the-art odometry and localization methods perform well in simple settings but degrade significantly on Boreas-RT, underscoring the dataset’s critical role in assessing algorithmic robustness and generalization.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Large-scale security measurements

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.

Problem

• autonomous driving
• challenging roads
• multi-sensor dataset
• odometry
• localization

Innovation

• multi-sensor fusion
• challenging road conditions
• Doppler-enabled LiDAR
• autonomous driving benchmark
• metric localization