FRED: A Multi-Modal Autonomous Driving Dataset for Flooded Road Environments

2026-05-21

AI Summary

This work addresses the scarcity of high-quality multimodal data for autonomous driving in flooded road scenarios by constructing and publicly releasing the first dataset specifically focused on water-logged environments. The dataset integrates synchronized measurements from a 2.3MP FLIR camera, an Ouster OS1-64 LiDAR, an iXblue ATLANS-C IMU, and a Geoflex RTK-GNSS system, captured across five distinct locations under varying dry and wet conditions. It includes fine-grained semantic annotations and is organized in both KITTI and RTMaps formats to facilitate research on flood-related perception, localization, SLAM, and multisensor fusion algorithms. By providing this benchmark resource, the study aims to support the development and evaluation of robust autonomous driving systems operating in adverse weather and road conditions.

Abstract

The Flooded Road Environments Dataset (FRED) is, to our knowledge, the first multi-modal autonomous driving dataset specifically targeting the collection of data from scenarios involving water hazards on the road. The dataset contains images from a 2.3 MP FLIR Blackfly USB3 camera, 64-beam 360$^\circ$ point clouds from an Ouster OS1-64 LiDAR, and data from an iXblue ATLANS-C IMU corrected by a Geoflex RTK GNSS, from five separate locations captured both during and after flooding events. The data has been released in two formats: a KITTI-style format for easy integration with existing data tools, and the RTMaps format for direct replay of the vehicle's data capture. We provide semantic labels to enable the training and evaluation of both single-sensor and sensor-fusion methods for water hazard detection. Position and velocity, as well as data captured under dry conditions, are provided to enable the development of location-based detection methods that may incorporate maps, and to evaluate other tasks such as localisation and SLAM.

Problem

• flooded road
• autonomous driving
• multi-modal dataset
• water hazard detection
• sensor fusion

Innovation

• multi-modal dataset
• flooded road environments
• autonomous driving
• sensor fusion
• water hazard detection