arXiv:2605.22018v2 Announce Type: replace-cross 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 degree 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-
The increasing frequency and severity of extreme weather events, particularly flooding, necessitate more robust autonomous driving capabilities in adverse conditions, driving research and data collection in this area.
This dataset addresses a critical gap in autonomous driving data, allowing for the training and validation of perception systems that can safely navigate environments impacted by water hazards, which is crucial for wider adoption.
Autonomous driving systems can now be specifically trained and tested on real-world flooded road scenarios, moving beyond ideal conditions and enabling more resilient and safer operation in diverse environments.
- · Autonomous vehicle developers
- · Insurance companies
- · Logistics and transportation industries
- · Autonomous driving systems untrained for adverse weather
Improved safety and reliability of autonomous vehicles in flood-prone areas due to enhanced perception capabilities.
Accelerated deployment of autonomous vehicles in regions experiencing frequent heavy rainfall or coastal flooding.
Reduced accident rates and economic losses associated with road incidents during adverse weather, impacting urban planning and infrastructure design.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI