ROADVIEW

SPRING

ROADVIEW

EU Horizon: ROADVIEW
(Robust Automated Driving in Extreme Weather)

The Project

The SPRING group is part of the ROADVIEW project, consisting of 15 member consortia spread across Europe, funded by the EU Horizon Europe Innovation Action. ROADVIEW aims to develop robust and cost-efficient in-vehicle perception and decision-making systems for connected and automated vehicles with enhanced performance under harsh weather conditions and different traffic scenarios. Harsh weather challenges are a severe technological barrier for automated vehicles. More information on the project can be found here.

Weather noise modelling validation

The SPRING group created novel physics-based weather noise models for camera, LiDAR and 4D RADAR. The camera noise models have been specifically created to be applied on Bayer image data; LiDAR noise models based on energy and agnostic to input data; and weather noise models applied to a novel 4D RADAR. The weather noise models were validated against real data from the REHEARSE dataset using a range of image quality assessment (IQA) and pointcloud (PC) metrics.

Simulation and X-i-L Testing

The SPRING group integrated the developed sensor weather noise models, running in real-time, into the automotive CARLA simulator. These models enable repeatable and controlled X-i-L testing under different weather conditions. Additionally, the scenarios were designed formatted into OpenScenario structure to enable automated testing in H-i-L.