The new SAFER associated project SEVVOS will contribute to better test methodologies for future vehicle safety systems

May, 13 2022

A major challenge in the development of future traffic systems and vehicle safety technologies is to be able to carry out tests in a real environment, which gives reliable results in all possible weather conditions and that also is repeatable. This problem is now being addressed by researchers by developing a method for simulating water spray, emulating water spray in rigs, and verifying that the results obtained correlate with real data. The SEVVOS project, Simulation and Emulation of Water Spray for Validation of Optical Sensors, is expected to provide good opportunities for better and more reliable tests, but also contribute to contact with a larger network of international researchers for a continued exchange of knowledge and opportunities for common research. The project is associated with AI-SEE in Euripides2 Penta.

In the project, Veoneer contributes with a vehicle that is equipped with a very advanced suite of sensors that will collect data from public roads in various weather conditions. Collected data and datasets, both from available open sources and from the AI-SEE project, then form the basis for simulation of water spray, using machine learning. The researchers aim to develop a deeper understanding for the creation of aerosols in different traffic conditions considering vehicle parameters, weather, driving environment and traffic situations.

The project is financed by Vinnova and the SAFER partners engaged in the project are AstaZero, Veoneer, Chalmers University and RISE. The project started in January and will continue until end 2024. The budget is 5,9 MSEK.
The project will be hosted by SAFER’s research area for Systems for accident prevention and automated driving.

About AI-SEE
SEVVOS is an associated partner in the European project AI-SEE, that aims to build a novel, robust sensing system supported by AI that will enable automated travel in varied traffic, lighting and weather conditions. It will extend the Operational Design Domain (ODD) of automated vehicles, i.e. the scope of what they can do, taking the technology from SAE level 3 to level 4 where vehicles drive themselves with no human interaction in most circumstances. AI-SEE is focusing primarily on improved sensing capabilities and lower-cost sensors and by increasing the environmental and situational awareness of vehicles.

The goal is to introduce reliable, secure, trustable sensors and software by implementing self-diagnosis, adaptation and robustness. The AI-SEE concept is built on four main blocks:

1.    A 24/365 high resolution adaptive all-weather sensor suite
2.    An AI platform for predictive detection of prevailing environmental conditions including signal enhancement and sensor adaptation
3.    Smart sensor data fusion to create the 24/365 adaptive all-weather robust perception system
4.    A demonstrator and system validation plan, with testing carried out in simulations and in real-world environments in northern Europe

The project will deliver the first high-resolution adaptive multi-sensor suite building on an innovative novel AI perception-processing scheme for low visibility conditions.

Read more about AI-SEE here: AI-SEE - Penta (