AVEAS – Survey, analyze and simulate traffic situations relevant to safeguarding

Understanding real traffic - safeguarding automated mobility

The safe introduction of highly and fully automated vehicles depends crucially on how well we can digitally map traffic events - especially critical situations. AVEAS develops scalable, data protection-compliant methods for systematically recording and modeling critical scenarios and transferring them to virtual test environments.

Three sources of risk at a glance

• Human driving behavior: large-scale real data collection using a fleet of measurement vehicles, infrastructure sensors and aerial photography.
• Human-machine interaction: Driving simulator studies analyze the transfer of driving responsibility.
• Technical system limits: Sensor measurement campaigns in challenging environments investigate perception errors of automated vehicles.

This combined approach makes it possible to test automated driving functions for real system limits as early as the simulation stage.

Contribution of the Fraunhofer IOSB

• Scientific management of the project.
• Surveying traffic situations from the air: video data is collected over highways using light and ultralight aircraft. High-precision 3D terrain models are calculated from this data, roads are annotated, vehicles are recognized using AI processes and time-resolved trajectories are calculated.
• Modeling of system boundaries in the OCTAS® simulation platform: Challenging driving scenarios are mapped in detailed simulation models - especially for camera and laser scanner data. Several open data datasets, including Synset Boulevard and Synset Signset Germany, have already been published.
• Coordination of the DIN SAE SPEC 91518 standard as a comprehensive data format for storing traffic scenarios, based on ASAM OpenDRIVE and ASAM OpenLABEL.