Exploring Unknown Unsafe Scenarios for ADAS and AV Development

The introduction of the SOTIF (Safety Of The Intended Functionality) standard has brought along a fundamental shift in the safety case for vehicles with Advanced driver assistance systems (ADAS) or with high levels of autonomy in autonomous vehicles (AV’s) resulting in the vehicle manufacturer carrying an increased burden of responsibility and liability. The operational design domain (ODD) represents the driving conditions the autonomous vehicle will safely operate in. Siemens has developed a proprietary methodology to systematically generate unsafe-unknown scenarios for a specific operational design domain (ODD) and (optionally) recorded data. To measure criticality, Siemens has developed a severity indicator, which combines a key performance index (KPI) for criticality such as Time to Collision (TTC) with a proprietary KPI for novelty. The combination of these two generates a normalized severity value which provides an indication of how unsafe and unknown a scenario is for the vehicle under test. By adopting the Critical Scenario Creation process, OEM’s and AV suppliers have a methodology to automatically generate unknow-unsafe scenarios. Additionally, cities and traffic planners can use the tool to identify problem areas and consequently design and implement infrastructure that supports the safest operations, thus minimizing risks in the urban environment.