Scenario Description Language for Automated Driving Systems: A Two Level Abstraction Approach

The complexities associated with Automated Driving Systems (ADSs) and their interaction with the environment pose a challenge for their safety evaluation. Number of miles driven has been suggested as one of the metrics to demonstrate technological maturity. However, the experiences or the scenarios encountered by the ADSs is a more meaningful metric, and has led to a shift to scenario-based testing approach in the automotive industry and research community. Variety of scenario generation techniques have been advocated, including real-world data analysis, accident data analysis and via systems hazard analysis. While scenario generation can be done via these methods, there is a need for a scenario description language format which enables the exchange of scenarios between diverse stakeholders (as part of the systems engineering lifecycle) with varied usage requirements. In this paper, we propose a two-level abstraction approach to scenario description language (SDL) - SDL level 1 and SDL level 2. SDL level 1 is a textual description of the scenario at a higher abstraction level to be used by regulators or system engineers. SDL level 2 is a formal machine-readable language which is ingested by testing platform e.g. simulation or test track. One can transform a scenario in SDL level 1 into SDL level 2 by adding more details or from SDL level 2 to SDL level 1 by abstracting.