Ontology based Scene Creation for the Development of Automated Vehicles
The introduction of automated vehicles without permanent human supervision demands a functional system description including functional system boundaries and a comprehensive safety analysis. These inputs to the technical development can be identified and analyzed by a scenario-based approach. Experts are doing well to identify scenarios that are difficult to handle or unlikely to happen. To establish an economical test and release process, a large number of scenarios must be identified to enable an execution of test-cases in simulation environments. Expert knowledge modeled for computer aided processing may help for the purpose of providing a wide range of scenarios. This contribution reviews the use of ontologies as knowledge-based systems in the field of automated vehicles, and proposes a modeling concept for traffic scenes. Afterwards, a process to create scenes from the gathered knowledge is introduced and the utilization of ontologies in the given problem statement is evaluated using criteria from literature.
READ FULL TEXT