Simulation Driven Development Process Utilizing Carla Simulator for Autonomous Vehicles

We present a new approach to design the system of autonomous vehicles based on practical test scenarios in simulation. As the level of driving automation functions advances, various events and problems have occurred in many unexpected or unseen situations, so the design of autonomous driving systems is required to be more robust and sufficiently practical. We propose a Simulation Driven Development Process (SDDP) based on practical test scenarios in a simulation environment. We described the Euro NCAP test scenarios and harsh conditions using the ASAM OpenSCENARIO format and implemented them using the Carla simulator. We can verify how realistic and functional the system requirements are through the simulation results. It is also possible to derive numerical values optimized for Advanced Driver Assistance System (ADAS) function safety from the simulation results, and we can get the requirements robust and improve ADAS performance by applying them to V-model. We created the Euro NCAP AEB-VRU test scenario to design an effective AEB function. We used RoadRunner to build the test road and used ScenarioRunner to render the test scenario written by ASAM OpenSCENARIO format according to Euro NCAP test requirement. The result of AEBVRU has been investigated under normal conditions and harsh environments as well. This work shows that we can extend the safety of the AEB function by changing the vehicle speed according to situation perception, which indicates the possibility of utilization of a simulator for autonomous vehicle system design.