The automated driving industry has recognized the importance of simulation tools for the development of self-driving vehicles.  Yet  many are still at odds with the proper use of simulation, weighing its benefits and limitations. Such players do not want to run the risk of either being too optimistic about simulation technologies and compromising on safety; or being too conservative and lagging behind their competitors.
This paper shows how automated testing with simulation tools can accelerate the development of automated driving solutions, while also making them safer.

Key topics in this paper:

• What are the demands of simulation for autonomous driving?
• What are the uses and limitations of simulated training data for neural networks?
• How can simulated scenarios be defined based on real-world situations, alongside functional safety engineering?
• Insights from two case studies into two areas where aiSim has already proven to solve problems and accelerate AImotive’s internal development efforts of the aiDrive self-driving stack