Automated lane keeping systems (ALKS) are important components in advancing vehicle autonomy and ensuring road safety. However, the development of these systems in the automotive industry must follow strict regulatory standards to ensure compliance, reliability and safety.

This thesis explores the implementation of Bayesian optimization algorithms to improve the efficiency of the simulation process in the design and testing phases of ALKS development. The implementation focuses on optimizing simulation parameters to reduce computational cost while maintaining the high reliability required for regulatory compliance. By integrating Bayesian optimization into the workflow, the study demonstrates possible improvements in simulation efficiency, enabling faster iterativ edevelopment cycles without compromising safety standards.

The results demonstrate the ability to combine robust algorithmic techniques with regulatory compliance, providing a path for automakers to more efficiently develop automated systems. This research contributes to the broader field of autonomous vehicle development by demonstrating a practical approach to meeting regulatory requirements while leveraging advanced optimization methods.