Master Thesis An autonomous vehicle is a complex cyber-physical system that requires state-of-the-art ML/AI software components and sophisticated hardware equipment to work together. For the application of testing autonomous driving systems under different driving conditions, AVL is developing various machine learning components that are integrated into complex virtualized testing environment or used together with well-accepted ADAS/AD sensors, NVIDIA Pegasus AGX, NVIDIA Xavier AGX in the in-vehicle PC hardware. Development of new generation machine learning methods focused on the detection of object, lane and driving scenarios Integration of the developed methods into AVL platforms Testing and analysing full self-driving stacks under different hardware and software configurations with the integrated methods