Ensuring the safety of AI in safety-critical systems is essential for the deployment of automated driving technology. While AI has demonstrated its potential to surpass classical approaches in handling complexity and enabling higher levels of autonomy, the necessary safety assurance frameworks remain underdeveloped. This presentation will provide a forward-looking perspective on the interdependencies between AI safety research, standardization, and regulation. In contrast to conventional discussions that focus primarily on research, this talk will highlight the interplay between these three domains, identifying emerging trends, gaps, and key challenges that must be addressed. By presenting a holistic view, the session aims to equip researchers, safety experts, and industry professionals with insights into the current status and future directions of AI safety assurance in automated driving.

In this session, you will learn more about:

• Explore the rising demand for AI safety assurance across research, standardization, and regulation
• Understand the core aspects of AI safety assurance—data dependency, lifecycle management, and safety abstraction
• Gain a forward-looking perspective to overcome current challenges in AI safety assurance