Physical AI is becoming more and more prominent in highly automated driving systems (ADS). Many new ADS architectures are pursuing the end-to-end approach, from sensors to vehicle movement. For such physical AI-centric (or AI-heavy) ADS, the validation challenges multiply beyond the traditional ones. The presentation will cover validation and training approaches used to meet the challenge of ensuring the safety of physical AI ADS implementations.

• What is physical AI, and the unique characteristics of AI-centric AVs
• The challenges of validating physical AI-centric AVs and ensuring their safety
• Proposed solutions to those challenges