In this paper, we propose an extension to Neural Architecture Search (NAS) incorporating accurate inference energy prediction. An exemplary dedicated AI accelerator is emulated in a digital twin and power is measured for a dataset of different Neural Networks. These measurements can then be used for energy-aware NAS. In the presentation, the methodology and virtual platform will be presented, before the accuracy of the extended NAS is evaluated.

AI-based perception alone cannot ensure the safety of automated vehicles. The presentation discusses the safety aspects of typical perception and planning stacks. It proposes a complementary safety channel to address currently used algorithms’ weaknesses. This safety channel explicitly handles unsafe and unknown objects and ensures that the automated vehicle never collides with any of them.

Key takeaways:
• AI-based perception alone cannot ensure the safety of automated vehicles.
• Unknown objects need to be detected for safe automated driving.
• A safety channel with Dynamic Grid technology ensures collision-free driving.