SMIRK: A machine learning-based pedestrian automatic emergency braking system with a complete safety case
Kasper Socha, Markus Borg, Jens Henriksson · Software Impacts · 2022
SMIRK is a pedestrian automatic emergency braking system that facilitates research on safety-critical systems embedding machine learning components. As a fully transparent driver-assistance system, SMIRK can support future research on trustworthy AI systems, e.g., verification & validation, requirements engineering, and testing. SMIRK is implemented for the simulator ESI Pro-SiVIC with core components including a radar sensor, a mono camera, a YOLOv5 model, and an anomaly detector. ISO/PAS 21448 SOTIF guided the development, and we present a complete safety case for a restricted ODD using the AMLAS methodology. Finally, all training data used to train the perception system is publicly available.