Research papers · Posted 2022.04.16 · Publication / acceptance: author-reported
Ergo, SMIRK is Safe: A Safety Case for a Machine Learning Component in a Pedestrian Automatic Emergency Brake System
Ergo, SMIRK is Safe: A Safety Case for a Machine Learning Component in a Pedestrian Automatic Emergency Brake System
Overview
SMIRK is an ML-based pedestrian emergency-braking demonstrator in an industrial simulator. The study applies AMLAS within a minimal operational domain, releasing its component safety case and implementation while reporting assurance lessons learned.
Publication and version information
Publication, acceptance or venue information is author-reported on arXiv. The exact source wording is preserved below.
Author-supplied source information
Author-supplied information on arXiv.
Accepted for publication in Software Quality Journal
Version: arXiv v3 — manuscript revision