Mock, MichaelMichaelMockScholz, StefanStefanScholzBlank, FrederikFrederikBlankHüger, FabianFabianHügerRohatschek, AndreasAndreasRohatschekSchwarz, LorenLorenSchwarzStauner, ThomasThomasStauner2022-10-142022-10-142021-08-25https://publica.fraunhofer.de/handle/publica/41278310.1007/978-3-030-83906-2_21Developing a stringent safety argumentation for AI-based perception functions requires a complete methodology to systematically organize the complex interplay between specifications, data and training of AI-functions, safety measures and metrics, risk analysis, safety goals and safety requirements. The paper presents the overall approach of the German research project "KI-Absicherung" for developing a stringent safety-argumentation for AI-based perception functions. It is a risk-based approach in which an assurance case is constructed by an evidence-based safety argumentation.EnglischAutomated DrivingSafe AISafety argumentationDDC::000 Informatik, Informationswissenschaft, allgemeine Werke::000 Informatik, Wissen, Systeme::005 Computerprogrammierung, Programme, DatenDDC::000 Informatik, Informationswissenschaft, allgemeine Werke::000 Informatik, Wissen, Systeme::006 Spezielle ComputerverfahrenDDC::600 Technik, Medizin, angewandte Wissenschaften::620 Ingenieurwissenschaften::629 Andere Fachrichtungen der Ingenieurwissenschaftenconference paper