A consistent safety case argumentation for artificial intelligence in safety related automotive systems - Proceeding of the 9th European Congress on Embedded Real Time Software and Systems Access content directly
Conference Papers Year : 2018

A consistent safety case argumentation for artificial intelligence in safety related automotive systems

Alexander Rudolph
  • Function : Author
  • PersonId : 1048865
Stefan Voget
  • Function : Author
  • PersonId : 1048866
Jürgen Mottok
  • Function : Author
  • PersonId : 1048867

Abstract

Regarding the actual automotive safety norms the use of artificial intelligence (AI) in safety critical environments like autonomous driving is not possible. This paper introduces a new conceptual safety modelling approach and a safety argumentation to certify AI algorithms in a safety related context. Therefore, a model of an AI-system is presented first. Afterwards, methods and safety argumentation are applied to the model, whereas it is limited to a specific subset of AI-systems, i.e. off-board learning deterministic neural networks in this case. Other cases are left over for future research. The result is a consistent safety analysis approach that applies state of the art safety argumentations from other domains to the automotive domain. This will enforce the adaptation of the functional safety norm ISO26262 to enable general AI methods in safety critical systems in future.
Fichier principal
Vignette du fichier
ERTS_2018_paper_13.pdf (694.61 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02156048 , version 1 (18-06-2019)

Identifiers

  • HAL Id : hal-02156048 , version 1

Cite

Alexander Rudolph, Stefan Voget, Jürgen Mottok. A consistent safety case argumentation for artificial intelligence in safety related automotive systems. ERTS 2018, Jan 2018, Toulouse, France. ⟨hal-02156048⟩

Collections

ERTS2018
561 View
635 Download

Share

Gmail Facebook X LinkedIn More