A System's Perspective Towards an Architecture Framework for Safe Automated Vehicles

TL;DR

This paper proposes an extended architecture framework for automated vehicles that integrates multiple viewpoints to better analyze and ensure system safety, enabling traceability of safety requirements across development stages.

Contribution

It introduces a capability-based assessment approach within architecture frameworks to improve safety analysis and requirement attribution for automated vehicle systems.

Findings

Extended architecture viewpoints for safety analysis

Derived behavioral safety requirements for automated vehicles

Demonstrated traceability of safety requirements across system views

Abstract

With an increasing degree of automation, automated vehicle systems become more complex in terms of functional components as well as interconnected hardware and software components. Thus, holistic systems engineering becomes a severe challenge. Emergent properties like system safety are not solely arguable in singular viewpoints such as structural representations of software or electrical wiring (e.g. fault tolerant). This states the need to get several viewpoints on a system and describe correspondences between these views in order to enable traceability of emergent system properties. Today, the most abstract view found in architecture frameworks is a logical description of system functions which structures the system in terms of information flow and functional components. In this article we extend established system viewpoints towards a capability-based assessment of an automated vehicle and conduct an exemplary safety analysis to derive behavioral safety requirements. These requirements can afterwards be attributed to different viewpoints in an architecture frameworks and thus be integrated into a development process for automated vehicles.