Architecting Safety Supervisors for High Levels of Automated Driving

TL;DR

This paper proposes a functional architecture for safety supervisors in high-level automated driving systems, aiming to enhance fault tolerance and safety assurance through a structured approach.

Contribution

It introduces a novel fault-tolerant ADI architecture with safety supervisors, detailing responsibilities, fault handling, and control transfer mechanisms.

Findings

Proposed a fault-tolerant ADI architecture with safety supervisors.

Analyzed sources of hazardous events and responsibility division.

Outlined directions for future research in safety supervision.

Abstract

The complexity of automated driving poses challenges for providing safety assurance. Focusing on the architecting of an Autonomous Driving Intelligence (ADI), i.e. the computational intelligence, sensors and communication needed for high levels of automated driving, we investigate so called safety supervisors that complement the nominal functionality. We present a problem formulation and a functional architecture of a fault-tolerant ADI that encompasses a nominal and a safety supervisor channel. We then discuss the sources of hazardous events, the division of responsibilities among the channels, and when the supervisor should take over. We conclude with identified directions for further work.