Behavior Trees in Functional Safety Supervisors for Autonomous Vehicles

TL;DR

This paper presents a behavior tree-based software architecture for real-time supervision of autonomous vehicle safety, ensuring compliance with ISO 26262 and enhancing reliability in integrating AI algorithms.

Contribution

It introduces a novel behavior tree framework for supervising functional safety in autonomous vehicles, aligned with safety standards and applicable to industrial road vehicles.

Findings

Ensures compliance with ISO 26262 safety standards.

Implemented in a Renault Mégane at SAE level 3.

Enhances safety and reliability of autonomous driving systems.

Abstract

The rapid advancements in autonomous vehicle software present both opportunities and challenges, especially in enhancing road safety. The primary objective of autonomous vehicles is to reduce accident rates through improved safety measures. However, the integration of new algorithms into the autonomous vehicle, such as Artificial Intelligence methods, raises concerns about the compliance with established safety regulations. This paper introduces a novel software architecture based on behavior trees, aligned with established standards and designed to supervise vehicle functional safety in real time. It specifically addresses the integration of algorithms into industrial road vehicles, adhering to the ISO 26262. The proposed supervision methodology involves the detection of hazards and compliance with functional and technical safety requirements when a hazard arises. This methodology, implemented in this study in a Renault M\'egane (currently at SAE level 3 of automation), not only guarantees compliance with safety standards, but also paves the way for safer and more reliable autonomous driving technologies.