A Prototypical Expert-Driven Approach Towards Capability-Based Monitoring of Automated Driving Systems

TL;DR

This paper introduces a framework for real-time capability monitoring of automated vehicles, combining expert-driven Bayesian Networks and fuzzy logic to assess system quality during operation.

Contribution

It presents a novel online capability monitor for automated driving systems, integrating a graphical system model with Bayesian Networks and fuzzy logic for runtime assessment.

Findings

Enables real-time capability assessment of automated vehicles.

Uses Bayesian Networks parameterized by expert knowledge.

Provides a structured approach to monitor system quality during operation.

Abstract

Supervising the safe operation of automated vehicles is a key requirement in order to unleash their full potential in future transportation systems. In particular, previous publications have argued that SAE Level 4 vehicles should be aware of their capabilities at runtime to make appropriate behavioral decisions. In this paper, we present a framework that enables the implementation of an online capability monitor. We derive a graphical system model that captures the relationships between the quality of system elements across different architectural views. In an expert-driven approach, we parameterize Bayesian Networks based on this structure using Fuzzy Logic. Using the online monitor, we infer the quality of the system's capabilities based on technical measurements acquired at runtime.