Open-Source Tool Based Framework for Automated Performance Evaluation of an AD Function

TL;DR

This paper presents an open-source framework for automated performance evaluation of automated driving functions using virtual scenario-based testing, emphasizing the impact of road network parameters on system safety and reliability.

Contribution

It introduces an automated workflow for generating road networks, varying parameters, and evaluating ADF performance, enhancing testing efficiency and comprehensiveness.

Findings

Road network topology significantly affects ADF performance.

Automated scenario generation improves testing coverage.

Framework facilitates systematic safety assessment of ADFs.

Abstract

As automation in the field of automated driving (AD) progresses, ensuring the safety and functionality of AD functions (ADFs) becomes crucial. Virtual scenario-based testing has emerged as a prevalent method for evaluating these systems, allowing for a wider range of testing environments and reproducibility of results. This approach involves AD-equipped test vehicles operating within predefined scenarios to achieve specific driving objectives. To comprehensively assess the impact of road network properties on the performance of an ADF, varying parameters such as intersection angle, curvature and lane width is essential. However, covering all potential scenarios is impractical, necessitating the identification of feasible parameter ranges and automated generation of corresponding road networks for simulation. Automating the workflow of road network generation, parameter variation, simulation, and evaluation leads to a comprehensive understanding of an ADF's behavior in diverse road network conditions. This paper aims to investigate the influence of road network parameters on the performance of a prototypical ADF through virtual scenario-based testing, ultimately advocating the importance of road topology in assuring safety and reliability of ADFs.