With growing complexity and responsibility of automated driving functions in road traffic and growing scope of their operational design domains, there is increasing demand for covering significant parts of development, validation, and verification via virtual environments and simulation models. If, however, simulations are meant not only to augment real-world experiments, but to replace them, quantitative approaches are required that measure to what degree and under which preconditions simulation models adequately represent reality, and thus allow their usage for virtual testing of driving functions. Especially in research and development areas related to the safety impacts of the "open world", there is a significant shortage of real-world data to parametrize and/or validate simulations - especially with respect to the behavior of human traffic participants, whom automated vehicles will meet in mixed traffic. This paper presents the intermediate results of the German AVEAS research project (www.aveas.org) which aims at developing methods and metrics for the harmonized, systematic, and scalable acquisition of real-world data for virtual verification and validation of advanced driver assistance systems and automated driving, and establishing an online database following the FAIR principles.
@article{arxiv.2405.06286,
title = {A Joint Approach Towards Data-Driven Virtual Testing for Automated Driving: The AVEAS Project},
author = {Leon Eisemann and Mirjam Fehling-Kaschek and Silke Forkert and Andreas Forster and Henrik Gommel and Susanne Guenther and Stephan Hammer and David Hermann and Marvin Klemp and Benjamin Lickert and Florian Luettner and Robin Moss and Nicole Neis and Maria Pohle and Dominik Schreiber and Cathrina Sowa and Daniel Stadler and Janina Stompe and Michael Strobelt and David Unger and Jens Ziehn},
journal= {arXiv preprint arXiv:2405.06286},
year = {2024}
}