Glass-box Automated Driving: Insights and Future Trends

Mauro Bellone, Raivo Sell, Ralf-Martin Soe

2025

Abstract

Automated driving has advanced significantly through the use of black-box AI models, particularly in perception tasks. However, as these models have grown, concerns over the loss of explainability and interpretability have emerged, prompting a demand for creating ’glass-box’ models. Glass-box models in automated driving aim to design AI systems that are transparent, interpretable, and explainable. While such models are essential for understanding how machines operate, achieving perfect transparency in complex systems like autonomous driving may not be entirely practicable nor feasible. This paper explores arguments on both sides, suggesting a shift of the focus towards balancing interpretability and performance rather than considering them as conflicting concepts.

Paper Citation

in Harvard Style

Bellone M., Sell R. and Soe R. (2025). Glass-box Automated Driving: Insights and Future Trends. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: IAI; ISBN 978-989-758-737-5, SciTePress, pages 880-885. DOI: 10.5220/0013384300003890

in Bibtex Style

@conference{iai25,
author={Mauro Bellone and Raivo Sell and Ralf-Martin Soe},
title={Glass-box Automated Driving: Insights and Future Trends},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: IAI},
year={2025},
pages={880-885},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013384300003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: IAI
TI - Glass-box Automated Driving: Insights and Future Trends
SN - 978-989-758-737-5
AU - Bellone M.
AU - Sell R.
AU - Soe R.
PY - 2025
SP - 880
EP - 885
DO - 10.5220/0013384300003890
PB - SciTePress