EUVIMEDEUVIMED entdecken
Systematische Übersicht

Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review

Anton Kuznietsov, Balint Gyevnar, Cheng Wang, Steven Peters, Stefano V. Albrecht

IEEE Transactions on Intelligent Transportation Systems · 2024-12 · 25 (12) · 19342-19364

DOI: 10.1109/tits.2024.3474469 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2024-12. Verfasst von Anton Kuznietsov und 4 weiteren Autor:innen. Die Arbeit wurde bisher 167-mal zitiert (Crossref) und nennt 194 Literaturangaben. Gefördert von: Project by the Federal Ministry of Education and Research of Germany, Project “AUTOtech.agil”, United Kingdom Research and Innovation (UKRI) Centre for Doctoral Training in Natural Language Processing.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial Intelligence (AI) shows promising applications for the perception and planning tasks in autonomous driving (AD) due to its superior performance compared to conventional methods. However, highly complex AI systems exacerbate the existing challenge of safety assurance of AD. One way to mitigate this challenge is to utilize explainable AI (XAI) techniques. To this end, we present the first comprehensive systematic literature review of explainable methods for safe and trustworthy AD. We begin by analyzing the requirements for AI in the context of AD, focusing on three key aspects: data, model, and agency. We find that XAI is fundamental to meeting these requirements. Based on this, we explain the sources of explanations in AI and describe a taxonomy of XAI. We then identify five key contributions of XAI for safe and trustworthy AI in AD, which are interpretable design, interpretable surrogate models, interpretable monitoring, auxiliary explanations, and interpretable validation. Finally, we propose a conceptual modular framework called SafeX to integrate the reviewed methods, enabling explanation delivery to users while simultaneously ensuring the safety of AI models.

Förderung

  • Project by the Federal Ministry of Education and Research of Germany
  • Project “AUTOtech.agil”
  • United Kingdom Research and Innovation (UKRI) Centre for Doctoral Training in Natural Language Processing

Zitieren

APA

Kuznietsov, A., Gyevnar, B., Wang, C., Peters, S., & Albrecht, S. V. (2024). Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review. IEEE Transactions on Intelligent Transportation Systems, 25(12), 19342-19364. https://doi.org/10.1109/tits.2024.3474469

Vancouver

Kuznietsov A, Gyevnar B, Wang C, Peters S, Albrecht SV. Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review. IEEE Transactions on Intelligent Transportation Systems. 2024;25(12):19342-19364. doi:10.1109/tits.2024.3474469

BibTeX
@article{Kuznietsov2024,
  author = {Kuznietsov, Anton and Gyevnar, Balint and Wang, Cheng and Peters, Steven and Albrecht, Stefano V.},
  title = {Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2024},
  volume = {25},
  number = {12},
  pages = {19342--19364},
  doi = {10.1109/tits.2024.3474469}
}
Kostenlos starten →