Research papers · 2025.10
Safety Implications of Explainable Artificial Intelligence in End-to-End Autonomous Driving
Safety Implications of Explainable Artificial Intelligence in End-to-End Autonomous Driving
Overview
The paper examines how explanations may affect end-to-end driving safety. Conceptual discussion, critical cases and empirical observations identify potential benefits, limitations and caveats of practical explainable-AI methods for autonomous vehicles.
Author-supplied source information
Author-supplied information on arXiv.
Accepted for publication in IEEE Transactions on Intelligent Transportation Systems
Version: arXiv v5 — manuscript revision