We explore the use of conformal prediction to provide statistical uncertainty guarantees for runway detection in vision-based landing systems (VLS). Using fine-tuned YOLOv5 and YOLOv6 models on aerial imagery, we apply conformal prediction to quantify localization reliability under user-defined risk levels. We also introduce Conformal mean Average Precision (C-mAP), a novel metric aligning object detection performance with conformal guarantees. Our results show that conformal prediction can improve the reliability of runway detection by quantifying uncertainty in a statistically sound way, increasing safety on-board and paving the way for certification of ML system in the aerospace domain.
@article{arxiv.2505.16740,
title = {Robust Vision-Based Runway Detection through Conformal Prediction and Conformal mAP},
author = {Alya Zouzou and Léo andéol and Mélanie Ducoffe and Ryma Boumazouza},
journal= {arXiv preprint arXiv:2505.16740},
year = {2025}
}