Robust Vision-Based Runway Detection through Conformal Prediction and Conformal mAP
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 11 of its 27 references that are in the map. First posted on arXiv 22 May 2025.
Builds on
11 of 27 references.
References · 11
- 2020End-to-End Object Detection with Transformerscited by 7,414
- 2013Intriguing properties of neural networkscited by 5,155
- 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 275
- 2020FCOS: A simple and strong anchor-free object detectorcited by 171
- 2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 151
- 2017Dropout Sampling for Robust Object Detection in Open-Set Conditionscited by 112
- 2019BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectorscited by 68
- 2024Adaptive Bounding Box Uncertainties via Two-Step Conformal Predictioncited by 23
- 2023Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signalingcited by 22
- 2021Monte Carlo DropBlock for Modelling Uncertainty in Object Detectioncited by 20
- 2023LARD -- Landing Approach Runway Detection -- Dataset for Vision Based Landingcited by 14
Built on by
Citing papers per year: 2025: 1; 2026: 4.
5 papers.
- 2026LARD 2.0: Enhanced Datasets and Benchmarking for Autonomous Landing Systemscited by 4
- 2025Conformal Object Detection by Sequential Risk Controlcited by 3
- 2026Conformal Prediction Sets for Instance Segmentationcited by 1
- 2026Unifying Runtime Monitoring Approaches for Safety-Critical Machine Learning: Application to Vision-Based Landingcited by 0
- 2026Robust Validation to Geometric Perturbations for Autonomous Pose Estimationcited by 0
- 2026Robust Validation to Geometric Perturbations for Autonomous Pose Estimation21 Aug 2026
- 2026Unifying Runtime Monitoring Approaches for Safety-Critical Machine Learning: Application to Vision-Based Landing29 Apr 2026
- 2026LARD 2.0: Enhanced Datasets and Benchmarking for Autonomous Landing Systems23 Mar 2026
- 2026Conformal Prediction Sets for Instance Segmentation10 Feb 2026
- 2025Conformal Object Detection by Sequential Risk Control29 May 2025