Logo image
Unifying Runtime Monitoring Approaches for Safety-Critical Machine Learning: Application to Vision-Based Landing
Acte de colloque   Open Access

Unifying Runtime Monitoring Approaches for Safety-Critical Machine Learning: Application to Vision-Based Landing

Mathieu Dario, Florent Chenevier, Kevin Delmas, Joris Guerin et Jérémie Guiochet
28th International Conference on Pattern Recognition (ICPR 2026) (Lyon, France, 17/08/2026–22/08/2026)
08/2026

Résumé

Vision-based Landing Safety-critical Machine Learning Runtime Monitoring
Runtime monitoring is essential to ensure the safety of ML applications in safetycritical domains. However, current research is fragmented, with independent methods emerging from different communities. In this paper, we propose a unified framework categorising runtime monitoring approaches into three distinct types: Operational Design Domain (ODD) monitoring, which ensures compliance with expected operating conditions; Out-of-Distribution (OOD) monitoring, which rejects inputs that deviate from the training data; and Out-of-Model-Scope (OMS) monitoring, which detects anomalous model behaviour based its internal states or outputs. We demonstrate the benefits of this categorization with a dedicated experiment on an aeronautical safety-critical application: runway detection during landing. This framework facilitates design of monitoring activities, with complementary categories of monitors, and enables evaluation and comparison of different monitors using common, safety-oriented metrics.

Fichiers et liens (1)

url
Find in HALAfficher

Indicateurs

1 Consultations de la notice

Détails

Logo image