Conference Paper · 2026
Coverage-Driven Verification for Safety-by-Design in AI-Based Collision Avoidance Systems
35th Congress of the International Council of the Aeronautical Sciences (ICAS)
The Short Version
A process for assessing ODD representativeness compares target and observed data distributions using Kullback–Leibler divergence and chi-squared testing in collision-avoidance simulations.
Abstract
Artificial Intelligence (AI) offers significant potential for future aviation systems; however, its integration into safety-critical applications requires compliance with the aviation sector's stringent safety standards. For AI/ML-based systems, the European Union Aviation Safety Agency (EASA) emphasizes the need to demonstrate the representativeness of the Operational Design Domain (ODD) and the associated data distributions used during development and verification. Despite this requirement, a structured engineering process for defining target distributions and evaluating representativeness within high-dimensional ODDs remains largely unexplored. This work presents a method for representativeness assessment of AI/ML constituent ODDs in the context of aviation safety assurance. Starting from the methodical identification of suitable target distributions, a process flow is proposed that guides developers from ODD definition and parameter distribution modeling to the quantitative assessment and interpretation of coverage results with respect to EASA's learning assurance objectives. As quantitative measures, the Kullback-Leibler divergence and the Chi-squared test are investigated and compared regarding their applicability for ODD representativeness assessment. The method is demonstrated using the example of AI-based airborne collision avoidance, employing experimental data from previous HorizontalCAS (HCAS) and VerticalCAS (VCAS) simulations. The results illustrate how statistical distribution comparison methods can support the assessment of representativeness for safety-critical AI applications and contribute toward a systematic Safety-by-Design AI engineering process aligned with emerging EASA guidance.
Reference
Cite This Work
Thomas Stefani, Johann Maximilian Christensen, Elena Hoemann, Frank Köster, Sven Hallerbach. "Coverage-Driven Verification for Safety-by-Design in AI-Based Collision Avoidance Systems". 35th Congress of the International Council of the Aeronautical Sciences (ICAS), 2026.