From High-Dimensional Spaces to Verifiable ODD Coverage for Safety-Critical AI-based Systems

TL;DR

This paper introduces a structured method to verify comprehensive coverage of AI systems' operational domains in high-dimensional spaces, ensuring safety standards are met in safety-critical applications.

Contribution

It presents a novel multi-step verification approach combining discretization, filtering, and dimension reduction to systematically validate ODD coverage.

Findings

Demonstrates systematic ODD coverage verification using simulation data.

Enables validation of high-dimensional ODD coverage for safety-critical AI systems.

Supports compliance with EASA certification standards.

Abstract

While Artificial Intelligence (AI) offers transformative potential for operational performance, its deployment in safety-critical domains such as aviation requires strict adherence to rigorous certification standards. Current EASA guidelines mandate demonstrating complete coverage of the AI/ML constituent's Operational Design Domain (ODD) -- a requirement that demands proof that no critical gaps exist within defined operational boundaries. However, as systems operate within high-dimensional parameter spaces, existing methods struggle to provide the scalability and formal grounding necessary to satisfy the completeness criterion. Currently, no standardized engineering method exists to bridge the gap between abstract ODD definitions and verifiable evidence. This paper addresses this void by proposing a method that integrates parameter discretization, constraint-based filtering, and criticality-based dimension reduction into a structured, multi-step ODD coverage verification process. Grounded in gathered simulation data from prior research on AI-based mid-air collision avoidance research, this work demonstrates a systematic engineering approach to defining and achieving coverage metrics that satisfy EASA's demand for completeness. Ultimately, this method enables the validation of ODD coverage in higher dimensions, advancing a Safety-by-Design approach while complying with EASA's standards.