Data-centric Operational Design Domain Characterization for Machine Learning-based Aeronautical Products
This addresses the need for rigorous ODD characterization in aeronautics to guide ML model design and assurance, though it is incremental as it adapts concepts from other sectors like self-driving vehicles.
The paper tackles the problem of characterizing Operational Design Domains (ODDs) for ML-based aeronautical products by proposing a data-centric approach that defines dimensions and data categories to capture ODD parameters, illustrating it with an aircraft flight envelope example.
We give a first rigorous characterization of Operational Design Domains (ODDs) for Machine Learning (ML)-based aeronautical products. Unlike in other application sectors (such as self-driving road vehicles) where ODD development is scenario-based, our approach is data-centric: we propose the dimensions along which the parameters that define an ODD can be explicitly captured, together with a categorization of the data that ML-based applications can encounter in operation, whilst identifying their system-level relevance and impact. Specifically, we discuss how those data categories are useful to determine: the requirements necessary to drive the design of ML Models (MLMs); the potential effects on MLMs and higher levels of the system hierarchy; the learning assurance processes that may be needed, and system architectural considerations. We illustrate the underlying concepts with an example of an aircraft flight envelope.