Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2601.22118 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911651152789504 |
|---|---|
| author | Christensen, Johann Maximilian Hoemann, Elena Köster, Frank Hallerbach, Sven |
| author_facet | Christensen, Johann Maximilian Hoemann, Elena Köster, Frank Hallerbach, Sven |
| contents | Artificial Intelligence (AI) has been on the rise in many domains, including numerous safety-critical applications. However, for complex systems in the real world, defining the underlying environmental conditions in which the AI-based system must operate -- the Operational Design Domain (ODD) -- is extremely challenging. This often results in an incomplete description of the ODD, which contrasts with the requirements of many domains for certifying AI-based systems. Traditionally, the ODD is created in the early stages of the development process, drawing on sophisticated expert knowledge and related standards. This paper presents a novel Safety-by-Design method to a posteriori define the ODD from previously collected data using a multi-dimensional kernel-based representation. This approach is validated through both Monte Carlo methods and a real-world aviation use case for a future collision-avoidance system. Moreover, by defining under what conditions two ODDs are similar, the paper shows that the data-driven ODD can produce a dataset similar to the original, hidden ODD. Deriving the novel, Safety-by-Design, deterministic kernel-based affinity representation of ODDs is fully automated via a bounded, order-independent algorithm. Utilizing the proposed ODD representation enables future certification of data-driven, safety-critical AI-based systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_22118 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Defining Operational Conditions for Safety-Critical AI-Based Systems from Data Christensen, Johann Maximilian Hoemann, Elena Köster, Frank Hallerbach, Sven Artificial Intelligence Artificial Intelligence (AI) has been on the rise in many domains, including numerous safety-critical applications. However, for complex systems in the real world, defining the underlying environmental conditions in which the AI-based system must operate -- the Operational Design Domain (ODD) -- is extremely challenging. This often results in an incomplete description of the ODD, which contrasts with the requirements of many domains for certifying AI-based systems. Traditionally, the ODD is created in the early stages of the development process, drawing on sophisticated expert knowledge and related standards. This paper presents a novel Safety-by-Design method to a posteriori define the ODD from previously collected data using a multi-dimensional kernel-based representation. This approach is validated through both Monte Carlo methods and a real-world aviation use case for a future collision-avoidance system. Moreover, by defining under what conditions two ODDs are similar, the paper shows that the data-driven ODD can produce a dataset similar to the original, hidden ODD. Deriving the novel, Safety-by-Design, deterministic kernel-based affinity representation of ODDs is fully automated via a bounded, order-independent algorithm. Utilizing the proposed ODD representation enables future certification of data-driven, safety-critical AI-based systems. |
| title | Defining Operational Conditions for Safety-Critical AI-Based Systems from Data |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2601.22118 |