Please use this identifier to cite or link to this item:
https://doi.org/10.48441/4427.3866
| Publisher DOI: | 10.1007/s13272-026-01018-1 | Title: | Constrained scenario adaptation in flight simulator training using conceptualized state spaces | Language: | English | Authors: | Lilla, Helge Niggemann, Oliver Netzel, Thomas |
Keywords: | Conceptualized state spaces; Constrained machine learning; Explainable AI; Cyber-physical systems; Flight simulator training | Issue Date: | 2026 | Publisher: | Springer | Journal or Series Name: | CEAS aeronautical journal : an official journal of the Council of European Aerospace Societies | Volume: | :tba | Issue: | :tba | Startpage: | :tba | Endpage: | :tba | Abstract: | The EASA AI Roadmap 2.0 establishes trustworthiness as the backbone of AI readiness in aviation, requiring that machine learning is not only accurate, but also deterministic, traceable to formally defined concepts, bounded by explicit safety constraints, and reconstructable post-hoc. Existing approaches treat machine learning as an unconstrained predictor over a latent feature space and apply constraints only as post-hoc filters. The central methodological problem remains open: a formal mapping from heterogeneous subsymbolic training evidence to admissible scenario adaptations that preserves these properties by construction. This paper formulates and realizes such a mapping, decomposable into formally defined substeps that satisfy four structural properties: determinism, semantic grounding, constraint compliance, and reconstructability. A realization for cyber-physical scenario-based flight training is presented. Its core is a deterministic conceptualized state space based on Deep-Linking Keywords that links theory-based assessment and simulator-based performance. A deterministic finite automaton governs instructional progression. Scenario adaptation is approximated by a constrained machine learning policy within an admissible action space enforced by monotonicity constraints, phase gating, and a projection operator that clips outputs to the admissible action space. The architecture is analytically verified by construction against the four properties and demonstrated empirically on N=160 policy cases using k=5 group-wise cross-validation. The constrained machine learning component approximates the deterministic baseline policy with a profile Mean Absolute Error (MAE) of 0.126 \pm 0.024 and a +0.344 improvement in scenario-focus classification accuracy over the majority-class baseline. Statistical generalization beyond this proof-of-concept scope is identified as the next step. |
URI: | https://hdl.handle.net/20.500.12738/20340 | DOI: | 10.48441/4427.3866 | ISSN: | 1869-5590 | Review status: | This version was peer reviewed (peer review) | Institute: | Fakultät Luftfahrt- und Fahrzeugsysteme Forschungs- und Transferzentrum Future Mobility and Acoustics |
Type: | Article |
| Appears in Collections: | Publications with full text |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| s13272-026-01018-1.pdf | 2.74 MB | Adobe PDF | View/Open |
Note about this record
Export
This item is licensed under a Creative Commons License