Human-in-the-Loop Testing of AI Agents for Air Traffic Control with a Regulated Assessment Framework

๐Ÿ“… 2026-01-07
๐Ÿ›๏ธ AIAA SCITECH 2026 Forum
๐Ÿ“ˆ Citations: 4
โœจ Influential: 0
๐Ÿ“„ PDF
๐Ÿค– AI Summary
This study addresses the lack of industry-compliant evaluation methodologies in existing AI research for air traffic control (ATC) tasks, which often fail to reflect real-world operational environments. To bridge this gap, the work introducesโ€” for the first timeโ€”the legally mandated ATC training assessment framework into AI agent testing. It proposes a human-in-the-loop evaluation paradigm grounded in regulatory-certified simulator curricula, wherein domain-expert instructors conduct contextually accurate assessments of AI agent performance. This approach aligns AI capabilities with established human professional standards, substantially narrowing the divide between academic research and actual ATC operations, and lays a foundational framework for future human-AI collaborative air traffic management systems.

Technology Category

Application Category

๐Ÿ“ Abstract
We present a rigorous, human-in-the-loop evaluation framework for assessing the performance of AI agents on the task of Air Traffic Control, grounded in a regulator-certified simulator-based curriculum used for training and testing real-world trainee controllers. By leveraging legally regulated assessments and involving expert human instructors in the evaluation process, our framework enables a more authentic and domain-accurate measurement of AI performance. This work addresses a critical gap in the existing literature: the frequent misalignment between academic representations of Air Traffic Control and the complexities of the actual operational environment. It also lays the foundations for effective future human-machine teaming paradigms by aligning machine performance with human assessment targets.
Problem

Research questions and friction points this paper is trying to address.

Air Traffic Control
Human-in-the-Loop
AI Evaluation
Regulated Assessment
Operational Realism
Innovation

Methods, ideas, or system contributions that make the work stand out.

human-in-the-loop
AI evaluation framework
air traffic control
regulator-certified simulation
human-machine teaming
๐Ÿ”Ž Similar Papers
No similar papers found.
B
Ben Carvell
NATS, Whiteley, Hampshire, PO15 7FL, United Kingdom
M
Marc Thomas
NATS, Whiteley, Hampshire, PO15 7FL, United Kingdom
A
Andrew Pace
NATS, Whiteley, Hampshire, PO15 7FL, United Kingdom
C
Christopher Dorney
NATS, Whiteley, Hampshire, PO15 7FL, United Kingdom
George De Ath
George De Ath
Lecturer in Computer Science, University of Exeter
Bayesian OptimizationMulti-Objective OptimizationArtificial IntelligenceMachine Learning
R
R. Everson
University of Exeter, Exeter, England EX4 4QJ, United Kingdom
Nick Pepper
Nick Pepper
The Alan Turing Institute
A
Adam Keane
The Alan Turing Institute, London, England NW1 2DB, United Kingdom
S
Samuel Tomlinson
NATS, Whiteley, Hampshire, PO15 7FL, United Kingdom
R
Richard Cannon
NATS, Whiteley, Hampshire, PO15 7FL, United Kingdom