A Probabilistic Digital Twin of UK En Route Airspace for Training and Evaluating AI Agents for Air Traffic Control

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pepper, Nick, Keane, Adam, Hodgkin, Amy, Gould, Dewi, Henderson, Edward, Lauritsen, Lynge, Vlahos, Christos, De Ath, George, Everson, Richard, Cannon, Richard, Castro, Alvaro Sierra, Korna, John, Carvell, Ben, Thomas, Marc
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917193879388160
author Pepper, Nick
Keane, Adam
Hodgkin, Amy
Gould, Dewi
Henderson, Edward
Lauritsen, Lynge
Vlahos, Christos
De Ath, George
Everson, Richard
Cannon, Richard
Castro, Alvaro Sierra
Korna, John
Carvell, Ben
Thomas, Marc
author_facet Pepper, Nick
Keane, Adam
Hodgkin, Amy
Gould, Dewi
Henderson, Edward
Lauritsen, Lynge
Vlahos, Christos
De Ath, George
Everson, Richard
Cannon, Richard
Castro, Alvaro Sierra
Korna, John
Carvell, Ben
Thomas, Marc
contents This paper presents the first probabilistic Digital Twin of operational en route airspace, developed for the London Area Control Centre. The Digital Twin is intended to support the development and rigorous human-in-the-loop evaluation of AI agents for Air Traffic Control (ATC), providing a virtual representation of real-world airspace that enables safe exploration of higher levels of ATC automation. This paper makes three significant contributions: firstly, we demonstrate how historical and live operational data may be combined with a probabilistic, physics-informed machine learning model of aircraft performance to reproduce real-world traffic scenarios, while accurately reflecting the level of uncertainty inherent in ATC. Secondly, we develop a structured assurance case, following the Trustworthy and Ethical Assurance framework, to provide quantitative evidence for the Digital Twin's accuracy and fidelity. This is crucial to building trust in this novel technology within this safety-critical domain. Thirdly, we describe how the Digital Twin forms a unified environment for agent testing and evaluation. This includes fast-time execution (up to x200 real-time), a standardised Python-based ``gym'' interface that supports a range of AI agent designs, and a suite of quantitative metrics for assessing performance. Crucially, the framework facilitates competency-based assessment of AI agents by qualified Air Traffic Control Officers through a Human Machine Interface. We also outline further applications and future extensions of the Digital Twin architecture.
format Preprint
id arxiv_https___arxiv_org_abs_2601_03113
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Probabilistic Digital Twin of UK En Route Airspace for Training and Evaluating AI Agents for Air Traffic Control
Pepper, Nick
Keane, Adam
Hodgkin, Amy
Gould, Dewi
Henderson, Edward
Lauritsen, Lynge
Vlahos, Christos
De Ath, George
Everson, Richard
Cannon, Richard
Castro, Alvaro Sierra
Korna, John
Carvell, Ben
Thomas, Marc
Computational Engineering, Finance, and Science
This paper presents the first probabilistic Digital Twin of operational en route airspace, developed for the London Area Control Centre. The Digital Twin is intended to support the development and rigorous human-in-the-loop evaluation of AI agents for Air Traffic Control (ATC), providing a virtual representation of real-world airspace that enables safe exploration of higher levels of ATC automation. This paper makes three significant contributions: firstly, we demonstrate how historical and live operational data may be combined with a probabilistic, physics-informed machine learning model of aircraft performance to reproduce real-world traffic scenarios, while accurately reflecting the level of uncertainty inherent in ATC. Secondly, we develop a structured assurance case, following the Trustworthy and Ethical Assurance framework, to provide quantitative evidence for the Digital Twin's accuracy and fidelity. This is crucial to building trust in this novel technology within this safety-critical domain. Thirdly, we describe how the Digital Twin forms a unified environment for agent testing and evaluation. This includes fast-time execution (up to x200 real-time), a standardised Python-based ``gym'' interface that supports a range of AI agent designs, and a suite of quantitative metrics for assessing performance. Crucially, the framework facilitates competency-based assessment of AI agents by qualified Air Traffic Control Officers through a Human Machine Interface. We also outline further applications and future extensions of the Digital Twin architecture.
title A Probabilistic Digital Twin of UK En Route Airspace for Training and Evaluating AI Agents for Air Traffic Control
topic Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2601.03113