Institution profile

Alan Turing Institute

Academic institutioneurope · gb
Official website
Research library340linked papers
Opportunities0open roles
Selected work

Representative Papers

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

Jan 06, 2026AIAA SCITECH 2026 Forum

This study addresses the critical gap in current AI research for air traffic control—namely, the absence of a safe, high-fidelity, and quantifiable virtual environment for training and evaluation. The authors present the first probabilistic digital twin system tailored to UK en-route airspace, integrating historical and real-time operational data with physics-informed machine learning models to faithfully reproduce realistic traffic scenarios and enable human–AI collaborative assessment. Innovatively, the framework incorporates a structured validation methodology grounded in trustworthiness and ethical safeguards, delivering a unified, high-speed, standardized testing platform capable of simulating up to 200× real-time speed. Through a Python Gym interface, an interactive human-in-the-loop interface, and quantitative performance metrics, the system facilitates rapid iteration of AI agents and controller-led capability evaluation in a high-fidelity airspace, laying the groundwork for advanced automation in air traffic management.

6 citationsRead paper

Self-Play Only Evolves When Self-Synthetic Pipeline Ensures Learnable Information Gain

Feb 10, 2026

Existing self-evolution systems for large language models often plateau rapidly due to synthetic data lacking sufficient learnable information gain. This work proposes a triadic role-based self-evolution framework comprising a proposer, a solver, and a verifier, which sustains high information gain across iterative cycles through asymmetric weak–strong–weak co-evolution, dynamic model capacity expansion, and active incorporation of external knowledge. By centering the system design on learnable information gain, this study achieves, for the first time, sustainable self-evolution at the architectural level. Empirical validation on self-play programming tasks demonstrates the framework’s capability to consistently surpass performance plateaus and enable stable, continuous capability improvement.

4 citationsRead paper

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

Jan 07, 2026AIAA SCITECH 2026 Forum

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 introduces— for the first time—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.

4 citationsRead paper

Online Action-Stacking Improves Reinforcement Learning Performance for Air Traffic Control

Jan 07, 2026AIAA SCITECH 2026 Forum

This work addresses the challenge of applying reinforcement learning to air traffic control, where directly generating operationally compliant compound instructions is difficult and high-dimensional action spaces hinder training. To overcome this, the authors propose an online action stacking mechanism that dynamically composes a small set of five basic discrete actions—learned during training—into practical compound commands during inference, achieving performance comparable to a 37-dimensional policy. Built upon the Proximal Policy Optimization (PPO) algorithm and trained on the BluebirdDT digital twin platform, the approach incorporates an action damping penalty to regulate instruction frequency. Experimental results demonstrate that the method significantly reduces the number of issued commands in lateral navigation tasks while effectively resolving two-aircraft conflicts and managing altitude, thereby balancing training efficiency with operational realism.

3 citationsRead paper

A Future Capabilities Agent for Tactical Air Traffic Control

Jan 07, 2026AIAA SCITECH 2026 Forum

This work proposes Agent Mallard, a rule-based forward-planning agent designed to address the challenge of ensuring both safety and interpretability in air traffic management under uncertainty. Mallard innovatively integrates stochastic digital twins into a rule-driven conflict resolution loop, combining causal attribution, topological plan stitching, and monotonic axis constraints to enable safe, verifiable, hierarchical tactical decision-making. The system employs depth-limited backtracking search, a conflict-resolution strategy library informed by expert knowledge, and discretized route selection, while incorporating safety verification mechanisms tailored to uncertain scenarios such as wind shifts and communication outages. Preliminary experiments demonstrate that Mallard’s behavior aligns with expert reasoning, efficiently resolving flight conflicts in simplified airspace while maintaining strong guarantees of safety, interpretability, and computational tractability.

3 citationsRead paper
Recent publications

Latest Papers