AirTrafficGen: Configurable Air Traffic Scenario Generation with Large Language Models

2025-08-04

AI Summary

Manually designing air traffic control (ATC) training scenarios is time-consuming and labor-intensive, severely limiting scenario diversity and coverage. To address this, we propose an LLM-based automated ATC scenario generation framework: first, a graph-structured airspace representation is constructed to explicitly encode topological relationships and regulatory constraints; second, a configurable prompt engineering pipeline coupled with natural language feedback-driven iterative refinement enables fine-grained controllability over key parameters—including interaction types, spatial locations, and traffic density. Evaluated using Gemini 2.5 Pro and OpenAI o3, the method generates highly realistic ATC training cases for high-density, high-complexity operational environments. Our approach substantially reduces manual design effort and, for the first time, systematically demonstrates the feasibility and controllability of LLMs in safety-critical, complex spatiotemporal planning tasks.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: Generation
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

The manual design of scenarios for Air Traffic Control (ATC) training is a demanding and time-consuming bottleneck that limits the diversity of simulations available to controllers. To address this, we introduce a novel, end-to-end approach, AirTrafficGen, that leverages large language models (LLMs) to automate and control the generation of complex ATC scenarios. Our method uses a purpose-built, graph-based representation to encode sector topology (including airspace geometry, routes, and fixes) into a format LLMs can process. Through rigorous benchmarking, we show that state-of-the-art models like Gemini 2.5 Pro and OpenAI o3 can generate high-traffic scenarios whilst maintaining operational realism. Our engineered prompting enables fine-grained control over interaction presence, type, and location. Initial findings suggest these models are also capable of iterative refinement, correcting flawed scenarios based on simple textual feedback. This approach provides a scalable alternative to manual scenario design, addressing the need for a greater volume and variety of ATC training and validation simulations. More broadly, this work showcases the potential of LLMs for complex planning in safety-critical domains.

Problem

• Automate ATC scenario generation to reduce manual effort
• Enhance scenario diversity for ATC training simulations
• Ensure operational realism in LLM-generated air traffic scenarios

Innovation

• Leverages LLMs for ATC scenario automation
• Uses graph-based sector topology encoding
• Enables iterative refinement via textual feedback