Learning to Explain Air Traffic Situation

2025-02-15

AI Summary

This study addresses the lack of understanding regarding air traffic controllers’ mechanisms for constructing dynamic situational awareness—i.e., the “mental picture”—in complex airspace. We propose an interpretable multi-agent trajectory modeling framework grounded in cognitive principles. Innovatively, we adapt the Transformer attention mechanism for air traffic control (ATC) cognitive modeling, enabling the first global, non-pairwise, spatiotemporally coupled representation of high-dimensional collaborative interactions among aircraft, pilots, and controllers. By interpreting attention weights, we quantify the causal influence of individual aircraft on overall traffic evolution. The model is trained and validated on real-world trajectory data from Incheon Airport’s terminal maneuvering area. It successfully identifies critical influence aircraft and canonical traffic evolution pathways, thereby significantly enhancing the interpretability of ATC decision-support systems and improving transparency of controller situational awareness.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Multiagent Systems: Modeling other Agents

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Understanding how air traffic controllers construct a mental 'picture' of complex air traffic situations is crucial but remains a challenge due to the inherently intricate, high-dimensional interactions between aircraft, pilots, and controllers. Previous work on modeling the strategies of air traffic controllers and their mental image of traffic situations often centers on specific air traffic control tasks or pairwise interactions between aircraft, neglecting to capture the comprehensive dynamics of an air traffic situation. To address this issue, we propose a machine learning-based framework for explaining air traffic situations. Specifically, we employ a Transformer-based multi-agent trajectory model that encapsulates both the spatio-temporal movement of aircraft and social interaction between them. By deriving attention scores from the model, we can quantify the influence of individual aircraft on overall traffic dynamics. This provides explainable insights into how air traffic controllers perceive and understand the traffic situation. Trained on real-world air traffic surveillance data collected from the terminal airspace around Incheon International Airport in South Korea, our framework effectively explicates air traffic situations. This could potentially support and enhance the decision-making and situational awareness of air traffic controllers.

Problem

• Modeling air traffic controllers' mental picture
• Capturing comprehensive air traffic dynamics
• Explaining aircraft influence on traffic

Innovation

• Transformer-based multi-agent model
• Spatio-temporal and social interaction analysis
• Explainable insights from attention scores