Explainable Reinforcement Learning for assisting Air Traffic Controllers
2026-07-24 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors focus on making AI systems easier to understand and trust, especially in critical fields like air traffic control. They trained an AI using reinforcement learning to pick safe flight paths that avoid restricted areas in a simplified scenario. To help explain how the AI makes its decisions, they used a saliency map that highlights the most important information the AI pays attention to. This helps people see why the AI chooses certain routes, which is important for safety and trust.
Reinforcement LearningExplainabilitySaliency MapAir Traffic ControlNo-fly ZonesAI TrustDeep LearningHuman-AI Collaboration
Authors
Anduel Mehmeti, Gabriella Gigante, Salvatore Venticinque
Abstract
To effectively integrate AI into high-stakes, critical environments such as healthcare, autonomous driving, and aviation--and to advance toward higher levels of automation and seamless human-AI collaboration--building trust in AI-driven solutions is essential. Trust, in turn, is closely linked to the explainability of AI systems. The rapid advancements in AI across various domains have underscored the challenges of establishing trust, raising increasing interest in AI explainability even more when applied to deep learning. In this context, the present work aims to explore the application of explainability techniques to Reinforcement Learning (RL) algorithms, specifically within the safety-critical domain of Air Traffic Control (ATC). Using a simplified ATC environment as an initial testbed, an intelligent agent is trained with a reinforcement learning algorithm to make decisions on alternative flight routes that avoid no-fly zones. As a preliminary explainability approach, a saliency map is employed, providing insights into the input features that most significantly influence the agent's decision-making process.