2025/01/01 by Anduel Mehmeti, Gabriella Gigante, Salvatore Venticinque · 2 citations
Engineering · Psychology · #Air Traffic Management and Optimization #Artificial intelligence #Autonomous Vehicle Technology and Safety #Computer science #Environmental science #Human-Automation Interaction and Safety #Psychology #Reinforcement #Reinforcement learning #Social psychology
paper · pdf · doi:10.1007/978-3-031-87778-0_14
published in Lecture notes on data engineering and communications technologies, 148-157 (Springer International Publishing)
openalex publication_date 2025/01/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
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.