AI4ATM: A review on how Artificial Intelligence paves the way towards autonomous Air Traffic Management

Artificial Intelligence (AI) applications have tremendous impact on all aspects of our life, including the way we fly. In this study, we provide a comprehensive review of AI applications in Air Traffic Management (ATM). We highlight the transition from rule-based systems to sophisticated machine/deep learning models and other techniques rooted in natural language and image processing. Our methodology begins by analyzing the core components of ATM, namely air traffic control, air traffic flow management, and airspace management. We then extract and synthesize the AI-related efforts within each component. Our review reveals that AI plays a significant role in enhancing prediction and optimization, surveillance, and communication capabilities across ATM. Through this paper, we identify the state of the art, current challenges, and interesting future research directions, emphasizing the potential of AI to further improve air traffic management, in terms of operational efficiency, safety, and passenger experience.