Research

This research focuses on modeling complex air traffic flows and accurately estimating airspace demand and capacity using large-scale aviation data. By leveraging state-of-the-art machine & deep learning architectures, such as Transformers, we precisely predict 4D trajectories to maximize the efficiency of Trajectory-based Operations (TBO). Furthermore, we develop Agentic AI models for airline operations, aiming to build a more intelligent and autonomous next-generation air traffic management system. 

To ensure the safe operation of Urban Air Mobility (UAM) and Unmanned Aircraft Systems (UAS), we research technologies to effectively analyze and manage complex low-altitude airspace. This study involves developing dynamic Geofencing boundaries based on 3D terrain and obstacle data, as well as Path Planning algorithms that generate optimal flight routes through real-time Airspace Analysis. This work contributes to securing low-altitude airspace safety and enhancing the operational efficiency of UAM/UAS. 

We develop models to proactively identify and resolve potential collision risks during aircraft operations. This research precisely models complex Air & Ground Collision scenarios, considering various variables including abnormal maneuvers or "blunders." By implementing algorithms for real-time Conflict Detection & Resolution that suggest optimal avoidance maneuvers, we aim to secure safe buffer zones and ensure the highest level of operational safety.