ISUAM: Intelligent and Safe UAM with Deep Reinforcement Learning

Urban air mobility (UAM) is on the verge of a fast-growing expansion as the major aircraft manufacturers are in the late-stage development of various Electric Vertical Take-Off and Landing (eVTOL) aircraft models. In recent decades, conflict detection and resolution (CD&R) in air traffic management has been widely studied. However, factors such as the wide availability of unmanned aerial vehicles (UAV), the expected use of eVTOL, and the latest development of groundbreaking deep reinforcement learning (DRL) have generated new interest in this research field. Some characteristics of this new aircraft type, such as weight, speed, and maneuverability, require a revisit of the CD&R for adaptation to the new paradigm. We propose an Intelligent and Safe UAM with Deep Reinforcement Learning (ISUAM) system that can perform tactical deviation maneuvers in the UAM environment using some latest DRL models. After extensive testing, including various DRL agents, Dueling Deep Q Networks (Dueling DQN) has provided the best performance and proved its ability to provide satisfactory conflict resolution.