Key points are not available for this paper at this time.
Urban Air Mobility (UAM) has emerged as a promising solution to address some of the challenges of transportation congestion and associated pollution, especially in large cities. However, the development of drone transportation and UAM services is limited by the capacity of the low altitude airspace where these new vehicles will operate. Without suitable regulatory advancements and associated traffic management systems, air traffic in the densest low-altitude sectors may incur congestion, which, in addition to affecting operational efficiency, can increase systemic risk and fuel emergency occurrences, thereby affecting the safety of people and property in the air and on the ground. To address these challenges, this study aims to develop an intelligent Uncrewed Aircraft Traffic Management (UTM) system that leverages the complementary strengths of metaheuristic and machine learning algorithms for an effective management of dense low altitude airspace. The UTM system determines time-based three-dimensional airspace Demand-Capacity Balancing (DCB) solutions by processing real-time data updates and dynamically replanning flight paths and DCB decisions in any given context, while also providing UAM operators with relevant inputs for autonomous decision-making. Simulation-based verification activities in representative conditions show that the proposed UTM system has the ability to effectively resolve overload instances and minimize potential conflicts in low-altitude airspace, with an operationally acceptable running time. We conclude that the proposed hybrid algorithm can support a successful implementation of UAM services in and around cities, and it has high potential to address critical airspace resource constraints also in traditional Air Traffic Flow Management (ATFM).
Xie et al. (Fri,) studied this question.