English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Majority of aircraft under the Urban Air Mobility (UAM) concept are expectedto be of the electric vertical takeoff and landing (eVTOL) vehicle type, whichwill operate out of vertiports. While this is akin to the relationship betweengeneral aviation aircraft and airports, the conceived location of vertiportswithin dense urban environments presents unique challenges in managing the airtraffic served by a vertiport. This challenge becomes pronounced withinincreasing frequency of scheduled landings and take-offs. This paper assumes acentralized air traffic controller (ATC) to explore the performance of a new AIdriven ATC approach to manage the eVTOLs served by the vertiport. Minimumseparation-driven safety and delays are the two important considerations inthis case. The ATC problem is modeled as a task allocation problem, anduncertainties due to communication disruptions (e.g., poor link quality) andinclement weather (e.g., high gust effects) are added as a small probability ofaction failures. To learn the vertiport ATC policy, a novel graph-basedreinforcement learning (RL) solution called "Urban Air Mobility- VertiportSchedule Management (UAM-VSM)" is developed. This approach uses graphconvolutional networks (GCNs) to abstract the vertiport space and eVTOL spaceas graphs, and aggregate information for a centralized ATC agent to helpgeneralize the environment. Unreal Engine combined with Airsim is used as thesimulation environment over which training and testing occurs. Uncertaintiesare considered only during testing, due to the high cost of Mc sampling oversuch realistic simulations. The proposed graph RL method demonstratessignificantly better performance on the test scenarios when compared against afeasible random decision-making baseline and a first come first serve (FCFS)baseline, including the ability to generalize to unseen scenarios and withuncertainties.

Graph Learning Based Decision Support for Multi-Aircraft Take-Off and Landing at Urban Air Mobility Vertiports