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/

Global: Zendy Plus annual

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

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Air traffic control is an example of a highly challenging operational problemthat is readily amenable to human expertise augmentation via decision supporttechnologies. In this paper, we propose a new intelligent decision makingframework that leverages multi-agent reinforcement learning (MARL) todynamically suggest adjustments of aircraft speeds in real-time. The goal ofthe system is to enhance the ability of an air traffic controller to provideeffective guidance to aircraft to avoid air traffic congestion, near-misssituations, and to improve arrival timeliness. We develop a novel deep ensembleMARL method that can concisely capture the complexity of the air trafficcontrol problem by learning to efficiently arbitrate between the decisions of alocal kernel-based RL model and a wider-reaching deep MARL model. The proposedmethod is trained and evaluated on an open-source air traffic managementsimulator developed by Eurocontrol. Extensive empirical results on a real-worlddataset including thousands of aircraft demonstrate the feasibility of usingmulti-agent RL for the problem of en-route air traffic control and show thatour proposed deep ensemble MARL method significantly outperforms threestate-of-the-art benchmark approaches.

A Deep Ensemble Multi-Agent Reinforcement Learning Approach for Air Traffic Control