Ajou University repository

Multi-Agent Reinforcement Learning for Cooperative Air Transportation Services in City-Wide Autonomous Urban Air Mobilityoa mark
  • Park, Chanyoung ;
  • Kim, Gyu Seon ;
  • Park, Soohyun ;
  • Jung, Soyi ;
  • Kim, Joongheon
Citations

SCOPUS

0

Citation Export

Publication Year
2023-08-01
Journal
IEEE Transactions on Intelligent Vehicles
Publisher
Institute of Electrical and Electronics Engineers Inc.
Citation
IEEE Transactions on Intelligent Vehicles, Vol.8 No.8, pp.4016-4030
Keyword
air transportation servicecentralized training and distributed execution (CTDE)multi-agent deep reinforcement learning (MADRL)Urban-air-mobility (UAM)
Mesh Keyword
Air transportation serviceAtmospheric modelingCentralisedCentralized training and distributed executionDeep learningMulti agentMulti-agent deep reinforcement learningReinforcement learningsTransportation servicesUrban airUrban areasUrban-air-mobility
All Science Classification Codes (ASJC)
Automotive EngineeringControl and OptimizationArtificial Intelligence
Abstract
The development of urban-air-mobility (UAM) is rapidly progressing with spurs, and the demand for efficient transportation management systems is a rising need due to the multifaceted environmental uncertainties. Thus, this article proposes a novel air transportation service management algorithm based on multi-agent deep reinforcement learning (MADRL) to address the challenges of multi-UAM cooperation. Specifically, the proposed algorithm in this article is based on communication network (CommNet) method utilizing centralized training and distributed execution (CTDE) in multiple UAMs for providing efficient air transportation services to passengers collaboratively. Furthermore, this article adopts actual vertiport maps and UAM specifications for constructing realistic air transportation networks. By evaluating the performance of the proposed algorithm in data-intensive simulations, the results show that the proposed algorithm outperforms existing approaches in terms of air transportation service quality. Furthermore, there are no inferior UAMs by utilizing parameter sharing in CommNet and a centralized critic network in CTDE. Therefore, it can be confirmed that the research results in this article can provide a promising solution for autonomous air transportation management systems in city-wide urban areas.
ISSN
2379-8858
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/33461
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85161597966&origin=inward
DOI
https://doi.org/2-s2.0-85161597966
Journal URL
http://ieeexplore.ieee.org/xpl/tocresult.jsp?isnumber=7433488&punumber=7274857
Type
Conference
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Jung, Soyi Image
Jung, Soyi정소이
Department of Electrical and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.