Multi-UAV Reinforcement Learning With Realistic Communication Models: Recent Advances and Challenges

The interest in applications related to Multi-Unmanned Aerial Vehicle (UAV) systems has been growing exponentially inthe last few years. Reinforcement Learning (RL) presents one of the most popular alternatives for solving Multi-UAV tasks, thanks to its flexible requirements for modelingthe problem....

Full description

Saved in:
Bibliographic Details
Main Authors: Tiziana Cattai, Francesco Frattolillo, Andrea Lacava, Prasanna Raut, Jennifer Simonjan, Salvatore D'Oro, Tommaso Melodia, Evgenii Vinogradov, Enrico Natalizio, Stefania Colonnese, Francesca Cuomo, Luca Iocchi
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Open Journal of Vehicular Technology
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11072350/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849772826993623040
author Tiziana Cattai
Francesco Frattolillo
Andrea Lacava
Prasanna Raut
Jennifer Simonjan
Salvatore D'Oro
Tommaso Melodia
Evgenii Vinogradov
Enrico Natalizio
Stefania Colonnese
Francesca Cuomo
Luca Iocchi
author_facet Tiziana Cattai
Francesco Frattolillo
Andrea Lacava
Prasanna Raut
Jennifer Simonjan
Salvatore D'Oro
Tommaso Melodia
Evgenii Vinogradov
Enrico Natalizio
Stefania Colonnese
Francesca Cuomo
Luca Iocchi
author_sort Tiziana Cattai
collection DOAJ
description The interest in applications related to Multi-Unmanned Aerial Vehicle (UAV) systems has been growing exponentially inthe last few years. Reinforcement Learning (RL) presents one of the most popular alternatives for solving Multi-UAV tasks, thanks to its flexible requirements for modelingthe problem. However, it is often applied to abstractions of the original problem, thus leaving to next development phases the integration of RL solutions to the actual systems. This choice may not guarantee the overall optimal performance of the implemented system. In this survey, we analyze the literature on Multi-UAV applications that utilize reinforcement learning, with particular attention to works that consider realistic communication channels. We focus on identifying the key variables that influence communication and whether these variables are integrated within the RL framework or considered externally. Additionally, we identify key trends, challenges, and future directions in the field, providing a comprehensive overview for researchers and practitioners interested in the practical deployment of RL-based Multi-UAV systems.
format Article
id doaj-art-5fa26456110f4fa39f7b7e6dc17a134c
institution DOAJ
issn 2644-1330
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Open Journal of Vehicular Technology
spelling doaj-art-5fa26456110f4fa39f7b7e6dc17a134c2025-08-20T03:02:14ZengIEEEIEEE Open Journal of Vehicular Technology2644-13302025-01-0162067208110.1109/OJVT.2025.358677411072350Multi-UAV Reinforcement Learning With Realistic Communication Models: Recent Advances and ChallengesTiziana Cattai0https://orcid.org/0000-0002-6128-2246Francesco Frattolillo1https://orcid.org/0000-0002-2040-3355Andrea Lacava2https://orcid.org/0000-0001-9217-5956Prasanna Raut3https://orcid.org/0000-0002-3489-7405Jennifer Simonjan4https://orcid.org/0000-0002-2735-957XSalvatore D'Oro5https://orcid.org/0000-0002-7690-0449Tommaso Melodia6https://orcid.org/0000-0002-2719-1789Evgenii Vinogradov7https://orcid.org/0000-0002-4156-0317Enrico Natalizio8https://orcid.org/0000-0001-8553-5722Stefania Colonnese9https://orcid.org/0000-0002-1807-2155Francesca Cuomo10https://orcid.org/0000-0002-9122-7993Luca Iocchi11https://orcid.org/0000-0001-9057-8946Department of Information Engineering, Electronics and Telecommunication, Sapienza University of Rome, Rome, ItalyDepartment of Computer, Control and Management Engineering Sapienza University of Rome, Rome, ItalyDepartment of Information Engineering, Electronics and Telecommunication, Sapienza University of Rome, Rome, ItalyTechnology Innovation Institute Abu Dhabi, Abu Dhabi, UAETechnology Innovation Institute Abu Dhabi, Abu Dhabi, UAEInstitute for the Wireless Internet of Things, Northeastern University, Boston, MA, USAInstitute for the Wireless Internet of Things, Northeastern University, Boston, MA, USATechnology Innovation Institute Abu Dhabi, Abu Dhabi, UAETechnology Innovation Institute Abu Dhabi, Abu Dhabi, UAEDepartment of Information Engineering, Electronics and Telecommunication, Sapienza University of Rome, Rome, ItalyDepartment of Information Engineering, Electronics and Telecommunication, Sapienza University of Rome, Rome, ItalyDepartment of Computer, Control and Management Engineering Sapienza University of Rome, Rome, ItalyThe interest in applications related to Multi-Unmanned Aerial Vehicle (UAV) systems has been growing exponentially inthe last few years. Reinforcement Learning (RL) presents one of the most popular alternatives for solving Multi-UAV tasks, thanks to its flexible requirements for modelingthe problem. However, it is often applied to abstractions of the original problem, thus leaving to next development phases the integration of RL solutions to the actual systems. This choice may not guarantee the overall optimal performance of the implemented system. In this survey, we analyze the literature on Multi-UAV applications that utilize reinforcement learning, with particular attention to works that consider realistic communication channels. We focus on identifying the key variables that influence communication and whether these variables are integrated within the RL framework or considered externally. Additionally, we identify key trends, challenges, and future directions in the field, providing a comprehensive overview for researchers and practitioners interested in the practical deployment of RL-based Multi-UAV systems.https://ieeexplore.ieee.org/document/11072350/Multi-UAVreinforcement learning5Gcommunications
spellingShingle Tiziana Cattai
Francesco Frattolillo
Andrea Lacava
Prasanna Raut
Jennifer Simonjan
Salvatore D'Oro
Tommaso Melodia
Evgenii Vinogradov
Enrico Natalizio
Stefania Colonnese
Francesca Cuomo
Luca Iocchi
Multi-UAV Reinforcement Learning With Realistic Communication Models: Recent Advances and Challenges
IEEE Open Journal of Vehicular Technology
Multi-UAV
reinforcement learning
5G
communications
title Multi-UAV Reinforcement Learning With Realistic Communication Models: Recent Advances and Challenges
title_full Multi-UAV Reinforcement Learning With Realistic Communication Models: Recent Advances and Challenges
title_fullStr Multi-UAV Reinforcement Learning With Realistic Communication Models: Recent Advances and Challenges
title_full_unstemmed Multi-UAV Reinforcement Learning With Realistic Communication Models: Recent Advances and Challenges
title_short Multi-UAV Reinforcement Learning With Realistic Communication Models: Recent Advances and Challenges
title_sort multi uav reinforcement learning with realistic communication models recent advances and challenges
topic Multi-UAV
reinforcement learning
5G
communications
url https://ieeexplore.ieee.org/document/11072350/
work_keys_str_mv AT tizianacattai multiuavreinforcementlearningwithrealisticcommunicationmodelsrecentadvancesandchallenges
AT francescofrattolillo multiuavreinforcementlearningwithrealisticcommunicationmodelsrecentadvancesandchallenges
AT andrealacava multiuavreinforcementlearningwithrealisticcommunicationmodelsrecentadvancesandchallenges
AT prasannaraut multiuavreinforcementlearningwithrealisticcommunicationmodelsrecentadvancesandchallenges
AT jennifersimonjan multiuavreinforcementlearningwithrealisticcommunicationmodelsrecentadvancesandchallenges
AT salvatoredoro multiuavreinforcementlearningwithrealisticcommunicationmodelsrecentadvancesandchallenges
AT tommasomelodia multiuavreinforcementlearningwithrealisticcommunicationmodelsrecentadvancesandchallenges
AT evgeniivinogradov multiuavreinforcementlearningwithrealisticcommunicationmodelsrecentadvancesandchallenges
AT enriconatalizio multiuavreinforcementlearningwithrealisticcommunicationmodelsrecentadvancesandchallenges
AT stefaniacolonnese multiuavreinforcementlearningwithrealisticcommunicationmodelsrecentadvancesandchallenges
AT francescacuomo multiuavreinforcementlearningwithrealisticcommunicationmodelsrecentadvancesandchallenges
AT lucaiocchi multiuavreinforcementlearningwithrealisticcommunicationmodelsrecentadvancesandchallenges