DETEAMSK: A Model-Based Reinforcement Learning Approach to Intelligent Top-Level Planning and Decisions for Multi-Drone Ad Hoc Teamwork by Decoupling the Identification of Teammate and Task

The ability to collaborate with new teammates, adapt to unfamiliar environments, and engage in effective planning is essential for multi-drone agents within unmanned combat systems. This paper introduces DETEAMSK (Model-based Reinforcement Learning by Decoupling the Identification of Teammates and T...

Full description

Saved in:
Bibliographic Details
Main Authors: Penghui Xu, Yu Zhang, Le Hao, Qilin Yan
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Aerospace
Subjects:
Online Access:https://www.mdpi.com/2226-4310/12/7/635
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849714491461206016
author Penghui Xu
Yu Zhang
Le Hao
Qilin Yan
author_facet Penghui Xu
Yu Zhang
Le Hao
Qilin Yan
author_sort Penghui Xu
collection DOAJ
description The ability to collaborate with new teammates, adapt to unfamiliar environments, and engage in effective planning is essential for multi-drone agents within unmanned combat systems. This paper introduces DETEAMSK (Model-based Reinforcement Learning by Decoupling the Identification of Teammates and Tasks), a model-based reinforcement learning method in intelligent top-level planning and decisions designed for ad hoc teamwork among multi-drone agents. It specifically addresses integrated reconnaissance and strike missions in urban combat scenarios under varying conditions. DETEAMSK’s performance is evaluated through comprehensive, multidimensional experiments and compared with other baseline models. The results demonstrate that DETEAMSK exhibits superior effectiveness, robustness, and generalization capabilities across a range of task domains. Moreover, the model-based reinforcement learning approach offers distinct advantages over traditional models, such as the PLASTIC-Model, and model-free approaches, like the PLASTIC-Policy, due to its unique “dynamic decoupling identification” feature. This study provides valuable insights for advancing both theoretical and applied research in model-based reinforcement learning methods for multi-drone systems.
format Article
id doaj-art-45d5333203bc44119bb567d67ff37d19
institution DOAJ
issn 2226-4310
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Aerospace
spelling doaj-art-45d5333203bc44119bb567d67ff37d192025-08-20T03:13:42ZengMDPI AGAerospace2226-43102025-07-0112763510.3390/aerospace12070635DETEAMSK: A Model-Based Reinforcement Learning Approach to Intelligent Top-Level Planning and Decisions for Multi-Drone Ad Hoc Teamwork by Decoupling the Identification of Teammate and TaskPenghui Xu0Yu Zhang1Le Hao2Qilin Yan3College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaThe ability to collaborate with new teammates, adapt to unfamiliar environments, and engage in effective planning is essential for multi-drone agents within unmanned combat systems. This paper introduces DETEAMSK (Model-based Reinforcement Learning by Decoupling the Identification of Teammates and Tasks), a model-based reinforcement learning method in intelligent top-level planning and decisions designed for ad hoc teamwork among multi-drone agents. It specifically addresses integrated reconnaissance and strike missions in urban combat scenarios under varying conditions. DETEAMSK’s performance is evaluated through comprehensive, multidimensional experiments and compared with other baseline models. The results demonstrate that DETEAMSK exhibits superior effectiveness, robustness, and generalization capabilities across a range of task domains. Moreover, the model-based reinforcement learning approach offers distinct advantages over traditional models, such as the PLASTIC-Model, and model-free approaches, like the PLASTIC-Policy, due to its unique “dynamic decoupling identification” feature. This study provides valuable insights for advancing both theoretical and applied research in model-based reinforcement learning methods for multi-drone systems.https://www.mdpi.com/2226-4310/12/7/635multiagent drone systemintelligent planning and decisionad hoc teamworkmodel-based reinforcement learningmodel-free reinforcement learningdynamic identification with decoupling
spellingShingle Penghui Xu
Yu Zhang
Le Hao
Qilin Yan
DETEAMSK: A Model-Based Reinforcement Learning Approach to Intelligent Top-Level Planning and Decisions for Multi-Drone Ad Hoc Teamwork by Decoupling the Identification of Teammate and Task
Aerospace
multiagent drone system
intelligent planning and decision
ad hoc teamwork
model-based reinforcement learning
model-free reinforcement learning
dynamic identification with decoupling
title DETEAMSK: A Model-Based Reinforcement Learning Approach to Intelligent Top-Level Planning and Decisions for Multi-Drone Ad Hoc Teamwork by Decoupling the Identification of Teammate and Task
title_full DETEAMSK: A Model-Based Reinforcement Learning Approach to Intelligent Top-Level Planning and Decisions for Multi-Drone Ad Hoc Teamwork by Decoupling the Identification of Teammate and Task
title_fullStr DETEAMSK: A Model-Based Reinforcement Learning Approach to Intelligent Top-Level Planning and Decisions for Multi-Drone Ad Hoc Teamwork by Decoupling the Identification of Teammate and Task
title_full_unstemmed DETEAMSK: A Model-Based Reinforcement Learning Approach to Intelligent Top-Level Planning and Decisions for Multi-Drone Ad Hoc Teamwork by Decoupling the Identification of Teammate and Task
title_short DETEAMSK: A Model-Based Reinforcement Learning Approach to Intelligent Top-Level Planning and Decisions for Multi-Drone Ad Hoc Teamwork by Decoupling the Identification of Teammate and Task
title_sort deteamsk a model based reinforcement learning approach to intelligent top level planning and decisions for multi drone ad hoc teamwork by decoupling the identification of teammate and task
topic multiagent drone system
intelligent planning and decision
ad hoc teamwork
model-based reinforcement learning
model-free reinforcement learning
dynamic identification with decoupling
url https://www.mdpi.com/2226-4310/12/7/635
work_keys_str_mv AT penghuixu deteamskamodelbasedreinforcementlearningapproachtointelligenttoplevelplanninganddecisionsformultidroneadhocteamworkbydecouplingtheidentificationofteammateandtask
AT yuzhang deteamskamodelbasedreinforcementlearningapproachtointelligenttoplevelplanninganddecisionsformultidroneadhocteamworkbydecouplingtheidentificationofteammateandtask
AT lehao deteamskamodelbasedreinforcementlearningapproachtointelligenttoplevelplanninganddecisionsformultidroneadhocteamworkbydecouplingtheidentificationofteammateandtask
AT qilinyan deteamskamodelbasedreinforcementlearningapproachtointelligenttoplevelplanninganddecisionsformultidroneadhocteamworkbydecouplingtheidentificationofteammateandtask