Strategies for Scaleable Communication and Coordination in Multi-Agent (UAV) Systems

A system is considered in which agents (UAVs) must cooperatively discover interest-points (i.e., burning trees, geographical features) evolving over a grid. The objective is to locate as many interest-points as possible in the shortest possible time frame. There are two main problems: a control prob...

Full description

Bibliographic Details
Main Authors: Jonathan Ponniah, Or D. Dantsker
Format: Article
Language:English
Published: MDPI AG 2022-08-01
Series:Aerospace
Subjects:
Online Access:https://www.mdpi.com/2226-4310/9/9/488
_version_ 1827664625808703488
author Jonathan Ponniah
Or D. Dantsker
author_facet Jonathan Ponniah
Or D. Dantsker
author_sort Jonathan Ponniah
collection DOAJ
description A system is considered in which agents (UAVs) must cooperatively discover interest-points (i.e., burning trees, geographical features) evolving over a grid. The objective is to locate as many interest-points as possible in the shortest possible time frame. There are two main problems: a control problem, where agents must collectively determine the optimal action, and a communication problem, where agents must share their local states and infer a common global state. Both problems become intractable when the number of agents is large. This survey/concept paper curates a broad selection of work in the literature pointing to a possible solution; a unified control/communication architecture within the framework of reinforcement learning. Two components of this architecture are locally interactive structure in the state-space, and hierarchical multi-level clustering for system-wide communication. The former mitigates the complexity of the control problem and the latter adapts to fundamental throughput constraints in wireless networks. The challenges of applying reinforcement learning to multi-agent systems are discussed. The role of clustering is explored in multi-agent communication. Research directions are suggested to unify these components.
first_indexed 2024-03-10T01:03:37Z
format Article
id doaj.art-7c32bdbd7c644f7da3cc7a8f25a44a90
institution Directory Open Access Journal
issn 2226-4310
language English
last_indexed 2024-03-10T01:03:37Z
publishDate 2022-08-01
publisher MDPI AG
record_format Article
series Aerospace
spelling doaj.art-7c32bdbd7c644f7da3cc7a8f25a44a902023-11-23T14:30:47ZengMDPI AGAerospace2226-43102022-08-019948810.3390/aerospace9090488Strategies for Scaleable Communication and Coordination in Multi-Agent (UAV) SystemsJonathan Ponniah0Or D. Dantsker1Department of Electrical Engineering, San Jose State University, San Jose, CA 95192, USATUM School of Engineering and Design, Technical University of Munich, D-85748 Garching, GermanyA system is considered in which agents (UAVs) must cooperatively discover interest-points (i.e., burning trees, geographical features) evolving over a grid. The objective is to locate as many interest-points as possible in the shortest possible time frame. There are two main problems: a control problem, where agents must collectively determine the optimal action, and a communication problem, where agents must share their local states and infer a common global state. Both problems become intractable when the number of agents is large. This survey/concept paper curates a broad selection of work in the literature pointing to a possible solution; a unified control/communication architecture within the framework of reinforcement learning. Two components of this architecture are locally interactive structure in the state-space, and hierarchical multi-level clustering for system-wide communication. The former mitigates the complexity of the control problem and the latter adapts to fundamental throughput constraints in wireless networks. The challenges of applying reinforcement learning to multi-agent systems are discussed. The role of clustering is explored in multi-agent communication. Research directions are suggested to unify these components.https://www.mdpi.com/2226-4310/9/9/488reinforcement learningmulti-agent systemsdistributed systemsclusteringmobile ad-hoc networkstracking
spellingShingle Jonathan Ponniah
Or D. Dantsker
Strategies for Scaleable Communication and Coordination in Multi-Agent (UAV) Systems
Aerospace
reinforcement learning
multi-agent systems
distributed systems
clustering
mobile ad-hoc networks
tracking
title Strategies for Scaleable Communication and Coordination in Multi-Agent (UAV) Systems
title_full Strategies for Scaleable Communication and Coordination in Multi-Agent (UAV) Systems
title_fullStr Strategies for Scaleable Communication and Coordination in Multi-Agent (UAV) Systems
title_full_unstemmed Strategies for Scaleable Communication and Coordination in Multi-Agent (UAV) Systems
title_short Strategies for Scaleable Communication and Coordination in Multi-Agent (UAV) Systems
title_sort strategies for scaleable communication and coordination in multi agent uav systems
topic reinforcement learning
multi-agent systems
distributed systems
clustering
mobile ad-hoc networks
tracking
url https://www.mdpi.com/2226-4310/9/9/488
work_keys_str_mv AT jonathanponniah strategiesforscaleablecommunicationandcoordinationinmultiagentuavsystems
AT orddantsker strategiesforscaleablecommunicationandcoordinationinmultiagentuavsystems