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...
Main Authors: | , |
---|---|
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 |