Multi-UAV Mapping and Target Finding in Large, Complex, Partially Observable Environments

Coordinating multiple unmanned aerial vehicles (UAVs) for the purposes of target finding or surveying points of interest in large, complex, and partially observable environments remains an area of exploration. This work proposes a modeling approach and software framework for multi-UAV search and tar...

Full description

Bibliographic Details
Main Authors: Violet Walker, Fernando Vanegas, Felipe Gonzalez
Format: Article
Language:English
Published: MDPI AG 2023-07-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/15/15/3802
_version_ 1797586088511930368
author Violet Walker
Fernando Vanegas
Felipe Gonzalez
author_facet Violet Walker
Fernando Vanegas
Felipe Gonzalez
author_sort Violet Walker
collection DOAJ
description Coordinating multiple unmanned aerial vehicles (UAVs) for the purposes of target finding or surveying points of interest in large, complex, and partially observable environments remains an area of exploration. This work proposes a modeling approach and software framework for multi-UAV search and target finding within large, complex, and partially observable environments. Mapping and path-solving is carried out by an extended NanoMap library; the global planning problem is defined as a decentralized partially observable Markov decision process and solved using an online model-based solver, and the local control problem is defined as two separate partially observable Markov decision processes that are solved using deep reinforcement learning. Simulated testing demonstrates that the proposed framework enables multiple UAVs to search and target-find within large, complex, and partially observable environments.
first_indexed 2024-03-11T00:17:22Z
format Article
id doaj.art-4f96944300a046ba91ce5a721003fefd
institution Directory Open Access Journal
issn 2072-4292
language English
last_indexed 2024-03-11T00:17:22Z
publishDate 2023-07-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj.art-4f96944300a046ba91ce5a721003fefd2023-11-18T23:31:00ZengMDPI AGRemote Sensing2072-42922023-07-011515380210.3390/rs15153802Multi-UAV Mapping and Target Finding in Large, Complex, Partially Observable EnvironmentsViolet Walker0Fernando Vanegas1Felipe Gonzalez2School of Electrical Engineering and Robotics, Queensland University of Technology, Brisbane, QLD 4000, AustraliaSchool of Electrical Engineering and Robotics, Queensland University of Technology, Brisbane, QLD 4000, AustraliaSchool of Electrical Engineering and Robotics, Queensland University of Technology, Brisbane, QLD 4000, AustraliaCoordinating multiple unmanned aerial vehicles (UAVs) for the purposes of target finding or surveying points of interest in large, complex, and partially observable environments remains an area of exploration. This work proposes a modeling approach and software framework for multi-UAV search and target finding within large, complex, and partially observable environments. Mapping and path-solving is carried out by an extended NanoMap library; the global planning problem is defined as a decentralized partially observable Markov decision process and solved using an online model-based solver, and the local control problem is defined as two separate partially observable Markov decision processes that are solved using deep reinforcement learning. Simulated testing demonstrates that the proposed framework enables multiple UAVs to search and target-find within large, complex, and partially observable environments.https://www.mdpi.com/2072-4292/15/15/3802UAVmulti-UAVplanningcontrolPOMDPDEC-POMDP
spellingShingle Violet Walker
Fernando Vanegas
Felipe Gonzalez
Multi-UAV Mapping and Target Finding in Large, Complex, Partially Observable Environments
Remote Sensing
UAV
multi-UAV
planning
control
POMDP
DEC-POMDP
title Multi-UAV Mapping and Target Finding in Large, Complex, Partially Observable Environments
title_full Multi-UAV Mapping and Target Finding in Large, Complex, Partially Observable Environments
title_fullStr Multi-UAV Mapping and Target Finding in Large, Complex, Partially Observable Environments
title_full_unstemmed Multi-UAV Mapping and Target Finding in Large, Complex, Partially Observable Environments
title_short Multi-UAV Mapping and Target Finding in Large, Complex, Partially Observable Environments
title_sort multi uav mapping and target finding in large complex partially observable environments
topic UAV
multi-UAV
planning
control
POMDP
DEC-POMDP
url https://www.mdpi.com/2072-4292/15/15/3802
work_keys_str_mv AT violetwalker multiuavmappingandtargetfindinginlargecomplexpartiallyobservableenvironments
AT fernandovanegas multiuavmappingandtargetfindinginlargecomplexpartiallyobservableenvironments
AT felipegonzalez multiuavmappingandtargetfindinginlargecomplexpartiallyobservableenvironments