國立虎尾科技大學 |

On the Deployment Optimization of Sensors and Coverage Path Planning for Drone Inspections.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	On the Deployment Optimization of Sensors and Coverage Path Planning for Drone Inspections./
Author:	Kopanon, Andrew M.
Description:	1 online resource (114 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
Contained By:	Dissertations Abstracts International85-12B.
Subject:	Engineering. -
Online resource:	click for full text (PQDT)
ISBN:	9798382838076

On the Deployment Optimization of Sensors and Coverage Path Planning for Drone Inspections.
Kopanon, Andrew M.

On the Deployment Optimization of Sensors and Coverage Path Planning for Drone Inspections. - 1 online resource (114 pages)

Source: Dissertations Abstracts International, Volume: 85-12, Section: B.

Thesis (Ph.D.)--State University of New York at Buffalo, 2024.

Includes bibliographical references

In an era marked by rapid technological advancement, the integration of sensor networks and drone technologies has significantly transformed surveillance, monitoring, and infrastructure maintenance practices. Maximizing sensor coverage and employing drones for inspection purposes emerge as pivotal areas of research and development, carrying far-reaching significance for defense, security, environmental surveillance, and infrastructure upkeep. This work presents a new collaborative sensor coverage maximization problem, a methodology for drone inspection mission coverage path planning, and an end-to-end software suite to plan drone inspection missions utilizing a large language model (LLM).Firstly, the Sensor Coverage Maximization Problem with Collaborative Coverage (SCMP-CC) is introduced to strategically deploy heterogeneous sensors in a given area to maximize coverage in an area of interest. The SCMP-CC utilizes a collaborative reward function considering sensor types, coverage capabilities, prioritized regions, and obstacles. A non-linear program was developed to model the problem, and a simulated annealing heuristic is employed to solve the problem. A specific case of the SCMP-CC was formulated as a linear model to assess the heuristic's effectiveness. The results demonstrate the heuristic's scalability and efficiency, solving large-scale problems within approximately 10 minutes.Secondly, the challenge of optimizing complete coverage boustrophedonic (lawn-mower pattern) drone routes and image collection points for building inspections is addressed, particularly accommodating complex structures with insets or protrusions while adhering to photogrammetric constraints. A Mixed Integer Program Approximation (MIPA) and a continuous space Complete Coverage Boustrophedonic (CCB) model are proposed, with the latter significantly outperforming in terms of computational speed without comprising solution quality. An end-to-end drone inspection pipeline is developed to utilize a pre-site survey image to map the insets and protrusions of the facade, and generate a route and image collection point for complete coverage in real space.Finally, this end-to-end pipeline was implemented in an open-source software suite that utilizes a LLM to aid in the mission planning and inspection route generation process. This Drone-Inspection Mission Planner (DMP) is hosted on a web-based Cesium platform, integrating OpenStreetMap (OSM) Buildings database for easy access to building dimensional data, and Google Photorealistic Tiles for life-like pre-site survey images. The LLM is used to facilitate interactive, multi-modal path planning, achieving a 93% accuracy in mission parameter handling. The DMP serves as an essential component within a broader drone command and control architecture, paving the way for further LLM integration and expanded utility in real-world inspection missions.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798382838076Subjects--Topical Terms:

561152
Engineering.
Subjects--Index Terms:

CoverageIndex Terms--Genre/Form:

554714
Electronic books.

On the Deployment Optimization of Sensors and Coverage Path Planning for Drone Inspections.
LDR:04315ntm a22004097 4500 001 1151920
005 20241118135908.5
006 m o d
007 cr mn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798382838076
035 $a (MiAaPQ)AAI31295345
035 $a AAI31295345
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Kopanon, Andrew M. $3 1478763
245 1 0 $a On the Deployment Optimization of Sensors and Coverage Path Planning for Drone Inspections.
264 0 $c 2024
300 $a 1 online resource (114 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
500 $a Advisor: Murray, Chase.
502 $a Thesis (Ph.D.)--State University of New York at Buffalo, 2024.
504 $a Includes bibliographical references
520 $a In an era marked by rapid technological advancement, the integration of sensor networks and drone technologies has significantly transformed surveillance, monitoring, and infrastructure maintenance practices. Maximizing sensor coverage and employing drones for inspection purposes emerge as pivotal areas of research and development, carrying far-reaching significance for defense, security, environmental surveillance, and infrastructure upkeep. This work presents a new collaborative sensor coverage maximization problem, a methodology for drone inspection mission coverage path planning, and an end-to-end software suite to plan drone inspection missions utilizing a large language model (LLM).Firstly, the Sensor Coverage Maximization Problem with Collaborative Coverage (SCMP-CC) is introduced to strategically deploy heterogeneous sensors in a given area to maximize coverage in an area of interest. The SCMP-CC utilizes a collaborative reward function considering sensor types, coverage capabilities, prioritized regions, and obstacles. A non-linear program was developed to model the problem, and a simulated annealing heuristic is employed to solve the problem. A specific case of the SCMP-CC was formulated as a linear model to assess the heuristic's effectiveness. The results demonstrate the heuristic's scalability and efficiency, solving large-scale problems within approximately 10 minutes.Secondly, the challenge of optimizing complete coverage boustrophedonic (lawn-mower pattern) drone routes and image collection points for building inspections is addressed, particularly accommodating complex structures with insets or protrusions while adhering to photogrammetric constraints. A Mixed Integer Program Approximation (MIPA) and a continuous space Complete Coverage Boustrophedonic (CCB) model are proposed, with the latter significantly outperforming in terms of computational speed without comprising solution quality. An end-to-end drone inspection pipeline is developed to utilize a pre-site survey image to map the insets and protrusions of the facade, and generate a route and image collection point for complete coverage in real space.Finally, this end-to-end pipeline was implemented in an open-source software suite that utilizes a LLM to aid in the mission planning and inspection route generation process. This Drone-Inspection Mission Planner (DMP) is hosted on a web-based Cesium platform, integrating OpenStreetMap (OSM) Buildings database for easy access to building dimensional data, and Google Photorealistic Tiles for life-like pre-site survey images. The LLM is used to facilitate interactive, multi-modal path planning, achieving a 93% accuracy in mission parameter handling. The DMP serves as an essential component within a broader drone command and control architecture, paving the way for further LLM integration and expanded utility in real-world inspection missions.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Engineering. $3 561152
650 4 $a Remote sensing. $3 557272
653 $a Coverage
653 $a Drone
653 $a Inspection
653 $a Large language model
653 $a Path planning
653 $a Sensors
655 7 $a Electronic books. $2 local $3 554714
690 $a 0796
690 $a 0537
690 $a 0799
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a State University of New York at Buffalo. $b Industrial and Systems Engineering. $3 1478764
773 0 $t Dissertations Abstracts International $g 85-12B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31295345 $z click for full text (PQDT)