東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Infrastructure Planning for Unmanned Vehicle Navigation in Constrained Environments.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Infrastructure Planning for Unmanned Vehicle Navigation in Constrained Environments./
作者:	Misra, Sohum.
面頁冊數:	1 online resource (162 pages)
附註:	Source: Dissertations Abstracts International, Volume: 83-05, Section: B.
Contained By:	Dissertations Abstracts International83-05B.
標題:	Computer engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28845369click for full text (PQDT)
ISBN:	9798460491704

Infrastructure Planning for Unmanned Vehicle Navigation in Constrained Environments.
Misra, Sohum.

Infrastructure Planning for Unmanned Vehicle Navigation in Constrained Environments. - 1 online resource (162 pages)

Source: Dissertations Abstracts International, Volume: 83-05, Section: B.

Thesis (Ph.D.)--University of Cincinnati, 2021.

Includes bibliographical references

Path planning algorithms for Unmanned Vehicles (UVs) that rely on Global Positioning System (GPS) for localization can be rendered ineffective upon disruption of GPS signals. Several authors have addressed this issue by considering an information rich environment. However, information may not be readily available and optimal feature (landmark) selection or placement is a challenge in itself. In this dissertation, the main focus is on addressing the problem of infrastructure planning to enable navigation of UVs through GPS degraded, and challenging areas. This work addresses incrementally challenging situations with the addition of constraints on information availability.Information availability depends upon existing infrastructure. Since infrastructure development has an associated cost, we seek the answer to the question: Is it possible to efficiently select/develop infrastructure while ensuring that all the constraints required for UV localization are satisfied? The answer to this question not only reduces infrastructure development cost but also improves the computational efficiency for estimation.Firstly, we developed techniques that would jointly reduce the cost of vehicle routing and infrastructure placement considering that we have the freedom to place landmarks in known locations using geometrical and graph connectivity based approaches.Next, we investigated further challenging scenarios to provide localization guarantees in feature deficient environments using (i) Relative, and (ii) Global frame-based navigation. For (i), conditions were developed for a group of UVs localizing themselves in a frame relative to a target without any additional requirement for infrastructure development. For the latter, we pursued several research directions to provide global guarantees.Finally, we developed a hybrid optimization solution to address the problem of providing uncertainty guarantees for an UV navigating in a dark, GPS constrained, and feature deficient environment, containing repetitive visual features, while ensuring a minimum number of landmarks are used and all the mission constraints are satisfied. In such a situation, Visual SLAM based techniques may fail to deliver the necessary localization performance. Our method utilizes range-based sensors as landmarks, that are carried by the vehicle and are deployed in the environment for localization. Our goal is to estimate and reduce the number of landmarks before the start of the mission, given some information about the environment. We validated the efficiency of our algorithms through extensive simulation and hardware testing.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798460491704Subjects--Topical Terms:

621879
Computer engineering.
Subjects--Index Terms:

EstimationIndex Terms--Genre/Form:

542853
Electronic books.

Infrastructure Planning for Unmanned Vehicle Navigation in Constrained Environments.
LDR:04034nmm a2200409K 4500 001 2354081
005 20230324111153.5
006 m o d
007 cr mn ---uuuuu
008 241011s2021 xx obm 000 0 eng d
020 $a 9798460491704
035 $a (MiAaPQ)AAI28845369
035 $a (MiAaPQ)OhioLINKucin1614079054152227
035 $a AAI28845369
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Misra, Sohum. $3 3694422
245 1 0 $a Infrastructure Planning for Unmanned Vehicle Navigation in Constrained Environments.
264 0 $c 2021
300 $a 1 online resource (162 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: 83-05, Section: B.
502 $a Thesis (Ph.D.)--University of Cincinnati, 2021.
504 $a Includes bibliographical references
520 $a Path planning algorithms for Unmanned Vehicles (UVs) that rely on Global Positioning System (GPS) for localization can be rendered ineffective upon disruption of GPS signals. Several authors have addressed this issue by considering an information rich environment. However, information may not be readily available and optimal feature (landmark) selection or placement is a challenge in itself. In this dissertation, the main focus is on addressing the problem of infrastructure planning to enable navigation of UVs through GPS degraded, and challenging areas. This work addresses incrementally challenging situations with the addition of constraints on information availability.Information availability depends upon existing infrastructure. Since infrastructure development has an associated cost, we seek the answer to the question: Is it possible to efficiently select/develop infrastructure while ensuring that all the constraints required for UV localization are satisfied? The answer to this question not only reduces infrastructure development cost but also improves the computational efficiency for estimation.Firstly, we developed techniques that would jointly reduce the cost of vehicle routing and infrastructure placement considering that we have the freedom to place landmarks in known locations using geometrical and graph connectivity based approaches.Next, we investigated further challenging scenarios to provide localization guarantees in feature deficient environments using (i) Relative, and (ii) Global frame-based navigation. For (i), conditions were developed for a group of UVs localizing themselves in a frame relative to a target without any additional requirement for infrastructure development. For the latter, we pursued several research directions to provide global guarantees.Finally, we developed a hybrid optimization solution to address the problem of providing uncertainty guarantees for an UV navigating in a dark, GPS constrained, and feature deficient environment, containing repetitive visual features, while ensuring a minimum number of landmarks are used and all the mission constraints are satisfied. In such a situation, Visual SLAM based techniques may fail to deliver the necessary localization performance. Our method utilizes range-based sensors as landmarks, that are carried by the vehicle and are deployed in the environment for localization. Our goal is to estimate and reduce the number of landmarks before the start of the mission, given some information about the environment. We validated the efficiency of our algorithms through extensive simulation and hardware testing.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Computer engineering. $3 621879
650 4 $a Automotive engineering. $3 2181195
650 4 $a Transportation. $3 555912
650 4 $a Robotics. $3 519753
653 $a Estimation
653 $a Optimization
653 $a Path Planning
653 $a Infrastructure Planning
653 $a Localization
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0464
690 $a 0709
690 $a 0540
690 $a 0771
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a University of Cincinnati. $b Engineering and Applied Science: Aerospace Engineering. $3 3277533
773 0 $t Dissertations Abstracts International $g 83-05B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28845369 $z click for full text (PQDT)