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 到查詢結果 [ null ]

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Active Information Gathering Using Distributed Mobile Sensing Networks.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Active Information Gathering Using Distributed Mobile Sensing Networks./
作者:	Chen, Jun.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	180 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
Contained By:	Dissertations Abstracts International83-03B.
標題:	Robotics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28647282
ISBN:	9798538103911

Active Information Gathering Using Distributed Mobile Sensing Networks.
Chen, Jun.

Active Information Gathering Using Distributed Mobile Sensing Networks. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 180 p.

Source: Dissertations Abstracts International, Volume: 83-03, Section: B.

Thesis (Ph.D.)--Temple University, 2021.

This item must not be sold to any third party vendors.

An autonomous robot system requires robots to actively gather information using sensors in order to make control decisions. Some problems where autonomous robots are useful include mapping, environmental monitoring, and surveillance. In some cases, information gathering turns into a multiple target tracking (MTT) problem. Usually, an MTT tracker is utilized to recursively estimate both the number of targets and the state of each target. In order to estimate more efficiently and reliably, sensors must balance exploiting current knowledge to track known targets while simultaneously exploring to find information about new targets. This yields to the coverage control problem, which is aimed at maximizing the total sensing capability of a sensing network over the entire mission space. Many applications of sensing networks benefit from utilizing distributed manners, in which cases networks are able to be scaled to large swarms and better tolerate failures of individual sensors. A distributed network requires sensors to exchange data locally and cooperate in decision making globally.This dissertation studies MTT based on random finite set (RFS) for iterative target states estimation and Voronoi-based coverage control algorithms for target tracking. We address a series of four main problems aiming at allowing reliable and efficient target tracking for distributed multi-robot systems in complicated real-world scenarios and push forward the realization of robot coordination techniques. Firstly, we propose novel target estimation and coverage control schemes to incorporate robots with localization uncertainty. Secondly, we improve target search efficiency for teams of robot with no prior knowledge of target models or distributions by enabling active search and environment learning. Thirdly, we allow robots with heterogeneous capacities in perception and kinematics to cooperatively search and track in an efficient way. Lastly, we develop an improved MTT tracker to allow estimating semantic object labels over time. The efficacy of the proposed methods has been validated in series of simulations and/or hardware validations.

ISBN: 9798538103911Subjects--Topical Terms:

519753
Robotics.
Subjects--Index Terms:

Multiple target tracking

Active Information Gathering Using Distributed Mobile Sensing Networks.
LDR:03374nmm a2200385 4500 001 2352142
005 20221118093821.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798538103911
035 $a (MiAaPQ)AAI28647282
035 $a AAI28647282
040 $a MiAaPQ $c MiAaPQ
100 1 $a Chen, Jun. $3 1001539
245 1 0 $a Active Information Gathering Using Distributed Mobile Sensing Networks.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 180 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
500 $a Advisor: Dames, Philip.
502 $a Thesis (Ph.D.)--Temple University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a An autonomous robot system requires robots to actively gather information using sensors in order to make control decisions. Some problems where autonomous robots are useful include mapping, environmental monitoring, and surveillance. In some cases, information gathering turns into a multiple target tracking (MTT) problem. Usually, an MTT tracker is utilized to recursively estimate both the number of targets and the state of each target. In order to estimate more efficiently and reliably, sensors must balance exploiting current knowledge to track known targets while simultaneously exploring to find information about new targets. This yields to the coverage control problem, which is aimed at maximizing the total sensing capability of a sensing network over the entire mission space. Many applications of sensing networks benefit from utilizing distributed manners, in which cases networks are able to be scaled to large swarms and better tolerate failures of individual sensors. A distributed network requires sensors to exchange data locally and cooperate in decision making globally.This dissertation studies MTT based on random finite set (RFS) for iterative target states estimation and Voronoi-based coverage control algorithms for target tracking. We address a series of four main problems aiming at allowing reliable and efficient target tracking for distributed multi-robot systems in complicated real-world scenarios and push forward the realization of robot coordination techniques. Firstly, we propose novel target estimation and coverage control schemes to incorporate robots with localization uncertainty. Secondly, we improve target search efficiency for teams of robot with no prior knowledge of target models or distributions by enabling active search and environment learning. Thirdly, we allow robots with heterogeneous capacities in perception and kinematics to cooperatively search and track in an efficient way. Lastly, we develop an improved MTT tracker to allow estimating semantic object labels over time. The efficacy of the proposed methods has been validated in series of simulations and/or hardware validations.
590 $a School code: 0225.
650 4 $a Robotics. $3 519753
650 4 $a Robots. $3 529507
650 4 $a Simulation. $3 644748
650 4 $a Cameras. $3 524039
650 4 $a Algorithms. $3 536374
650 4 $a Localization. $3 3560711
650 4 $a Teams. $3 3546566
650 4 $a Decision making. $3 517204
650 4 $a Sensors. $3 3549539
650 4 $a Semantics. $3 520060
650 4 $a Geographic information science. $3 3432445
650 4 $a Information science. $3 554358
653 $a Multiple target tracking
653 $a Distributed manners
653 $a Random finite set
653 $a Iterative target states estimation
653 $a Voronoi-based coverage control
653 $a Target tracking
690 $a 0771
690 $a 0370
690 $a 0723
710 2 $a Temple University. $b Mechanical Engineering. $3 2094048
773 0 $t Dissertations Abstracts International $g 83-03B.
790 $a 0225
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28647282