東華大學圖書館 |

Visual Methods towards Autonomous Underwater Manipulation.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Visual Methods towards Autonomous Underwater Manipulation./
作者:	Billings, Gideon H.
面頁冊數:	1 online resource (140 pages)
附註:	Source: Dissertations Abstracts International, Volume: 84-01, Section: B.
Contained By:	Dissertations Abstracts International84-01B.
標題:	Marine geology. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29274901click for full text (PQDT)
ISBN:	9798438777892

Visual Methods towards Autonomous Underwater Manipulation.
Billings, Gideon H.

Visual Methods towards Autonomous Underwater Manipulation. - 1 online resource (140 pages)

Source: Dissertations Abstracts International, Volume: 84-01, Section: B.

Thesis (Ph.D.)--University of Michigan, 2022.

Includes bibliographical references

Extra-terrestrial ocean worlds like Europa offer tantalizing targets in the search for extant life beyond the confines of Earth's atmosphere. However, reaching and exploring the underwater environments of these alien worlds is a task with immense challenges. Unlike terrestrial based missions, the exploration of ocean worlds necessitates robots which are capable of fully automated operation. These robots must rely on local sensors to interpret the scene, plan their motions, and complete their mission tasks. Manipulation tasks, such as sample collection, are particularly challenging in underwater environments, where the manipulation platform is mobile, and the environment is unstructured. This dissertation addresses some of the challenges in visual scene understanding to support autonomous manipulation with underwater vehicle manipulator systems (UVMSs). Specifically, this work addresses the problems of tool detection and pose estimation, 3D scene reconstruction, underwater camera system design, underwater dataset collection, and UVMS manipulator automation. The developed visual methods are demonstrated with a lightweight vision system, composed of a vehicle mounted stereo pair and a manipulator wrist mounted fisheye camera, that can be easily integrated on existing UVMSs. While the stereo camera primarily supports 3D reconstruction of the manipulator working area, the wrist mounted camera enables dynamic viewpoint acquisition for detecting objects, such as tools, and extending the scene reconstruction beyond the fixed stereo view. A further objective of this dissertation was to apply deep learning with the developed visual methods. While deep learning has greatly advanced the state-of-the-art in terrestrial based visual methods across diverse applications, the challenges of accessing the underwater environment and collecting underwater datasets for training these methods has hindered progress in advancing visual methods for underwater applications. Following is an overview of the contributions made by this dissertation. The first contribution is a novel deep learning method for object detection and pose estimation from monocular images. The second contribution is a general framework for adapting monocular image-based pose estimation networks to work on full fisheye or omni-directional images with minimal modification to the network architecture. The third contribution is a visual SLAM method designed for UVMSs that fuses features from both the wrist mounted fisheye camera and the vehicle mounted stereo pair into the same map, where the map scale is constrained by the stereo features, and the wrist camera can actively extend the map beyond the limited stereo view. The fourth contribution is an open-source tool to aid the design of underwater camera and lighting systems. The fifth contribution is an autonomy framework for UVMS manipulator control and the vision system that was used throughout this dissertation work, along with experimental results from field trials in natural deep ocean environments, including an active submarine volcano in the Mediterranean basin. The sixth contribution is a large scale annotated underwater visual dataset for object pose estimation and 3D scene reconstruction. The dataset was collected with our vision system in natural deep ocean environments and supported the development of the visual methods contributed by this dissertation.

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

Mode of access: World Wide Web

ISBN: 9798438777892Subjects--Topical Terms:

3173821
Marine geology.
Subjects--Index Terms:

Autonomous Underwater ManipulationIndex Terms--Genre/Form:

542853
Electronic books.

Visual Methods towards Autonomous Underwater Manipulation.
LDR:04801nmm a2200397K 4500 001 2354891
005 20230505090452.5
006 m o d
007 cr mn ---uuuuu
008 241011s2022 xx obm 000 0 eng d
020 $a 9798438777892
035 $a (MiAaPQ)AAI29274901
035 $a (MiAaPQ)umichrackham004106
035 $a AAI29274901
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Billings, Gideon H. $3 3695265
245 1 0 $a Visual Methods towards Autonomous Underwater Manipulation.
264 0 $c 2022
300 $a 1 online resource (140 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: 84-01, Section: B.
500 $a Advisor: Johnson-Roberson, Matthew.
502 $a Thesis (Ph.D.)--University of Michigan, 2022.
504 $a Includes bibliographical references
520 $a Extra-terrestrial ocean worlds like Europa offer tantalizing targets in the search for extant life beyond the confines of Earth's atmosphere. However, reaching and exploring the underwater environments of these alien worlds is a task with immense challenges. Unlike terrestrial based missions, the exploration of ocean worlds necessitates robots which are capable of fully automated operation. These robots must rely on local sensors to interpret the scene, plan their motions, and complete their mission tasks. Manipulation tasks, such as sample collection, are particularly challenging in underwater environments, where the manipulation platform is mobile, and the environment is unstructured. This dissertation addresses some of the challenges in visual scene understanding to support autonomous manipulation with underwater vehicle manipulator systems (UVMSs). Specifically, this work addresses the problems of tool detection and pose estimation, 3D scene reconstruction, underwater camera system design, underwater dataset collection, and UVMS manipulator automation. The developed visual methods are demonstrated with a lightweight vision system, composed of a vehicle mounted stereo pair and a manipulator wrist mounted fisheye camera, that can be easily integrated on existing UVMSs. While the stereo camera primarily supports 3D reconstruction of the manipulator working area, the wrist mounted camera enables dynamic viewpoint acquisition for detecting objects, such as tools, and extending the scene reconstruction beyond the fixed stereo view. A further objective of this dissertation was to apply deep learning with the developed visual methods. While deep learning has greatly advanced the state-of-the-art in terrestrial based visual methods across diverse applications, the challenges of accessing the underwater environment and collecting underwater datasets for training these methods has hindered progress in advancing visual methods for underwater applications. Following is an overview of the contributions made by this dissertation. The first contribution is a novel deep learning method for object detection and pose estimation from monocular images. The second contribution is a general framework for adapting monocular image-based pose estimation networks to work on full fisheye or omni-directional images with minimal modification to the network architecture. The third contribution is a visual SLAM method designed for UVMSs that fuses features from both the wrist mounted fisheye camera and the vehicle mounted stereo pair into the same map, where the map scale is constrained by the stereo features, and the wrist camera can actively extend the map beyond the limited stereo view. The fourth contribution is an open-source tool to aid the design of underwater camera and lighting systems. The fifth contribution is an autonomy framework for UVMS manipulator control and the vision system that was used throughout this dissertation work, along with experimental results from field trials in natural deep ocean environments, including an active submarine volcano in the Mediterranean basin. The sixth contribution is a large scale annotated underwater visual dataset for object pose estimation and 3D scene reconstruction. The dataset was collected with our vision system in natural deep ocean environments and supported the development of the visual methods contributed by this dissertation.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Marine geology. $3 3173821
650 4 $a Robotics. $3 519753
650 4 $a Computer science. $3 523869
650 4 $a Aerospace engineering. $3 1002622
653 $a Autonomous Underwater Manipulation
653 $a Marine robotics
653 $a Computer vision
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0771
690 $a 0556
690 $a 0984
690 $a 0538
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a University of Michigan. $b Robotics. $3 3546383
773 0 $t Dissertations Abstracts International $g 84-01B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29274901 $z click for full text (PQDT)