國立虎尾科技大學 |

Situational Awareness for Low Cost Underwater Autonomy.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Situational Awareness for Low Cost Underwater Autonomy./
Author:	McConnell, John.
Description:	1 online resource (120 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 84-11, Section: B.
Contained By:	Dissertations Abstracts International84-11B.
Subject:	Robotics. -
Online resource:	click for full text (PQDT)
ISBN:	9798379566159

Situational Awareness for Low Cost Underwater Autonomy.
McConnell, John.

Situational Awareness for Low Cost Underwater Autonomy. - 1 online resource (120 pages)

Source: Dissertations Abstracts International, Volume: 84-11, Section: B.

Thesis (Ph.D.)--Stevens Institute of Technology, 2023.

Includes bibliographical references

Underwater robots have matured over the past few decades to support the increasing need for maritime infrastructure assessment and other offshore activity. However, deploying underwater robots often involves a high startup cost associated with vehicle acquisition. It is often the case that companies not engaged in oil and gas exploration are priced out of this technology. This is primarily due to the highly accurate, often tactical-grade inertial navigation systems (INS) required to make state estimation reliable enough for long-duration autonomous operations. Moreover, sonars are the perceptual sensor of choice due to the frequent need to operate in high-turbidity water. Sonars, however, do not provide the dense 3D information required for offshore asset evaluation or autonomous navigation. In this work, we consider an underwater robot's situational awareness, i.e., the required knowledge of a robot's environment to complete its mission safely.We propose several sub-systems that assist in bridging the situational awareness gap in low-cost underwater autonomous systems equipped with imaging sonars. Firstly, we employ a stereo pair of orthogonal sonars to recover lost 3D data. Second, we generalize the method of orthogonal sensor fusion to work in large-scale environments through object-level inference. Next, we use public domain prior information to enhance the state estimation capabilities of a low-cost underwater robot. We then use submaps to recover 3D maps, providing dense 3D maps without object-level inference. Lastly, we extend our thinking to the multi-robot case. We showcase a system that performs multi-robot simultaneous localization and mapping (SLAM) using real-world underwater imaging sonar data, the first of its kind. In future work, this will enable multi-robot systems that are capable of safely operating in marine environments and cooperatively completing their tasks efficiently.

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

Mode of access: World Wide Web

ISBN: 9798379566159Subjects--Topical Terms:

561941
Robotics.
Subjects--Index Terms:

Underwater autonomyIndex Terms--Genre/Form:

554714
Electronic books.

Situational Awareness for Low Cost Underwater Autonomy.
LDR:03315ntm a2200397K 4500 001 1141061
005 20231130111601.5
006 m o d
007 cr mn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798379566159
035 $a (MiAaPQ)AAI30316580
035 $a AAI30316580
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a McConnell, John. $3 1464641
245 1 0 $a Situational Awareness for Low Cost Underwater Autonomy.
264 0 $c 2023
300 $a 1 online resource (120 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: 84-11, Section: B.
500 $a Advisor: Englot, Brendan.
502 $a Thesis (Ph.D.)--Stevens Institute of Technology, 2023.
504 $a Includes bibliographical references
520 $a Underwater robots have matured over the past few decades to support the increasing need for maritime infrastructure assessment and other offshore activity. However, deploying underwater robots often involves a high startup cost associated with vehicle acquisition. It is often the case that companies not engaged in oil and gas exploration are priced out of this technology. This is primarily due to the highly accurate, often tactical-grade inertial navigation systems (INS) required to make state estimation reliable enough for long-duration autonomous operations. Moreover, sonars are the perceptual sensor of choice due to the frequent need to operate in high-turbidity water. Sonars, however, do not provide the dense 3D information required for offshore asset evaluation or autonomous navigation. In this work, we consider an underwater robot's situational awareness, i.e., the required knowledge of a robot's environment to complete its mission safely.We propose several sub-systems that assist in bridging the situational awareness gap in low-cost underwater autonomous systems equipped with imaging sonars. Firstly, we employ a stereo pair of orthogonal sonars to recover lost 3D data. Second, we generalize the method of orthogonal sensor fusion to work in large-scale environments through object-level inference. Next, we use public domain prior information to enhance the state estimation capabilities of a low-cost underwater robot. We then use submaps to recover 3D maps, providing dense 3D maps without object-level inference. Lastly, we extend our thinking to the multi-robot case. We showcase a system that performs multi-robot simultaneous localization and mapping (SLAM) using real-world underwater imaging sonar data, the first of its kind. In future work, this will enable multi-robot systems that are capable of safely operating in marine environments and cooperatively completing their tasks efficiently.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Robotics. $3 561941
650 4 $a Ocean engineering. $3 857658
650 4 $a Remote sensing. $3 557272
653 $a Underwater autonomy
653 $a Vehicle acquisition
653 $a Inertial navigation systems
653 $a Autonomous navigation
653 $a Orthogonal sonars
655 7 $a Electronic books. $2 local $3 554714
690 $a 0771
690 $a 0547
690 $a 0799
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Stevens Institute of Technology. $b Mechanical Engineer. $3 1178936
773 0 $t Dissertations Abstracts International $g 84-11B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30316580 $z click for full text (PQDT)