본문

서브메뉴

Deep Learning Methods for Autonomous Underwater Survey, Reacquisition, and Close-Range Inspection
Deep Learning Methods for Autonomous Underwater Survey, Reacquisition, and Close-Range Ins...
Deep Learning Methods for Autonomous Underwater Survey, Reacquisition, and Close-Range Inspection

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105220
ISBN  
9798291566176
DDC  
629.8
저자명  
Sethuraman, Advaith V.
서명/저자  
Deep Learning Methods for Autonomous Underwater Survey, Reacquisition, and Close-Range Inspection
발행사항  
[Sl] : University of Michigan, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
131 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-03, Section: B.
주기사항  
Advisor: Skinner, Katherine A.
학위논문주기  
Thesis (Ph.D.)--University of Michigan, 2025.
초록/해제  
요약Underwater robots perform crucial search, inspection, and manipulation tasks in environments that are dangerous or impossible for humans to operate in. In order to safely perform useful work, it is crucial for these robotic systems to be equipped with algorithms that enable spatial awareness, decision making, and localization. Alternate sensing modalities such as sonar address some of these challenges but introduce new trade-offs: acoustic noise, view-dependent imaging, and lack of large datasets for machine learning methods. This dissertation addresses challenges associated with autonomous survey, reacquisition, and inspection missions for underwater robots. Autonomous survey encompasses the deployment of robots to capture imagery of a large search area. Reacquisition refers to the maneuvers to capture varying views of any found objects. Finally, close-up inspection of objects involves capturing optical and acoustic imagery of objects for downstream tasks. These tasks are crucial to search and rescue, oceanography, defense, and infrastructure inspection applications. Traditionally, search for submerged objects of interest has been carried out with ship-mounted sonar and human divers. However, this manual process is time consuming and does not scale to large search areas. The use of AUV promises to speed up the process of underwater survey and inspection. However, the data these vehicles collect often requires manual analysis by humans, which can take weeks and does not enable in-situ autonomous decision making. Although machine learning methods can speed up decision making and data processing, there are several challenges for deploying machine learning methods in the field. After an item has been found, marine robotic systems can be deployed for a close-up inspection to enable detailed surveys of targets. This work contributes several novel methods that aim to enable autonomous search and survey for marine robotic systems. The first contribution of this work is a method that addresses the lack of training datasets for object identification in sonar imagery collected from robotic search missions. Specifically, this work presents a method for shipwreck segmentation that is trained entirely in simulation and performs zero-shot shipwreck segmentation with no additional fine-tuning on real data. The second contribution is a diverse, open-source dataset and benchmark for shipwreck segmentation in sonar imagery. This contribution establishes an open-source benchmark and enables future research in machine learning for ocean exploration. After an object is found, operators may perform lower-altitude, specialized survey patterns for imaging the object of interest. The third contribution is an adaptive surveying algorithm that plans more efficient re-inspections of detected targets using side scan sonar. This algorithm is a novel active perception method for side scan sonar that both chooses the next best view to maximize classifier performance and aggregates and classifies multiple views from an adaptive survey. Finally, we develop a novel Gaussian splatting framework for close-range inspections using imaging sonar that demonstrates realistic novel view synthesis, accurate 3D reconstruction, and models acoustic streaking phenomena. This method can enable 3D mapping, synthetic data generation of realistic imaging sonar data for training deep learning models, and additionally enables denoising of captured sonar data, allowing for increased interpretability. The methods presented throughout this thesis are evaluated on real-world datasets collected from field work experiments using marine robotics platforms. This dissertation represents progress toward fully autonomous underwater systems that can operate with minimal human oversight in order to greatly accelerate search and survey missions for critical underwater applications.
일반주제명  
Robotics
일반주제명  
Mechanical engineering
키워드  
Underwater robotics
키워드  
Machine learning methods
키워드  
Computer vision
기타저자  
University of Michigan Robotics
기본자료저록  
Dissertations Abstracts International. 87-03B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017359826
■00520260202105220
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798291566176
■035    ▼a(MiAaPQ)AAI32271802
■035    ▼a(MiAaPQ)umichrackham006207
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a629.8
■1001  ▼aSethuraman,  Advaith  V.
■24510▼aDeep  Learning  Methods  for  Autonomous  Underwater  Survey,  Reacquisition,  and  Close-Range  Inspection
■260    ▼a[Sl]▼bUniversity  of  Michigan▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a131  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-03,  Section:  B.
■500    ▼aAdvisor:  Skinner,  Katherine    A.
■5021  ▼aThesis  (Ph.D.)--University  of  Michigan,  2025.
■520    ▼aUnderwater  robots  perform  crucial  search,  inspection,  and  manipulation  tasks  in  environments  that  are  dangerous  or  impossible  for  humans  to  operate  in.  In  order  to  safely  perform  useful  work,  it  is  crucial  for  these  robotic  systems  to  be  equipped  with  algorithms  that  enable  spatial  awareness,  decision  making,  and  localization.  Alternate  sensing  modalities  such  as  sonar  address  some  of  these  challenges  but  introduce  new  trade-offs:  acoustic  noise,  view-dependent  imaging,  and  lack  of  large  datasets  for  machine  learning  methods.      This  dissertation  addresses  challenges  associated  with  autonomous  survey,  reacquisition,  and  inspection  missions  for  underwater  robots.  Autonomous  survey  encompasses  the  deployment  of  robots  to  capture  imagery  of  a  large  search  area.  Reacquisition  refers  to  the  maneuvers  to  capture  varying  views  of  any  found  objects.  Finally,  close-up  inspection  of  objects  involves  capturing  optical  and  acoustic  imagery  of  objects  for  downstream  tasks.  These  tasks  are  crucial  to  search  and  rescue,  oceanography,  defense,  and  infrastructure  inspection  applications.  Traditionally,  search  for  submerged  objects  of  interest  has  been  carried  out  with  ship-mounted  sonar  and  human  divers.  However,  this  manual  process  is  time  consuming  and  does  not  scale  to  large  search  areas.  The  use  of  AUV  promises  to  speed  up  the  process  of  underwater  survey  and  inspection.  However,  the  data  these  vehicles  collect  often  requires  manual  analysis  by  humans,  which  can  take  weeks  and  does  not  enable  in-situ  autonomous  decision  making.  Although  machine  learning  methods  can  speed  up  decision  making  and  data  processing,  there  are  several  challenges  for  deploying  machine  learning  methods  in  the  field.  After  an  item  has  been  found,  marine  robotic  systems  can  be  deployed  for  a  close-up  inspection  to  enable  detailed  surveys  of  targets.    This  work  contributes  several  novel  methods  that  aim  to  enable  autonomous  search  and  survey  for  marine  robotic  systems.  The  first  contribution  of  this  work  is  a  method  that  addresses  the  lack  of  training  datasets  for  object  identification  in  sonar  imagery  collected  from  robotic  search  missions.  Specifically,  this  work  presents  a  method  for  shipwreck  segmentation  that  is  trained  entirely  in  simulation  and  performs  zero-shot  shipwreck  segmentation  with  no  additional  fine-tuning  on  real  data.  The  second  contribution  is  a  diverse,  open-source  dataset  and  benchmark  for  shipwreck  segmentation  in  sonar  imagery.  This  contribution  establishes  an  open-source  benchmark  and  enables  future  research  in  machine  learning  for  ocean  exploration.  After  an  object  is  found,  operators  may  perform  lower-altitude,  specialized  survey  patterns  for  imaging  the  object  of  interest.  The  third  contribution  is  an  adaptive  surveying  algorithm  that  plans  more  efficient  re-inspections  of  detected  targets  using  side  scan  sonar.  This  algorithm  is  a  novel  active  perception  method  for  side  scan  sonar  that  both  chooses  the  next  best  view  to  maximize  classifier  performance  and  aggregates  and  classifies  multiple  views  from  an  adaptive  survey.  Finally,  we  develop  a  novel  Gaussian  splatting  framework  for  close-range  inspections  using  imaging  sonar  that  demonstrates  realistic  novel  view  synthesis,  accurate  3D  reconstruction,  and  models  acoustic  streaking  phenomena.  This  method  can  enable  3D  mapping,  synthetic  data  generation  of  realistic  imaging  sonar  data  for  training  deep  learning  models,  and  additionally  enables  denoising  of  captured  sonar  data,  allowing  for  increased  interpretability.  The  methods  presented  throughout  this  thesis  are  evaluated  on  real-world  datasets  collected  from  field  work  experiments  using  marine  robotics  platforms.  This  dissertation  represents  progress  toward  fully  autonomous  underwater  systems  that  can  operate  with  minimal  human  oversight  in  order  to  greatly  accelerate  search  and  survey  missions  for  critical  underwater  applications.
■590    ▼aSchool  code:  0127.
■650  4▼aRobotics
■650  4▼aMechanical  engineering
■653    ▼aUnderwater  robotics
■653    ▼aMachine  learning  methods
■653    ▼aComputer  vision
■690    ▼a0771
■690    ▼a0800
■690    ▼a0548
■71020▼aUniversity  of  Michigan▼bRobotics.
■7730  ▼tDissertations  Abstracts  International▼g87-03B.
■790    ▼a0127
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359826▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF17909 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.