본문

서브메뉴

From 3D Mapping to Scene Representations for Embodied AI
From 3D Mapping to Scene Representations for Embodied AI
From 3D Mapping to Scene Representations for Embodied AI

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20260209102904
ISBN  
9798265405449
DDC  
616.8
저자명  
Cartillier, Vincent.
서명/저자  
From 3D Mapping to Scene Representations for Embodied AI
발행사항  
[Sl] : Georgia Institute of Technology, 2023
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2023
형태사항  
153 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-06, Section: B.
주기사항  
Advisor: Essa, Irfan;Romberg, Justin.
학위논문주기  
Thesis (Ph.D.)--Georgia Institute of Technology, 2023.
초록/해제  
요약In the past few years, a burgeoning field of research has emerged within the broader AI community known as "Embodied AI." This field encompasses various challenges, including the development of scene datasets and simulators used to train AI agents in diverse tasks, necessitating a comprehensive set of skills. Generally speaking, Embodied AI research projects assume a similar setup where an agent equipped with a set of sensors (usually an RGB and Depth camera) is trained to accomplish certain tasks such as navigation, pick-and-place, question answering etc. While there are many approaches and designs of such Embodied AI agents, this thesis focuses on methods involving intermediate scene representations. In contrast to end-to-end approaches, AI systems with intermediate explicit scene representations comprise two distinct modules: one for raw input sensor processing and a second one for planning and acting. Agents utilizing scene representations offer several advantages, including reduced susceptibility to the forgetting effect observed in their RNN counterparts, easier incorporation of inductive bias directly into the representations (e.g., geometrical constraints), and improved interpretability.Towards this end, this thesis serves as an investigation towards the design of such scene representations. We specifically research how to leverage 3D mapping techniques in order to build rich, dense and useful representations for Embodied AI applications. We start by studying representations in the form of 2D topdown metric maps. These 2D maps can store features, labels or geometrical information to form a useful training signal for the tasks of semantic mapping, navigation or question answering. We then study 3D representations in the forms of implicit maps applied for SLAM and 3D object-based maps for multi-object re-identification. Next we extend our research to dynamic scenes and explore 4D representations in the form of localized keyframes. Finally, the thesis also explores connections between these different representations while highlighting their strengths and limitations.
일반주제명  
Episodic memory
일반주제명  
Semantics
키워드  
3D mapping techniques
키워드  
Geometrical information
기타저자  
Georgia Institute of Technology.
기본자료저록  
Dissertations Abstracts International. 87-06B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260203s2023        us                              c    eng  d
■001000017365961
■00520260209102904
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798265405449
■035    ▼a(MiAaPQ)AAI32315571
■035    ▼a(MiAaPQ)GeorgiaTech73112
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a616.8
■1001  ▼aCartillier,  Vincent.
■24510▼aFrom  3D  Mapping  to  Scene  Representations  for  Embodied  AI
■260    ▼a[Sl]▼bGeorgia  Institute  of  Technology▼c2023
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2023
■300    ▼a153  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-06,  Section:  B.
■500    ▼aAdvisor:  Essa,  Irfan;Romberg,  Justin.
■5021  ▼aThesis  (Ph.D.)--Georgia  Institute  of  Technology,  2023.
■520    ▼aIn  the  past  few  years,  a  burgeoning  field  of  research  has  emerged  within  the  broader  AI  community  known  as  "Embodied  AI."  This  field  encompasses  various  challenges,  including  the  development  of  scene  datasets  and  simulators  used  to  train  AI  agents  in  diverse  tasks,  necessitating  a  comprehensive  set  of  skills.  Generally  speaking,  Embodied  AI  research  projects  assume  a  similar  setup  where  an  agent  equipped  with  a  set  of  sensors  (usually  an  RGB  and  Depth  camera)  is  trained  to  accomplish  certain  tasks  such  as  navigation,  pick-and-place,  question  answering  etc.  While  there  are  many  approaches  and  designs  of  such  Embodied  AI  agents,  this  thesis  focuses  on  methods  involving  intermediate  scene  representations.  In  contrast  to  end-to-end  approaches,  AI  systems  with  intermediate  explicit  scene  representations  comprise  two  distinct  modules:  one  for  raw  input  sensor  processing  and  a  second  one  for  planning  and  acting.  Agents  utilizing  scene  representations  offer  several  advantages,  including  reduced  susceptibility  to  the  forgetting  effect  observed  in  their  RNN  counterparts,  easier  incorporation  of  inductive  bias  directly  into  the  representations  (e.g.,  geometrical  constraints),  and  improved  interpretability.Towards  this  end,  this  thesis  serves  as  an  investigation  towards  the  design  of  such  scene  representations.  We  specifically  research  how  to  leverage  3D  mapping  techniques  in  order  to  build  rich,  dense  and  useful  representations  for  Embodied  AI  applications.  We  start  by  studying  representations  in  the  form  of  2D  topdown  metric  maps.  These  2D  maps  can  store  features,  labels  or  geometrical  information  to  form  a  useful  training  signal  for  the  tasks  of  semantic  mapping,  navigation  or  question  answering.  We  then  study  3D  representations  in  the  forms  of  implicit  maps  applied  for  SLAM  and  3D  object-based  maps  for  multi-object  re-identification.  Next  we  extend  our  research  to  dynamic  scenes  and  explore  4D  representations  in  the  form  of  localized  keyframes.  Finally,  the  thesis  also  explores  connections  between  these  different  representations  while  highlighting  their  strengths  and  limitations.
■590    ▼aSchool  code:  0078.
■650  4▼aEpisodic  memory
■650  4▼aSemantics
■653    ▼a3D  mapping  techniques
■653    ▼aGeometrical  information
■690    ▼a0800
■71020▼aGeorgia  Institute  of  Technology.
■7730  ▼tDissertations  Abstracts  International▼g87-06B.
■790    ▼a0078
■791    ▼aPh.D.
■792    ▼a2023
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17365961▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

Preview

Export

ChatGPT Discussion

AI Recommended Related Books


    New Books MORE
    Statistics for the past 3 years. Go to brief

    Подробнее информация.

    • Бронирование
    • не существует
    • моя папка
    • Первый запрос зрения
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    материал
    Reg No. Количество платежных Местоположение статус Ленд информации
    TF15741 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Бронирование доступны в заимствований книги. Чтобы сделать предварительный заказ, пожалуйста, нажмите кнопку бронирование

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.