본문

서브메뉴

Perceiving and Simulating Human-World Interactions for Egocentric Agents
Perceiving and Simulating Human-World Interactions for Egocentric Agents
Perceiving and Simulating Human-World Interactions for Egocentric Agents

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105622
ISBN  
9798265427540
DDC  
530
저자명  
Pan, Boxiao.
서명/저자  
Perceiving and Simulating Human-World Interactions for Egocentric Agents
발행사항  
[Sl] : Stanford University, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
121 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-05, Section: B.
주기사항  
Advisor: Guibas, Leonidas.
학위논문주기  
Thesis (Ph.D.)--Stanford University, 2025.
초록/해제  
요약The research in this dissertation is motivated by the challenge of building computational systems that can perceive, understand, and interact with the world from a first-person, or egocentric, perspective. The central premise of this work is that the egocentric viewpoint is fundamental for creating technologies enabling entities that can effectively and safely collaborate with people in their daily environments, from augmented reality assistants to mobile robots.A principal impediment to progress in this domain is the scarcity of large-scale, diverse datasets that provide the necessary supervision for training robust models. Specifically, there is a need for data that concurrently captures rich, first-person sensory inputs with their corresponding three-dimensional world states and actions. The difficulty in acquiring and annotating such data at scale motivated the primary technical challenges that this thesis aims to address.To overcome this data scarcity problem, the research presented here is structured around the paradigm of a "perception-simulation loop". This framework treats perception and simulation as symbiotic and complementary processes, where each can be used to improve the other. The contributions of this dissertation are therefore organized into two main parts, each investigating a different arc of this loop.The first part of the thesis focuses on perception, investigating methods that learn directly from egocentric visual data. The work on COPILOT explores the use of large-scale synthetic data for near-term collision prediction, while the work on LookOut leverages targeted real-world data collection to model longer-term navigational intent in dynamic environments. The second part of the thesis shifts to simulation and modeling, exploring the use of strong priors to generate plausible human-world interactions. Here, MultiPhys demonstrates a physics-based approach to refining multi-person motion estimates, while ActAnywhere introduces a data-driven approach, using a generative model trained on large-scale video to synthesize semantically coherent scenes.Collectively, these projects demonstrate a multi-faceted strategy for mitigating the data scarcity problem in egocentric perception and simulation. The thesis concludes with a summary of these contributions and a discussion of promising future research directions. I hope that the methods and insights presented here will contribute to the development of more powerful, robust, safe, and intuitive interactive systems.
일반주제명  
Spacetime
일반주제명  
Visualization
일반주제명  
Theoretical physics
기타저자  
Stanford University.
기본자료저록  
Dissertations Abstracts International. 87-05B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017360809
■00520260202105622
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798265427540
■035    ▼a(MiAaPQ)AAI32316518
■035    ▼a(MiAaPQ)Stanfordmj570dn8359
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a530
■1001  ▼aPan,  Boxiao.
■24510▼aPerceiving  and  Simulating  Human-World  Interactions  for  Egocentric  Agents
■260    ▼a[Sl]▼bStanford  University▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a121  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-05,  Section:  B.
■500    ▼aAdvisor:  Guibas,  Leonidas.
■5021  ▼aThesis  (Ph.D.)--Stanford  University,  2025.
■520    ▼aThe  research  in  this  dissertation  is  motivated  by  the  challenge  of  building  computational  systems  that  can  perceive,  understand,  and  interact  with  the  world  from  a  first-person,  or  egocentric,  perspective.  The  central  premise  of  this  work  is  that  the  egocentric  viewpoint  is  fundamental  for  creating  technologies  enabling  entities  that  can  effectively  and  safely  collaborate  with  people  in  their  daily  environments,  from  augmented  reality  assistants  to  mobile  robots.A  principal  impediment  to  progress  in  this  domain  is  the  scarcity  of  large-scale,  diverse  datasets  that  provide  the  necessary  supervision  for  training  robust  models.  Specifically,  there  is  a  need  for  data  that  concurrently  captures  rich,  first-person  sensory  inputs  with  their  corresponding  three-dimensional  world  states  and  actions.  The  difficulty  in  acquiring  and  annotating  such  data  at  scale  motivated  the  primary  technical  challenges  that  this  thesis  aims  to  address.To  overcome  this  data  scarcity  problem,  the  research  presented  here  is  structured  around  the  paradigm  of  a  "perception-simulation  loop".  This  framework  treats  perception  and  simulation  as  symbiotic  and  complementary  processes,  where  each  can  be  used  to  improve  the  other.  The  contributions  of  this  dissertation  are  therefore  organized  into  two  main  parts,  each  investigating  a  different  arc  of  this  loop.The  first  part  of  the  thesis  focuses  on  perception,  investigating  methods  that  learn  directly  from  egocentric  visual  data.  The  work  on  COPILOT  explores  the  use  of  large-scale  synthetic  data  for  near-term  collision  prediction,  while  the  work  on  LookOut  leverages  targeted  real-world  data  collection  to  model  longer-term  navigational  intent  in  dynamic  environments.  The  second  part  of  the  thesis  shifts  to  simulation  and  modeling,  exploring  the  use  of  strong  priors  to  generate  plausible  human-world  interactions.  Here,  MultiPhys  demonstrates  a  physics-based  approach  to  refining  multi-person  motion  estimates,  while  ActAnywhere  introduces  a  data-driven  approach,  using  a  generative  model  trained  on  large-scale  video  to  synthesize  semantically  coherent  scenes.Collectively,  these  projects  demonstrate  a  multi-faceted  strategy  for  mitigating  the  data  scarcity  problem  in  egocentric  perception  and  simulation.  The  thesis  concludes  with  a  summary  of  these  contributions  and  a  discussion  of  promising  future  research  directions.  I  hope  that  the  methods  and  insights  presented  here  will  contribute  to  the  development  of  more  powerful,  robust,  safe,  and  intuitive  interactive  systems.
■590    ▼aSchool  code:  0212.
■650  4▼aSpacetime
■650  4▼aVisualization
■650  4▼aTheoretical  physics
■690    ▼a0753
■71020▼aStanford  University.
■7730  ▼tDissertations  Abstracts  International▼g87-05B.
■790    ▼a0212
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17360809▼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
    TF18264 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.