본문

서브메뉴

Data-Centric Generalization for Robot Manipulation: Simulation, Augmentation, and Adaptation
Data-Centric Generalization for Robot Manipulation: Simulation, Augmentation, and Adaptati...
Data-Centric Generalization for Robot Manipulation: Simulation, Augmentation, and Adaptation

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202103610
ISBN  
9798288865503
DDC  
629.8
저자명  
Chen, Lawrence Yunliang.
서명/저자  
Data-Centric Generalization for Robot Manipulation: Simulation, Augmentation, and Adaptation
발행사항  
[Sl] : University of California, Berkeley, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
243 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-01, Section: B.
주기사항  
Advisor: Goldberg, Ken.
학위논문주기  
Thesis (Ph.D.)--University of California, Berkeley, 2025.
초록/해제  
요약Robot learning has made significant strides in enabling complex manipulation skills across a variety of tasks. Yet, a central challenge remains: achieving generalization. Current methods often falter when faced with unseen objects, novel embodiments, or varying environments. This dissertation addresses this challenge through data-centric approaches to enhance the generalization of robot manipulation policies, focusing on three pillars: the combined use of simulation and real-world data, training-time data augmentation, and test-time adaptation. The core thesis is that strategically leveraging and augmenting data leads to robot systems that are more data-efficient, robust, and adaptable.The first two parts investigate training-time strategies using simulation and data augmentation to build robustness into the policy. This includes bridging the reality gap through self-supervision and co-training across simulated and real-world domains, augmenting data to simulate varied robot morphologies and camera viewpoints, and leveraging simple single-arm demonstrations to train coordinated bimanual policies.The third part introduces test-time adaptation techniques that avoid costly retraining. I present methods for adapting to new objects, transferring policies across diverse robot arms, rapidly imitating novel tasks with transformers, and enabling zero-shot grasping via multi-modal models-allowing robots to handle novelty in tasks, objects, and embodiments.Through extensive simulation and real-world experiments, this dissertation shows that data-centric methods-simulation, augmentation, and adaptation-can enhance generalization across tasks, objects, and embodiments, while making robot learning more robust and efficient.
일반주제명  
Robotics
일반주제명  
Computer science
일반주제명  
Industrial engineering
키워드  
Robot learning
키워드  
Robot systems
키워드  
Data augmentation
키워드  
Data-centric methods
기타저자  
University of California, Berkeley Industrial Engineering & Operations Research
기본자료저록  
Dissertations Abstracts International. 87-01B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017357861
■00520260202103610
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798288865503
■035    ▼a(MiAaPQ)AAI32043083
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a629.8
■1001  ▼aChen,  Lawrence  Yunliang.
■24510▼aData-Centric  Generalization  for  Robot  Manipulation:  Simulation,  Augmentation,  and  Adaptation
■260    ▼a[Sl]▼bUniversity  of  California,  Berkeley▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a243  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-01,  Section:  B.
■500    ▼aAdvisor:  Goldberg,  Ken.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Berkeley,  2025.
■520    ▼aRobot  learning  has  made  significant  strides  in  enabling  complex  manipulation  skills  across  a  variety  of  tasks.  Yet,  a  central  challenge  remains:  achieving  generalization.  Current  methods  often  falter  when  faced  with  unseen  objects,  novel  embodiments,  or  varying  environments.  This  dissertation  addresses  this  challenge  through  data-centric  approaches  to  enhance  the  generalization  of  robot  manipulation  policies,  focusing  on  three  pillars:  the  combined  use  of  simulation  and  real-world  data,  training-time  data  augmentation,  and  test-time  adaptation.  The  core  thesis  is  that  strategically  leveraging  and  augmenting  data  leads  to  robot  systems  that  are  more  data-efficient,  robust,  and  adaptable.The  first  two  parts  investigate  training-time  strategies  using  simulation  and  data  augmentation  to  build  robustness  into  the  policy.  This  includes  bridging  the  reality  gap  through  self-supervision  and  co-training  across  simulated  and  real-world  domains,  augmenting  data  to  simulate  varied  robot  morphologies  and  camera  viewpoints,  and  leveraging  simple  single-arm  demonstrations  to  train  coordinated  bimanual  policies.The  third  part  introduces  test-time  adaptation  techniques  that  avoid  costly  retraining.  I  present  methods  for  adapting  to  new  objects,  transferring  policies  across  diverse  robot  arms,  rapidly  imitating  novel  tasks  with  transformers,  and  enabling  zero-shot  grasping  via  multi-modal  models-allowing  robots  to  handle  novelty  in  tasks,  objects,  and  embodiments.Through  extensive  simulation  and  real-world  experiments,  this  dissertation  shows  that  data-centric  methods-simulation,  augmentation,  and  adaptation-can  enhance  generalization  across  tasks,  objects,  and  embodiments,  while  making  robot  learning  more  robust  and  efficient.
■590    ▼aSchool  code:  0028.
■650  4▼aRobotics
■650  4▼aComputer  science
■650  4▼aIndustrial  engineering
■653    ▼aRobot  learning
■653    ▼aRobot  systems
■653    ▼aData  augmentation
■653    ▼aData-centric  methods
■690    ▼a0771
■690    ▼a0800
■690    ▼a0984
■690    ▼a0796
■690    ▼a0546
■71020▼aUniversity  of  California,  Berkeley▼bIndustrial  Engineering  &  Operations  Research.
■7730  ▼tDissertations  Abstracts  International▼g87-01B.
■790    ▼a0028
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17357861▼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
    TF14884 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.