본문

서브메뉴

Large-Scale Real-World Robotic Manipulation Using Diverse Data- [electronic resource]
Large-Scale Real-World Robotic Manipulation Using Diverse Data - [electronic resource]
Large-Scale Real-World Robotic Manipulation Using Diverse Data- [electronic resource]

Detailed Information

자료유형  
 학위논문파일 국외
최종처리일시  
20240214095926
ISBN  
9798380367677
DDC  
629.8
저자명  
Ebert, Frederik D.
서명/저자  
Large-Scale Real-World Robotic Manipulation Using Diverse Data - [electronic resource]
발행사항  
[S.l.]: : University of California, Berkeley., 2022
발행사항  
Ann Arbor : : ProQuest Dissertations & Theses,, 2022
형태사항  
1 online resource(127 p.)
주기사항  
Source: Dissertations Abstracts International, Volume: 85-03, Section: B.
주기사항  
Advisor: Levine, Sergey;Finn, Chelsea.
학위논문주기  
Thesis (Ph.D.)--University of California, Berkeley, 2022.
사용제한주기  
This item must not be sold to any third party vendors.
초록/해제  
요약Recent breakthroughs in computer vision and natural language processing have been largely propelled by scaling up both dataset diversity as well as model capacity, leading to robust generalization. In this thesis I am addressing the question of 1) whether for learning-based robotic manipulation we can similarly scale up dataset diversity and model capacity in order to achieve generalization and adaptation to new scenes and environments, new objects, new tasks and even different types of robots, and 2) the question of how re-collecting data from scratch for every new task and environment can be avoided, since this often leads to poor generalization and performance. To answer these questions we propose two different methodologies, a model-based reinforcement learning approach based on video-prediction, and a model-free and imitation-learning-based approach. We collect several of the biggest robotic interaction datasets to date, and show that by leveraging and effectively reusing diverse prior datasets, we can allow an agent to generalize to never-before-seen objects, learn new tasks based on only a handful of demonstrations, and even adapt to new robot types.
일반주제명  
Robotics.
일반주제명  
Computer science.
키워드  
Robotic manipulation
키워드  
Diverse data
키워드  
Natural language processing
키워드  
Learning-based approach
기타저자  
University of California, Berkeley Electrical Engineering & Computer Sciences
기본자료저록  
Dissertations Abstracts International. 85-03B.
기본자료저록  
Dissertation Abstract International
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008240612s2022      us  |||||||||||||||c||eng  d
■001000016931148
■00520240214095926
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798380367677
■035    ▼a(MiAaPQ)AAI29327855
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a629.8
■1001  ▼aEbert,  Frederik  D.
■24510▼aLarge-Scale  Real-World  Robotic  Manipulation  Using  Diverse  Data▼h[electronic  resource]
■260    ▼a[S.l.]:▼bUniversity  of  California,  Berkeley.  ▼c2022
■260  1▼aAnn  Arbor  :▼bProQuest  Dissertations  &  Theses,  ▼c2022
■300    ▼a1  online  resource(127  p.)
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-03,  Section:  B.
■500    ▼aAdvisor:  Levine,  Sergey;Finn,  Chelsea.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Berkeley,  2022.
■506    ▼aThis  item  must  not  be  sold  to  any  third  party  vendors.
■520    ▼aRecent  breakthroughs  in  computer  vision  and  natural  language  processing  have  been  largely  propelled  by  scaling  up  both  dataset  diversity  as  well  as  model  capacity,  leading  to  robust  generalization.  In  this  thesis  I  am  addressing  the  question  of  1)  whether  for  learning-based  robotic  manipulation  we  can  similarly  scale  up  dataset  diversity  and  model  capacity  in  order  to  achieve  generalization  and  adaptation  to  new  scenes  and  environments,  new  objects,  new  tasks  and  even  different  types  of  robots,  and  2)  the  question  of  how  re-collecting  data  from  scratch  for  every  new  task  and  environment  can  be  avoided,  since  this  often  leads  to  poor  generalization  and  performance.  To  answer  these  questions  we  propose  two  different  methodologies,  a  model-based  reinforcement  learning  approach  based  on  video-prediction,  and  a  model-free  and  imitation-learning-based  approach.  We  collect  several  of  the  biggest  robotic  interaction  datasets  to  date,  and  show  that  by  leveraging  and  effectively  reusing  diverse  prior  datasets,  we  can  allow  an  agent  to  generalize  to  never-before-seen  objects,  learn  new  tasks  based  on  only  a  handful  of  demonstrations,  and  even  adapt  to  new  robot  types.
■590    ▼aSchool  code:  0028.
■650  4▼aRobotics.
■650  4▼aComputer  science.
■653    ▼aRobotic  manipulation
■653    ▼aDiverse  data
■653    ▼aNatural  language  processing
■653    ▼aLearning-based  approach
■690    ▼a0771
■690    ▼a0984
■690    ▼a0800
■71020▼aUniversity  of  California,  Berkeley▼bElectrical  Engineering  &  Computer  Sciences.
■7730  ▼tDissertations  Abstracts  International▼g85-03B.
■773    ▼tDissertation  Abstract  International
■790    ▼a0028
■791    ▼aPh.D.
■792    ▼a2022
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16931148▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.
■980    ▼a202402▼f2024

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
    TF07578 전자도서 My Folder 부재도서신고 비도서대출신청

    * 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.