본문

서브메뉴

Learning Generalizable Robot Policies by Understanding Semantics and Logic from Task Demonstrations
Learning Generalizable Robot Policies by Understanding Semantics and Logic from Task Demon...
Learning Generalizable Robot Policies by Understanding Semantics and Logic from Task Demonstrations

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20250211150925
ISBN  
9798381974874
DDC  
621.3
저자명  
Wang, Tianyu.
서명/저자  
Learning Generalizable Robot Policies by Understanding Semantics and Logic from Task Demonstrations
발행사항  
[Sl] : University of California, San Diego, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
151 p
주기사항  
Source: Dissertations Abstracts International, Volume: 85-10, Section: B.
주기사항  
Advisor: Atanasov, Nikolay.
학위논문주기  
Thesis (Ph.D.)--University of California, San Diego, 2024.
초록/해제  
요약Autonomous robots have the potential to play a critical role in various aspects of modern life, including search and rescue, autonomous driving, medical surgery, agricultural farms, etc. Reinforcement learning algorithms allow intelligent agents to discover optimal behavior through trial and error from the interactions with the environment and have been successfully applied to playing video games, mastering the game of Go and training large language models. In robotics, this data driven learning approach is also promising for locomotion, manipulation and navigation. When demonstrations are available, an agent can learn to perform a task by imitating expert behavior. However, the agent has to generalize to novel scenarios that are not seen in training. This thesis introduces two aspects to learn generalizable policies from demonstrations. The first method infers a cost function from semantic and geometric information from observations and can generalize to unseen, dynamic, partially observable simulated environments for autonomous driving scenarios. The second method infers task logic from demonstrations which are in turn used as constraints for motion planning. It exploits the hierarchical logic structure from demonstrated trajectories and can generalize to sequential, compositional planning problems.Another challenge towards deploying robots in the natural world is the ability to bridge the simulation to reality gap. While simulation provides training data at low cost, the policy should be able to account for mismatches in sensing and actuation when deployed on real robots. To address these challenges, this dissertation introduces a latent space alignment approach where policies trained on a source robot can be adapted to a target robot of different embodiments. Finally, this dissertation also presents a sim-to-real method for throwing and catching objects with bimanual robots, where they need to cooperate precisely to interact with diverse objects at high speed.
일반주제명  
Electrical engineering
일반주제명  
Computer engineering
일반주제명  
Robotics
키워드  
Autonomous robots
키워드  
Reinforcement learning algorithms
키워드  
Motion planning
기타저자  
University of California, San Diego Electrical and Computer Engineering
기본자료저록  
Dissertations Abstracts International. 85-10B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017160169
■00520250211150925
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798381974874
■035    ▼a(MiAaPQ)AAI30988450
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a621.3
■1001  ▼aWang,  Tianyu.
■24510▼aLearning  Generalizable  Robot  Policies  by  Understanding  Semantics  and  Logic  from  Task  Demonstrations
■260    ▼a[Sl]▼bUniversity  of  California,  San  Diego▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a151  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-10,  Section:  B.
■500    ▼aAdvisor:  Atanasov,  Nikolay.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  San  Diego,  2024.
■520    ▼aAutonomous  robots  have  the  potential  to  play  a  critical  role  in  various  aspects  of  modern  life,  including  search  and  rescue,  autonomous  driving,  medical  surgery,  agricultural  farms,  etc.  Reinforcement  learning  algorithms  allow  intelligent  agents  to  discover  optimal  behavior  through  trial  and  error  from  the  interactions  with  the  environment  and  have  been  successfully  applied  to  playing  video  games,  mastering  the  game  of  Go  and  training  large  language  models.  In  robotics,  this  data  driven  learning  approach  is  also  promising  for  locomotion,  manipulation  and  navigation.    When  demonstrations  are  available,  an  agent  can  learn  to  perform  a  task  by  imitating  expert  behavior.  However,  the  agent  has  to  generalize  to  novel  scenarios  that  are  not  seen  in  training.  This  thesis  introduces  two  aspects  to  learn  generalizable  policies  from  demonstrations.  The  first  method  infers  a  cost  function  from  semantic  and  geometric  information  from  observations  and  can  generalize  to  unseen,  dynamic,  partially  observable  simulated  environments  for  autonomous  driving  scenarios.  The  second  method  infers  task  logic  from  demonstrations  which  are  in  turn  used  as  constraints  for  motion  planning.  It  exploits  the  hierarchical  logic  structure  from  demonstrated  trajectories  and  can  generalize  to  sequential,  compositional  planning  problems.Another  challenge  towards  deploying  robots  in  the  natural  world  is  the  ability  to  bridge  the  simulation  to  reality  gap.  While  simulation  provides  training  data  at  low  cost,  the  policy  should  be  able  to  account  for  mismatches  in  sensing  and  actuation  when  deployed  on  real  robots.  To  address  these  challenges,  this  dissertation  introduces  a  latent  space  alignment  approach  where  policies  trained  on  a  source  robot  can  be  adapted  to  a  target  robot  of  different  embodiments.  Finally,  this  dissertation  also  presents  a  sim-to-real  method  for  throwing  and  catching  objects  with  bimanual  robots,  where  they  need  to  cooperate  precisely  to  interact  with  diverse  objects  at  high  speed.
■590    ▼aSchool  code:  0033.
■650  4▼aElectrical  engineering
■650  4▼aComputer  engineering
■650  4▼aRobotics
■653    ▼aAutonomous  robots
■653    ▼aReinforcement  learning  algorithms
■653    ▼aMotion  planning
■690    ▼a0544
■690    ▼a0464
■690    ▼a0771
■71020▼aUniversity  of  California,  San  Diego▼bElectrical  and  Computer  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g85-10B.
■790    ▼a0033
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17160169▼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
    TF10290 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.