본문

서브메뉴

Modeling-Based Optimization for Robotic Manipulation
Modeling-Based Optimization for Robotic Manipulation
Modeling-Based Optimization for Robotic Manipulation

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211152802
ISBN  
9798384474159
DDC  
004
저자명  
Huang, Zhiao.
서명/저자  
Modeling-Based Optimization for Robotic Manipulation
발행사항  
[Sl] : University of California, San Diego, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
166 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-04, Section: B.
주기사항  
Advisor: Su, Hao;Gao, Sicun.
학위논문주기  
Thesis (Ph.D.)--University of California, San Diego, 2024.
초록/해제  
요약This dissertation explores the intersection of modeling and optimization in robotics, focusing on the development of efficient and effective systems for robotic manipulation. The primary objective is to study how to integrate modeling techniques with optimization processes, a concept we term "modeling-based optimization."We first introduce a differentiable physics simulator for soft-body manipulation, demonstrating the power of environment modeling in policy learning. By simulating elastoplastic materials such as plasticine, we benchmark reinforcement learning (RL) and gradient-based optimization methods, highlighting the strengths and limitations of each approach. The findings reveal that while gradient-based methods excel in environments with well-modeled physics, they struggle with long-term planning and multi-stage tasks.To address these challenges, we propose a reparameterized policy gradient method, which leverages latent variable models to facilitate exploration and avoid local minima. This approach integrates generative models to enhance policy expressiveness and improve performance in hard-exploration tasks. We further extend the concept of hierarchical policy modeling by introducing graph-based and vision-language-driven methods. These techniques enable robots to plan and execute long-horizon tasks by abstracting the search space and using human-like instructions to guide complex manipulations.The contributions of this thesis include the development of novel algorithms for soft-body manipulation, hierarchical policy modeling, and the integration of generative models with reinforcement learning. These advancements offer new insights into the relationship between learning, modeling, and optimization in robotics. 
일반주제명  
Computer science
일반주제명  
Information technology
일반주제명  
Robotics
키워드  
Generative modeling
키워드  
Optimization
키워드  
Robotic manipulation
키워드  
Simulation
키워드  
Soft body
기타저자  
University of California, San Diego Computer Science and Engineering
기본자료저록  
Dissertations Abstracts International. 86-04B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017163856
■00520250211152802
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798384474159
■035    ▼a(MiAaPQ)AAI31556639
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aHuang,  Zhiao.
■24510▼aModeling-Based  Optimization  for  Robotic  Manipulation
■260    ▼a[Sl]▼bUniversity  of  California,  San  Diego▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a166  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-04,  Section:  B.
■500    ▼aAdvisor:  Su,  Hao;Gao,  Sicun.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  San  Diego,  2024.
■520    ▼aThis  dissertation  explores  the  intersection  of  modeling  and  optimization  in  robotics,  focusing  on  the  development  of  efficient  and  effective  systems  for  robotic  manipulation.  The  primary  objective  is  to  study  how  to  integrate  modeling  techniques  with  optimization  processes,  a  concept  we  term  "modeling-based  optimization."We  first  introduce  a  differentiable  physics  simulator  for  soft-body  manipulation,  demonstrating  the  power  of  environment  modeling  in  policy  learning.  By  simulating  elastoplastic  materials  such  as  plasticine,  we  benchmark  reinforcement  learning  (RL)  and  gradient-based  optimization  methods,  highlighting  the  strengths  and  limitations  of  each  approach.  The  findings  reveal  that  while  gradient-based  methods  excel  in  environments  with  well-modeled  physics,  they  struggle  with  long-term  planning  and  multi-stage  tasks.To  address  these  challenges,  we  propose  a  reparameterized  policy  gradient  method,  which  leverages  latent  variable  models  to  facilitate  exploration  and  avoid  local  minima.  This  approach  integrates  generative  models  to  enhance  policy  expressiveness  and  improve  performance  in  hard-exploration  tasks.  We  further  extend  the  concept  of  hierarchical  policy  modeling  by  introducing  graph-based  and  vision-language-driven  methods.  These  techniques  enable  robots  to  plan  and  execute  long-horizon  tasks  by  abstracting  the  search  space  and  using  human-like  instructions  to  guide  complex  manipulations.The  contributions  of  this  thesis  include  the  development  of  novel  algorithms  for  soft-body  manipulation,  hierarchical  policy  modeling,  and  the  integration  of  generative  models  with  reinforcement  learning.  These  advancements  offer  new  insights  into  the  relationship  between  learning,  modeling,  and  optimization  in  robotics. 
■590    ▼aSchool  code:  0033.
■650  4▼aComputer  science
■650  4▼aInformation  technology
■650  4▼aRobotics
■653    ▼aGenerative  modeling
■653    ▼aOptimization
■653    ▼aRobotic  manipulation
■653    ▼aSimulation
■653    ▼aSoft  body
■690    ▼a0984
■690    ▼a0489
■690    ▼a0800
■690    ▼a0771
■71020▼aUniversity  of  California,  San  Diego▼bComputer  Science  and  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g86-04B.
■790    ▼a0033
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17163856▼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
    TF09894 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.