본문

서브메뉴

Integration of Learning-Based and Model-Based Autonomy: From System Modeling to Control Policy
Integration of Learning-Based and Model-Based Autonomy: From System Modeling to Control Po...
Integration of Learning-Based and Model-Based Autonomy: From System Modeling to Control Policy

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202103556
ISBN  
9798288862083
DDC  
621
저자명  
Li, Chenran.
서명/저자  
Integration of Learning-Based and Model-Based Autonomy: From System Modeling to Control Policy
발행사항  
[Sl] : University of California, Berkeley, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
164 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-01, Section: B.
주기사항  
Advisor: Tomizuka, Masayoshi.
학위논문주기  
Thesis (Ph.D.)--University of California, Berkeley, 2025.
초록/해제  
요약Autonomous systems operating in dynamic, uncertain, and socially interactive environments must effectively integrate learning-based and model-based methods, while reconciling data-driven and reward-driven objectives. Learning-based approaches offer flexibility and scalability but often suffer from brittleness under distribution shifts. Model-based methods provide robustness and predictive foresight, yet face challenges in modeling complex, high-dimensional dynamics. Similarly, data-driven policies trained from demonstrations may lack adaptability to new objectives, while reward-driven optimization can be inefficient and unstable without strong priors.This dissertation addresses these challenges by proposing a set of approaches that combine predictive modeling with residual Q-learning frameworks to enhance the robustness and adaptability of autonomous systems. At a high level, the work builds methods that enable autonomous agents to extract structured models from data, predict and reason about dynamic environments, and flexibly adapt their behavior to changing objectives without discarding prior knowledge.The first part of the dissertation focuses on building models from data to support reliable estimation and planning. We develop a dual estimation framework that jointly estimates latent system states and time-varying dynamic parameters in real time, enabling adaptive model-based control under changing conditions. Additionally, we propose a game-theoretic planning framework that incorporates predictive heuristics into Monte Carlo Tree Search, allowing the agent to reason about socially compliant interactions while maintaining computational efficiency in multi-agent environments.The second part of the dissertation introduces residual Q-learning as a principled mechanism for integrating data-driven behaviors with reward-driven adaptation. We formulate the policy customization problem and propose Residual Q-learning, a method that enables policies to adapt to new task objectives without requiring access to the original reward signals. We extend residual Q-learning to policy gradient methods, developing a unified structure that connects data-driven and reward-driven objectives. Finally, we integrate residual Q-learning into model-predictive path integral control, enabling fast, adaptive continuous control by combining learned priors with real-time model-based optimization.Through these, the dissertation advances scalable, adaptable, and robust decision-making frameworks for autonomous systems, bridging the gap between offline learning and real-world deployment.
일반주제명  
Mechanical engineering
일반주제명  
Computer science
일반주제명  
Robotics
키워드  
Behavior modeling
키워드  
Imitation learning
키워드  
Planning
키워드  
Reinforcement learning
기타저자  
University of California, Berkeley Mechanical Engineering
기본자료저록  
Dissertations Abstracts International. 87-01B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017357756
■00520260202103556
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798288862083
■035    ▼a(MiAaPQ)AAI32042064
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a621
■1001  ▼aLi,  Chenran.
■24510▼aIntegration  of  Learning-Based  and  Model-Based  Autonomy:  From  System  Modeling  to  Control  Policy
■260    ▼a[Sl]▼bUniversity  of  California,  Berkeley▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a164  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-01,  Section:  B.
■500    ▼aAdvisor:  Tomizuka,  Masayoshi.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Berkeley,  2025.
■520    ▼aAutonomous  systems  operating  in  dynamic,  uncertain,  and  socially  interactive  environments  must  effectively  integrate  learning-based  and  model-based  methods,  while  reconciling  data-driven  and  reward-driven  objectives.  Learning-based  approaches  offer  flexibility  and  scalability  but  often  suffer  from  brittleness  under  distribution  shifts.  Model-based  methods  provide  robustness  and  predictive  foresight,  yet  face  challenges  in  modeling  complex,  high-dimensional  dynamics.  Similarly,  data-driven  policies  trained  from  demonstrations  may  lack  adaptability  to  new  objectives,  while  reward-driven  optimization  can  be  inefficient  and  unstable  without  strong  priors.This  dissertation  addresses  these  challenges  by  proposing  a  set  of  approaches  that  combine  predictive  modeling  with  residual  Q-learning  frameworks  to  enhance  the  robustness  and  adaptability  of  autonomous  systems.  At  a  high  level,  the  work  builds  methods  that  enable  autonomous  agents  to  extract  structured  models  from  data,  predict  and  reason  about  dynamic  environments,  and  flexibly  adapt  their  behavior  to  changing  objectives  without  discarding  prior  knowledge.The  first  part  of  the  dissertation  focuses  on  building  models  from  data  to  support  reliable  estimation  and  planning.  We  develop  a  dual  estimation  framework  that  jointly  estimates  latent  system  states  and  time-varying  dynamic  parameters  in  real  time,  enabling  adaptive  model-based  control  under  changing  conditions.  Additionally,  we  propose  a  game-theoretic  planning  framework  that  incorporates  predictive  heuristics  into  Monte  Carlo  Tree  Search,  allowing  the  agent  to  reason  about  socially  compliant  interactions  while  maintaining  computational  efficiency  in  multi-agent  environments.The  second  part  of  the  dissertation  introduces  residual  Q-learning  as  a  principled  mechanism  for  integrating  data-driven  behaviors  with  reward-driven  adaptation.  We  formulate  the  policy  customization  problem  and  propose  Residual  Q-learning,  a  method  that  enables  policies  to  adapt  to  new  task  objectives  without  requiring  access  to  the  original  reward  signals.  We  extend  residual  Q-learning  to  policy  gradient  methods,  developing  a  unified  structure  that  connects  data-driven  and  reward-driven  objectives.  Finally,  we  integrate  residual  Q-learning  into  model-predictive  path  integral  control,  enabling  fast,  adaptive  continuous  control  by  combining  learned  priors  with  real-time  model-based  optimization.Through  these,  the  dissertation  advances  scalable,  adaptable,  and  robust  decision-making  frameworks  for  autonomous  systems,  bridging  the  gap  between  offline  learning  and  real-world  deployment.
■590    ▼aSchool  code:  0028.
■650  4▼aMechanical  engineering
■650  4▼aComputer  science
■650  4▼aRobotics
■653    ▼aBehavior  modeling
■653    ▼aImitation  learning
■653    ▼aPlanning
■653    ▼aReinforcement  learning
■690    ▼a0548
■690    ▼a0984
■690    ▼a0771
■690    ▼a0800
■71020▼aUniversity  of  California,  Berkeley▼bMechanical  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g87-01B.
■790    ▼a0028
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17357756▼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
    TF19311 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.