본문

서브메뉴

Algorithms for Data-Efficient Continual Robot Learning
Algorithms for Data-Efficient Continual Robot Learning
Algorithms for Data-Efficient Continual Robot Learning

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202104722
ISBN  
9798291595497
DDC  
629.8
저자명  
Abuduweili, Abulikemu.
서명/저자  
Algorithms for Data-Efficient Continual Robot Learning
발행사항  
[Sl] : Carnegie Mellon University, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
280 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-03, Section: B.
주기사항  
Advisor: Liu, Changliu.
학위논문주기  
Thesis (Ph.D.)--Carnegie Mellon University, 2025.
초록/해제  
요약The deployment of intelligent robotic agents in complex, non-stationary human environments-such as collaborative manufacturing, autonomous driving, and long-term navigation-hinges on their ability to learn continually from a dynamic stream of real-world data. Traditional machine learning paradigms, which rely on offline training with static datasets, are fundamentally ill-suited for these settings. They are plagued by critical limitations, most notably catastrophic forgetting, where new knowledge overwrites previously learned skills; profound data inefficiency, a particularly acute problem in robotics where data collection is expensive and time-consuming; and the challenge of modeling and controlling complex nonlinear dynamics with adaptability and generalizability from limited data.This thesis presents a systematic investigation into a new class of learning algorithms designed to overcome these barriers, enabling robust and data-efficient continual learning for robots. The contributions are organized into three synergistic pillars. The first pillar, Data-Efficient Optimization, introduces novel algorithms for both online and offline learning. We develop a family of Extended Kalman Filter (EKF)-based optimizers that leverage second-order information to achieve superior convergence for online adaptation. We also improve adaptive gradient methods for offline pretraining by introducing a data-driven approach to initialize optimizer states, enhancing stability and performance. The second pillar, Continual Learning with Memory Mechanisms, addresses catastrophic forgetting through bio-inspired memory architectures. This includes a feedforward compensation strategy that proactively uses critical past experiences to improve adaptation and the BioSLAM dual-memory system, which explicitly manages short-term plasticity and long-term knowledge consolidation for lifelong place recognition. The third and culminating pillar, Models for Efficient Robot Learning, presents novel frameworks for learning generalizable system models for control. We pioneer the continual learning and lifting of Koopman dynamics, a breakthrough approach for linearizing high-dimensional, nonlinear systems like legged robots from streaming data. This pillar also investigates methods for estimating neural network robustness via Lipschitz constants, a crucial step for deploying learned models in safety-critical applications.Collectively, this body of work provides a foundational framework for creating truly adaptive, resilient, and intelligent robots. By developing solutions for data-efficient optimization, memory-augmented learning, and continual dynamics modeling, this thesis paves the way for the safe and effective deployment of autonomous systems in the open world.
일반주제명  
Robotics
일반주제명  
Electrical engineering
일반주제명  
Computer engineering
키워드  
Continual learning
키워드  
Control
키워드  
Data-efficient learning
키워드  
Neural network
키워드  
Robot learning
기타저자  
Carnegie Mellon University Electrical and Computer Engineering
기본자료저록  
Dissertations Abstracts International. 87-03B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017358582
■00520260202104722
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798291595497
■035    ▼a(MiAaPQ)AAI32121596
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a629.8
■1001  ▼aAbuduweili,  Abulikemu.▼0(orcid)0000-0002-3186-1976
■24510▼aAlgorithms  for  Data-Efficient  Continual  Robot  Learning
■260    ▼a[Sl]▼bCarnegie  Mellon  University▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a280  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-03,  Section:  B.
■500    ▼aAdvisor:  Liu,  Changliu.
■5021  ▼aThesis  (Ph.D.)--Carnegie  Mellon  University,  2025.
■520    ▼aThe  deployment  of  intelligent  robotic  agents  in  complex,  non-stationary  human  environments-such  as  collaborative  manufacturing,  autonomous  driving,  and  long-term  navigation-hinges  on  their  ability  to  learn  continually  from  a  dynamic  stream  of  real-world  data.  Traditional  machine  learning  paradigms,  which  rely  on  offline  training  with  static  datasets,  are  fundamentally  ill-suited  for  these  settings.  They  are  plagued  by  critical  limitations,  most  notably  catastrophic  forgetting,  where  new  knowledge  overwrites  previously  learned  skills;  profound  data  inefficiency,  a  particularly  acute  problem  in  robotics  where  data  collection  is  expensive  and  time-consuming;  and  the  challenge  of  modeling  and  controlling  complex  nonlinear  dynamics  with  adaptability  and  generalizability  from  limited  data.This  thesis  presents  a  systematic  investigation  into  a  new  class  of  learning  algorithms  designed  to  overcome  these  barriers,  enabling  robust  and  data-efficient  continual  learning  for  robots.  The  contributions  are  organized  into  three  synergistic  pillars.  The  first  pillar,  Data-Efficient  Optimization,  introduces  novel  algorithms  for  both  online  and  offline  learning.  We  develop  a  family  of  Extended  Kalman  Filter  (EKF)-based  optimizers  that  leverage  second-order  information  to  achieve  superior  convergence  for  online  adaptation.  We  also  improve  adaptive  gradient  methods  for  offline  pretraining  by  introducing  a  data-driven  approach  to  initialize  optimizer  states,  enhancing  stability  and  performance.  The  second  pillar,  Continual  Learning  with  Memory  Mechanisms,  addresses  catastrophic  forgetting  through  bio-inspired  memory  architectures.  This  includes  a  feedforward  compensation  strategy  that  proactively  uses  critical  past  experiences  to  improve  adaptation  and  the  BioSLAM  dual-memory  system,  which  explicitly  manages  short-term  plasticity  and  long-term  knowledge  consolidation  for  lifelong  place  recognition.  The  third  and  culminating  pillar,  Models  for  Efficient  Robot  Learning,  presents  novel  frameworks  for  learning  generalizable  system  models  for  control.  We  pioneer  the  continual  learning  and  lifting  of  Koopman  dynamics,  a  breakthrough  approach  for  linearizing  high-dimensional,  nonlinear  systems  like  legged  robots  from  streaming  data.  This  pillar  also  investigates  methods  for  estimating  neural  network  robustness  via  Lipschitz  constants,  a  crucial  step  for  deploying  learned  models  in  safety-critical  applications.Collectively,  this  body  of  work  provides  a  foundational  framework  for  creating  truly  adaptive,  resilient,  and  intelligent  robots.  By  developing  solutions  for  data-efficient  optimization,  memory-augmented  learning,  and  continual  dynamics  modeling,  this  thesis  paves  the  way  for  the  safe  and  effective  deployment  of  autonomous  systems  in  the  open  world.
■590    ▼aSchool  code:  0041.
■650  4▼aRobotics
■650  4▼aElectrical  engineering
■650  4▼aComputer  engineering
■653    ▼aContinual  learning
■653    ▼aControl
■653    ▼aData-efficient  learning
■653    ▼aNeural  network
■653    ▼aRobot  learning
■690    ▼a0771
■690    ▼a0800
■690    ▼a0544
■690    ▼a0464
■71020▼aCarnegie  Mellon  University▼bElectrical  and  Computer  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g87-03B.
■790    ▼a0041
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17358582▼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
    TF18438 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.