서브메뉴
검색
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
- 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
- Control
- 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.


