서브메뉴
검색
Towards Human-Level Dexterity via Robot Learning
Towards Human-Level Dexterity via Robot Learning
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211153025
- ISBN
- 9798342747479
- DDC
- 629.8
- 서명/저자
- Towards Human-Level Dexterity via Robot Learning
- 발행사항
- [Sl] : Columbia University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 132 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-05, Section: B.
- 주기사항
- Advisor: Ciocarlie, Matei.
- 학위논문주기
- Thesis (Ph.D.)--Columbia University, 2024.
- 초록/해제
- 요약Dexterous intelligence-the ability to perform complex interactions with multi-fingered hands-is a pinnacle of human physical intelligence and emergent higher-order cognitive skills. However, contrary to Moravec's paradox, dexterous intelligence in humans appears simple only superficially. Many million years were spent co-evolving the human brain and hands including rich tactile sensing. Achieving human-level dexterity with robotic hands has long been a fundamental goal in robotics and represents a critical milestone toward general embodied intelligence. In this pursuit, computational sensorimotor learning has made significant progress, enabling feats such as arbitrary in-hand object reorientation. However, we observe that achieving higher levels of dexterity requires overcoming very fundamental limitations of computational sensorimotor learning.I develop robot learning methods for highly dexterous multi-fingered manipulation by directly addressing these limitations at their root cause. Chiefly, through key studies, this dissertation progressively builds an effective framework for reinforcement learning of dexterous multi-fingered manipulation skills. These methods adopt structured exploration, effectively overcoming the limitations of random exploration in reinforcement learning. The insights gained culminate in a highly effective reinforcement learning that incorporates sampling-based planning for direct exploration. Additionally, this thesis explores a new paradigm of using visuo-tactile human demonstrations for dexterity, introducing corresponding imitation learning techniques.
- 일반주제명
- Robotics
- 일반주제명
- Computer engineering
- 일반주제명
- Computer science
- 키워드
- Robot learning
- 키워드
- Tactile sensing
- 기타저자
- Columbia University Computer Science
- 기본자료저록
- Dissertations Abstracts International. 86-05B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017164633
■00520250211153025
■006m o d
■007cr#unu||||||||
■020 ▼a9798342747479
■035 ▼a(MiAaPQ)AAI31633673
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a629.8
■1001 ▼aKhandate, Gagan Muralidhar.
■24510▼aTowards Human-Level Dexterity via Robot Learning
■260 ▼a[Sl]▼bColumbia University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a132 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-05, Section: B.
■500 ▼aAdvisor: Ciocarlie, Matei.
■5021 ▼aThesis (Ph.D.)--Columbia University, 2024.
■520 ▼aDexterous intelligence-the ability to perform complex interactions with multi-fingered hands-is a pinnacle of human physical intelligence and emergent higher-order cognitive skills. However, contrary to Moravec's paradox, dexterous intelligence in humans appears simple only superficially. Many million years were spent co-evolving the human brain and hands including rich tactile sensing. Achieving human-level dexterity with robotic hands has long been a fundamental goal in robotics and represents a critical milestone toward general embodied intelligence. In this pursuit, computational sensorimotor learning has made significant progress, enabling feats such as arbitrary in-hand object reorientation. However, we observe that achieving higher levels of dexterity requires overcoming very fundamental limitations of computational sensorimotor learning.I develop robot learning methods for highly dexterous multi-fingered manipulation by directly addressing these limitations at their root cause. Chiefly, through key studies, this dissertation progressively builds an effective framework for reinforcement learning of dexterous multi-fingered manipulation skills. These methods adopt structured exploration, effectively overcoming the limitations of random exploration in reinforcement learning. The insights gained culminate in a highly effective reinforcement learning that incorporates sampling-based planning for direct exploration. Additionally, this thesis explores a new paradigm of using visuo-tactile human demonstrations for dexterity, introducing corresponding imitation learning techniques.
■590 ▼aSchool code: 0054.
■650 4▼aRobotics
■650 4▼aComputer engineering
■650 4▼aComputer science
■653 ▼aDexterous manipulation
■653 ▼aIn-hand reorientation
■653 ▼aReinforcement learning
■653 ▼aRobot learning
■653 ▼aSampling-based planning
■653 ▼aTactile sensing
■690 ▼a0771
■690 ▼a0800
■690 ▼a0984
■690 ▼a0464
■71020▼aColumbia University▼bComputer Science.
■7730 ▼tDissertations Abstracts International▼g86-05B.
■790 ▼a0054
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17164633▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.


