본문

서브메뉴

Learning Universal Humanoid Control
Learning Universal Humanoid Control
Learning Universal Humanoid Control

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202103821
ISBN  
9798280753334
DDC  
629.8
저자명  
Luo, Zhengyi.
서명/저자  
Learning Universal Humanoid Control
발행사항  
[Sl] : Carnegie Mellon University, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
197 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-12, Section: B.
주기사항  
Advisor: Kitani, Kris.
학위논문주기  
Thesis (Ph.D.)--Carnegie Mellon University, 2025.
초록/해제  
요약Since infancy, humans acquire motor skills, behavioral priors, and objectives by learning from their caregivers. Similarly, as we create humanoids in our own image, we aspire for them to learn from us and develop universal physical and cognitive capabilities that are comparable to, or even surpass, our own. In this thesis, we explore how to equip humanoids with the mobility, dexterity, and environmental awareness necessary to perform meaningful tasks. Unlike previous efforts that focus on learning a narrow set of tasks, such as traversing terrains, imitating a few human motion clips, or playing a single game, we emphasize scaling humanoid control tasks by leveraging large-scale human data (e.g., motion, videos). We show that scaling brings numerous benefits, gradually moving us closer to achieving truly "universal" capabilities.Our key idea centers around scaling up humanoid motion tracking and forming a foundational humanoid control prior that can be used to speed up task learning. Just like young animals are born with the instinct to walk, run, and grasp, we wish to equip humanoids with motor control priors that lead to human-like movement. We begin by scaling the reinforcement learning based motion tracking framework, enabling humanoids to imitate large-scale kinematic human motion datasets. This motion imitator forms the basis for acquiring motor skills: given a kinematic reference motion, the imitator can robustly control the humanoid to execute everyday activities and more complex, dynamic movements. Such a motion imitator can be used for human pose estimation, teleoperation, and controlling simulated avatars using first-person and third-person cameras.Equipped with such a motion tracker, we distill behaviors from the tracker into a compact, physics-based control latent space and form a general-purpose humanoid control prior. This prior enables the reuse of previously learned motor skills from a large-scale dataset. Randomly sampling from this latent space leads to human-like behaviors from the humanoid. Leveraging this latent representation in hierarchical reinforcement learning significantly improves sample efficiency and produces human-like motion. A critical aspect of this framework is ensuring that the latent space faithfully encapsulates the full range of motor skills present in the source dataset-a property we verify empirically.Building upon such a humanoid control prior, we study simulated humanoids equipped with dexterous hands, touch sensors, and vision to interact with their environments and manipulate objects. We find that our control prior significantly simplifies the training process for manipulation tasks, and we can learn policies that generalize across diverse sets of objects and scenes. Along the way, we solve practical problems involved in humanoid dexterous manipulation and perception-int-the-loop control.Finally, we take a step toward real-world deployment by transferring this framework to physical humanoids. As a first milestone, we train a universal humanoid motion tracker that runs in real time and can be used for humanoid teleoperation. This real-world deployment highlights the practicality of our approach and sets the stage for future work in learning universal controllers for real humanoids.
일반주제명  
Robotics
일반주제명  
Computer science
키워드  
Computer graphics
키워드  
Computer vision
키워드  
Humanoid control
키워드  
Reinforcement learning
기타저자  
Carnegie Mellon University Robotics Institute
기본자료저록  
Dissertations Abstracts International. 86-12B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017358256
■00520260202103821
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798280753334
■035    ▼a(MiAaPQ)AAI32038410
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a629.8
■1001  ▼aLuo,  Zhengyi.▼0(orcid)0000-0002-1842-7622
■24510▼aLearning  Universal  Humanoid  Control
■260    ▼a[Sl]▼bCarnegie  Mellon  University▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a197  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-12,  Section:  B.
■500    ▼aAdvisor:  Kitani,  Kris.
■5021  ▼aThesis  (Ph.D.)--Carnegie  Mellon  University,  2025.
■520    ▼aSince  infancy,  humans  acquire  motor  skills,  behavioral  priors,  and  objectives  by  learning  from  their  caregivers.  Similarly,  as  we  create  humanoids  in  our  own  image,  we  aspire  for  them  to  learn  from  us  and  develop  universal  physical  and  cognitive  capabilities  that  are  comparable  to,  or  even  surpass,  our  own.  In  this  thesis,  we  explore  how  to  equip  humanoids  with  the  mobility,  dexterity,  and  environmental  awareness  necessary  to  perform  meaningful  tasks.  Unlike  previous  efforts  that  focus  on  learning  a  narrow  set  of  tasks,  such  as  traversing  terrains,  imitating  a  few  human  motion  clips,  or  playing  a  single  game,  we  emphasize  scaling  humanoid  control  tasks  by  leveraging  large-scale  human  data  (e.g.,  motion,  videos).  We  show  that  scaling  brings  numerous  benefits,  gradually  moving  us  closer  to  achieving  truly  "universal"  capabilities.Our  key  idea  centers  around  scaling  up  humanoid  motion  tracking  and  forming  a  foundational  humanoid  control  prior  that  can  be  used  to  speed  up  task  learning.  Just  like  young  animals  are  born  with  the  instinct  to  walk,  run,  and  grasp,  we  wish  to  equip  humanoids  with  motor  control  priors  that  lead  to  human-like  movement.  We  begin  by  scaling  the  reinforcement  learning  based  motion  tracking  framework,  enabling  humanoids  to  imitate  large-scale  kinematic  human  motion  datasets.  This  motion  imitator  forms  the  basis  for  acquiring  motor  skills:  given  a  kinematic  reference  motion,  the  imitator  can  robustly  control  the  humanoid  to  execute  everyday  activities  and  more  complex,  dynamic  movements.  Such  a  motion  imitator  can  be  used  for  human  pose  estimation,  teleoperation,  and  controlling  simulated  avatars  using  first-person  and  third-person  cameras.Equipped  with  such  a  motion  tracker,  we  distill  behaviors  from  the  tracker  into  a  compact,  physics-based  control  latent  space  and  form  a  general-purpose  humanoid  control  prior.  This  prior  enables  the  reuse  of  previously  learned  motor  skills  from  a  large-scale  dataset.  Randomly  sampling  from  this  latent  space  leads  to  human-like  behaviors  from  the  humanoid.  Leveraging  this  latent  representation  in  hierarchical  reinforcement  learning  significantly  improves  sample  efficiency  and  produces  human-like  motion.  A  critical  aspect  of  this  framework  is  ensuring  that  the  latent  space  faithfully  encapsulates  the  full  range  of  motor  skills  present  in  the  source  dataset-a  property  we  verify  empirically.Building  upon  such  a  humanoid  control  prior,  we  study  simulated  humanoids  equipped  with  dexterous  hands,  touch  sensors,  and  vision  to  interact  with  their  environments  and  manipulate  objects.  We  find  that  our  control  prior  significantly  simplifies  the  training  process  for  manipulation  tasks,  and  we  can  learn  policies  that  generalize  across  diverse  sets  of  objects  and  scenes.  Along  the  way,  we  solve  practical  problems  involved  in  humanoid  dexterous  manipulation  and  perception-int-the-loop  control.Finally,  we  take  a  step  toward  real-world  deployment  by  transferring  this  framework  to  physical  humanoids.  As  a  first  milestone,  we  train  a  universal  humanoid  motion  tracker  that  runs  in  real  time  and  can  be  used  for  humanoid  teleoperation.  This  real-world  deployment  highlights  the  practicality  of  our  approach  and  sets  the  stage  for  future  work  in  learning  universal  controllers  for  real  humanoids.
■590    ▼aSchool  code:  0041.
■650  4▼aRobotics
■650  4▼aComputer  science
■653    ▼aComputer  graphics
■653    ▼aComputer  vision
■653    ▼aHumanoid  control
■653    ▼aReinforcement  learning
■690    ▼a0771
■690    ▼a0984
■690    ▼a0800
■71020▼aCarnegie  Mellon  University▼bRobotics  Institute.
■7730  ▼tDissertations  Abstracts  International▼g86-12B.
■790    ▼a0041
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17358256▼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
    TF17494 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.