본문

서브메뉴

Multi-Modal Perception With Vision, Language, and Touch for Robot Manipulation
Multi-Modal Perception With Vision, Language, and Touch for Robot Manipulation
Multi-Modal Perception With Vision, Language, and Touch for Robot Manipulation

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202103017
ISBN  
9798288861758
DDC  
629.8
저자명  
Huang, Huang.
서명/저자  
Multi-Modal Perception With Vision, Language, and Touch for Robot Manipulation
발행사항  
[Sl] : University of California, Berkeley, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
251 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-01, Section: B.
주기사항  
Advisor: Goldberg, Ken.
학위논문주기  
Thesis (Ph.D.)--University of California, Berkeley, 2025.
초록/해제  
요약Humans use multiple senses to interact with the environments in daily life. Visions are used for perceiving and understanding the environments. Body awareness is used for positioning. Language is used for communicating and semantic understanding, and touch is used for con- tact feedback. Similarly, robots need the same kind of sensory integration for manipulation tasks in unstructured, real-world environments. This thesis explores how combining these various sensory inputs can improve robots' ability to manipulate objects in the real world. By integrating vision (which gives the robot detailed spatial info), proprioception (providing feedback on body positioning), language (for understanding and following instructions), and touch (for precise contact details), I develop safe, efficient, and generalizable robot systems. I present a series of contributions spanning sensorimotor control, motion planning, imitation learning, mechanical search, contact-rich manipulation, and multi-modal alignment, with a focus on improving robots' ability to perceive, reason, and act beyond the limitations of a single sensory modality.I start by exploring vision and proprioception integration to enhance control under distribution shifts and improve planning efficiency through diffusion-based trajectory generation. I introduce in-context imitation learning via next-token prediction, enabling prompt-driven adaptation to novel tasks. Vision and language is then incorporated to improve mechanical search for occluded objects and general manipulation. By leveraging large vision-language models, I demonstrate improved semantic reasoning, resulting in more effective manipulation strategies. I then investigate touch sensing in precise manipulation tasks such as industrial insertion and garment handling, enabling self-supervised policy learning and visuo-tactile pretraining that significantly improve task success rates. Finally, I introduce a novel dataset aligning vision, touch, and language to facilitate multi-modal learning for robotics.Through theoretical analysis, simulation, and real-world experiments, this thesis demonstrates how multi-modal perception enhances generalization, adaptability, and safety in robot manipulation.
일반주제명  
Robotics
일반주제명  
Computer engineering
키워드  
Multi-modal perception
키워드  
Robot learning
키워드  
Vision language action models
기타저자  
University of California, Berkeley Electrical Engineering & Computer Sciences
기본자료저록  
Dissertations Abstracts International. 87-01B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017356686
■00520260202103017
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798288861758
■035    ▼a(MiAaPQ)AAI31843883
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a629.8
■1001  ▼aHuang,  Huang.
■24510▼aMulti-Modal  Perception  With  Vision,  Language,  and  Touch  for  Robot  Manipulation
■260    ▼a[Sl]▼bUniversity  of  California,  Berkeley▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a251  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-01,  Section:  B.
■500    ▼aAdvisor:  Goldberg,  Ken.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Berkeley,  2025.
■520    ▼aHumans  use  multiple  senses  to  interact  with  the  environments  in  daily  life.  Visions  are  used  for  perceiving  and  understanding  the  environments.  Body  awareness  is  used  for  positioning.  Language  is  used  for  communicating  and  semantic  understanding,  and  touch  is  used  for  con-  tact  feedback.  Similarly,  robots  need  the  same  kind  of  sensory  integration  for  manipulation  tasks  in  unstructured,  real-world  environments.  This  thesis  explores  how  combining  these  various  sensory  inputs  can  improve  robots'  ability  to  manipulate  objects  in  the  real  world.  By  integrating  vision  (which  gives  the  robot  detailed  spatial  info),  proprioception  (providing  feedback  on  body  positioning),  language  (for  understanding  and  following  instructions),  and  touch  (for  precise  contact  details),  I  develop  safe,  efficient,  and  generalizable  robot  systems.  I  present  a  series  of  contributions  spanning  sensorimotor  control,  motion  planning,  imitation  learning,  mechanical  search,  contact-rich  manipulation,  and  multi-modal  alignment,  with  a  focus  on  improving  robots'  ability  to  perceive,  reason,  and  act  beyond  the  limitations  of  a  single  sensory  modality.I  start  by  exploring  vision  and  proprioception  integration  to  enhance  control  under  distribution  shifts  and  improve  planning  efficiency  through  diffusion-based  trajectory  generation.  I  introduce  in-context  imitation  learning  via  next-token  prediction,  enabling  prompt-driven  adaptation  to  novel  tasks.  Vision  and  language  is  then  incorporated  to  improve  mechanical  search  for  occluded  objects  and  general  manipulation.  By  leveraging  large  vision-language  models,  I  demonstrate  improved  semantic  reasoning,  resulting  in  more  effective  manipulation  strategies.  I  then  investigate  touch  sensing  in  precise  manipulation  tasks  such  as  industrial  insertion  and  garment  handling,  enabling  self-supervised  policy  learning  and  visuo-tactile  pretraining  that  significantly  improve  task  success  rates.  Finally,  I  introduce  a  novel  dataset  aligning  vision,  touch,  and  language  to  facilitate  multi-modal  learning  for  robotics.Through  theoretical  analysis,  simulation,  and  real-world  experiments,  this  thesis  demonstrates  how  multi-modal  perception  enhances  generalization,  adaptability,  and  safety  in  robot  manipulation.
■590    ▼aSchool  code:  0028.
■650  4▼aRobotics
■650  4▼aComputer  engineering
■653    ▼aMulti-modal  perception
■653    ▼aRobot  learning
■653    ▼aVision  language  action  models
■690    ▼a0771
■690    ▼a0464
■71020▼aUniversity  of  California,  Berkeley▼bElectrical  Engineering  &  Computer  Sciences.
■7730  ▼tDissertations  Abstracts  International▼g87-01B.
■790    ▼a0028
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17356686▼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
    TF15967 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.