본문

서브메뉴

Between Pixels and Policies: Toward Interpretable Representations for (Inter)Action
Between Pixels and Policies: Toward Interpretable Representations for (Inter)Action
Between Pixels and Policies: Toward Interpretable Representations for (Inter)Action

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105103
ISBN  
9798293892969
DDC  
629.8
저자명  
Stocking, Kaylene Caswell.
서명/저자  
Between Pixels and Policies: Toward Interpretable Representations for (Inter)Action
발행사항  
[Sl] : University of California, Berkeley, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
108 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-04, Section: B.
주기사항  
Advisor: Tomlin, Claire Jennifer.
학위논문주기  
Thesis (Ph.D.)--University of California, Berkeley, 2025.
초록/해제  
요약Robots and other embodied agents use an internal representation of their surrounding environment to pick actions that are appropriate for their purpose or goal. In robotics, this representation is often computed directly from camera images by using deep learning algorithms to extract relevant high-level features. However, unlike in other computer vision applications, robot representations must support closed-loop interaction, where current actions affect future observations. Furthermore, the need for safety and transparency in robotics motivates closer scrutiny of the contents and limitations of learned representations.This dissertation argues that performant and interpretable robot representations are a goal of both scientific interest and practical importance. Two possible paths toward these representations are new representation learning algorithms that are engineered with interpretability in mind ("design"), and better tools for improving our understanding of the representations learned by existing algorithms ("interpretation"). However, current techniques fall far short of the goal of both strong learning performance and deep mechanistic understanding. This dissertation describes research that advances the state of the art along both paths. Part I proposes two algorithms that learn symbolic representations that facilitate a robot's ability to reason about other agents. By focusing on more realistic settings than prior works, these chapters show that interpretable-by-design algorithms need not be limited to simple toy problems. Part II introduces interpretability tools from other disciplines to robotics for the first time, leading to novel insights about the representations learned by a deep end-to-end neural network trained for autonomous driving (similar to human drivers' representations for low-level vision but not for representations of other agents) and vision-language-action models (deeply semantic despite being fine-tuned to only output actions). A common thread throughout both parts is making connections between robot representations and the representations that support human cognition and action. Whether the design path or the interpretation path ultimately proves more fruitful, this research works toward a holistic understanding of how capable embodied agents represent their environments.
일반주제명  
Robotics
일반주제명  
Neurosciences
키워드  
Interpretability
키워드  
Machine learning
키워드  
Perception
키워드  
Representation learning
기타저자  
University of California, Berkeley Electrical Engineering & Computer Sciences
기본자료저록  
Dissertations Abstracts International. 87-04B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017359332
■00520260202105103
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798293892969
■035    ▼a(MiAaPQ)AAI32236299
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a629.8
■1001  ▼aStocking,  Kaylene  Caswell.
■24510▼aBetween  Pixels  and  Policies:  Toward  Interpretable  Representations  for  (Inter)Action
■260    ▼a[Sl]▼bUniversity  of  California,  Berkeley▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a108  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-04,  Section:  B.
■500    ▼aAdvisor:  Tomlin,  Claire  Jennifer.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Berkeley,  2025.
■520    ▼aRobots  and  other  embodied  agents  use  an  internal  representation  of  their  surrounding  environment  to  pick  actions  that  are  appropriate  for  their  purpose  or  goal.  In  robotics,  this  representation  is  often  computed  directly  from  camera  images  by  using  deep  learning  algorithms  to  extract  relevant  high-level  features.  However,  unlike  in  other  computer  vision  applications,  robot  representations  must  support  closed-loop  interaction,  where  current  actions  affect  future  observations.  Furthermore,  the  need  for  safety  and  transparency  in  robotics  motivates  closer  scrutiny  of  the  contents  and  limitations  of  learned  representations.This  dissertation  argues  that  performant  and  interpretable  robot  representations  are  a  goal  of  both  scientific  interest  and  practical  importance.  Two  possible  paths  toward  these  representations  are  new  representation  learning  algorithms  that  are  engineered  with  interpretability  in  mind  ("design"),  and  better  tools  for  improving  our  understanding  of  the  representations  learned  by  existing  algorithms  ("interpretation").  However,  current  techniques  fall  far  short  of  the  goal  of  both  strong  learning  performance  and  deep  mechanistic  understanding.  This  dissertation  describes  research  that  advances  the  state  of  the  art  along  both  paths.  Part  I  proposes  two  algorithms  that  learn  symbolic  representations  that  facilitate  a  robot's  ability  to  reason  about  other  agents.  By  focusing  on  more  realistic  settings  than  prior  works,  these  chapters  show  that  interpretable-by-design  algorithms  need  not  be  limited  to  simple  toy  problems.  Part  II  introduces  interpretability  tools  from  other  disciplines  to  robotics  for  the  first  time,  leading  to  novel  insights  about  the  representations  learned  by  a  deep  end-to-end  neural  network  trained  for  autonomous  driving  (similar  to  human  drivers'  representations  for  low-level  vision  but  not  for  representations  of  other  agents)  and  vision-language-action  models  (deeply  semantic  despite  being  fine-tuned  to  only  output  actions).  A  common  thread  throughout  both  parts  is  making  connections  between  robot  representations  and  the  representations  that  support  human  cognition  and  action.  Whether  the  design  path  or  the  interpretation  path  ultimately  proves  more  fruitful,  this  research  works  toward  a  holistic  understanding  of  how  capable  embodied  agents  represent  their  environments.
■590    ▼aSchool  code:  0028.
■650  4▼aRobotics
■650  4▼aNeurosciences
■653    ▼aInterpretability
■653    ▼aMachine  learning
■653    ▼aPerception
■653    ▼aRepresentation  learning
■690    ▼a0771
■690    ▼a0800
■690    ▼a0317
■71020▼aUniversity  of  California,  Berkeley▼bElectrical  Engineering  &  Computer  Sciences.
■7730  ▼tDissertations  Abstracts  International▼g87-04B.
■790    ▼a0028
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359332▼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
    TF15464 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.