서브메뉴
검색
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
- 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
- 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.


