서브메뉴
검색
Autonomous Robots With Gaze-Based User Supervision
Autonomous Robots With Gaze-Based User Supervision
Detailed Information
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260311091530.5
- ISBN
- 9798270231675
- DDC
- 006.8
- 서명/저자
- Autonomous Robots With Gaze-Based User Supervision / Christina Petlowany
- 발행사항
- [Sl] : The University of Texas at Austin, 2025
- 형태사항
- 1 electronic resource (162 pages)
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-06, Section: A.
- 주기사항
- Advisors: Pryor, Mitch; Seepersad, Carolyn Committee members: Deshpande, Ashish; Hahn, Nathan; Hart, Justin.
- 학위논문주기
- - Ph.D. : The University of Texas at Austin, 2025.
- 초록/해제
- 요약Controlling a robot or multiple robots can be an arduous task. A single robot might require more than one operator, much less a group of robots. Human supervision of robots, even with increasing autonomy, is unlikely to be removed in the future. For robotics to truly make an impact there needs to be an increase in the ratio of robots to humans and lower training barriers for human supervisors, ultimately increasing the adoption of robots into new and/or less structured environments. Operating or supervising a robot is conceptually difficult. A supervisor needs to track the robot and its associated appendages and sensors and account for the difference between the task frame, robot frame, and supervisor frame. This can be difficult as humans have limited cognitive processing which is known to suffer during multitasking. Users struggle to maintain situational awareness (SA) as they oversee more robots and the robots become more autonomous. Augmented Reality (AR) provides a new paradigm of human-robot interaction, enabling supervisors to track robots with real-world context as opposed to a traditional tablet or computer interface. The Microsoft HoloLens 2 and other commercially available systems include gaze tracking intended for multi-modal interaction with a headset, but gaze also conveys information about a person's intent, emotions, cognitive load, and more. This research investigates applications of gaze in robotic systems to answer the following questions: • Gaze Granularity: what upper and lower bounds are there on task size for gaze-based interfacing? (Chapter 3) • Gaze Scalability: is gaze a useful tool in multi-robot systems? (Chapter 4 and Chapter 6) • Gaze Generality: do gaze metrics exist that are extensible to many scenarios instead of task-specific? (Chapter 5 and Chapter 6) • Gaze Online Feedback Capability: does gaze provide real-time feedback about a supervisor's perception of a robot's performance? (Chapter 6) This compilation of four separate works explores the above in different ways. Two works focus on AR user interfaces (UIs) that empower users to complete tasks-whether the task is known or unknown to the user; here, gaze is a means of direct, or explicit, interaction with a system. One work examines extensibility of the gaze interface, or understanding the range of task sizes (from small, hands-on to large, room-scale tasks) to which gaze interfaces are applicable. The other hones in on scalability, how the gaze-based interface improves user task performance with increasing numbers of autonomous agents. The next two works analyze gaze as a metric for the user's inner experience, either their navigation intent or ranking of robot performance. Both look at gaze as a general metric that applies to multiple navigation scenarios and robot tasks. These works treat gaze as an indirect, or implicit, signal for interacting with a system. The first outlines the way gaze and body language signals indicate a person's navigational intent; the second forms relationships between a supervisor's psychophysiological gaze signals and the proficiency with which a robot-or robots-performs a task.
- 언어주기
- English
- 일반주제명
- Engineering
- 일반주제명
- Communication
- 일반주제명
- Information technology
- 일반주제명
- Robotics
- 기타저자
- The University of Texas at Austin Mechanical Engineering
- 기본자료저록
- Dissertations Abstracts International. 87-06A.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260311s2025 us eng d■001000017361187
■00520260311091530.5
■006m o d
■007cr|nu||||||||
■020 ▼a9798270231675
■040 ▼aMiAaPQD▼beng▼cMiAaPQD▼erda
■082 ▼a006.8
■1001 ▼aPetlowany, Christina▼eauthor.
■24510▼aAutonomous Robots With Gaze-Based User Supervision ▼cChristina Petlowany
■260 ▼a[Sl]▼bThe University of Texas at Austin▼c2025
■264 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a1 electronic resource (162 pages)
■336 ▼atext▼btxt▼2rdacontent
■337 ▼acomputer▼bc▼2rdamedia
■338 ▼aonline resource▼bcr▼2rdacarrier
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-06, Section: A.
■500 ▼aAdvisors: Pryor, Mitch; Seepersad, Carolyn Committee members: Deshpande, Ashish; Hahn, Nathan; Hart, Justin.
■5021 ▼bPh.D.▼cThe University of Texas at Austin▼d2025.
■520 ▼aControlling a robot or multiple robots can be an arduous task. A single robot might require more than one operator, much less a group of robots. Human supervision of robots, even with increasing autonomy, is unlikely to be removed in the future. For robotics to truly make an impact there needs to be an increase in the ratio of robots to humans and lower training barriers for human supervisors, ultimately increasing the adoption of robots into new and/or less structured environments. Operating or supervising a robot is conceptually difficult. A supervisor needs to track the robot and its associated appendages and sensors and account for the difference between the task frame, robot frame, and supervisor frame. This can be difficult as humans have limited cognitive processing which is known to suffer during multitasking. Users struggle to maintain situational awareness (SA) as they oversee more robots and the robots become more autonomous. Augmented Reality (AR) provides a new paradigm of human-robot interaction, enabling supervisors to track robots with real-world context as opposed to a traditional tablet or computer interface. The Microsoft HoloLens 2 and other commercially available systems include gaze tracking intended for multi-modal interaction with a headset, but gaze also conveys information about a person's intent, emotions, cognitive load, and more. This research investigates applications of gaze in robotic systems to answer the following questions: • Gaze Granularity: what upper and lower bounds are there on task size for gaze-based interfacing? (Chapter 3) • Gaze Scalability: is gaze a useful tool in multi-robot systems? (Chapter 4 and Chapter 6) • Gaze Generality: do gaze metrics exist that are extensible to many scenarios instead of task-specific? (Chapter 5 and Chapter 6) • Gaze Online Feedback Capability: does gaze provide real-time feedback about a supervisor's perception of a robot's performance? (Chapter 6) This compilation of four separate works explores the above in different ways. Two works focus on AR user interfaces (UIs) that empower users to complete tasks-whether the task is known or unknown to the user; here, gaze is a means of direct, or explicit, interaction with a system. One work examines extensibility of the gaze interface, or understanding the range of task sizes (from small, hands-on to large, room-scale tasks) to which gaze interfaces are applicable. The other hones in on scalability, how the gaze-based interface improves user task performance with increasing numbers of autonomous agents. The next two works analyze gaze as a metric for the user's inner experience, either their navigation intent or ranking of robot performance. Both look at gaze as a general metric that applies to multiple navigation scenarios and robot tasks. These works treat gaze as an indirect, or implicit, signal for interacting with a system. The first outlines the way gaze and body language signals indicate a person's navigational intent; the second forms relationships between a supervisor's psychophysiological gaze signals and the proficiency with which a robot-or robots-performs a task.
■546 ▼aEnglish
■590 ▼aSchool code: 0227
■650 4▼aEngineering
■650 4▼aCommunication
■650 4▼aInformation technology
■650 4▼aRobotics
■653 ▼aMulti-robot systems
■653 ▼aAutonomous agents
■653 ▼aHuman-robot interaction
■653 ▼aAugmented Reality
■7102 ▼aThe University of Texas at Austin▼bMechanical Engineering.▼edegree granting institution.
■7201 ▼aPryor, Mitch▼edegree supervisor.
■7201 ▼aSeepersad, Carolyn▼edegree supervisor.
■7730 ▼tDissertations Abstracts International▼g87-06A.
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17361187▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
Preview
Export
ChatGPT Discussion
AI Recommended Related Books
Подробнее информация.
- Бронирование
- не существует
- моя папка
- Первый запрос зрения
- Non-Book Loan Application
- Nighttime Book Loan Application
Available after logging in.


