서브메뉴
검색
Motion and Behavior Planning for Socially Assistive Robots
Motion and Behavior Planning for Socially Assistive Robots
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202103641
- ISBN
- 9798314873854
- DDC
- 004
- 서명/저자
- Motion and Behavior Planning for Socially Assistive Robots
- 발행사항
- [Sl] : University of Michigan, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 105 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-11, Section: B.
- 주기사항
- Advisor: Ghaffari, Maani;Yang, X. Jessie.
- 학위논문주기
- Thesis (Ph.D.)--University of Michigan, 2025.
- 초록/해제
- 요약Socially Assistive Robots (SARs) are embodied and non-embodied robotic agents employed to assist humans through social interactions. As robotic technology has become sophisticated over the years, we have started seeing the acceptance and need of robots in a social space, meaningfully interacting with people. One of the major challenges of robots becoming ubiquitous in our day-to-day environments is that we need them to function in semi-structured environments designed and inhabited by humans. This thesis tackles robot behavior and motion planning when navigating around humans in complex, dynamic scenarios. We use the case of a tour guide robot as a test bed for our work.The first part focuses on tour planning with a shared map created collaboratively by Providers (managers) and Robots to guide Clients (visitors). The planner dynamically adapts routes based on constraints, highlighting the importance of shared maps in human-robot tasks.The second part explores low-level motion planning. We start with crowd navigation, designing an agent to move through groups without disrupting the human flow. We then tackle narrow crossings, using Smooth Maximum Entropy Deep Inverse Reinforcement Learning (S-MEDIRL), the robot learns from raw data to yield and avoid deadlock without relying on handcrafted heuristics.Finally, we evaluate Foundation Models in Socially Assistive settings, demonstrating a robot as a greeter and tour guide at the University of Michigan Museum of Art (UMMA). The second part explores incorporating feedback from Vision and Language Models to distinguish between qualitatively good and bad social behaviors. We evaluate the efficacy of these generalized models in supervising and improving socially aware navigation, specifically in the narrow crossing scenario.In conclusion, this thesis advances motion and behavior modules for robots in assistive settings, focusing on making them interactive and socially aware. It evaluates various components of the robotics software stack, exploring methods to enhance their effectiveness and inspire future advancements in developing socially assistive robotics.
- 일반주제명
- Computer science
- 일반주제명
- Robotics
- 일반주제명
- Engineering
- 기타저자
- University of Michigan Robotics
- 기본자료저록
- Dissertations Abstracts International. 86-11B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017358082
■00520260202103641
■006m o d
■007cr#unu||||||||
■020 ▼a9798314873854
■035 ▼a(MiAaPQ)AAI32092530
■035 ▼a(MiAaPQ)umichrackham006166
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aKathuria, Tribhi.
■24510▼aMotion and Behavior Planning for Socially Assistive Robots
■260 ▼a[Sl]▼bUniversity of Michigan▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a105 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-11, Section: B.
■500 ▼aAdvisor: Ghaffari, Maani;Yang, X. Jessie.
■5021 ▼aThesis (Ph.D.)--University of Michigan, 2025.
■520 ▼aSocially Assistive Robots (SARs) are embodied and non-embodied robotic agents employed to assist humans through social interactions. As robotic technology has become sophisticated over the years, we have started seeing the acceptance and need of robots in a social space, meaningfully interacting with people. One of the major challenges of robots becoming ubiquitous in our day-to-day environments is that we need them to function in semi-structured environments designed and inhabited by humans. This thesis tackles robot behavior and motion planning when navigating around humans in complex, dynamic scenarios. We use the case of a tour guide robot as a test bed for our work.The first part focuses on tour planning with a shared map created collaboratively by Providers (managers) and Robots to guide Clients (visitors). The planner dynamically adapts routes based on constraints, highlighting the importance of shared maps in human-robot tasks.The second part explores low-level motion planning. We start with crowd navigation, designing an agent to move through groups without disrupting the human flow. We then tackle narrow crossings, using Smooth Maximum Entropy Deep Inverse Reinforcement Learning (S-MEDIRL), the robot learns from raw data to yield and avoid deadlock without relying on handcrafted heuristics.Finally, we evaluate Foundation Models in Socially Assistive settings, demonstrating a robot as a greeter and tour guide at the University of Michigan Museum of Art (UMMA). The second part explores incorporating feedback from Vision and Language Models to distinguish between qualitatively good and bad social behaviors. We evaluate the efficacy of these generalized models in supervising and improving socially aware navigation, specifically in the narrow crossing scenario.In conclusion, this thesis advances motion and behavior modules for robots in assistive settings, focusing on making them interactive and socially aware. It evaluates various components of the robotics software stack, exploring methods to enhance their effectiveness and inspire future advancements in developing socially assistive robotics.
■590 ▼aSchool code: 0127.
■650 4▼aComputer science
■650 4▼aRobotics
■650 4▼aEngineering
■653 ▼aHuman robot interaction
■653 ▼aInverse reinforcement learning
■653 ▼aSocially aware motion planning
■653 ▼aSocially Assistive Robots
■690 ▼a0771
■690 ▼a0984
■690 ▼a0800
■690 ▼a0537
■71020▼aUniversity of Michigan▼bRobotics.
■7730 ▼tDissertations Abstracts International▼g86-11B.
■790 ▼a0127
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17358082▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.


