서브메뉴
검색
Human Nervous System-Based Human-Robot Collaboration in Construction
Human Nervous System-Based Human-Robot Collaboration in Construction
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202105226
- ISBN
- 9798291566596
- DDC
- 620
- 저자명
- Baek, Francis.
- 서명/저자
- Human Nervous System-Based Human-Robot Collaboration in Construction
- 발행사항
- [Sl] : University of Michigan, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 124 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-03, Section: B.
- 주기사항
- Advisor: Lee, SangHyun.
- 학위논문주기
- Thesis (Ph.D.)--University of Michigan, 2025.
- 초록/해제
- 요약Human-robot collaboration (HRC) is an emerging form of work anticipated to improve construction processes by combining human expertise with robotic automation. Human workers' (co-workers') physical, cognitive, and emotional responses can be essential to achieving productive HRC, as the responses can affect co-workers' performance and cohesion with robots. However, existing studies have primarily focused on advancing robotic capabilities alone, such as speed, precision, and autonomy, without considering their potential influence on co-workers. My research proposes human nervous system-based HRC in construction, which aims for robots to 1) understand co-workers' physical, cognitive, and emotional responses by considering human nervous system activity-which fundamentally regulates human responses-across the brain and body and 2) adapt their actions to foster desired responses in co-workers, such as positive emotions while complying with co-workers' deliberate gestures, that can contribute to achieving productive HRC. To this end, an electroencephalogram (EEG) headset and an electrodermal activity (EDA) wristband have been utilized to understand co-workers' physical, cognitive, and emotional responses during HRC. Additionally, a model-based reinforcement learning technique was applied to develop a stable and reliable response-adaptive robot behavior strategy, while a computer vision-based 2D human pose estimation technique was applied to develop a gesture recognition pipeline for reliable robot control during HRC. Major results from simulated HRC with participants and real KUKA robots in lab environments demonstrated significant variations in all participants' physical, cognitive, and emotional responses during HRC, which could affect productivity in human-robot teams, presenting the importance of considering co-workers' responses. While potential trade-offs were also identified between fostering desired co-workers' responses and maximizing team productivity, the proposed response-adaptive robot behavior strategy demonstrated its effectiveness in fostering desired responses in co-workers during simulated HRC in virtual environments, which presents the potential to balance co-workers' responses and team productivity. Moreover, the proposed gesture recognition pipeline achieved reliable performance (F1-score of 94.91%) in recognizing gestures even when people are wearing gloves and holding tools-a plausible scenario during HRC-presenting the potential to enhance communication between co-workers and robots for more productive HRC. The findings of this research are expected to serve as a solid foundation to provide insights into achieving more productive and cohesive human-robot teams in construction grounded on co-workers' well-being.
- 일반주제명
- Engineering
- 일반주제명
- Robotics
- 키워드
- Well-being
- 기타저자
- University of Michigan Civil Engineering
- 기본자료저록
- Dissertations Abstracts International. 87-03B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017359859
■00520260202105226
■006m o d
■007cr#unu||||||||
■020 ▼a9798291566596
■035 ▼a(MiAaPQ)AAI32271852
■035 ▼a(MiAaPQ)umichrackham006293
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a620
■1001 ▼aBaek, Francis.
■24510▼aHuman Nervous System-Based Human-Robot Collaboration in Construction
■260 ▼a[Sl]▼bUniversity of Michigan▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a124 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-03, Section: B.
■500 ▼aAdvisor: Lee, SangHyun.
■5021 ▼aThesis (Ph.D.)--University of Michigan, 2025.
■520 ▼aHuman-robot collaboration (HRC) is an emerging form of work anticipated to improve construction processes by combining human expertise with robotic automation. Human workers' (co-workers') physical, cognitive, and emotional responses can be essential to achieving productive HRC, as the responses can affect co-workers' performance and cohesion with robots. However, existing studies have primarily focused on advancing robotic capabilities alone, such as speed, precision, and autonomy, without considering their potential influence on co-workers. My research proposes human nervous system-based HRC in construction, which aims for robots to 1) understand co-workers' physical, cognitive, and emotional responses by considering human nervous system activity-which fundamentally regulates human responses-across the brain and body and 2) adapt their actions to foster desired responses in co-workers, such as positive emotions while complying with co-workers' deliberate gestures, that can contribute to achieving productive HRC. To this end, an electroencephalogram (EEG) headset and an electrodermal activity (EDA) wristband have been utilized to understand co-workers' physical, cognitive, and emotional responses during HRC. Additionally, a model-based reinforcement learning technique was applied to develop a stable and reliable response-adaptive robot behavior strategy, while a computer vision-based 2D human pose estimation technique was applied to develop a gesture recognition pipeline for reliable robot control during HRC. Major results from simulated HRC with participants and real KUKA robots in lab environments demonstrated significant variations in all participants' physical, cognitive, and emotional responses during HRC, which could affect productivity in human-robot teams, presenting the importance of considering co-workers' responses. While potential trade-offs were also identified between fostering desired co-workers' responses and maximizing team productivity, the proposed response-adaptive robot behavior strategy demonstrated its effectiveness in fostering desired responses in co-workers during simulated HRC in virtual environments, which presents the potential to balance co-workers' responses and team productivity. Moreover, the proposed gesture recognition pipeline achieved reliable performance (F1-score of 94.91%) in recognizing gestures even when people are wearing gloves and holding tools-a plausible scenario during HRC-presenting the potential to enhance communication between co-workers and robots for more productive HRC. The findings of this research are expected to serve as a solid foundation to provide insights into achieving more productive and cohesive human-robot teams in construction grounded on co-workers' well-being.
■590 ▼aSchool code: 0127.
■650 4▼aEngineering
■650 4▼aRobotics
■653 ▼aHuman-robot collaboration
■653 ▼aElectroencephalogram
■653 ▼aElectrodermal activity
■653 ▼aHuman-robot teams
■653 ▼aWell-being
■690 ▼a0543
■690 ▼a0537
■690 ▼a0771
■71020▼aUniversity of Michigan▼bCivil Engineering.
■7730 ▼tDissertations Abstracts International▼g87-03B.
■790 ▼a0127
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359859▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
