서브메뉴
검색
Rethinking the Safety Case for Risk-Aware Social Embodied Intelligence
Rethinking the Safety Case for Risk-Aware Social Embodied Intelligence
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202103209
- ISBN
- 9798315741718
- DDC
- 629.8
- 저자명
- Patrikar, Jay.
- 서명/저자
- Rethinking the Safety Case for Risk-Aware Social Embodied Intelligence
- 발행사항
- [Sl] : Carnegie Mellon University, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 156 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-11, Section: B.
- 주기사항
- Advisor: Scherer, Sebastian.
- 학위논문주기
- Thesis (Ph.D.)--Carnegie Mellon University, 2025.
- 초록/해제
- 요약Achieving real-world robot safety requires more than avoiding risk-it demands embracing and managing it effectively. This thesis presents a safety case for risk-aware decision-making and behavior modeling in complex, multi-agent environments such as aviation and autonomous driving. We argue that safety stems from an agent's ability to anticipate uncertainty, reason about intent, and act within operational boundaries defined by prior knowledge, rules of the road, social context, and historical precedent.To enable safe and interpretable decision-making, we integrate MCTS with logic specification to improve rule adherence into learned policies for both single and multi-agent settings. We develop symbolic rule-mining methods using inductive logic programming, extracting interpretable constraints from both trajectories and crash reports. To address out-of-distribution risk, we propose a fusion framework that combines neural imitation learning with symbolic rule-based systems. Finally, to mitigate modelling risks we will talk about combining RAG with crash reports for grounded action arbitrations in complex settings.To support learning from real-world behavior within aviation, we introduce three datasets: TrajAir, a social aerial navigation dataset; TartanAviation, a time-synced multimodal dataset for intent inference; and Amelia-48, a large-scale airport surface movement dataset across U.S. airports, enabling predictive analytics in air traffic management.Together, these contributions and the tools developed along the way enable autonomous systems to reason under uncertainty, incorporate diverse priors, and operate reliably in complex, real-world settings.
- 일반주제명
- Robotics
- 일반주제명
- Aerospace engineering
- 키워드
- Aviation
- 키워드
- Neurosymbolic AI
- 기타저자
- Carnegie Mellon University Robotics Institute
- 기본자료저록
- Dissertations Abstracts International. 86-11B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017357334
■00520260202103209
■006m o d
■007cr#unu||||||||
■020 ▼a9798315741718
■035 ▼a(MiAaPQ)AAI32000711
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a629.8
■1001 ▼aPatrikar, Jay.
■24510▼aRethinking the Safety Case for Risk-Aware Social Embodied Intelligence
■260 ▼a[Sl]▼bCarnegie Mellon University▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a156 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-11, Section: B.
■500 ▼aAdvisor: Scherer, Sebastian.
■5021 ▼aThesis (Ph.D.)--Carnegie Mellon University, 2025.
■520 ▼aAchieving real-world robot safety requires more than avoiding risk-it demands embracing and managing it effectively. This thesis presents a safety case for risk-aware decision-making and behavior modeling in complex, multi-agent environments such as aviation and autonomous driving. We argue that safety stems from an agent's ability to anticipate uncertainty, reason about intent, and act within operational boundaries defined by prior knowledge, rules of the road, social context, and historical precedent.To enable safe and interpretable decision-making, we integrate MCTS with logic specification to improve rule adherence into learned policies for both single and multi-agent settings. We develop symbolic rule-mining methods using inductive logic programming, extracting interpretable constraints from both trajectories and crash reports. To address out-of-distribution risk, we propose a fusion framework that combines neural imitation learning with symbolic rule-based systems. Finally, to mitigate modelling risks we will talk about combining RAG with crash reports for grounded action arbitrations in complex settings.To support learning from real-world behavior within aviation, we introduce three datasets: TrajAir, a social aerial navigation dataset; TartanAviation, a time-synced multimodal dataset for intent inference; and Amelia-48, a large-scale airport surface movement dataset across U.S. airports, enabling predictive analytics in air traffic management.Together, these contributions and the tools developed along the way enable autonomous systems to reason under uncertainty, incorporate diverse priors, and operate reliably in complex, real-world settings.
■590 ▼aSchool code: 0041.
■650 4▼aRobotics
■650 4▼aAerospace engineering
■653 ▼aAir traffic management
■653 ▼aAviation
■653 ▼aNeurosymbolic AI
■653 ▼aSocial navigation
■653 ▼aTrajectory prediction
■653 ▼aUncertainty quantification
■690 ▼a0771
■690 ▼a0538
■690 ▼a0800
■71020▼aCarnegie Mellon University▼bRobotics Institute.
■7730 ▼tDissertations Abstracts International▼g86-11B.
■790 ▼a0041
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17357334▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
