본문

서브메뉴

Safe Planning Under Uncertainty Using Surrogate Models
Safe Planning Under Uncertainty Using Surrogate Models
Safe Planning Under Uncertainty Using Surrogate Models

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202104747
ISBN  
9798290652283
DDC  
150
저자명  
Moss, Robert John.
서명/저자  
Safe Planning Under Uncertainty Using Surrogate Models
발행사항  
[Sl] : Stanford University, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
201 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-01, Section: B.
주기사항  
Advisor: Barrett, Clark;Kochenderfer, Mykel.
학위논문주기  
Thesis (Ph.D.)--Stanford University, 2025.
초록/해제  
요약To make safe decisions in real-world environments, algorithms must account for the inherent uncertainty in perception systems and agent dynamics, resulting in high-dimensional problems. The use of surrogate models to replace hand-crafted planning heuristics and avoid running the computationally expensive true system has shown promise in enabling large-scale, safe planning. This thesis introduces five main contributions to address the challenges of safe planning under uncertainty and validation. To improve planning efficiency over beliefs in partially observable Markov decision processes (POMDPs), we introduce batched belief-stateMDPs, which abstract belief-state planning using parallelizable batches of the underlying models. This abstraction requires models that can be easily parallelized; therefore, we can learn surrogate transition and observation models from data and propose the inversion variational autoencoder(I-VAE) to sample from the posterior belief given partial observations. To replace planning heuristics and enable long-horizon planning, we introduce BetaZero, a policy iteration algorithm that combines offline learning with online belief-state planning. Extending BetaZero to safety-critical problems, we propose ConstrainedZero, which solves chance-constrained POMDPs by optimizing the balance between utility and a target level of safety. Finally, given a learned safe policy, we develop a Bayesian safety validationmethod to estimate the failure probability of a black-box system using probabilistic surrogate models. We apply these algorithms to real-world problems, including aircraft collision avoidance, autonomous aircraft runway detection, safe carbon capture and storage, critical mineral exploration, robot navigation, and aerial wildfire suppression.
일반주제명  
Success
일반주제명  
Robots
일반주제명  
Adaptation
일반주제명  
Aviation
일반주제명  
Collisions
일반주제명  
Climate change
일반주제명  
Pilots
일반주제명  
Robotics
일반주제명  
Geology
일반주제명  
Aircraft
일반주제명  
Carbon sequestration
일반주제명  
Failure analysis
일반주제명  
Planning
일반주제명  
Decision making
일반주제명  
Neural networks
일반주제명  
Design
일반주제명  
Probability
기타저자  
Stanford University.
기본자료저록  
Dissertations Abstracts International. 87-01B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017358753
■00520260202104747
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798290652283
■035    ▼a(MiAaPQ)AAI32149762
■035    ▼a(MiAaPQ)Stanfordzg643rb0595
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a150
■1001  ▼aMoss,  Robert  John.
■24510▼aSafe  Planning  Under  Uncertainty  Using  Surrogate  Models
■260    ▼a[Sl]▼bStanford  University▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a201  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-01,  Section:  B.
■500    ▼aAdvisor:  Barrett,  Clark;Kochenderfer,  Mykel.
■5021  ▼aThesis  (Ph.D.)--Stanford  University,  2025.
■520    ▼aTo  make  safe  decisions  in  real-world  environments,  algorithms  must  account  for  the  inherent  uncertainty  in  perception  systems  and  agent  dynamics,  resulting  in  high-dimensional  problems.  The  use  of  surrogate  models  to  replace  hand-crafted  planning  heuristics  and  avoid  running  the  computationally  expensive  true  system  has  shown  promise  in  enabling  large-scale,  safe  planning.  This  thesis  introduces  five  main  contributions  to  address  the  challenges  of  safe  planning  under  uncertainty  and  validation.  To  improve  planning  efficiency  over  beliefs  in  partially  observable  Markov  decision  processes  (POMDPs),  we  introduce  batched  belief-stateMDPs,  which  abstract  belief-state  planning  using  parallelizable  batches  of  the  underlying  models.  This  abstraction  requires  models  that  can  be  easily  parallelized;  therefore,  we  can  learn  surrogate  transition  and  observation  models  from  data  and  propose  the  inversion  variational  autoencoder(I-VAE)  to  sample  from  the  posterior  belief  given  partial  observations.  To  replace  planning  heuristics  and  enable  long-horizon  planning,  we  introduce  BetaZero,  a  policy  iteration  algorithm  that  combines  offline  learning  with  online  belief-state  planning.  Extending  BetaZero  to  safety-critical  problems,  we  propose  ConstrainedZero,  which  solves  chance-constrained  POMDPs  by  optimizing  the  balance  between  utility  and  a  target  level  of  safety.  Finally,  given  a  learned  safe  policy,  we  develop  a  Bayesian  safety  validationmethod  to  estimate  the  failure  probability  of  a  black-box  system  using  probabilistic  surrogate  models.  We  apply  these  algorithms  to  real-world  problems,  including  aircraft  collision  avoidance,  autonomous  aircraft  runway  detection,  safe  carbon  capture  and  storage,  critical  mineral  exploration,  robot  navigation,  and  aerial  wildfire  suppression.
■590    ▼aSchool  code:  0212.
■650  4▼aSuccess
■650  4▼aRobots
■650  4▼aAdaptation
■650  4▼aAviation
■650  4▼aCollisions
■650  4▼aClimate  change
■650  4▼aPilots
■650  4▼aRobotics
■650  4▼aGeology
■650  4▼aAircraft
■650  4▼aCarbon  sequestration
■650  4▼aFailure  analysis
■650  4▼aPlanning
■650  4▼aDecision  making
■650  4▼aNeural  networks
■650  4▼aDesign
■650  4▼aProbability
■690    ▼a0771
■690    ▼a0372
■690    ▼a0389
■690    ▼a0404
■71020▼aStanford  University.
■7730  ▼tDissertations  Abstracts  International▼g87-01B.
■790    ▼a0212
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17358753▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF19347 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.