본문

서브메뉴

Optimization-Driven Autonomous Driving: Control, Intent, and Testing
Optimization-Driven Autonomous Driving: Control, Intent, and Testing
Optimization-Driven Autonomous Driving: Control, Intent, and Testing

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211152748
ISBN  
9798342107457
DDC  
320.52
저자명  
Dyro, Robert.
서명/저자  
Optimization-Driven Autonomous Driving: Control, Intent, and Testing
발행사항  
[Sl] : Stanford University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
129 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-04, Section: A.
주기사항  
Advisor: Pavone, Marco.
학위논문주기  
Thesis (Ph.D.)--Stanford University, 2024.
초록/해제  
요약The primary goal of this research is to develop behavior models amenable to the task of online intent inference. This is crucial as real-time intent inference is increasingly essential in dynamic environments where autonomous systems interact with humans as the number of other traffic participants increases. Secondly, building on developments in behavior models, we also focus on better Autonomous Vehicles (AV) testingvia counterfactual scenario creation, which is vital for enhancing the safety and reliability of AVs in complex and unpredictable real-world scenarios. We develop new optimization tools for accelerating the solution of bilevel programs, targeting online intent inference as a primary application.The methodological contribution leads us to focus on one type of behavior model: an inverse optimal control-based (IOC) agent behavior model. Our methodology removes the typical obstacle of applying IOC online, which is a large number of costly iterations, thus enabling online intent inference. We combine our new methodology with previous IOC approaches, leading to a hybrid method. This innovative approach addresses the urgent need for adaptable and efficient online intent inference in rapidly changing scenarios. We do so to allow both fast online intent inference in structured models with comparatively few but interpretable parameters (e.g., parameterized rule-based models, collision repulsion parameterization) and unstructured, expressive models with up to billions of parameters (e.g., neural network residual corrector models). This allows our methodology to speed up existing largely structured IOC approaches while also taking advantage of the power of unstructured deep learning.Acknowledging the growing public concern about the safety of AVs, we attempt to develop better testing for AVs. To do so, we leverage our improved behavior modeling techniques in conjunction with recent advancements in behavior models. We aim to facilitate more exhaustive AV testing by generating realistic, counterfactual scenarios, allowing for stress testing of AVs. Our method relies on extracting behavior probability distribution encoded in fitted behavior models to generate challenging but realistic counterfactual scenarios automatically. Our method has the advantage of being generally applicable to parametric behavior models, generating a diversity of scenarios and allowing for the explicit specification of the lower probability limit of the generated scenarios - blending stress-testing with realism.
일반주제명  
Conservatism
일반주제명  
Robust control
일반주제명  
Deep learning
일반주제명  
Sensitivity analysis
일반주제명  
Computer vision
일반주제명  
Planning
일반주제명  
Neural networks
일반주제명  
Decision making
일반주제명  
Convex analysis
일반주제명  
Realism
일반주제명  
Robotics
일반주제명  
Industrial engineering
일반주제명  
Mathematics
일반주제명  
Political science
일반주제명  
Computer science
기타저자  
Stanford University.
기본자료저록  
Dissertations Abstracts International. 86-04A.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017163746
■00520250211152748
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798342107457
■035    ▼a(MiAaPQ)AAI31520321
■035    ▼a(MiAaPQ)Stanfordts345km5140
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a320.52
■1001  ▼aDyro,  Robert.
■24510▼aOptimization-Driven  Autonomous  Driving:  Control,  Intent,  and  Testing
■260    ▼a[Sl]▼bStanford  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a129  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-04,  Section:  A.
■500    ▼aAdvisor:  Pavone,  Marco.
■5021  ▼aThesis  (Ph.D.)--Stanford  University,  2024.
■520    ▼aThe  primary  goal  of  this  research  is  to  develop  behavior  models  amenable  to  the  task  of  online  intent  inference.  This  is  crucial  as  real-time  intent  inference  is  increasingly  essential  in  dynamic  environments  where  autonomous  systems  interact  with  humans  as  the  number  of  other  traffic  participants  increases.  Secondly,  building  on  developments  in  behavior  models,  we  also  focus  on  better  Autonomous  Vehicles  (AV)  testingvia  counterfactual  scenario  creation,  which  is  vital  for  enhancing  the  safety  and  reliability  of  AVs  in  complex  and  unpredictable  real-world  scenarios.  We  develop  new  optimization  tools  for  accelerating  the  solution  of  bilevel  programs,  targeting  online  intent  inference  as  a  primary  application.The  methodological  contribution  leads  us  to  focus  on  one  type  of  behavior  model:  an  inverse  optimal  control-based  (IOC)  agent  behavior  model.  Our  methodology  removes  the  typical  obstacle  of  applying  IOC  online,  which  is  a  large  number  of  costly  iterations,  thus  enabling  online  intent  inference.  We  combine  our  new  methodology  with  previous  IOC  approaches,  leading  to  a  hybrid  method.  This  innovative  approach  addresses  the  urgent  need  for  adaptable  and  efficient  online  intent  inference  in  rapidly  changing  scenarios.  We  do  so  to  allow  both  fast  online  intent  inference  in  structured  models  with  comparatively  few  but  interpretable  parameters  (e.g.,  parameterized  rule-based  models,  collision  repulsion  parameterization)  and  unstructured,  expressive  models  with  up  to  billions  of  parameters  (e.g.,  neural  network  residual  corrector  models).  This  allows  our  methodology  to  speed  up  existing  largely  structured  IOC  approaches  while  also  taking  advantage  of  the  power  of  unstructured  deep  learning.Acknowledging  the  growing  public  concern  about  the  safety  of  AVs,  we  attempt  to  develop  better  testing  for  AVs.  To  do  so,  we  leverage  our  improved  behavior  modeling  techniques  in  conjunction  with  recent  advancements  in  behavior  models.  We  aim  to  facilitate  more  exhaustive  AV  testing  by  generating  realistic,  counterfactual  scenarios,  allowing  for  stress  testing  of  AVs.  Our  method  relies  on  extracting  behavior  probability  distribution  encoded  in  fitted  behavior  models  to  generate  challenging  but  realistic  counterfactual  scenarios  automatically.  Our  method  has  the  advantage  of  being  generally  applicable  to  parametric  behavior  models,  generating  a  diversity  of  scenarios  and  allowing  for  the  explicit  specification  of  the  lower  probability  limit  of  the  generated  scenarios  -  blending  stress-testing  with  realism.
■590    ▼aSchool  code:  0212.
■650  4▼aConservatism
■650  4▼aRobust  control
■650  4▼aDeep  learning
■650  4▼aSensitivity  analysis
■650  4▼aComputer  vision
■650  4▼aPlanning
■650  4▼aNeural  networks
■650  4▼aDecision  making
■650  4▼aConvex  analysis
■650  4▼aRealism
■650  4▼aRobotics
■650  4▼aIndustrial  engineering
■650  4▼aMathematics
■650  4▼aPolitical  science
■650  4▼aComputer  science
■690    ▼a0771
■690    ▼a0800
■690    ▼a0546
■690    ▼a0405
■690    ▼a0615
■690    ▼a0984
■71020▼aStanford  University.
■7730  ▼tDissertations  Abstracts  International▼g86-04A.
■790    ▼a0212
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17163746▼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
    TF10671 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.