본문

서브메뉴

Dense Learning for Advancing Safety Performance of Autonomous Vehicles
Dense Learning for Advancing Safety Performance of Autonomous Vehicles
Dense Learning for Advancing Safety Performance of Autonomous Vehicles

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105237
ISBN  
9798291567968
DDC  
004
저자명  
Zhu, Haojie.
서명/저자  
Dense Learning for Advancing Safety Performance of Autonomous Vehicles
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: Liu, Henry X.
학위논문주기  
Thesis (Ph.D.)--University of Michigan, 2025.
초록/해제  
요약Autonomous Vehicles (AVs) have garnered substantial attention and investment over the past two decades, yet their commercial availability remains limited. A significant barrier to widespread deployment is the ongoing struggle to attain safety performance comparable to or surpassing that of human drivers, particularly given the extreme rarity of safety-critical events in complex, real-world driving environments. Existing approaches, which heavily rely on learning from failure data, often encounter a performance plateau caused by the seesaw effect-improvements in some scenarios are counterbalanced by regressions in others, limiting overall progress in AV safety performance. This dissertation introduces Dense Reinforcement Learning, a new learning paradigm designed to overcome the limitations imposed by the Curse of Rarity (CoR). By densifying the information content within training datasets, this approach reduces variance in policy optimization and improves training efficiency without compromising unbiasedness. Dense Reinforcement Learning prioritizes both failure cases and informative successes, selectively sampling data according to their contribution to policy gradients and exposure frequencies, while discarding non-informative examples that dilute learning progress. To support this framework, a learned safety metric is developed to evaluate the risk levels of driving behaviors and assist in identifying informative data samples during training. Trained on diverse autonomous driving trajectories, the learned safety metric demonstrates superior accuracy in predicting safety-critical events compared to widely used baselines. Moreover, it shows strong generalization capabilities across highways, intersections, roundabouts, and other complex driving environments, further enhancing its utility for AV safety training. The Dense Reinforcement Learning approach is validated through the development and training of a safety-critical driving agent in an urban test track environment augmented by mixed reality technology. Extensive experiments demonstrate that dense learning substantially enhances AV safety performance, achieving improvements ranging from one to two orders of magnitude compared to baseline methods. These results highlight the potential of dense learning to break through the safety performance stagnation commonly observed in traditional Reinforcement Learning (RL) frameworks, paving the way for AVs to achieve and even surpass human driving safety performance. Beyond AV applications, the dense learning methodology offers broader implications for machine learning domains involving rare, high-stakes events. In particular, dense learning principles have the potential to improve supervised learning processes and enhance the pre-training and fine-tuning stages of Large Language Models (LLMs), where data sparsity and safety considerations remain critical challenges.
일반주제명  
Computer science
일반주제명  
Transportation
일반주제명  
Computer engineering
일반주제명  
Automotive engineering
키워드  
Autonomous vehicles
키워드  
Safety
키워드  
Safety-critical events
키워드  
Dense Reinforcement Learning
키워드  
Large Language Models
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
■001000017359928
■00520260202105237
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798291567968
■035    ▼a(MiAaPQ)AAI32271961
■035    ▼a(MiAaPQ)umichrackham006532
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aZhu,  Haojie.
■24510▼aDense  Learning  for  Advancing  Safety  Performance  of  Autonomous  Vehicles
■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:  Liu,  Henry  X.
■5021  ▼aThesis  (Ph.D.)--University  of  Michigan,  2025.
■520    ▼aAutonomous  Vehicles  (AVs)  have  garnered  substantial  attention  and  investment  over  the  past  two  decades,  yet  their  commercial  availability  remains  limited.  A  significant  barrier  to  widespread  deployment  is  the  ongoing  struggle  to  attain  safety  performance  comparable  to  or  surpassing  that  of  human  drivers,  particularly  given  the  extreme  rarity  of  safety-critical  events  in  complex,  real-world  driving  environments.  Existing  approaches,  which  heavily  rely  on  learning  from  failure  data,  often  encounter  a  performance  plateau  caused  by  the  seesaw  effect-improvements  in  some  scenarios  are  counterbalanced  by  regressions  in  others,  limiting  overall  progress  in  AV  safety  performance.  This  dissertation  introduces  Dense  Reinforcement  Learning,  a  new  learning  paradigm  designed  to  overcome  the  limitations  imposed  by  the  Curse  of  Rarity  (CoR).  By  densifying  the  information  content  within  training  datasets,  this  approach  reduces  variance  in  policy  optimization  and  improves  training  efficiency  without  compromising  unbiasedness.  Dense  Reinforcement  Learning  prioritizes  both  failure  cases  and  informative  successes,  selectively  sampling  data  according  to  their  contribution  to  policy  gradients  and  exposure  frequencies,  while  discarding  non-informative  examples  that  dilute  learning  progress.  To  support  this  framework,  a  learned  safety  metric  is  developed  to  evaluate  the  risk  levels  of  driving  behaviors  and  assist  in  identifying  informative  data  samples  during  training.  Trained  on  diverse  autonomous  driving  trajectories,  the  learned  safety  metric  demonstrates  superior  accuracy  in  predicting  safety-critical  events  compared  to  widely  used  baselines.  Moreover,  it  shows  strong  generalization  capabilities  across  highways,  intersections,  roundabouts,  and  other  complex  driving  environments,  further  enhancing  its  utility  for  AV  safety  training.  The  Dense  Reinforcement  Learning  approach  is  validated  through  the  development  and  training  of  a  safety-critical  driving  agent  in  an  urban  test  track  environment  augmented  by  mixed  reality  technology.  Extensive  experiments  demonstrate  that  dense  learning  substantially  enhances  AV  safety  performance,  achieving  improvements  ranging  from  one  to  two  orders  of  magnitude  compared  to  baseline  methods.  These  results  highlight  the  potential  of  dense  learning  to  break  through  the  safety  performance  stagnation  commonly  observed  in  traditional  Reinforcement  Learning  (RL)  frameworks,  paving  the  way  for  AVs  to  achieve  and  even  surpass  human  driving  safety  performance.  Beyond  AV  applications,  the  dense  learning  methodology  offers  broader  implications  for  machine  learning  domains  involving  rare,  high-stakes  events.  In  particular,  dense  learning  principles  have  the  potential  to  improve  supervised  learning  processes  and  enhance  the  pre-training  and  fine-tuning  stages  of  Large  Language  Models  (LLMs),  where  data  sparsity  and  safety  considerations  remain  critical  challenges.
■590    ▼aSchool  code:  0127.
■650  4▼aComputer  science
■650  4▼aTransportation
■650  4▼aComputer  engineering
■650  4▼aAutomotive  engineering
■653    ▼aAutonomous  vehicles
■653    ▼aSafety
■653    ▼aSafety-critical  events
■653    ▼aDense  Reinforcement  Learning
■653    ▼aLarge  Language  Models
■690    ▼a0709
■690    ▼a0984
■690    ▼a0464
■690    ▼a0540
■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=T17359928▼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
    TF15894 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.