본문

서브메뉴

Programming Abstractions & Systems for Autonomous Vehicles
Programming Abstractions & Systems for Autonomous Vehicles
Programming Abstractions & Systems for Autonomous Vehicles

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211152755
ISBN  
9798384455943
DDC  
004
저자명  
Kalra, Sukrit.
서명/저자  
Programming Abstractions & Systems for Autonomous Vehicles
발행사항  
[Sl] : University of California, Berkeley, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
174 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-03, Section: A.
주기사항  
Advisor: Stoica, Ion.
학위논문주기  
Thesis (Ph.D.)--University of California, Berkeley, 2024.
초록/해제  
요약Autonomous Vehicles (AVs) have the potential to revolutionize transportation through their significant safety, environmental and mobility benefits. However, despite their benefits and significant investment spanning over a decade, AVs remain restricted to locations with favorable driving conditions, due to the complications arising from the long-tail of complex driving scenarios. Most research has sought to address this critical challenge through the design of robust algorithms and machine learning (ML) models that underpin the various decision making components of a modern AV computational pipeline. In contrast, there has been relatively little focus on the software systems that must orchestrate an efficient, real-time execution of these components on the AV's constrained, heterogeneous hardware.This dissertation examines the often-overlooked design of such software systems and presents a clean slate approach to developing AVs. We introduce D3, a novel programming model for AVs that enables the computation to proactively adjust to dynamically-varying deadlines and models missed deadlines as exceptions. We realize D3 in our open-source system, ERDOS, whose novel extensions to concepts from streaming data systems enable it to speculatively execute computation and enforce deadlines between an arbitrary set of events. ERDOS's efficient execution of AV pipelines is further enabled by two key scheduling contributions of this dissertation: SuperServe and DAGSched. SuperServe unlocks a resource-efficient serving of the entire range of ML models spanning the latency-accuracy tradeoff space, enabling AV pipelines to quickly adjust to dynamically-varying deadlines. In addition, DAGSched efficiently multiplexes the available compute resources in an AV amongst the decision making components, with an aim to maximize the ability of the AV pipeline to meet dynamically-varying deadlines. Finally, we address the crucial lack of AV benchmarks by providing the first completely open-source AV pipeline, Pylot, and use it to evaluate the positive effects of D3 and ERDOS on the driving safety of AVs. Together, these systems span the entire workflow of developing and evaluating AVs, and we believe are crucial to bridging the gap towards achieving "fully autonomous vehicles".
일반주제명  
Computer science
키워드  
Autonomous vehicles
키워드  
Distributed systems
키워드  
Machine learning
키워드  
Resource management
키워드  
Scheduling
기타저자  
University of California, Berkeley Computer Science
기본자료저록  
Dissertations Abstracts International. 86-03A.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017163804
■00520250211152755
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798384455943
■035    ▼a(MiAaPQ)AAI31555772
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aKalra,  Sukrit.
■24510▼aProgramming  Abstractions  &  Systems  for  Autonomous  Vehicles
■260    ▼a[Sl]▼bUniversity  of  California,  Berkeley▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a174  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-03,  Section:  A.
■500    ▼aAdvisor:  Stoica,  Ion.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Berkeley,  2024.
■520    ▼aAutonomous  Vehicles  (AVs)  have  the  potential  to  revolutionize  transportation  through  their  significant  safety,  environmental  and  mobility  benefits.  However,  despite  their  benefits  and  significant  investment  spanning  over  a  decade,  AVs  remain  restricted  to  locations  with  favorable  driving  conditions,  due  to  the  complications  arising  from  the  long-tail  of  complex  driving  scenarios.  Most  research  has  sought  to  address  this  critical  challenge  through  the  design  of  robust  algorithms  and  machine  learning  (ML)  models  that  underpin  the  various  decision  making  components  of  a  modern  AV  computational  pipeline.  In  contrast,  there  has  been  relatively  little  focus  on  the  software  systems  that  must  orchestrate  an  efficient,  real-time  execution  of  these  components  on  the  AV's  constrained,  heterogeneous  hardware.This  dissertation  examines  the  often-overlooked  design  of  such  software  systems  and  presents  a  clean  slate  approach  to  developing  AVs.  We  introduce  D3,  a  novel  programming  model  for  AVs  that  enables  the  computation  to  proactively  adjust  to  dynamically-varying  deadlines  and  models  missed  deadlines  as  exceptions.  We  realize  D3  in  our  open-source  system,  ERDOS,  whose  novel  extensions  to  concepts  from  streaming  data  systems  enable  it  to  speculatively  execute  computation  and  enforce  deadlines  between  an  arbitrary  set  of  events.  ERDOS's  efficient  execution  of  AV  pipelines  is  further  enabled  by  two  key  scheduling  contributions  of  this  dissertation:  SuperServe  and  DAGSched.  SuperServe  unlocks  a  resource-efficient  serving  of  the  entire  range  of  ML  models  spanning  the  latency-accuracy  tradeoff  space,  enabling  AV  pipelines  to  quickly  adjust  to  dynamically-varying  deadlines.  In  addition,  DAGSched  efficiently  multiplexes  the  available  compute  resources  in  an  AV  amongst  the  decision  making  components,  with  an  aim  to  maximize  the  ability  of  the  AV  pipeline  to  meet  dynamically-varying  deadlines.  Finally,  we  address  the  crucial  lack  of  AV  benchmarks  by  providing  the  first  completely  open-source  AV  pipeline,  Pylot,  and  use  it  to  evaluate  the  positive  effects  of  D3  and  ERDOS  on  the  driving  safety  of  AVs.  Together,  these  systems  span  the  entire  workflow  of  developing  and  evaluating  AVs,  and  we  believe  are  crucial  to  bridging  the  gap  towards  achieving  "fully  autonomous  vehicles".
■590    ▼aSchool  code:  0028.
■650  4▼aComputer  science
■653    ▼aAutonomous  vehicles
■653    ▼aDistributed  systems
■653    ▼aMachine  learning
■653    ▼aResource  management
■653    ▼aScheduling
■690    ▼a0984
■690    ▼a0454
■690    ▼a0800
■71020▼aUniversity  of  California,  Berkeley▼bComputer  Science.
■7730  ▼tDissertations  Abstracts  International▼g86-03A.
■790    ▼a0028
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17163804▼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
    TF13688 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.