본문

Efficient 3D Vision for Autonomous Driving
Efficient 3D Vision for Autonomous Driving
Efficient 3D Vision for Autonomous Driving

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211152753
ISBN  
9798384450580
DDC  
621.3
저자명  
Jacobson, Philip.
서명/저자  
Efficient 3D Vision for Autonomous Driving
발행사항  
[Sl] : University of California, Berkeley, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
107 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-03, Section: B.
주기사항  
Advisor: Wu, Ming C.
학위논문주기  
Thesis (Ph.D.)--University of California, Berkeley, 2024.
초록/해제  
요약Self-driving vehicles have long been envisioned as a massive leap forward in transportation technology. Although several efforts to developing fully autonomous vehicles are currently being undertaken in both industry and academia, so far none have achieved the promise of full self-driving. Of the challenges in building the autonomous software for self-driving cars, one of the most prominent is perception, or the ability for the vehicle to sense the world around it. To meet the requirements for practical deployment onto autonomous vehicles, perception systems must meet four key metrics of efficiency: accuracy, low-latency, reasonable compute hardware, and training data efficiency.In this dissertation, we will introduce novel approaches to AV perception while aiming to address the four metrics for efficiency. We introduce four major new perception schemes during the course of this dissertation.In Chapter 2, we consider a combined hardware/algorithms approach to perception to achieve accelerated training speeds on limited compute hardware. We introduce system based on the principles of delayed-feedback reservoir computing implemented using an optoelectronic delay system. To tailor this approach to computer vision tasks, we combine it with a high-speed digital preprocessing through untrained convolutional layers to generate randomized feature maps that are then circulated through our reservoir. We experimentally validate our approach on the classic MNIST handwritten digit recognition task, and achiever performance on-par with a digitally-trained convolutional neural network, while achieving a training-time speed-up of up to 10x.In Chapter 3, we consider 3D object detection in autonomous driving settings, and specifically consider the problem of efficient LiDAR-camera fusion. We introduce a novel sensor fusion approach, dubbed Center Feature Fusion, which operates through fusing camera and LiDAR deep features in the bird's-eye-view space. To enable low-latency fusion, we propose a sparse feature fusion, we projects only a set of identified key camera features to bird's-eye-view. As a result, we are able to achieve performance on-par with competing sensor fusion approaches, while reducing runtime latency by several times.In Chapter 4, we consider the problem of 3D object detection from the data efficiency angle, aiming to reduce the labeled data requirement needed to train the computer vision models necessary for autonomous vehicles. In this chapter, we introduce doubly-robust self-training, a novel generalized approach to semi-supervised learning. We conduct both theoretical analysis to demonstrate its superiority over the standard self-training approaches regardless of teacher model quality, and experimental analysis on both image classification and object detection. For both vision tasks, we achieve performance superior to the self-training baseline with no extra computational costs.In Chapter 5, we continue exploring semi-supervised 3D object detection through leveraging the motion forecasting component of the autonomy stack to improve perception models. We introduce our novel algorithm , TrajSSL, which uses a pre-trained prediction model to generate a set of synthetic labels to enhance the training of a student detector model. The generate synthetic labels are used to establish temporal consistency, and thus filter out low-quality pseudo-labels during training, while simultaneously correcting for missing pseudo-labels. TrajSSL outperforms the state-of-the-art for semi-supervised 3D object detection across a wide variety of scenarios.
일반주제명  
Electrical engineering
일반주제명  
Computer engineering
일반주제명  
Automotive engineering
키워드  
Self-driving vehicles
키워드  
Transportation technology
키워드  
Autonomous vehicles
키워드  
Autonomous software
키워드  
Novel algorithm
기타저자  
University of California, Berkeley Electrical Engineering & Computer Sciences
기본자료저록  
Dissertations Abstracts International. 86-03B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017163784
■00520250211152753
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798384450580
■035    ▼a(MiAaPQ)AAI31555516
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a621.3
■1001  ▼aJacobson,  Philip.
■24510▼aEfficient  3D  Vision  for  Autonomous  Driving
■260    ▼a[Sl]▼bUniversity  of  California,  Berkeley▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a107  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-03,  Section:  B.
■500    ▼aAdvisor:  Wu,  Ming  C.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Berkeley,  2024.
■520    ▼aSelf-driving  vehicles  have  long  been  envisioned  as  a  massive  leap  forward  in  transportation  technology.  Although  several  efforts  to  developing  fully  autonomous  vehicles  are  currently  being  undertaken  in  both  industry  and  academia,  so  far  none  have  achieved  the  promise  of  full  self-driving.  Of  the  challenges  in  building  the  autonomous  software  for  self-driving  cars,  one  of  the  most  prominent  is  perception,  or  the  ability  for  the  vehicle  to  sense  the  world  around  it.  To  meet  the  requirements  for  practical  deployment  onto  autonomous  vehicles,  perception  systems  must  meet  four  key  metrics  of  efficiency:  accuracy,  low-latency,  reasonable  compute  hardware,  and  training  data  efficiency.In  this  dissertation,  we  will  introduce  novel  approaches  to  AV  perception  while  aiming  to  address  the  four  metrics  for  efficiency.  We  introduce  four  major  new  perception  schemes  during  the  course  of  this  dissertation.In  Chapter  2,  we  consider  a  combined  hardware/algorithms  approach  to  perception  to  achieve  accelerated  training  speeds  on  limited  compute  hardware.  We  introduce  system  based  on  the  principles  of  delayed-feedback  reservoir  computing  implemented  using  an  optoelectronic  delay  system.  To  tailor  this  approach  to  computer  vision  tasks,  we  combine  it  with  a  high-speed  digital  preprocessing  through  untrained  convolutional  layers  to  generate  randomized  feature  maps  that  are  then  circulated  through  our  reservoir.  We  experimentally  validate  our  approach  on  the  classic  MNIST  handwritten  digit  recognition  task,  and  achiever  performance  on-par  with  a  digitally-trained  convolutional  neural  network,  while  achieving  a  training-time  speed-up  of  up  to  10x.In  Chapter  3,  we  consider  3D  object  detection  in  autonomous  driving  settings,  and  specifically  consider  the  problem  of  efficient  LiDAR-camera  fusion.  We  introduce  a  novel  sensor  fusion  approach,  dubbed  Center  Feature  Fusion,  which  operates  through  fusing  camera  and  LiDAR  deep  features  in  the  bird's-eye-view  space.  To  enable  low-latency  fusion,  we  propose  a  sparse  feature  fusion,  we  projects  only  a  set  of  identified  key  camera  features  to  bird's-eye-view.  As  a  result,  we  are  able  to  achieve  performance  on-par  with  competing  sensor  fusion  approaches,  while  reducing  runtime  latency  by  several  times.In  Chapter  4,  we  consider  the  problem  of  3D  object  detection  from  the  data  efficiency  angle,  aiming  to  reduce  the  labeled  data  requirement  needed  to  train  the  computer  vision  models  necessary  for  autonomous  vehicles.  In  this  chapter,  we  introduce  doubly-robust  self-training,  a  novel  generalized  approach  to  semi-supervised  learning.  We  conduct  both  theoretical  analysis  to  demonstrate  its  superiority  over  the  standard  self-training  approaches  regardless  of  teacher  model  quality,  and  experimental  analysis  on  both  image  classification  and  object  detection.  For  both  vision  tasks,  we  achieve  performance  superior  to  the  self-training  baseline  with  no  extra  computational  costs.In  Chapter  5,  we  continue  exploring  semi-supervised  3D  object  detection  through  leveraging  the  motion  forecasting  component  of  the  autonomy  stack  to  improve  perception  models.  We  introduce  our  novel  algorithm  ,  TrajSSL,  which  uses  a  pre-trained  prediction  model  to  generate  a  set  of  synthetic  labels  to  enhance  the  training  of  a  student  detector  model.  The  generate  synthetic  labels  are  used  to  establish  temporal  consistency,  and  thus  filter  out  low-quality  pseudo-labels  during  training,  while  simultaneously  correcting  for  missing  pseudo-labels.  TrajSSL  outperforms  the  state-of-the-art  for  semi-supervised  3D  object  detection  across  a  wide  variety  of  scenarios.
■590    ▼aSchool  code:  0028.
■650  4▼aElectrical  engineering
■650  4▼aComputer  engineering
■650  4▼aAutomotive  engineering
■653    ▼aSelf-driving  vehicles
■653    ▼aTransportation  technology
■653    ▼aAutonomous  vehicles
■653    ▼aAutonomous  software
■653    ▼aNovel  algorithm
■690    ▼a0544
■690    ▼a0464
■690    ▼a0540
■71020▼aUniversity  of  California,  Berkeley▼bElectrical  Engineering  &  Computer  Sciences.
■7730  ▼tDissertations  Abstracts  International▼g86-03B.
■790    ▼a0028
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17163784▼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
    TF09801 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.