본문

서브메뉴

Flexible Perception for High-Performance Robot Navigation
Flexible Perception for High-Performance Robot Navigation
Flexible Perception for High-Performance Robot Navigation

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202103510
ISBN  
9798315741732
DDC  
629.8
저자명  
Ho, Cherie.
서명/저자  
Flexible Perception for High-Performance Robot Navigation
발행사항  
[Sl] : Carnegie Mellon University, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
136 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-11, Section: B.
주기사항  
Advisor: Scherer, Sebastian.
학위논문주기  
Thesis (Ph.D.)--Carnegie Mellon University, 2025.
초록/해제  
요약Real-world autonomy requires perception systems that deliver rich, accurate information given the task and environment. However, as robots scale to diverse and rapidly evolving settings, maintaining this level of performance becomes increasingly brittle and labor-intensive, requiring significant human engineering and retraining for even small changes in environment and problem definition. To overcome this bottleneck, this thesis advances flexible robot perception by improving its generalizability, adaptivity, and uncertainty-awareness, enabling robots to operate effectively across more environments with minimal additional human intervention.First, to enable stronger zero-shot generalization, we introduce MapItAnywhere (MIA), a scalable ecosystem for generalizable bird's-eye view (BEV) mapping. At its core, MIA provides a data engine for automated curation of BEV maps using crowd-sourced, publicly available data. This advances flexible perception by leveraging existing world-scale labels from disparate data sources to improve BEV mapping performance in previously unseen areas, without requiring additional manual data collection, labeling, or curation.However, even generalizable perception systems face inevitable performance drops when deployed in new environments. To bridge this gap automatically, we develop ALTER, a perception system that adapts online to new environments while mitigating catastrophic forgetting and label noise. ALTER advances flexible perception by introducing a system that automatically labels new data using LiDAR and groups them in latent space for efficient retraining, enabling perception systems to operate at higher performance in new scenarios without human intervention.Lastly, while an adaptive perception system can improve over time, collecting data in low-information regions leads to inefficient learning. To this end, we present MapEx, an indoor exploration algorithm that builds an uncertainty-aware representation using an ensemble of world model predictors. MapEx advances flexible perception by jointly leveraging map prediction uncertainty and sensor coverage to guide data collection, enabling improved perceptual understanding in new environments without human supervision and reducing the need for manual data collection.This thesis advances the core capabilities of generalization, adaptation, and uncertainty awareness needed for flexible and automated robot perception. Together, these capabilities address the fundamental bottlenecks of current engineering-intensive workflows and bring us closer to scalable real-world autonomy.
일반주제명  
Robotics
일반주제명  
Computer science
일반주제명  
Information technology
키워드  
Computer vision
키워드  
Field robotics
키워드  
Perception
키워드  
Robot learning
기타저자  
Carnegie Mellon University Robotics Institute
기본자료저록  
Dissertations Abstracts International. 86-11B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017357425
■00520260202103510
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798315741732
■035    ▼a(MiAaPQ)AAI32003234
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a629.8
■1001  ▼aHo,  Cherie.▼0(orcid)0000-0003-1886-1020
■24510▼aFlexible  Perception  for  High-Performance  Robot  Navigation
■260    ▼a[Sl]▼bCarnegie  Mellon  University▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a136  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-11,  Section:  B.
■500    ▼aAdvisor:  Scherer,  Sebastian.
■5021  ▼aThesis  (Ph.D.)--Carnegie  Mellon  University,  2025.
■520    ▼aReal-world  autonomy  requires  perception  systems  that  deliver  rich,  accurate  information  given  the  task  and  environment.  However,  as  robots  scale  to  diverse  and  rapidly  evolving  settings,  maintaining  this  level  of  performance  becomes  increasingly  brittle  and  labor-intensive,  requiring  significant  human  engineering  and  retraining  for  even  small  changes  in  environment  and  problem  definition.  To  overcome  this  bottleneck,  this  thesis  advances  flexible  robot  perception  by  improving  its  generalizability,  adaptivity,  and  uncertainty-awareness,  enabling  robots  to  operate  effectively  across  more  environments  with  minimal  additional  human  intervention.First,  to  enable  stronger  zero-shot  generalization,  we  introduce  MapItAnywhere  (MIA),  a  scalable  ecosystem  for  generalizable  bird's-eye  view  (BEV)  mapping.  At  its  core,  MIA  provides  a  data  engine  for  automated  curation  of  BEV  maps  using  crowd-sourced,  publicly  available  data.  This  advances  flexible  perception  by  leveraging  existing  world-scale  labels  from  disparate  data  sources  to  improve  BEV  mapping  performance  in  previously  unseen  areas,  without  requiring  additional  manual  data  collection,  labeling,  or  curation.However,  even  generalizable  perception  systems  face  inevitable  performance  drops  when  deployed  in  new  environments.  To  bridge  this  gap  automatically,  we  develop  ALTER,  a  perception  system  that  adapts  online  to  new  environments  while  mitigating  catastrophic  forgetting  and  label  noise.  ALTER  advances  flexible  perception  by  introducing  a  system  that  automatically  labels  new  data  using  LiDAR  and  groups  them  in  latent  space  for  efficient  retraining,  enabling  perception  systems  to  operate  at  higher  performance  in  new  scenarios  without  human  intervention.Lastly,  while  an  adaptive  perception  system  can  improve  over  time,  collecting  data  in  low-information  regions  leads  to  inefficient  learning.  To  this  end,  we  present  MapEx,  an  indoor  exploration  algorithm  that  builds  an  uncertainty-aware  representation  using  an  ensemble  of  world  model  predictors.  MapEx  advances  flexible  perception  by  jointly  leveraging  map  prediction  uncertainty  and  sensor  coverage  to  guide  data  collection,  enabling  improved  perceptual  understanding  in  new  environments  without  human  supervision  and  reducing  the  need  for  manual  data  collection.This  thesis  advances  the  core  capabilities  of  generalization,  adaptation,  and  uncertainty  awareness  needed  for  flexible  and  automated  robot  perception.  Together,  these  capabilities  address  the  fundamental  bottlenecks  of  current  engineering-intensive  workflows  and  bring  us  closer  to  scalable  real-world  autonomy.
■590    ▼aSchool  code:  0041.
■650  4▼aRobotics
■650  4▼aComputer  science
■650  4▼aInformation  technology
■653    ▼aComputer  vision
■653    ▼aField  robotics
■653    ▼aPerception
■653    ▼aRobot  learning
■690    ▼a0771
■690    ▼a0489
■690    ▼a0984
■690    ▼a0800
■71020▼aCarnegie  Mellon  University▼bRobotics  Institute.
■7730  ▼tDissertations  Abstracts  International▼g86-11B.
■790    ▼a0041
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17357425▼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
    TF17021 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.