본문

서브메뉴

Reliable Autonomy Under Uncertainty: from Learning-Based to Non-Rational Control
Reliable Autonomy Under Uncertainty: from Learning-Based to Non-Rational Control
Reliable Autonomy Under Uncertainty: from Learning-Based to Non-Rational Control

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105059
ISBN  
9798288818349
DDC  
629.8
저자명  
Kargin, Taylan.
서명/저자  
Reliable Autonomy Under Uncertainty: from Learning-Based to Non-Rational Control
발행사항  
[Sl] : California Institute of Technology, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
363 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-01, Section: B.
주기사항  
Advisor: Hassibi, Babak.
학위논문주기  
Thesis (Ph.D.)--California Institute of Technology, 2025.
초록/해제  
요약Autonomous systems are profoundly reshaping our societies, industries, and daily lives, delivering unprecedented levels of efficiency, innovation, and adaptability. From self-driving vehicles navigating dense urban traffic and coordinated swarms of search-and-rescue robots operating in hazardous environments, to next-generation intelligent power grids and high-precision industrial automation, these systems are increasingly deployed in safety-critical and high-stakes settings where they are routinely entrusted with split‑second decisions that carry profound economic and lethal consequences. In such contexts, the imperative for reliability, safety, and robustness is paramount: a single unanticipated failure within a power distribution network can trigger extensive blackouts, and a momentary lapse in decision-making or perception by an autonomous vehicle can endanger lives.Despite their remarkable capabilities, securing such reliability guarantees faces formidable and multifaceted challenges. The environments in which these systems operate are characterized by unprecedented complexity, vast scale, and pervasive uncertainty as they frequently interact with numerous external entities such as humans or other autonomous agents whose behaviors may be volatile, adversarial, or fundamentally unknown. Explicitly and exhaustively modeling this complexity a priori is practically infeasible, compelling systems to infer, adapt, and respond to the novel environments by learning from data. Although contemporary machine‑learning models afford expressive representations, their assurances are limited by the scope and fidelity of their training data. Consequently, such models remain vulnerable to distribution shifts, rare events, or unmodeled edge cases, which can precipitate catastrophic failure.Further complicating matters, real-world applications frequently impose stringent resource constraints, including limited computation, memory, communication, and power. These constraints demand principled trade-offs between competing performance objectives and operational constraints such as safety, stability, robustness, and efficiency, especially in high-stakes and uncertainty-laden settings. This dissertation addresses these challenges by contributing fundamental theoretical results and practical computational tools towards provably reliable, resource‑efficient, and scalable autonomy.Operating safely in dynamic and a priori unknown environments poses a fundamental challenge for autonomous systems: balancing exploration, i.e., the pursuit of long-term optimality by probing uncertain policy landscape at the risk of degraded safety, against exploitation, i.e., leveraging current knowledge to ensure short-term performance and stability at the expense of settling for a suboptimal policy. In Part 1, we study online reinforcement learning approaches for unknown linear dynamical systems to address this challenge. We present computationally efficient algorithms for online learning and control in both state-feedback and measurement-feedback settings that operate safely without any prior knowledge of the system. We rigorously establish their feasibility through finite-time guarantees on performance, computational complexity, and stability, matching the fundamental theoretical bounds.Statistical models underlie every layer of an autonomous system, serving as representations of complex data-generating phenomena. Typically constructed from empirical data through a blend of explicit modeling, machine learning, and simulation, these models are vulnerable to distribution shift, i.e., discrepancies between design and deployment conditions, which can jeopardize both performance and safety. In Part 2, we investigate distributionally robust optimization (DRO) methods for control, prediction, communication, and unsupervised learning to guard against model misspecification and distribution shifts. DRO blends average-case optimality with worst‑case guarantees: by maximizing expected performance against the least‑favorable statistical model consistent with the available data, it strikes a balanced trade-off between robustness and performance informed by data.Autonomous control systems must often balance several performance goals, such as cost efficiency, robustness, risk tolerance, and stability, while meeting practical constraints such as suitability for real‑time implementation and scalability. Because these design problems are inherently infinite‑dimensional, only a handful of special cases admit exact, tractable solutions (e.g., Linear‑Quadratic‑Gaussian, ℋ∞‑optimal, or regret‑optimal control) while widely studied formulations like mixed ℋ₂/ℋ∞ control remain unresolved. In Part 3, we present non‑rational control, a unified framework that makes many such problems both solvable and implementable. The key is an optimize‑then‑approximate strategy that delivers provably near‑optimal, stabilizing, finite‑order (rational) controllers even when the true optimum resides in an infinite‑dimensional (non‑rational) policy space.
일반주제명  
Robust control
일반주제명  
Closed loop systems
일반주제명  
Optimization techniques
일반주제명  
Dynamical systems
일반주제명  
System theory
일반주제명  
Computer science
일반주제명  
Systems science
기타저자  
California Institute of Technology Engineering and Applied Science
기본자료저록  
Dissertations Abstracts International. 87-01B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017359310
■00520260202105059
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798288818349
■035    ▼a(MiAaPQ)AAI32205964
■035    ▼a(MiAaPQ)Caltech17440
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a629.8
■1001  ▼aKargin,  Taylan.▼0(orcid)0000-0001-6744-654X
■24510▼aReliable  Autonomy  Under  Uncertainty:  from  Learning-Based  to  Non-Rational  Control
■260    ▼a[Sl]▼bCalifornia  Institute  of  Technology▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a363  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-01,  Section:  B.
■500    ▼aAdvisor:  Hassibi,  Babak.
■5021  ▼aThesis  (Ph.D.)--California  Institute  of  Technology,  2025.
■520    ▼aAutonomous  systems  are  profoundly  reshaping  our  societies,  industries,  and  daily  lives,  delivering  unprecedented  levels  of  efficiency,  innovation,  and  adaptability.  From  self-driving  vehicles  navigating  dense  urban  traffic  and  coordinated  swarms  of  search-and-rescue  robots  operating  in  hazardous  environments,  to  next-generation  intelligent  power  grids  and  high-precision  industrial  automation,  these  systems  are  increasingly  deployed  in  safety-critical  and  high-stakes  settings  where  they  are  routinely  entrusted  with  split‑second  decisions  that  carry  profound  economic  and  lethal  consequences.  In  such  contexts,  the  imperative  for  reliability,  safety,  and  robustness  is  paramount:  a  single  unanticipated  failure  within  a  power  distribution  network  can  trigger  extensive  blackouts,  and  a  momentary  lapse  in  decision-making  or  perception  by  an  autonomous  vehicle  can  endanger  lives.Despite  their  remarkable  capabilities,  securing  such  reliability  guarantees  faces  formidable  and  multifaceted  challenges.  The  environments  in  which  these  systems  operate  are  characterized  by  unprecedented  complexity,  vast  scale,  and  pervasive  uncertainty  as  they  frequently  interact  with  numerous  external  entities  such  as  humans  or  other  autonomous  agents  whose  behaviors  may  be  volatile,  adversarial,  or  fundamentally  unknown.  Explicitly  and  exhaustively  modeling  this  complexity  a  priori  is  practically  infeasible,  compelling  systems  to  infer,  adapt,  and  respond  to  the  novel  environments  by  learning  from  data.  Although  contemporary  machine‑learning  models  afford  expressive  representations,  their  assurances  are  limited  by  the  scope  and  fidelity  of  their  training  data.  Consequently,  such  models  remain  vulnerable  to  distribution  shifts,  rare  events,  or  unmodeled  edge  cases,  which  can  precipitate  catastrophic  failure.Further  complicating  matters,  real-world  applications  frequently  impose  stringent  resource  constraints,  including  limited  computation,  memory,  communication,  and  power.  These  constraints  demand  principled  trade-offs  between  competing  performance  objectives  and  operational  constraints  such  as  safety,  stability,  robustness,  and  efficiency,  especially  in  high-stakes  and  uncertainty-laden  settings.  This  dissertation  addresses  these  challenges  by  contributing  fundamental  theoretical  results  and  practical  computational  tools  towards  provably  reliable,  resource‑efficient,  and  scalable  autonomy.Operating  safely  in  dynamic  and  a  priori  unknown  environments  poses  a  fundamental  challenge  for  autonomous  systems:  balancing  exploration,  i.e.,  the  pursuit  of  long-term  optimality  by  probing  uncertain  policy  landscape  at  the  risk  of  degraded  safety,  against  exploitation,  i.e.,  leveraging  current  knowledge  to  ensure  short-term  performance  and  stability  at  the  expense  of  settling  for  a  suboptimal  policy.  In  Part  1,  we  study  online  reinforcement  learning  approaches  for  unknown  linear  dynamical  systems  to  address  this  challenge.  We  present  computationally  efficient  algorithms  for  online  learning  and  control  in  both  state-feedback  and  measurement-feedback  settings  that  operate  safely  without  any  prior  knowledge  of  the  system.  We  rigorously  establish  their  feasibility  through  finite-time  guarantees  on  performance,  computational  complexity,  and  stability,  matching  the  fundamental  theoretical  bounds.Statistical  models  underlie  every  layer  of  an  autonomous  system,  serving  as  representations  of  complex  data-generating  phenomena.  Typically  constructed  from  empirical  data  through  a  blend  of  explicit  modeling,  machine  learning,  and  simulation,  these  models  are  vulnerable  to  distribution  shift,  i.e.,  discrepancies  between  design  and  deployment  conditions,  which  can  jeopardize  both  performance  and  safety.  In  Part  2,  we  investigate  distributionally  robust  optimization  (DRO)  methods  for  control,  prediction,  communication,  and  unsupervised  learning  to  guard  against  model  misspecification  and  distribution  shifts.  DRO  blends  average-case  optimality  with  worst‑case  guarantees:  by  maximizing  expected  performance  against  the  least‑favorable  statistical  model  consistent  with  the  available  data,  it  strikes  a  balanced  trade-off  between  robustness  and  performance  informed  by  data.Autonomous  control  systems  must  often  balance  several  performance  goals,  such  as  cost  efficiency,  robustness,  risk  tolerance,  and  stability,  while  meeting  practical  constraints  such  as  suitability  for  real‑time  implementation  and  scalability.  Because  these  design  problems  are  inherently  infinite‑dimensional,  only  a  handful  of  special  cases  admit  exact,  tractable  solutions  (e.g.,  Linear‑Quadratic‑Gaussian,  ℋ∞‑optimal,  or  regret‑optimal  control)  while  widely  studied  formulations  like  mixed  ℋ₂/ℋ∞  control  remain  unresolved.  In  Part  3,  we  present  non‑rational  control,  a  unified  framework  that  makes  many  such  problems  both  solvable  and  implementable.  The  key  is  an  optimize‑then‑approximate  strategy  that  delivers  provably  near‑optimal,  stabilizing,  finite‑order  (rational)  controllers  even  when  the  true  optimum  resides  in  an  infinite‑dimensional  (non‑rational)  policy  space.
■590    ▼aSchool  code:  0037.
■650  4▼aRobust  control
■650  4▼aClosed  loop  systems
■650  4▼aOptimization  techniques
■650  4▼aDynamical  systems
■650  4▼aSystem  theory
■650  4▼aComputer  science
■650  4▼aSystems  science
■690    ▼a0984
■690    ▼a0790
■71020▼aCalifornia  Institute  of  Technology▼bEngineering  and  Applied  Science.
■7730  ▼tDissertations  Abstracts  International▼g87-01B.
■790    ▼a0037
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359310▼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
    TF15262 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.