본문

서브메뉴

A Practical Approach to Learning Dynamics for Rough Terrain Navigation
A Practical Approach to Learning Dynamics for Rough Terrain Navigation
A Practical Approach to Learning Dynamics for Rough Terrain Navigation

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20250211151001
ISBN  
9798382610849
DDC  
629.8
저자명  
Wang, Sean J.
서명/저자  
A Practical Approach to Learning Dynamics for Rough Terrain Navigation
발행사항  
[Sl] : Carnegie Mellon University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
139 p
주기사항  
Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
주기사항  
Advisor: Johnson, Aaron M.
학위논문주기  
Thesis (Ph.D.)--Carnegie Mellon University, 2024.
초록/해제  
요약Unmanned ground vehicles offer great potential, but struggle in rough terrain environments due to their inability to reason about complex dynamics over longer horizons. Thus, driving strategies are often short-sighted and underutilize the robot's dynamic capabilities. This thesis addresses the challenges of long-horizon, dynamics-aware decision making in rough terrain, arising from the inability to model complex system dynamics. The findings reveal two key insights: 1) leveraging low-quality simulation data can reduce training requirements of real-world dynamics models; and 2) long-horizon decision making can still utilize imprecise dynamics models through careful handling of prediction uncertainty.We first discuss our model-based reinforcement learning approach for rough terrain navigation. This approach trains a dynamics model to predict the robot's trajectory over uneven terrain and capture prediction uncertainty. Decision making uses this model along with a closed-loop divergence constraint to aid in longer-horizon trajectory prediction and prevent exploitation of potentially problematic modeling errors. We show that this approach leads to robust, non-myopic driving strategies that take full advantage of the robot's capabilities.Next, we explore leveraging simulation to reduce real-world training data requirements. This culminates in an approach that uses a large variety of simulated systems to train a dynamics model that quickly and probabilistically adapts to any new, including real-world, target system using any available target system data. Using this model within an uncertainty-aware decision making framework results in safe, albeit low performance, driving upon initialization. As more target system observations are collected, the adaptive dynamics model becomes more tailored to the target system resulting in increased driving performance.Finally, we combine these concepts to form a non-myopic rough terrain navigation framework that can quickly and robustly adapt to new target systems. We show that upon initialization, this framework chooses conservative routes that avoids obstacles. However, after just one demonstration of driving over obstacles, the framework chooses more aggressive routes over obstacles that match the system's capabilities.
일반주제명  
Robotics
일반주제명  
Information technology
키워드  
Model-based reinforcement learning
키워드  
Rough terrain navigation
키워드  
Sim2real
키워드  
Terrain environments
키워드  
Learning dynamics
기타저자  
Carnegie Mellon University Mechanical Engineering
기본자료저록  
Dissertations Abstracts International. 85-11B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017160346
■00520250211151001
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798382610849
■035    ▼a(MiAaPQ)AAI30993985
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a629.8
■1001  ▼aWang,  Sean  J.
■24512▼aA  Practical  Approach  to  Learning  Dynamics  for  Rough  Terrain  Navigation
■260    ▼a[Sl]▼bCarnegie  Mellon  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a139  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-11,  Section:  B.
■500    ▼aAdvisor:  Johnson,  Aaron  M.
■5021  ▼aThesis  (Ph.D.)--Carnegie  Mellon  University,  2024.
■520    ▼aUnmanned  ground  vehicles  offer  great  potential,  but  struggle  in  rough  terrain  environments  due  to  their  inability  to  reason  about  complex  dynamics  over  longer  horizons.  Thus,  driving  strategies  are  often  short-sighted  and  underutilize  the  robot's  dynamic  capabilities.  This  thesis  addresses  the  challenges  of  long-horizon,  dynamics-aware  decision  making  in  rough  terrain,  arising  from  the  inability  to  model  complex  system  dynamics.  The  findings  reveal  two  key  insights:  1)  leveraging  low-quality  simulation  data  can  reduce  training  requirements  of  real-world  dynamics  models;  and  2)  long-horizon  decision  making  can  still  utilize  imprecise  dynamics  models  through  careful  handling  of  prediction  uncertainty.We  first  discuss  our  model-based  reinforcement  learning  approach  for  rough  terrain  navigation.  This  approach  trains  a  dynamics  model  to  predict  the  robot's  trajectory  over  uneven  terrain  and  capture  prediction  uncertainty.  Decision  making  uses  this  model  along  with  a  closed-loop  divergence  constraint  to  aid  in  longer-horizon  trajectory  prediction  and  prevent  exploitation  of  potentially  problematic  modeling  errors.  We  show  that  this  approach  leads  to  robust,  non-myopic  driving  strategies  that  take  full  advantage  of  the  robot's  capabilities.Next,  we  explore  leveraging  simulation  to  reduce  real-world  training  data  requirements.  This  culminates  in  an  approach  that  uses  a  large  variety  of  simulated  systems  to  train  a  dynamics  model  that  quickly  and  probabilistically  adapts  to  any  new,  including  real-world,  target  system  using  any  available  target  system  data.  Using  this  model  within  an  uncertainty-aware  decision  making  framework  results  in  safe,  albeit  low  performance,  driving  upon  initialization.  As  more  target  system  observations  are  collected,  the  adaptive  dynamics  model  becomes  more  tailored  to  the  target  system  resulting  in  increased  driving  performance.Finally,  we  combine  these  concepts  to  form  a  non-myopic  rough  terrain  navigation  framework  that  can  quickly  and  robustly  adapt  to  new  target  systems.  We  show  that  upon  initialization,  this  framework  chooses  conservative  routes  that  avoids  obstacles.  However,  after  just  one  demonstration  of  driving  over  obstacles,  the  framework  chooses  more  aggressive  routes  over  obstacles  that  match  the  system's  capabilities.
■590    ▼aSchool  code:  0041.
■650  4▼aRobotics
■650  4▼aInformation  technology
■653    ▼aModel-based  reinforcement  learning
■653    ▼aRough  terrain  navigation
■653    ▼aSim2real
■653    ▼aTerrain  environments
■653    ▼aLearning  dynamics
■690    ▼a0771
■690    ▼a0489
■690    ▼a0800
■71020▼aCarnegie  Mellon  University▼bMechanical  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g85-11B.
■790    ▼a0041
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17160346▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

Preview

Export

ChatGPT Discussion

AI Recommended Related Books


    New Books MORE
    Statistics for the past 3 years. Go to brief

    Подробнее информация.

    • Бронирование
    • не существует
    • моя папка
    • Первый запрос зрения
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    материал
    Reg No. Количество платежных Местоположение статус Ленд информации
    TF10740 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Бронирование доступны в заимствований книги. Чтобы сделать предварительный заказ, пожалуйста, нажмите кнопку бронирование

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.