본문

서브메뉴

Geometric- and Learning-Based Perception and Control for Robotic Systems- [electronic resource]
Geometric- and Learning-Based Perception and Control for Robotic Systems - [electronic res...
Geometric- and Learning-Based Perception and Control for Robotic Systems- [electronic resource]

상세정보

자료유형  
 학위논문파일 국외
최종처리일시  
20240214100319
ISBN  
9798380618939
DDC  
629.8
저자명  
Fahandezhsaadi, Saman.
서명/저자  
Geometric- and Learning-Based Perception and Control for Robotic Systems - [electronic resource]
발행사항  
[S.l.]: : University of California, Berkeley., 2021
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2021
형태사항  
1 online resource(112 p.)
주기사항  
Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
주기사항  
Advisor: Tomizuka, Masayoshi.
학위논문주기  
Thesis (Ph.D.)--University of California, Berkeley, 2021.
사용제한주기  
This item must not be sold to any third party vendors.
초록/해제  
요약A reliable, accurate, and robust robotic system is highly dependent on perception, the ability of a robot to sense and interpret its environment. A variety of sensing technologies and methods can be integrated for perception purposes depending on a particular robotic setting and the surrounding. Uncertainty, environment variability, and limited sensing capabilities are factors that pose challenges to the perception task. This dissertation focuses on exploiting geometric and probabilistic characteristics as well as hidden structural properties of robotic systems and their surroundings to address some of these challenges.A geometric state estimator is presented for an agent with the ability to measure single ranges to fixed points (anchors) in its environment. The state estimator is generic, and can be immediately applied to any robot with the range sensor. A greedy optimization algorithm is developed to select the best measurement in each time step. The selection algorithm is added to the extended Kalman filter, resulting in choosing the best measurement out of all the available range values. The effectiveness of the presented estimator algorithm is demonstrated through experimental setup for a flying robot.The estimation accuracy is improved under the assumption that the ranging infrastructure is not perfect. A real\extendash time restructure of the setup allows to enhance the localization accuracy of the ego agent. The estimator is incorporated into an adaptive algorithm. Using a mobile UWB ranging sensor, the mobile anchor moves to improve localization accuracy of the main robot. The algorithm reconstructs the range sensor network in real\extendash time to minimize the covariance matrix in the extended Kalman filter. The presented algorithm is experimentally validated in a network of range sensors. A probabilistic\extendash based approach for pose estimation using point clouds is presented. The point registration algorithm is based on directional statistics, which estimates the rigid transformation (i.e. rotation matrix and translation vector) between two point cloud frames. The algorithm outputs the robot's pose estimation (location and orientation). The framework transforms the point registration task on a unit sphere, and solves the problem in two steps of correspondence and alignment. In particular, a mixture model (as an example of directional statistics on unit sphere in R3) is adopted and the process of point registration has been carried out by the two phases of Expectation\extendash Maximization algorithm. The method has been evaluated with point clouds from LiDAR sensors in an indoor environment. A deep graph network is presented, to improve the robustness and accuracy of point registration. The framework models the point registration task based on the flexible architecture of Graph Network (GN) blocks. Three main modules\extendash an encoder, a core, and a decoder\extendash are responsible to perform both steps of correspondence and assignment in point matching process. The experiments and examination of the proposed model shows comparable results with other state\extendash of\extendash the\extendash art geometric\extendash or learning\extendash based algorithm in terms of accuracy as well as robustness with regard to bad initial conditions and presence of outliers in data points. The flexibility and configurability of the framework allows to easily change, add, and/or combine various customized deep modules and mechanisms to the presented graph\extendash based framework.The last part of this dissertation, studies ReLU network architecture in the domain of control. The input/output domain and structure of the network and its proximity to explicit Model Predictive Control (eMPC). The mathematical equivalency of feedforward ReLU and piecewise affine function is presented, and we investigate the prospect of representing state feedback policy of eMPC as a ReLU DNN, and vice versa. A sampling based method has been developed to identify input\extendash space regions in ReLU networks.
일반주제명  
Robotics.
일반주제명  
Computer engineering.
일반주제명  
Statistics.
키워드  
Perception task
키워드  
Ranging sensor
키워드  
Limited sensing capabilities
기타저자  
University of California, Berkeley Mechanical Engineering
기본자료저록  
Dissertations Abstracts International. 85-04B.
기본자료저록  
Dissertation Abstract International
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008240612s2021      us  |||||||||||||||c||eng  d
■001000016931873
■00520240214100319
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798380618939
■035    ▼a(MiAaPQ)AAI28868910
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a629.8
■1001  ▼aFahandezhsaadi,  Saman.
■24510▼aGeometric-  and  Learning-Based  Perception  and  Control  for  Robotic  Systems▼h[electronic  resource]
■260    ▼a[S.l.]:▼bUniversity  of  California,  Berkeley.  ▼c2021
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2021
■300    ▼a1  online  resource(112  p.)
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-04,  Section:  B.
■500    ▼aAdvisor:  Tomizuka,  Masayoshi.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Berkeley,  2021.
■506    ▼aThis  item  must  not  be  sold  to  any  third  party  vendors.
■520    ▼aA  reliable,  accurate,  and  robust  robotic  system  is  highly  dependent  on  perception,  the  ability  of  a  robot  to  sense  and  interpret  its  environment.  A  variety  of  sensing  technologies  and  methods  can  be  integrated  for  perception  purposes  depending  on  a  particular  robotic  setting  and  the  surrounding.  Uncertainty,  environment  variability,  and  limited  sensing  capabilities  are  factors  that  pose  challenges  to  the  perception  task.  This  dissertation  focuses  on  exploiting  geometric  and  probabilistic  characteristics  as  well  as  hidden  structural  properties  of  robotic  systems  and  their  surroundings  to  address  some  of  these  challenges.A  geometric  state  estimator  is  presented  for  an  agent  with  the  ability  to  measure  single  ranges  to  fixed  points  (anchors)  in  its  environment.  The  state  estimator  is  generic,  and  can  be  immediately  applied  to  any  robot  with  the  range  sensor.  A  greedy  optimization  algorithm  is  developed  to  select  the  best  measurement  in  each  time  step.  The  selection  algorithm  is  added  to  the  extended  Kalman  filter,  resulting  in  choosing  the  best  measurement  out  of  all  the  available  range  values.  The  effectiveness  of  the  presented  estimator  algorithm  is  demonstrated  through  experimental  setup  for  a  flying  robot.The  estimation  accuracy  is  improved  under  the  assumption  that  the  ranging  infrastructure  is  not  perfect.  A  real\extendash  time  restructure  of  the  setup  allows  to  enhance  the  localization  accuracy  of  the  ego  agent.  The  estimator  is  incorporated  into  an  adaptive  algorithm.  Using  a  mobile  UWB  ranging  sensor,  the  mobile  anchor  moves  to  improve  localization  accuracy  of  the  main  robot.  The  algorithm  reconstructs  the  range  sensor  network  in  real\extendash  time  to  minimize  the  covariance  matrix  in  the  extended  Kalman  filter.  The  presented  algorithm  is  experimentally  validated  in  a  network  of  range  sensors.  A  probabilistic\extendash  based  approach  for  pose  estimation  using  point  clouds  is  presented.  The  point  registration  algorithm  is  based  on  directional  statistics,  which  estimates  the  rigid  transformation  (i.e.  rotation  matrix  and  translation  vector)  between  two  point  cloud  frames.  The  algorithm  outputs  the  robot's  pose  estimation  (location  and  orientation).  The  framework  transforms  the  point  registration  task  on  a  unit  sphere,  and  solves  the  problem  in  two  steps  of  correspondence  and  alignment.  In  particular,  a  mixture  model  (as  an  example  of  directional  statistics  on  unit  sphere  in  R3)  is  adopted  and  the  process  of  point  registration  has  been  carried  out  by  the  two  phases  of  Expectation\extendash  Maximization  algorithm.  The  method  has  been  evaluated  with  point  clouds  from  LiDAR  sensors  in  an  indoor  environment.  A  deep  graph  network  is  presented,  to  improve  the  robustness  and  accuracy  of  point  registration.  The  framework  models  the  point  registration  task  based  on  the  flexible  architecture  of  Graph  Network  (GN)  blocks.  Three  main  modules\extendash  an  encoder,  a  core,  and  a  decoder\extendash  are  responsible  to  perform  both  steps  of  correspondence  and  assignment  in  point  matching  process.  The  experiments  and  examination  of  the  proposed  model  shows  comparable  results  with  other  state\extendash  of\extendash  the\extendash  art  geometric\extendash  or  learning\extendash  based  algorithm  in  terms  of  accuracy  as  well  as  robustness  with  regard  to  bad  initial  conditions  and  presence  of  outliers  in  data  points.  The  flexibility  and  configurability  of  the  framework  allows  to  easily  change,  add,  and/or  combine  various  customized  deep  modules  and  mechanisms  to  the  presented  graph\extendash  based  framework.The  last  part  of  this  dissertation,  studies  ReLU  network  architecture  in  the  domain  of  control.  The  input/output  domain  and  structure  of  the  network  and  its  proximity  to  explicit  Model  Predictive  Control  (eMPC).  The  mathematical  equivalency  of  feedforward  ReLU  and  piecewise  affine  function  is  presented,  and  we  investigate  the  prospect  of  representing  state  feedback  policy  of  eMPC  as  a  ReLU  DNN,  and  vice  versa.  A  sampling  based  method  has  been  developed  to  identify  input\extendash  space  regions  in  ReLU  networks.
■590    ▼aSchool  code:  0028.
■650  4▼aRobotics.
■650  4▼aComputer  engineering.
■650  4▼aStatistics.
■653    ▼aPerception  task
■653    ▼aRanging  sensor
■653    ▼aLimited  sensing  capabilities
■690    ▼a0771
■690    ▼a0464
■690    ▼a0463
■71020▼aUniversity  of  California,  Berkeley▼bMechanical  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g85-04B.
■773    ▼tDissertation  Abstract  International
■790    ▼a0028
■791    ▼aPh.D.
■792    ▼a2021
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16931873▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.
■980    ▼a202402▼f2024

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
    TF07415 전자도서 마이폴더 부재도서신고 비도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.