본문

Geometric- and Learning-Based Perception and Control for Robotic Systems- [electronic resource]
Geometric- and Learning-Based Perception and Control for Robotic Systems - [electronic res...
내용보기
Geometric- and Learning-Based Perception and Control for Robotic Systems- [electronic resource]
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.
신착도서 더보기
최근 3년간 통계입니다.

소장정보

  • 예약
  • 소재불명신고
  • 나의폴더
  • 우선정리요청
  • 비도서대출신청
  • 야간 도서대출신청
소장자료
등록번호 청구기호 소장처 대출가능여부 대출정보
TF06065 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.