English  |  正體中文  |  简体中文  |  Items with full text/Total items : 55184/89457 (62%)
Visitors : 10679251      Online Users : 87
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/47066

    Title: 異質機器人在未知環境中的視覺式合作巡航
    Other Titles: Vision-Based Cooperative Navigation of Heterogeneous Robots in Unknown Environments
    Authors: 王銀添
    Contributors: 淡江大學機械與機電工程學系
    Keywords: 行動機器人;同時定位與建圖;異質機器人;特徵偵測與追蹤;地圖管理;Mobile Robots;Simultaneous Localization and Mapping;HeterogeneousRobots;Feature Detection and Tracking;Map Management
    Date: 2009
    Issue Date: 2010-04-15 16:11:53 (UTC+8)
    Abstract: 本研究將針對異質機器人在未知與大範圍環境中的影像特徵偵測與追蹤、同 時定位與建圖(SLAM)、與合作巡航等議題,進行為期兩年的研究。目標是在兩年內 完成一套整合與執行系統,使兩部異質機器人具備在未知環境中同時定位與建圖的能 力,以順利進行合作巡航與傳遞訊息等任務。 本計畫分兩年執行:在第一年,將改良影像特徵偵測與追蹤方法,以及規劃 特徵初始化程序與影像深度演算法,並且整合應用於人形機器人,以便在未知環境中 執行同時定位與建圖的任務。本年度將使用擴張型卡爾曼過濾器進行人形機器人系統 狀態的估測,因此,也將進行擴張型卡爾曼過濾器的共變異數矩陣之推導與特性分 析。第二年將利用機率式SLAM 的分解概念來設計輪式驅動機器人的同時定位與建 圖演算法,將使用粒子過濾器估測機器人的狀態,以擴張型卡爾曼過濾器估測地標的 位置。所建立的機率式SLAM 演算法將可以應用於輪式驅動機器人,以便在未知環 境中執行任務。最後將人形與輪式驅動等異質機器人整合,在未知環境中進行SLAM 訊息傳遞與合作巡航等任務。本計畫所發展的異質機器人合作巡航系統,將以實地測 試方式評估所提相關演算法的實用性。 In this research plan, we propose a two-year investigation to focus on image feature detection and tracking, robot simultaneous localization and mapping (SLAM), and robot cooperative navigation in unknown environments. The aim of this project is to develop an integrated execution system, providing two heterogeneous robots with suitable SLAM competence in unknown and large-scale environments in order to perform the tasks of data communication and cooperative navigation. This project will be performed in two years. In the first year, the modified image feature detection and tracking algorithm, including feature initialization and image depth calculation, is proposed for a humanoid robot to perform SLAM in unknown environments. The SLAM is implemented by utilizing an extended Kalman filter (EKF) for estimation of system states. Therefore, the covariance matrix will be derived and the characteristics of EKF will be analyzed. In the second year, the concept of partitioned probabilistic SLAM is applied to design the SLAM algorithm for wheeled mobile robot. In the algorithm, we use a particle filter to determine the belief state of the robot, and apply extended Kalman filters to identify the position states of landmarks. Based on the probabilistic SLAM, the wheeled mobile robot is able to perform tasks in unknown environments. Two heterogeneous robots, including humanoid and wheeled robots, will be further integrated to perform the tasks of data communication and cooperative navigation in unknown and large-scale environments. The developed algorithms for feature detection and tracking, localization, and map building will be integrated with the robot systems, and furthermore the integrated system will be empirically validated based on experiments to evaluate the practical usage of the developed algorithms.
    Appears in Collections:[Graduate Institute & Department of Mechanical and Electro-Mechanical Engineering] Research Paper

    Files in This Item:

    There are no files associated with this item.

    All items in 機構典藏 are protected by copyright, with all rights reserved.

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - Feedback