English  |  正體中文  |  简体中文  |  Items with full text/Total items : 52047/87178 (60%)
Visitors : 8683344      Online Users : 100
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/987654321/105763

    Title: 視覺輔助Delta機器人偵測、追蹤與夾持工作檯上之移動工件
    Other Titles: Vision-assisted detection, tracking, and clamping of moving workpiece on worktable with a Delta robot
    Authors: 林宥廷;Lin, You-Ting
    Contributors: 淡江大學機械與機電工程學系碩士班
    王銀添;Wang, Yin-Tien
    Keywords: 視覺輔助量測系統;DELTA機器人;網路連線機器人;狀態估測;移動工件;vision-assisted measurement;DELTA Robot;Status estimate;Moving Workpiece
    Date: 2015
    Issue Date: 2016-01-22 15:04:39 (UTC+8)
    Abstract: 本論文發展視覺輔助移動工件偵測與追蹤系統,應用在DELTA機器人於工作平檯上的工件夾持任務。本論文發展了三個系統包含DELTA機器人、視覺輔助量測、與移動工件狀態估測等。在機器人系統架構部分,設計機器人機構、調整與設定馬達驅動器、與規劃機器人控制器等;在視覺輔助量測系統部分,進行影像處理、攝影機校準、視覺量測模型建立、與立體工件方位量測等;在移動工件狀態估測方面,規劃平面投影轉換與卡爾曼過濾器兩種工件狀態估測器。發展完成的三個系統,整合成視覺輔助Delta機器人偵測、追蹤與夾持系統。本論文使用單部攝影機裝設在工具軸的方式擷取影像,特點包括節省設備成本與裝設空間、可同時近距離做工件檢測與分析、可避免視覺感測被遮蔽、方便工具軸任務進行中重新調整定位姿態等。另外,視覺輔助工件量測與工具軸運動路徑規劃,則是轉換到卡氏世界座標運算,以利於分析狀態估測與夾取定位的精確度。本論文也測詴多項實驗,以驗證所發展的系統之效能。
    This research develops a vision-assisted detection and tracking system, and utilizes the system to the clamping tasks of moving work-pieces on worktable with a Delta robot. Three systems are developed in this thesis include the Delta robot, vision-assisted measurement and moving work-piece estimation. In the Delta robot system, major works include the design of robot mechanism, the setting and tuning of motor drive and robot motion controller. Image processing, camera calibration, vision model and three-dimensional measurement are implemented in the vision-assisted measurement system. For the moving work-piece estimation system, the planar homography transformation is used to measure the planar coordinates of the work-piece, while the extended Kalman filter is employed to estimate the positions and velocities of the work-piece. The developed systems are integrated to perform the tasks of vision-assisted detection, tracking and clamping of moving work-pieces. This research uses single camera-in-hand vision which has the advantages of reducing cost, small installation space, close-looking investigation of work-piece, and avoidance of vision obstruction. The camera-in-hand system also enables the tool frame to adjust its attitude during a task is running. Meanwhile, the visual measurement and path planning of tool frame are implemented in Cartesian coordinate system for further analysis of state estimation and positioning. The experimental works are also carried out in the study to validate the performance of the developed systems.
    Appears in Collections:[機械與機電工程學系暨研究所] 學位論文

    Files in This Item:

    File Description SizeFormat

    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