English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 47249/51115 (92%)
造訪人次 : 14206648      線上人數 : 662
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜尋範圍 查詢小技巧:
  • 您可在西文檢索詞彙前後加上"雙引號",以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋,建議至進階搜尋限定作者欄位,可獲得較完整資料
  • 進階搜尋
    主頁登入上傳說明關於CCUR管理 到手機版


    請使用永久網址來引用或連結此文件: https://irlib.pccu.edu.tw/handle/987654321/45349


    題名: 多台搬運機器人路徑導引系統之實現及其在智慧工廠之應用
    Implement of Multiple Handling Robots Path Guided System and Its Application in Intelligent Factory
    作者: 蘇國和
    貢獻者: 機械工程學系數位機電碩士班
    關鍵詞: 智慧工廠
    無人搬運機器人
    雲端伺服器
    Yolo影像辨識
    平滑路徑規劃與導引
    樹梅派
    定位系統
    日期: 2018-2019
    上傳時間: 2019-11-19 13:28:29 (UTC+8)
    摘要: 智慧工廠是工業4.0的一環,為應用過去的研究成果,且柯達科技公司正為代理的德國Fischertechnik工業4.0模擬平台進行功能提升專案,因此提出此產學合作第二階段計畫,開發並實作多台搬運機器人路徑導引系統,同時將其應用於智慧工廠中,以擴充並提升原來平台的功能。為實現智慧工廠的功能要求,此無人搬運系統的架構包括四部分:(1)多台無人搬運機器人及生產模擬系統: 無人搬運機器人配備超音波測距與追隨功能,上面建有置物平台,避免物料掉落,使用Python進行程式編寫,開機後,統合所有裝置並使用藍芽裝置所提供之BLE技術和三座藍芽機台,進行距離定位,當接到指令後會追隨伺服器所指定的夾爪機器人進行搬運工作,往返於物料區與生產線間。(2)雲端伺服器: 硬體採用Intel i7-8700K處理器,GTX1080Ti GPU,軟體採用WIN10專業版搭配Apache HTTP Server,MySQL Server,使用WiFi與搬運機器人進行聯繫,並使用Yolo影像辨識技術,使辨識更準確及時。(3)室內定位系統: 使用藍芽BLE的Beacon測距功能進行三角定位,設立三邊各為8公尺長的正三角形,最小基數為3台,可彈性擴充。(4)影像辨識系統:透過樹梅派鏡頭捕獲影像後,上傳雲端伺服器,伺服器使用Yolo類神經網路即時影像辨識技術,進行位置計算及種類辨識。在上述架構下,將完成下列功能:(1)搬運機器人及生產系統的機構及控制器設計,製作與整合。(2)雲端伺服器建置,功能包括Yolo類神經網路即時影像辨識;平滑路徑規劃與導引;依特殊要求,指派等待中的搬運機器人完成其他搬運工作;伺服器紀錄搬運機器人途程上資料,如位置座標,電壓,等待時間,搬運時間等。(3)室內藍芽定位系統之設計,製作與整合。
    The intelligent factory is a part of Industry 4.0. In order to expand and apply the past research results, the second-year cooperation program with Kotec Technology Company is proposed because they are upgrading the functions of the German Fischertechnik’s industry 4.0 simulation platform. The proposed project is to help them to implement a multiple handling robots path guided system and extend its application in intelligent factory.To build an intelligent factory, the architecture of this unmanned transport system consists of four parts: (1) Multiple handling robots and production systems: The unmanned robot equipped with ultrasonic ranging sensors and the built platform to avoid the materials falling. The Python is used to program the controller. After booting, the Raspberry Pi integrates all devices and positions the distance using the BLE technology with three Bluetooth consoles. After receiving the instruction, it will follow the gripper robot designated by the server and carry it back and forth between the material area and the production line. (2) Cloud server: Hardware includes the Intel i7-8700K processor and GTX1080ti GPU. The WIN10 Pro version with Apache HTTP Server, MYSQL Server is used. WiFi is adopted to communicate with the handling robots and YOLO technology is used to identify the image. (3) Indoor positioning system: The BLE beacon ranging function is used for triangular positioning according to the establishment of the Bluetooth consoles which are spread out every 8 meters. (4) Image identification system: After receiving the uploaded image from the Raspberry Pi, the cloud server uses the YOLO neural network real-time image recognition technology to carry on the position computation and identification.Under above architecture, following functions will be completed in this project:(1)Design and implement of the mechanism of the handling robots and production system as well as the controller.(2)Establish the cloud server, which includes YOLO neural network real-time image identification, smooth path planning and guidance, assigning handling robot to work, recording handling robots data such as position coordinates, voltage, waiting time, handling time, etc.(3)Design and implement of indoor Bluetooth positioning System.
    顯示於類別:[機械工程系暨機械工程學系數位機電研究所] 研究計畫

    文件中的檔案:

    檔案 描述 大小格式瀏覽次數
    index.html0KbHTML214檢視/開啟


    在CCUR中所有的資料項目都受到原著作權保護.


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©  2006-2025  - 回饋