簡易檢索 / 詳目顯示

研究生: 柯宏瑨
Ko, Hung-Chin
論文名稱: 使用機器人視覺及安全軌跡規劃於自動化汽車車門噴塗系統之研究
Study of Automated Car Door Painting System with Robotic Vision and Safety Trajectory Planning
指導教授: 陳瑄易
Chen, Syuan-Yi
口試委員: 林政宏
Lin, Cheng-Hung
蔣欣翰
Chiang, Hsin-Han
陳瑄易
Chen, Syuan-Yi
口試日期: 2023/10/12
學位類別: 碩士
Master
系所名稱: 電機工程學系
Department of Electrical Engineering
論文出版年: 2023
畢業學年度: 112
語文別: 中文
論文頁數: 57
中文關鍵詞: 機器人視覺軌跡規劃機械手臂工作空間監控人機協作安全
英文關鍵詞: Robitic vision, trajectory planning, robot arm, workspace monitoring, safe human-robot collaboration
研究方法: 實驗設計法
DOI URL: http://doi.org/10.6345/NTNU202301779
論文種類: 學術論文
相關次數: 點閱:161下載:10
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報
  • 自工業4.0興起後,機器手臂導入自動化的發展成為智慧製造中不可或缺的一部分,在許多生產或加工的工廠中可以見到機器手臂的應用,由於其具備快速及穩定的優點,使得製造過程得以在更短的時間內得到更好的成果,並大幅減少了人力及時間成本。本論文透過六軸協作型機器手臂整合RGB攝影機與二維光達執行汽車車門自動化噴漆的任務,首先機器手臂根據使用者設定的四個位置拍攝車門的影像,並將其儲存,透過影像拼接技術的幫助,將四張影像根據車門的特徵拼接,藉此得到完整的欲噴塗車門之影像。獲得完整的汽車車門影像後,使用色彩偵測方法將欲噴塗車門之範圍從原始影像中過濾出來,再利用輪廓檢測技術擷取出欲噴塗範圍之內輪廓。軌跡規劃演算法根據內輪廓的大小規劃出若干條車門噴漆之路徑,經過座標轉換將此路徑轉換為機器手臂的末端點座標,使得機器手臂得以根據的軌跡進行噴漆任務。在機器手臂進行噴漆的過程中,由於人類操作員有時需要查看汽車車門是否發生上漆不均勻的情況,為了避免機器手臂在噴塗的過程中發生人機碰撞的情形,透過二維光達監控是否有操作人員進入機器手臂工作範圍的情況,透過安全機制的協助得以避免人機碰撞的問題產生。

    Due to the raising of Industry 4.0, the development of automation technology with robotic arms has become the indispensable requirement in modern manufacturing systems. In many production and manufacturing facilities, the application of robotic arms is commonly observed. With the advantages of speed and stability, robotic arms allow manufacturing plants to achieve better results in a shorter amount of time, significantly reducing labor and time costs. This thesis presents a system that utilizes a six-axis collaborative robot integrated with an RGB camera and a 2D LiDAR to perform the task of automating the painting process for automotive doors. The robotic arm captures images of the car door from four user-defined positions and stores them. With the assistance of image stitching technology, the four images are merged based on the features of the car door to obtain a complete image of the door to be painted. After obtaining the complete image of the automotive door, color-based detection is used to filter out the painting area from the door image. Then, contour detection technology is employed to extract the inner contour of the area to be painted. The trajectory planning algorithm generates multiple painting paths for the car door based on the size of the inner contour. After the coordinate transformation, these paths are converted into end-point coordinates for the robotic arm, allowing it to execute the painting task along the planned trajectories. During the painting process, as human operators may need to inspect whether the car door is painted evenly, a 2D LiDAR is used to monitor changes in the surrounding environment. In the case of a human operator entering the working area of the robotic arm, the safety mechanism can be executed to avoid human-robot collisions.

    誌 謝 i 摘  要 ii ABSTRACT iii 目 錄 v 表 目 錄 vii 圖 目 錄 viii 第一章 緒論 1 1.1 研究背景 1 1.2 研究動機與目的 2 1.3 文獻探討 2 1.3.1 機器手臂之應用 2 1.3.2 機器手臂安全機制背景介紹 6 1.4 論文架構 8 第二章 機器手臂實驗平台及系統架構 9 2.1 實驗平台介紹 9 2.2 硬體設備 11 2.2.1 機器手臂 11 2.2.2 末端治具 13 2.2.3 機器視覺攝影機 14 2.2.4 光達感測器 17 2.3 系統架構 20 2.3.1 硬體設備連線及資料傳輸 20 2.3.2 人機介面設計 22 第三章 研究內容與方法 24 3.1 汽車車門影像拼接 24 3.2 車門待噴塗區域檢測 27 3.2.1 HSL色彩檢測 27 3.2.2 輪廓檢測 29 3.3 機器手臂車門噴漆之軌跡規劃 30 3.4 二維光達座標轉換 33 3.5 人機協作安全機制 34 3.5.1 Control Barrier Function介紹 34 3.5.2 Control Barrier Function應用於機器手臂移動規劃 35 3.5.3 Control Barrier Function於本論文機器手臂應用設計 37 第四章 實驗結果與分析 40 4.1 汽車車門影像擷取與拼接 40 4.2 機器手臂軌跡規劃 42 4.3 人機協作安全機制 43 第五章 結論與未來展望 52 5.1 結論 52 5.2 未來展望 52 參考文獻 53 自  傳 56 學術成就 57

    謝翔宇,“整合機器視覺與機器手臂快換裝置之虛實整合技術應用於彈性組裝任務學習”, 國立臺灣師範大學電機工程學系,中華民國111年9月。

    M. Costanzo, G. De Maria, G. Lettera and C. Natale, "Can Robots Refill a Supermarket Shelf?: Motion Planning and Grasp Control," in IEEE Robotics & Automation Magazine, vol. 28, no. 2, pp. 61-73, June 2021, doi: 10.1109/MRA.2021.3064754.

    R. K. Megalingam, V. Prithvi Darla and C. S. Kumar Nimmala, "Autonomous Wall Painting Robot," 2020 International Conference for Emerging Technology (INCET), Belgaum, India, 2020, pp. 1-6, doi: 10.1109/INCET49848.2020.9154020.

    M. Koskinopoulou, F. Raptopoulos, G. Papadopoulos, N. Mavrakis and M. Maniadakis, "Robotic Waste Sorting Technology: Toward a Vision-Based Categorization System for the Industrial Robotic Separation of Recyclable Waste," in IEEE Robotics & Automation Magazine, vol. 28, no. 2, pp. 50-60, June 2021, doi: 10.1109/MRA.2021.3066040.

    Zhao, J., Wei, S., Sun, X., and Ji, J. (July 4, 2023). "Kinematics and trajectory planning of the masonry robot." ASME. J. Auton. Veh. Sys. July 2022; 2(3): 031005.

    S. S. Nestinger, B. Chen and H. H. Cheng, "A Mobile Agent-Based Framework for Flexible Automation Systems," in IEEE/ASME Transactions on Mechatronics, vol. 15, no. 6, pp. 942-951, Dec. 2010, doi: 10.1109/TMECH.2009.2036169.

    Lu, Z., Li, M., Annamalai, A., & Yang, C. (2020). Recent advances in robot-assisted echography: Combining perception, control and cognition. Cognitive Computation and Systems, 2(3), 85-92. https://doi.org/10.1049/ccs.2020.0015.

    K. Zbiss, A. Kacem, M. Santillo and A. Mohammadi, "Automatic Collision-Free Trajectory Generation for Collaborative Robotic Car-Painting," in IEEE Access, vol. 10, pp. 9950-9959, 2022, doi: 10.1109/ACCESS.2022.3144631.

    D. Gleeson et al., "Generating Optimized Trajectories for Robotic Spray Painting," in IEEE Transactions on Automation Science and Engineering, vol. 19, no. 3, pp. 1380-1391, July 2022, doi: 10.1109/TASE.2022.3156803.

    A. D. Ames, S. Coogan, M. Egerstedt, G. Notomista, K. Sreenath and P. Tabuada, "Control Barrier Functions: Theory and Applications," 2019 18th European Control Conference (ECC), Naples, Italy, 2019, pp. 3420-3431, doi: 10.23919/ECC.2019.8796030.

    M. Costanzo, G. De Maria, G. Lettera and C. Natale, "A Multimodal Approach to Human Safety in Collaborative Robotic Workcells," in IEEE Transactions on Automation Science and Engineering, vol. 19, no. 2, pp. 1202-1216, April 2022, doi: 10.1109/TASE.2020.3043286.

    W. He, C. Xue, X. Yu, Z. Li and C. Yang, "Admittance-Based Controller Design for Physical Human–Robot Interaction in the Constrained Task Space," in IEEE Transactions on Automation Science and Engineering, vol. 17, no. 4, pp. 1937-1949, Oct. 2020, doi: 10.1109/TASE.2020.2983225.

    Y. Wen and P. Pagilla, "Path-Constrained and Collision-Free Optimal Trajectory Planning for Robot Manipulators," in IEEE Transactions on Automation Science and Engineering, vol. 20, no. 2, pp. 763-774, April 2023, doi: 10.1109/TASE.2022.3169989.

    DOBOT CR5六軸機器手臂規格,資料來源https://www.dobot-robots.com/products/cr-series/cr5.html

    IDS RGB攝影機,資料來源 https://en.ids-imaging.com/store/gv-5880cp-rev-2-2.html

    GenICam通訊協議,資料來源 https://www.baslerweb.com/zh-tw/learning/genicam-standard/

    台灣西克2-D LiDAR規格,資料來源https://www.sick.com/tw/zf/lidar/2d-lidar/tim/tim551-2050001/p/p343045

    Nikolaos Nikolakis, Vasilis Maratos, Sotiris Makris, “A cyber physical system (CPS) approach for safe human-robot collaboration in a shared workplace,” Robotics and Computer-Integrated Manufacturing, vol. 56, 2019, pp. 233-243, ISSN 0736-5845, https://doi.org/10.1016/j.rcim.2018.10.003.

    HSL色彩檢測,資料來源https://jongraphy.blogspot.com/2018/04/lightroom-5-hsl.html

    F. Ferraguti et al., "Safety and Efficiency in Robotics: The Control Barrier Functions Approach," in IEEE Robotics & Automation Magazine, vol. 29, no. 3, pp. 139-151, Sept. 2022, doi: 10.1109/MRA.2022.3174699.

    下載圖示
    QR CODE