簡易檢索 / 詳目顯示

研究生: 陳豈銘
Chi-Ming Chen
論文名稱: 以深度學習技術進行隨機堆疊擺放之零件的辨識及定位
Recognition and Positioning of Randomly Stacked Parts Using Deep Learning Techniques
指導教授: 林清安
Ching-An Lin
口試委員: 陳羽薰
黃中人
學位類別: 碩士
Master
系所名稱: 工程學院 - 機械工程系
Department of Mechanical Engineering
論文出版年: 2023
畢業學年度: 112
語文別: 中文
論文頁數: 163
中文關鍵詞: 物理引擎點資料處理深度學習機械手臂隨機拾取
外文關鍵詞: Physics engine, Point data processing, Deep learning, Robotic arms, Random bin picking
相關次數: 點閱:90下載:0
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

  • 摘要 I Abstract II 誌謝 III 目錄 IV 圖目錄 VIII 表目錄 XV 第一章 緒論 1 1.1 研究動機與目的 1 1.2 研究方法 2 1.3 文獻探討 4 1.3.1機械手臂隨機拾取 4 1.3.1.1夾取資訊分析 10 1.3.1.2 3D機器視覺之應用 13 1.3.2 研究議題及解決方案 20 1.4論文架構 20 第二章自動化產生點雲深度學習所需之數據集 22 2.1以物理引擎模擬零件之隨機擺放 22 2.1.1虛擬世界Pybullet 23 2.1.2物理模擬環境之建置 25 2.1.3零件坐標系之校正 27 2.1.4產生碰撞體積 29 2.1.5模擬零件之隨機擺放 31 2.2以點資料處理取得隨機擺放姿態之點雲 38 2.2.1產生標準點雲 39 2.2.2產生隨機擺放姿態之點雲 42 2.2.3以模擬化掃描進行遮蔽點移除 43 2.3以點資料處理取得各別零件之殘缺點雲 48 2.4點雲之資料格式 50 第三章 點雲分割之深度學習 52 3.1訓練點雲分割之深度學習模型 52 3.1.1 深度學習模型PointNet++ 53 3.1.2標準化點雲數據 62 3.1.3點雲數據增強 64 3.1.4深度學習之訓練過程 66 3.2點雲分割深度學習訓練結果 69 3.3點雲分割深度學習驗證結果 72 第四章 以點雲匹配之方位進行夾取分析 80 4.1 取得零件之夾取資訊 84 4.2 以點雲匹配取得現場方位 89 4.3取得實際夾取場景 91 4.3.1點雲場景重建 92 4.3.2轉換夾取點資訊 94 4.3分析夾取順序 95 4.4夾爪夾取之干涉檢測 98 4.4.1 產生夾爪運動軌跡點雲 98 4.4.2 以最近鄰近點搜索法搜索干涉點 101 第五章 實例驗證 107 5.1硬體設備 107 5.2軟體開發工具與系統環境 111 5.3系統運作流程 114 5.4實例驗證 119 5.4.1取得零件的夾取資訊. 119 5.4.2取得點雲資料及前處理 122 5.4.3以深度學習模型進行點雲分割 124 5.4.4以深度學習模型進行點雲匹配 125 5.4.5以點雲匹配之方位進行點雲場景重建 126 5.4.5以點雲匹配之方位轉換夾取資訊 128 5.4.6零件之夾取與分類 128 5.5結果與討論 133 第六章 結論與未來研究方向 137 6.1結論 137 6.2未來研究方向 139 參考文獻 141

    [1] Yanagihara Yoshimasa and Toshiro Kita (1991), “Parts picking in disordered environment,” IEEE International Workshop on Intelligent Robots and Systems , November 03-05, Osaka, Japan, pp. 517-522.
    [2] C. R. Hema, M.P. Paulraj, R. Nagarajan and Sazali Yaacob (2006), “Object localization using stereo sensors for adept scara robot,” IEEE Conference on Robotics Automation and Mechatronics, June 01-03, Bangkok, Thailand, pp. 1-5.
    [3] Martinez Carlos, Heping Chen and Remus Boca (2015), “ Automated 3D vision guided bin picking process for randomly located industrial parts,” IEEE International Conference on Industrial Technology, March 17-19, Seville, Spain, pp. 3172-3177.
    [4] 劉彥峰(2018),「以機械手臂輔助零件隨機拾取與表面瑕疵檢測之系統開發與應用」,碩士論文,國立臺灣科技大學機械工程系研究所。
    [5] Tuan-Tang Le and Chyi-Yeu Lin (2019), “picking for planar objects based on a deep learning network: a case study of USB packs,” Sensors, Vol. 19, No.16.
    [6] 賴以衛(2022),「以3D深度學習及點雲匹配技術進行機械手臂自動化複雜零件分類」,碩士論文,國立臺灣科技大學機械工程系研究所。
    [7] 林建利(2023),「以點資料處理及深度學習自動化分類堆疊擺放之零件」,碩士論文,國立臺灣科技大學機械工程系研究所。
    [8] 林冠成(2023),「以3D CAD模型及點雲匹配之深度學習進行複雜零件的隨機拾取」,碩士論文,國立臺灣科技大學機械工程系研究所。
    [9] 王柏富(2019),「以3D CAD模型及3D點資料處理技術進行自動化機械手臂物件夾取」,碩士論文,國立臺灣科技大學機械工程系研究所。
    [10] 張仁智(2019),「以機械手臂進行複雜幾何零件之自動化夾取」,碩士論文,國立臺灣科技大學機械工程系研究所。
    [11] I.A. Sainul, Sankha Deb and Alok Kanti Deb (2019), “A novel object slicing based grasp planner for 3D object grasping using underactuated robot gripper,” IECON 2019-45th Annual Conference of the IEEE Industrial Electronics Society, October 14-17, Lisbon, Portugal, Vol. 1, pp. 585-590.
    [12] Hongzhuo Liang, Xiaojian Ma, Suang Li, Michael Görner, Song Tang, Bin Fang, Fuchun Sun, Jianwei Zhang (2019), “Pointnetgpd: Detecting grasp configurations from point sets,” International Conference on Robotics and Automation (ICRA), May 20-24, Montreal, QC, Canada, pp. 3629-3635.
    [13] Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang and Jianxiong Xiao (2015), “3d shapenets: A deep representation for volumetric shapes,” IEEE conference on computer vision and pattern recognition, June 07-12, Boston, MA, USA, pp. 1912-1920.
    [14] Peng-Shuai Wang, Yu-Xiao Guo, Chun-Yu Sun and Xin Tong (2017), “O-cnn: Octree-based convolutional neural networks for 3d shape analysis, ” ACM Transactions On Graphics (TOG), Vol. 36, No.4, pp. 1-11.
    [15] Daniel Maturana and Sebastian Scherer (2015), “Voxnet: A 3d convolutional neural network for real-time object recognition,” IEEE/RSJ International Conference on Intelligent Robots and Systems, September 28 – October 02, Hamburg, Germany, pp. 922-928.
    [16] Charles R. Qi, Hao Su, Kaichun Mo and Leonidas J. Guibas (2017), “Pointnet: Deep learning on point sets for 3d classification and segmentation,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, Honolulu, HI, USA, pp. 652-660.
    [17] Charles R. Qi, Li Yi, Hao Su and Leonidas J. Guibas (2017), “PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space,” Advances in neural information processing systems, MIT, Cambridge, pp. 5099-5108.
    [18] Paul J. Besl and Neil D. McKay (1992), “A Method for Registration of 3-D Shapes,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 14, No. 2, pp. 239-256.
    [19] Jiaolong Yang, Hongdong Li, Dylan Campbell and Yunde Jia (2015), “Go-ICP: A Globally Optimal Solution to 3D ICP Point-set Registration,” IEEE transactions on Pattern Analysis and Machine Intelligence, Vol. 38, No. 11, pp. 2241-2254.
    [20] Radu Bogdan Rusu, Nico Blodow and Michael Beetz (2009), “Fast Point Feature Histograms (FPFH) for 3D Registration,” IEEE International Conference on Robotics and Automation, May 12-17, Kobe, Japan, pp. 3212-3217.
    [21] Martin A. Fischler and Robert C. Bolles (1981), “Random Sample Consensus: a Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography,” Communications of the ACM, Vol. 24, No. 11, pp. 381-395.
    [22] Shengyu Huang, Zan Gojcic, Mikhail Usvyatsov, Andreas Wieser and Konrad Schindler (2021), “Predator: Registration of 3d Point Clouds with Low Overlap,” IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 20-25, Nashville, TN, USA, pp. 4267-4276.
    [23] Lifa Zhu, Haining Guan, Changwei Lin and Renmin Han (2022), “Leveraging Inlier Correspondences Proportion for Point Cloud Registration,” arXiv preprint, arXiv:2201.12094.
    [24] Khaled Mamou, E Lengyel and A Peters (2016), Game Engine Gems 3, A K Peters/CRC Press, USA.
    [25] Serge Belongie (1999), “Rodrigues' Rotation Formula.” MathWorld--A Wolfram Web Resource, created by Eric W. Weisstein.
    https://mathworld.wolfram.com/RodriguesRotationFormula.html.
    [26] Liang Pan, Xinyi Chen, Zhongang Cai, Junzhe Zhang, Haiyu Zhao, Shuai Yi and Ziwei Liu (2021), “Variational relational point completion network.,” IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 20-25, Nashville, TN, USA, pp. 8524-8533.
    [27] Sagi Katz, Ayellet Tal and Ronen Basri (2007), “Direct Visibility of Point Sets,” ACM SIGGRAPH 2007 papers, Vol. 26, No. 3, Article 24, pp. 24-es.
    [28] Jon Louis Bentley (1975), “Multidimensional binary search trees used for associative searching,” Communications of the ACM, Vol. 18, No. 9, pp. 509-517.
    [29] https://physim etrics.com/hp-3d-structured-light-scanner-pro-s3/
    [30] https://www.epson.eu/en_EU/
    [31] https://schunk.com/ca/en
    [32] https://pointclouds.org/
    [33] https://www.ptc.com/tw/products/creo
    [34] https://pointclouds.org/
    [35] https://pybullet.org/
    [36] http://www.open3d.org/

    無法下載圖示 全文公開日期 2025/12/18 (校內網路)
    全文公開日期 2025/12/18 (校外網路)
    全文公開日期 2025/12/18 (國家圖書館:臺灣博碩士論文系統)
    QR CODE