簡易檢索 / 詳目顯示

研究生: 洪權甫
HUNG, Chuan-Fu
論文名稱: 藉由物件偵測與多動作識別之機器人演示學習系統
Robot Learning from Demonstration System using Object Detection and Multi-Action Recognition
指導教授: 王偉彥
Wang, Wei-Yen
口試委員: 王坤卿
Wang, Kun-Ching
陳翔傑
Chen, Hsiang-Chieh
王偉彥
Wang, Wei-Yen
蔣欣翰
Chiang, Hsin-Han
口試日期: 2022/01/06
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: 2022
畢業學年度: 110
語文別: 中文
論文頁數: 50
中文關鍵詞: 演示學習基於聚類分析的動作辨識法基於鏈接向量和虛擬關節的幾何分析機器人雙手臂即時模仿演示者架構控制導向之單攝影機測距
英文關鍵詞: learning from demonstration (LfD), action recognition method based on cluster analysis, geometrical analysis based on link vectors and virtual joints (GA-LLVJ), real-time motion following with dual arm, control-guided single-camera ranging
研究方法: 實驗設計法
DOI URL: http://doi.org/10.6345/NTNU202200224
論文種類: 學術論文
相關次數: 點閱:79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
  • 第一章 緒論 1 1.1 研究動機與目的 1 1.2 論文架構 3 第二章 文獻探討 4 2.1 示範中學習 4 2.2 基於鏈接向量和虛擬關節的幾何分析 9 第三章 硬體平台介紹 13 3.1 擬人型機器人 - ROBOTIS OP3 13 3.2 Kinect v2 RGBD攝影機 14 第四章 人類動作辨識與擬人型機器人模仿系統 15 4.1 示範中學習的實踐 15 4.2 人體關節角度與擬人型機器人映射方法 16 4.3 基於聚類分析之動作辨識法 19 4.4 擬人型機器人之人類上半身即時動作模仿 26 4.5 單攝影機測距 27 第五章 實驗與分析 30 5.1 動作辨識分析 30 5.2 人體關節角度與擬人型機器人映射分析 35 5.2.1 右肩膀的Roll分析 36 5.2.2 右肩膀的Pitch分析 39 5.2.3 右手肘角度分析 41 5.3 多機模仿架構 43 第六章 結論與貢獻 46 6.1 論文貢獻 46 6.2 結論 47 參考文獻 48 自傳 49 學術成就 50

    [1] P.-J. Hwang, C.-C. Hsu and W.-Y. Wang, "Development of a Mimic Robot—Learning From Demonstration Incorporating Object Detection and Multiaction Recognition," IEEE Consumer Electronics Magazine, vol. 9, no. 3, pp. 79-87, 2020.
    [2] B. D. Argall, S. Chernova, M. Veloso and B. Browning, "A survey of robot learning from demonstration," Robotics and Autonomous Systems, vol. 57, no. 5, pp. 469-483, 2009.
    [3] J. Redmon and A. Farhadi, "YOLOv3: An Incremental Improvement," arXiv, 2018.
    [4] A. Z. Joao Carreira, "Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
    [5] Z. Zhang, Y. Niu, Z. Yan and S. Lin, "Real-Time Whole-Body Imitation by Humanoid Robots and Task-Oriented Teleoperation Using an Analytical Mapping Method and Quantitative Evaluation," Applied Sciences, vol. 8, no. 10, p. 2005, 22 October 2018.
    [6] Robotis, "Robotis," Robotis, [Online]. Available: https://www.robotis.com/.
    [7] "Kinect for Windows SDK 2.0," Microsoft, 2014. [Online]. Available: https://www.microsoft.com/en-us/download/details.aspx?id=44561. [Accessed 29 12 2021].
    [8] A. Mobini, S. Behzadipour and M. S. Foumani, "Accuracy of Kinect’s skeleton tracking for upper body rehabilitation applications," Disability and Rehabilitation: Assistive Technology, vol. 9, no. 4, pp. 344-352, 2014.
    [9] Q. Wang, G. Kurillo, F. Ofli and R. Bajcsy, "Evaluation of Pose Tracking Accuracy in the First and Second Generations of Microsoft Kinect," in 2015 International Conference on Healthcare Informatics, Dallas, TX, USA, 2015.
    [10] zeFrenchy, "stack overflow," [Online]. Available: https://i.stack.imgur.com/LPlP3.png.
    [11] "Coordinate mapping," Microsoft, 21 10 2014. [Online]. Available: https://docs.microsoft.com/en-us/previous-versions/windows/kinect/dn785530(v=ieb.10). [Accessed 29 12 2021].
    [12] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher and P, "Scikit-learn: Machine Learning in Python," Journal of Machine Learning Research, vol. 12, pp. 2825-2830, 2011.
    [13] M. Muja and D. G. Lowe, "Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration," International Conference on Computer Vision Theory and Applications (VISAPP’09), pp. 331-340, 2009.
    [14] M. Muja and D. Lowe, FLANN-Fast Library for Approximate Nearest Neighbors User Manual, Vancouver, BC, Canada: Computer Science Department, University of British Columbia, 2009.

    無法下載圖示 電子全文延後公開
    2027/02/08
    QR CODE