跳到主要內容

臺灣博碩士論文加值系統

(44.200.194.255) 您好!臺灣時間:2024/07/23 04:33
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:周侑辰
研究生(外文):JHOU,YOU-CHEN
論文名稱:機器學習應用於空氣曲棍球之互動控制系統
論文名稱(外文):The Application of Machine Learning in Air Hockey Interactive Control System
指導教授:張慶龍張慶龍引用關係
指導教授(外文):CHANG,CHING-LUNG
口試委員:張傳育陳偉銘黃逸羣
口試委員(外文):CHANG,CHUAN-YUCHEN,WEI-MINGHUANG, YI-CYUN
口試日期:2020-07-17
學位類別:碩士
校院名稱:國立雲林科技大學
系所名稱:資訊工程系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2020
畢業學年度:108
語文別:中文
論文頁數:58
中文關鍵詞:卷積神經網路YOLO類神經網路線性滑軌步進馬達
外文關鍵詞:Convolutional Neural NetworkYOLONeural NetworkLinear GuidewayStepper Motor
相關次數:
  • 被引用被引用:0
  • 點閱點閱:238
  • 評分評分:
  • 下載下載:16
  • 收藏至我的研究室書目清單書目收藏:1
近年來,大型基體電路設計技術的進步,不管是計算效能或晶片體積皆有大幅進步,開展出人工智慧技術於實際場域應用如雨後春筍般發展,各行各業無不在探討如何應用機器學習技術增值產品競爭力。本論文主要是運用深度學習之目標物辨識,結合馬達控制,實現空氣曲棍球即時互動系統,驗證機器學習於即時互動系統之可行性。
本論文利用卷積神經網路YOLO(You Only Look Once)即時捉取曲棍球位置,結合反射定律及類神經網路預測曲棍球之終點位置,控制步進馬達移動線性滑軌阻擋曲棍球,實現空氣曲棍球即時互動系統。論文中將探討曲棍球終點位置預測的準確性、如何提升系統的反應時間,以滿足互動系統反應時間之需求。

In recent years, due to advances in chip design technology, artificial intelligence has made significant progress. Thus, this forces all of areas to investigate how to increase the competitiveness of products with machine learning technology. In this paper, we mainly use deep learning cooperated with motor control to realize the real-time interactive system of air hockey, and to verify the feasibility of machine learning in the real-time interactive system.
This paper uses convolutional neural network YOLO (You Only Look Once) to capture the hockey current position. At the same time, the law of reflection and neural network are applied to predict the end position of the hockey. Based on the predicted location, the system will control the stepping motor to move the linear slide to realize the real-time interactive air hockey system. The paper discusses the accuracy of the prediction of hockey end position and improve the system response time to meet the system requirements.

摘要 i
ABSTRACT ii
目錄 iii
表目錄 v
圖目錄 vi
1 緒論 1
1.1 研究動機與目的 1
1.2 相關研究 2
1.3 論文架構 4
2 背景知識 5
2.1 深度學習 5
2.1.1 類神經網路 5
2.1.2 激勵函數 7
2.1.3 損失函數 9
2.1.4 學習優化演算法 9
2.1.5 卷積神經網路 10
2.2 基於深度學習的目標檢測演算法 12
2.3 STM32 23
2.4 線性滑軌 23
2.5 步進馬達 24
3 系統實現 25
3.1 設計考量 26
3.2 系統架構 27
3.3 系統實現方法一:直接預測 28
3.4 系統實現方法二:兩階段預測 40
4 實驗環境與結果 49
4.1 實驗環境 49
4.2 Tiny-YOLOv3辨識效果 50
4.3 曲棍球之終點位置預測 51
4.4 防守者之移動控制 53
4.5 實際阻擋最快球速 60
4.6 實際遊戲統計結果 60
5 結論 61
參考文獻 62


[1]Y. Li and S. Huang, "Fast-moving object tracking in air hockey," 2017 IEEE International Conference on Mechatronics and Automation (ICMA), Takamatsu, 2017, pp. 1693-1697.
[2]I. Kawempy, S. Veera Ragavan and Khoo Boon How, "Intelligent system for intercepting moving objects," 2011 IEEE Recent Advances in Intelligent Computational Systems, Trivandrum, Kerala, 2011, pp. 792-797.
[3]J. Park, C. Partridge, and M. Spong, "Neural network-based state prediction for strategy planning of an air hockey robot," Journal of Robotic Systems, vol. 18, no. 4, pp. 187-196, 2001. (Pubitemid 32371543)
[4]Wen-June Wang, I-Da Tsai, Zhi-Da Chen and Guo-Hua Wang, "A vision based air hockey system with fuzzy control," Proceedings of the International Conference on Control Applications, Glasgow, UK, 2002, pp. 754-759 vol.2, doi: 10.1109/CCA.2002.1038695.
[5]Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, "Gradient-based learning applied to document recognition," in Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998, doi: 10.1109/5.726791.
[6]R. Girshick, J. Donahue, T. Darrell and J. Malik, "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation," 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, 2014, pp. 580-587.
[7]R. Girshick, "Fast R-CNN," 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, 2015, pp. 1440-1448.
[8]S. Ren, K. He, R. Girshick and J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137-1149, 1 June 2017.
[9]J. Redmon, S. Divvala, R. Girshick and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, 2016, pp. 779-788.
[10]J. Redmon and A. Farhadi, "YOLO9000: Better, Faster, Stronger," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 2017, pp. 6517-6525.
[11]J. MacQueen,"Some Methods for Classification and Analysis of Multivariate Observations", Proc. of the Fifth Berkeley Symposium on Math. Stat and Prob., vol. 1, pp. 281-296, 1967.
[12]R. Joseph, A. Farhadi, "YOLOv3: An incremental improvement", 2018.
[13]https://www.st.com/en/evaluation-tools/32f072bdiscovery.html


QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊