(34.237.124.210) 您好!臺灣時間:2021/03/02 06:43
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:::

我願授權國圖
: 
twitterline
研究生:王浩
研究生(外文):WANG, HAO
論文名稱:基於ROS及Duckietown的自動城市導覽的設計與實現
論文名稱(外文):Design and Implementation of Automated City Guides Based on ROS and Duckietown
指導教授:鄭佳炘鄭佳炘引用關係
指導教授(外文):CHENG, CHIA-HSIN
口試委員:李樹鴻黃永發蘇暉凱鄭佳炘
口試委員(外文):LEE, SHU-HONGHUANG, YUNG-FASU, HUI-KAICHENG, CHIA-HSIN
口試日期:2020-07-16
學位類別:碩士
校院名稱:國立虎尾科技大學
系所名稱:電機工程系碩士班
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:56
中文關鍵詞:物聯網自動駕駛汽車DuckiebotCNN深度學習電動車
外文關鍵詞:Internet of Thingsautonomous vehiclesDuckiebotCNNdeep learningelectric vehicles
相關次數:
  • 被引用被引用:0
  • 點閱點閱:60
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
隨著自動化的時代來臨對於無人駕駛汽車的想法及需求也漸漸的增加,在自駕車的未來發展上,是越來越受到學術界以及產業界的關注,但目前大多無人駕駛車的研究,只能侷限在特殊且固定的環境下才能夠完全的實現無人駕駛車,現今的自駕車大多數只適用於駕駛人的輔助系統,例如,自動跟車系統,車道偏移系統以及防追撞系統等等。本文將會在預設特定的環境下來實現城市導覽的自動駕駛車,而這輛自動駕駛車會使用近期熱門的小鴨車(Duckiebot),在實驗中則會使用到機器人作業系統(Robot Operating System, ROS)、Raspberry Pi、魚眼鏡頭、卷積神經網路(Convolutional Neural Network, CNN)的資料訓練以及Duckiebot的深度學習等功能。
With the advent of the era of automation, the idea and demand for driverless cars are gradually increasing. The future development of self-driving cars has attracted more and more attention from academia and industry. However, most of the current research on driverless vehicles can only be fully realized in a special and fixed environment.
Since most of today's self-driving cars are only suitable for driver assistance systems, such as automatic car following systems, lane-shifting systems, and anti-collision systems, etc. In this thesis, we will implement a self-driving car for city navigation in a preset specific environment, and this self-driving car will use the recently popular Duckiebot. In the experiment, we use Robot Operating System (ROS), Raspberry Pi, fisheye lens, Convolutional Neural Network (CNN) data training and Duckiebot's deep learning functions.

摘要......i
Abstract......ii
誌謝......iii
目錄......iv
表目錄......vi
圖目錄......vii
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論文架構......3
第二章 文獻探討......4
2.1 ROS機器人系統......4
2.1.1 ROS歷史......5
2.1.2 ROS設計目標......6
2.1.3 ROS設計目標......7
2.2 深度學習......9
2.2.1 類神經網路 10
2.2.3 卷積神經網路......11
2.2.4 卷積神經網路-卷積層......12
2.2.4 卷積神經網路-池化層......13
2.3 Duckiebot......14
2.3.1 Duckiebot車體......14
2.3.2 Duckietown的環境地圖......15
2.4 Raspberry Pi 3 B......16
2.5 OpenCV......17
2.5.1OpenCV歷史......17
2.5.2早期OpenCV的主要目標......18
2.5.3 AI視覺辨識......19
2.5.4應用領域及程式語言......19
2.5.5 Opencv圖像處理......20
第三章 系統架構......23
3.1硬體架構......23
3.2資料蒐集方法......24
3.2.1資料蒐集後轉換......25
3.3軟體架構-深度學習流程概述......26
3.4 ROS進行導覽功能流程圖......27
第四章 實驗與結果......28
4.1資料蒐集......29
4.1.1資料分類......30
4.2 CNN模型訓練實驗......30
4.3將資料進行CNN深度學習......31
4.3.1 CNN第一次自走訓練實驗......32
4.3.2 CNN第一次訓練實驗小結......37
4.3.3 CNN第二次自走訓練實驗......38
4.3.4 CNN第二次訓練實驗小結......43
4.3.5 CNN第三次自走訓練實驗......44
4.3.6 CNN第三次訓練實驗小結......46
4.3.7 CNN第四次自走導覽訓練實驗......47
4.3.8 CNN第四次訓練實驗總結......48
4.3.9 CNN訓練實驗總結......49
第五章 結論與未來研究......50
5.1 結論......50
5.1 未來研究......50
參考文獻......51
Extended Abstract......53

[1].S. Karnouskos, "Self-Driving Car Acceptance and the Role of Ethics," in IEEE Transactions on Engineering Management, vol. 67, no. 2, pp. 252-265, May 2020.
[2].F. Cheng, Z. Wang and J. Chen, "Integration of open source platform duckietown and gesture recognition as an interactive interface for the museum robotic guide," 2018 27th Wireless and Optical Communication Conference (WOCC), Hualien, 2018, pp. 1-5.
[3].L. Paull et al., "Duckietown: An open, inexpensive and flexible platform for autonomy education and research," 2017 IEEE International Conference on Robotics and Automation (ICRA), Singapore, 2017, pp. 1497-1504.
[4].O. Castro, A. Céspedes, R. Ubaldo and O. E. Ramos, "Lane Following with a Duckiebot Vehicle using Visual Feedback," 2019 IEEE Sciences and Humanities International Research Conference (SHIRCON), Lima, Peru, 2019, pp. 1-4.
[5].J. Tani, L. Paull et al., "Duckietown: an innovative way to teach autonomy", Edurobotics 2016, pp. 1-15, 2016.
[6].Z. GUO, W. YANG, M. LI, X. YI, Z. CAI and Y. WANG, "ALLIANCE-ROS: A Software Framework on ROS for Fault-Tolerant and Cooperative Mobile Robots," in Chinese Journal of Electronics, vol. 27, no. 3, pp. 467-475, 5 2018.
[7].L. Paull, G. Huang and J. J. Leonard, "A unified resource-constrained framework for graph SLAM," 2016 IEEE International Conference on Robotics and Automation (ICRA), Stockholm, 2016, pp. 1346-1353.
[8].N. Carlevaris-Bianco and R. M. Eustice, "Conservative edge sparsification for graph SLAM node removal," 2014 IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, 2014, pp. 854-860.
[9].Li Deng, Jinyu Li, Jui-Ting Huang, Kaisheng Yao, Dong Yu, Frank Seide, Michael Seltzer, GeojjZweig, Xiaodong He, Jason Williams, Yifan Gong, and Alex Acero, “Recent advances in deep learning for speech research at Microsoft,” in 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2013, pp. 8604–8608.
[10].A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” in 2012 Neural Information Processing Systems (NIPS), 2012, pp. 1097–1105.

[11].X. Gao and L. Liao, "A New One-Layer Neural Network for Linear and Quadratic Programming," in IEEE Transactions on Neural Networks, vol. 21, no. 6, pp. 918-929, June 2010.
[12].N. Passalis and A. Tefas, "Learning Bag-of-Features Pooling for Deep Convolutional Neural Networks," 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 2017, pp. 5766-5774.
[13].N. N. Aizenberg and I. N. Aizenberg, "CNN based on multi-valued neuron as a model of associative memory for grey scale images," CNNA '92 Proceedings Second International Workshop on Cellular Neural Networks and Their Applications, Munich, Germany, 1992, pp. 36-41.
[14].A. Monteiro, M. de Oliveira, R. de Oliveira and T. da Silva, "Embedded application of convolutional neural networks on Raspberry Pi for SHM," in Electronics Letters, vol. 54, no. 11, pp. 680-682, 31 5 2018.
[15].C. Edwards, "Not-so-humble raspberry pi gets big ideas," in Engineering & Technology, vol. 8, no. 3, pp. 30-33, April 2013.
[16].X. Farhodov, O. Kwon, K. W. Kang, S. Lee and K. Kwon, "Faster RCNN Detection Based OpenCV CSRT Tracker Using Drone Data," 2019 International Conference on Information Science and Communications Technologies (ICISCT), Tashkent, Uzbekistan, 2019, pp. 1-3.
[17].Yang Pingxian, Guo Rong, Guo Peng and Fang Zhaoju, "Research on lip detection based on Opencv," Proceedings 2011 International Conference on Transportation, Mechanical, and Electrical Engineering (TMEE), Changchun, 2011, pp. 1465-1468.

電子全文 電子全文(網際網路公開日期:20250820)
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔