輔助隧道巡檢人員定位之跟隨型機器人｜國立臺灣科技大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	何佳欣 Chia-Hsing Ho
論文名稱：	輔助隧道巡檢人員定位之跟隨型機器人 A Human Following Robot with Localization for Assisting Tunnel Inspector
指導教授：	謝佑明 Yo-Ming Hsieh
口試委員:	陳鴻銘 Hung-Ming Chen 楊元森 Yuan-Sen Yang 莊子毅 Tzu-Yi Chuang 謝佑明 Yo-Ming Hsieh
學位類別：	碩士 Master
系所名稱：	工程學院 - 營建工程系 Department of Civil and Construction Engineering
論文出版年：	2018
畢業學年度：	106
語文別：	中文
論文頁數：	88
中文關鍵詞：	跟隨型機器人、人員偵測、RGB-D影像、BLE 、隧道巡檢
外文關鍵詞：	human following, robot, people detection, RGB-D Image, tunnel inspection
相關次數：	點閱：235 下載：22
分享至:	分享至facebook 分享至twitter

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

上一筆

隧道為土木工程中非常重要之一環。在台灣，隧道被廣泛的利用，而適當的隧道管理與維護是非常重要的。隧道管理與維護的最前線作業，即為隧道之巡檢作業。巡測需要記錄異常狀況之狀態與位置資訊，然目前仍缺乏一經濟有效的方式，能在隧道內進行自動定位。
本研究使用一嵌入式開發版，搭配能拍攝包含深度影像的相機，開發一跟隨型機器人。其能自動尾隨隧道檢測人員進行目視檢測作業，並為其提供定位資訊，以達成輔助隧道檢測人員自動記錄隧道異狀位置之需求。本研究之機器人利用PCL函式庫，對RGB-D影像進行處理以找出屬於人的像素以進行人員偵測，並以PID控制器調整馬達的轉速，以達到自動尾隨的效果。為了監視機器人運行時的狀況，本研究開發使用低功耗藍牙BLE廣播Eddystone Beacon格式的技術，讓使用者可以利用手機了解機器人的運作情形，未來亦可透過此技術提供隧道巡檢人員之定位資訊。
本研究開發之機器人經由實際測試，確實可以跟隨在目標人物之後，並透過馬達內部的編碼器計算馬達旋轉量，以得知機器人的行走距離，達到定位的效果。唯程式判斷人物偵測的部分時好時壞，導致機器人行走時會不時中斷以等候獲得人物偵測的結果。

Tunnels are important infrastructures in Taiwan. To maintain these tunnels, visual inspections are regularly performed, and anomalies and their locations are recorded. However, locations are roughly estimated and recorded by inspectors. Errors may thus be introduced during this manual process. There is a need to provide location information automatically to eliminate such error.
In this work, we use an embedded system to build a human-following robot, which can follow a person through a stereo camera and locate itself while following the person. This robot can then provide tunnel inspectors their whereabouts for their recording of anomalies. The human following behavior is achieved by people detection and PID controller algorithm. People detection is done by PCL, an open source library, that processes RGB-D images and detects pixels belong to human. PID controller algorithm controls the motor in the robot to achieve human-following. The status of the robot is transmitted using Bluetooth Low Energy (BLE) that broadcasts Eddystone Beacon messages. The message can be shown to the user by Apps in mobile devices to monitor the robot, and also provide localization information to tunnel inspectors.
Through field tests, the developed robot in this research can successfully follow people. The walking distance of the robot can be inferred from the motor encoder, thus achieving localization. The performance of people detection is unstable and prevents smooth operation of the robot.

論文摘要    I
ABSTRACT    II
誌謝    III
目錄    V
圖目錄    IX
表目錄    XI
第一章 緒論    1
1    研究動機與目的    1
2    研究流程    3
3    論文架構    4
第二章 文獻回顧    5
1    跟隨型機器人之應用    5
2    人物偵測之方法    7
3    判斷人物距離遠近之方法    8
4    機器人移動控制方法    9
第三章 研究方法與工具    11
1    硬體架構    12
1.1    NVidia Jetson TX1開發套件    12
1.2    Intel RealSense ZR300相機    14
1.3    自走車底盤    15
1.3.1    馬達    16
1.3.2    編碼器    18
1.4    L298N晶片組    19
2    PCL函式庫    20
2.1    取得影像    21
2.2    人物偵測    21
3    PWM脈衝寬度調變    23
4    PID 比例-積分-微分控制器    24
4.1    比例(P)控制    25
4.2    積分(I)控制    25
4.3    微分(D)控制    26
5    Eddystone Beacon訊息    26
5.1    Eddystone UID    26
5.2    Eddystone URL    27
5.3    Eddystone TLM    28
5.4    Eddystone EID    28
6    IPC行程間通訊    29
第四章 系統分析與設計    31
1    硬體接線設計    31
2    系統流程圖    34
2.1    人物偵測    34
2.2    車子移動    35
2.3    藍牙傳輸    36
3    類別圖    37
3.1    人物偵測    37
3.2    共享記憶體    38
3.3    馬達操控    38
3.4    藍牙傳輸    39
4    協同合作圖    39
5    PID控制器參數設定    41
5.1    左右控制    41
5.2    前後控制    43
6    Eddystone URL設計    44
第五章 系統展示與驗證    49
1    系統展示    49
2    案例介紹    50
2.1    教室走廊(短程)    51
2.2    教室走廊(長程)    51
2.3    學校操場    52
2.4    人行地下道    52
3    測試結果    53
3.1    教室走廊(短程)    53
3.2    教室走廊(長程)    58
3.3    學校操場    62
3.4    人行地下道    63
4    小結    68
第六章 結論與建議    69
1    結論    69
2    建議與未來展望    69
參考文獻    71

                                

1. 黃燦輝等, 老舊交通隧道之安全檢測、維修與補強技術研訂. 1997: 交通部.
2. 陳鴻麟, 鐵路隧道. 2011: 交通部.
3. 廖育慶, 應用電腦視覺於隧道內定位之研究, in 營建工程系. 2014, 國立臺灣科技大學: 台北市. p. 111.
4. Yoshimi, T., et al. Development of a Person Following Robot with Vision Based Target Detection. in 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems. 2006.
5. Sales, J., et al., Multi-sensor person following in low-visibility scenarios. Sensors, 2010. 10(12): p. 10953-10966.
6. Naghsh, A., et al., Remote and in-situ multirobot interaction for firefighters interventions under smoke conditions. IFAC Proceedings Volumes, 2010. 43(23): p. 109-115.
7. Tani, A., et al. Study on a practical robotic follower to support home oxygen therapy patients-development and control of a mobile platform. in Intelligent Robots and Systems (IROS), 2011 IEEE/RSJ International Conference on. 2011. IEEE.
8. Ilias, B., et al., A nurse following robot with high speed Kinect sensor. ARPN Journal of Engineering and Applied Sciences, 2014. 9(12): p. 2454-2459.
9. Brown, M., P. Avery, and P. Sturgeon. Enhanced work zone safety through cooperative autonomous vehicle systems. in 2014 International Conference on Connected Vehicles and Expo (ICCVE). 2014.
10. Konno, S. and A. Mita. A study on a robot chasing a human using Kinect while identifying walking parameters using the back view. in Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2014. 2014. International Society for Optics and Photonics.
11. Brookshire, J., Person following using histograms of oriented gradients. International journal of social robotics, 2010. 2(2): p. 137-146.
12. Gupta, M., et al., A novel vision-based tracking algorithm for a human-following mobile robot. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2017. 47(7): p. 1415-1427.
13. Munaro, M., F. Basso, and E. Menegatti, OpenPTrack: Open source multi-camera calibration and people tracking for RGB-D camera networks. Robotics and Autonomous Systems, 2016. 75: p. 525-538.
14. Linder, T., et al. On multi-modal people tracking from mobile platforms in very crowded and dynamic environments. in Robotics and Automation (ICRA), 2016 IEEE International Conference on. 2016. IEEE.
15. 傅培耕, 即時物體追蹤之立體視覺導引自走車, in 機械工程研究所. 2004, 中原大學: 桃園縣. p. 60.
16. 顏大翔, 智慧型自主式車輛機器視覺系統之研究, in 機械工程系碩士班. 2008, 國立雲林科技大學: 雲林縣. p. 69.
17. 林哲瑋, 基於即時影像之模糊追隨控制. 臺北科技大學自動化科技研究所學位論文, 2007: p. 1-91.
18. 詹嘉峻, 基於即時影像之智慧型自走車避障與動態追蹤控制, in 通訊與導航工程系. 2010, 國立臺灣海洋大學: 基隆市. p. 98.
19. Morales, J., et al., Pure-pursuit reactive path tracking for nonholonomic mobile robots with a 2D laser scanner. EURASIP Journal on Advances in Signal Processing, 2009. 2009: p. 3.
20. Ohshima, A. and S.i. Yuta, Tracking and following people and robots in crowded environment by a mobile robot with sokuiki sensor, in Distributed Autonomous Robotic Systems 8. 2009, Springer. p. 575-584.
21. 黃星皓, 應用軟硬體共同設計的階層式滑動控制於車型自走車之軌跡追蹤、避障與目標趨近, in 電機工程系. 2015, 國立臺灣科技大學: 台北市. p. 60.
22. 李秉樹, 利用增強式骨架識別技術的智慧型避障自走車之人體跟隨控制, in 電機工程學系. 2016, 國立暨南國際大學: 南投縣. p. 51.
23. Dang, Q.K. and Y.S. Suh. Human-following robot using infrared camera. in Control, Automation and Systems (ICCAS), 2011 11th International Conference on. 2011. IEEE.
24. Wang, W.-J. and J.-W. Chang. Implementation of a mobile robot for people following. in System Science and Engineering (ICSSE), 2012 International Conference on. 2012. IEEE.
25. Caceres, C., J.M. Rosario, and D. Amaya. Approach of Kinematic Control for a Nonholonomic Wheeled Robot using Artificial Neural Networks and Genetic Algorithms. in 2017 International Conference and Workshop on Bioinspired Intelligence (IWOBI). 2017.
26. Paterega, I. Autonomous robot control by WTA neural network. in Perspective Technologies and Methods in MEMS Design (MEMSTECH), 2011 Proceedings of VIIth International Conference on. 2011. IEEE.
27. Khan, A. and F. Zhang. Using recurrent neural networks (RNNs) as planners for bio-inspired robotic motion. in 2017 IEEE Conference on Control Technology and Applications (CCTA). 2017.
28. NVIDIA 嵌入式系統開發套件、模組介紹. Available from: https://www.nvidia.com/zh-tw/autonomous-machines/embedded-systems-dev-kits-modules/.
29. Intel RealSense ZR300相機規格. Available from: https://www.intel.com/content/www/us/en/support/articles/000023521/emerging-technologies/intel-realsense-technology.html.
30. GM25-370 spec datasheet. Available from: http://p.globalsources.com/IMAGES/PDT/SPEC/301/K1123392301.pdf.
31. 維基百科 - 旋轉編碼器. Available from: https://en.wikipedia.org/wiki/Rotary_encoder.
32. PCL函式庫官方網站. Available from: http://pointclouds.org/.
33. LibrealSense Grabber函式庫. Available from: https://github.com/lebronzhang/pcl/tree/355a5f6d22253290cf4c13433b3cbc69338f0cdb/io/include/pcl/io/librealsense.
34. Buys, K., et al., An adaptable system for RGB-D based human body detection and pose estimation. Journal of visual communication and image representation, 2014. 25(1): p. 39-52.
35. 成大資工Wiki-PWM簡介. Available from: http://wiki.csie.ncku.edu.tw/embedded/PWM.
36. 維基百科－脈衝寬度調變. Available from: https://en.wikipedia.org/wiki/Pulse-width_modulation.
37. Arduino教學-PWM控制. Available from: https://www.arduino.cc/en/Tutorial/PWM.
38. 維基百科－PID控制器. Available from: https://en.wikipedia.org/wiki/PID_controller.
39. Google Eddystone官方網站. Available from: https://github.com/google/eddystone.
40. Google Eddystone Beacon格式規範. Available from: https://github.com/google/eddystone.
41. Stevens, W.R., UNIX網路程式設計：IPC行程間通訊程式設計. Vol. 2. 2002, 台北市: 台灣培生教育.
42. NVidia Jetson TX1-TX2 Developer Kit Carrier Board Specification. Available from: https://developer.nvidia.com/embedded/downloads.

簡易檢索 / 詳目顯示

相關論文