臺灣博碩士論文加值系統

近年來服務型機器人崛起，多樣化的自主服務機器人正導入我們生活當中，但都有其使用限制，例如掃地機器人只能在單一房間運行；AGV無人搬運車須仰賴專為其打造之大型倉儲空間，並依事先佈建之特徵軌進行導引。因應在多房間的室內環境中運行，具備開門能力是必要的功能，因此機器人需具備能開門的手臂與辨識門把的能力。本文提出一種輔以視覺之移動機器人開門策略，使機器人可自行打開房門、在室內隔間中穿梭，進而提升工作區域的範圍，且更符合實際應用情況。
本文所採用之門把手辨認方式可大致分為兩種:標籤式及直接辨認。標籤式採用ArUco標籤，ArUco具有辨識快速(20ms)、定位精確、開源等優勢，但此標籤需要人為事先布置；直接辨認法則透過機器學習的方式，對門把手的方向梯度特徵(HOG)做訓練，並以支持向量機(SVM)作為分類器，透過事先訓練好的樣本參數即可對新影像進行多尺度特徵檢索，從而達到在未知環境找到門把手功能。
執行平台的移動機器人使用Intel NUC作為系統核心，並採用機器人作業系統(ROS)，底盤使用麥克納姆輪驅動使機器人可做全向運動，並於正前方配置光學雷達(LiDAR)協助建圖及定位。移動機器人之基本功能包含了:定位、建圖、導航等需求，本文中使用ROS中已經相當成熟之演算法來實現，加速移動機器人之開發。
移動機器人上還搭載了以AI馬達驅動之手臂，在手臂前端裝有攝影機，並透過前述之物件偵測系統尋找門把手，當確定門把手位置後，導引機器人至適當的開門位置，接著手臂執行開門動作，期間透過推/拉門加上力回授方式確認門開啟的正確方向，完成開門之動作。此系統展示了自主開啟門、並穿梭於一般房屋具有的房間格局，多房間穿越使服務機器人的應用層面更加廣泛，也期待未來的服務型機器人能有更多應用。

This paper newly designed an indoor omnidirectional mobile robot with basic indoor positioning, mapping and navigation functions. The mobile robot supports the Robot Operating System (ROS) and relies on it to accelerate initial development. Another topic of this paper is the freedom to move indoors. To shuttle freely indoors, the robot has to overcome the problem of opening the door so that it can shuttle through the rooms freely.
To solve this problem, the robot on this article is equipped with a robotic arm, furthermore relies on computer vision and other sensors to try to determine the door handle and the environment. Identify the door handle part, use ArUco and Histogram of oriented gradient (HOG), and with the series of door opening procedures designed in this paper to complete the door opening action, so that the robot has the ability to shuttle the room. In the experimental stage, this paper successfully demonstrated the Simultaneous localization and mapping (SLAM) and Navigation functions of indoor robots, and achieved a success rate of 87.5% in the stage of using ArUco to assist in opening the door.
This paper has completed the design goals of indoor robots, and can be used to develop robots into navigation robots, sweeping robots, and service robots.

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　研究動機與背景...1
1.2 研究回顧...1
1.2.1 及時定位與地圖建構(SLAM)...1
1.2.2 路徑規劃...2
1.2.3 尋找門把手及開門策略...2
1.3 問題描述...3
1.4 論文架構說明...3
第二章 移動機器人設計...4
2.1 設計概述...4
2.2 機械結構...4
2.3 底盤結構...6
2.4 動力機構...7
2.5 機械手臂結構...8
第三章 運動分析...10
3.1 底盤運動學模型...10
第四章 硬體系統架構...15
4.1 系統概述...15
4.2 上層系統與OS...15
4.2.1 光學雷達LiDAR...16
4.2.2 攝影機...18
4.3 下層MCU執行單元...18
4.3.1 底盤驅動單元...18
4.3.2 手臂驅動單元...19
4.4 電力系統...19
第五章 方法設計與實現...22
5.1 方法概述...22
5.2 移動機器人底盤控制Base controller...22
5.2.1 PID參數調整...23
5.3 SLAM...24
5.4 Navigation...28
5.5 基於電腦視覺技術之門把手辨識...30
5.5.1 使用滑動視窗與輪廓特徵進行辨識...31
5.5.2 使用ArUco標籤輔助辨識...33
5.5.3 基於HOG+SVM之門把手辨識...34
5.6 開門策略...37
第六章 實驗結果...43
6.1 基礎功能測試...43
6.2 手臂負載測試...53
6.3 SLAM測試...59
6.4 Navigation導航功能測試...63
6.5 門把手檢測測試...68
6.6 開門測試...70
第七章 結論與未來展望...73
7.1 結論...73
7.2 未來展望...73
參考文獻...75
Extended Abstract...77

[1]Grisetti, G., C. Stachniss, and W. Burgard, Improved techniques for grid mapping with rao-blackwellized particle filters. IEEE transactions on Robotics, 2007. 23(1): p. 34-46.
[2]Kohlbrecher, S., et al. A flexible and scalable slam system with full 3d motion estimation. in Safety, Security, and Rescue Robotics (SSRR), 2011 IEEE International Symposium on. 2011. IEEE.
[3]Hess, W., et al. Real-time loop closure in 2D LIDAR SLAM. in Robotics and Automation (ICRA), 2016 IEEE International Conference on. 2016. IEEE.
[4]Hart, P.E., N.J. Nilsson, and B. Raphael, A formal basis for the heuristic determination of minimum cost paths. IEEE transactions on Systems Science and Cybernetics, 1968. 4(2): p. 100-107.
[5]Koenig, S. and M. Likhachev, Fast replanning for navigation in unknown terrain. IEEE Transactions on Robotics, 2005. 21(3): p. 354-363.
[6]Fox, D., W. Burgard, and S. Thrun, The dynamic window approach to collision avoidance. IEEE Robotics & Automation Magazine, 1997. 4(1): p. 23-33.
[7]Kobayashi, S., et al. Development of a door opening system on rescue robot for search “UMRS-2007”. in SICE Annual Conference, 2008. 2008. IEEE.
[8]Chung, W., et al., Door-opening control of a service robot using the multifingered robot hand. IEEE Transactions on Industrial Electronics, 2009. 56(10): p. 3975-3984.
[9]Jain, A. and C.C. Kemp. Behaviors for robust door opening and doorway traversal with a force-sensing mobile manipulator. 2008. Georgia Institute of Technology.
[10]Jain, A. and C.C. Kemp. Behavior-based door opening with equilibrium point control. 2009. Georgia Institute of Technology.
[11]Chitta, S., B. Cohen, and M. Likhachev. Planning for autonomous door opening with a mobile manipulator. in Robotics and Automation (ICRA), 2010 IEEE International Conference on. 2010. IEEE.
[12]Anguelov, D., et al. Detecting and modeling doors with mobile robots. in Robotics and Automation, 2004. Proceedings. ICRA'04. 2004 IEEE International Conference on. 2004. IEEE.
[13]Chen, Z. and S.T. Birchfield. Visual detection of lintel-occluded doors from a single image. in Computer Vision and Pattern Recognition Workshops, 2008. CVPRW'08. IEEE Computer Society Conference on. 2008. IEEE.
[14]Aude, E.P., et al., Door crossing and state identification using robotic vision. IFAC Proceedings Volumes, 2006. 39(15): p. 659-664.
[15]Andreopoulos, A. and J.K. Tsotsos, A Framework for Door Localization and Door Opening Using a Computer Controlled Wheelchair for People Living with Mobility Impairments.
[16]Andreopoulos, A. and J.K. Tsotsos. Active vision for door localization and door opening using playbot: A computer controlled wheelchair for people with mobility impairments. in Computer and Robot Vision, 2008. CRV'08. Canadian Conference on. 2008. IEEE.
[17]Kim, S., et al. Context-based object recognition for door detection. in Advanced Robotics (ICAR), 2011 15th International Conference on. 2011. IEEE.
[18]Rusu, R.B., et al. Laser-based perception for door and handle identification. in Advanced Robotics, 2009. ICAR 2009. International Conference on. 2009. IEEE.
[19]Klingbeil, E., A. Saxena, and A.Y. Ng. Learning to open new doors. in Intelligent Robots and Systems (IROS), 2010 IEEE/RSJ International Conference on. 2010. IEEE.
[20]Dalal, N. and B. Triggs. Histograms of oriented gradients for human detection. in Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on. 2005. IEEE.
[21]Taheri, H., B. Qiao, and N. Ghaeminezhad, Kinematic model of a four mecanum wheeled mobile robot. International journal of computer applications, 2015. 113(3).
[22]全向輪運動學與V-rep中全向移動機器人仿真. Available from: https://www.cnblogs.com/21207-iHome/p/7911748.html.
[23]Jimeno, J.M. Linorobot. Available from: https://linorobot.org/.
[24]gmapping Package. Available from: http://wiki.ros.org/gmapping.
[25]hector_slam Package. Available from: http://wiki.ros.org/hector_slam.
[26]Navigation Package. Available from: http://wiki.ros.org/navigation.
[27]Lu, D.V. Navigation Illumination - Shedding Light on the ROS Navstack. Available from: https://roscon.ros.org/2014/wp-content/uploads/2014/07/ROSCON2014_DLu.pdf.
[28]Monte Carlo localization. Available from: https://en.wikipedia.org/wiki/Monte_Carlo_localization.
[29]Thrun, S., W. Burgard, and D. Fox, Probabilistic Robotics.
[30]pr2_doors. Available from: http://wiki.ros.org/pr2_doors?distro=fuerte.