系統識別號 | U0002-1609201914292300 |
---|---|
DOI | 10.6846/TKU.2019.00465 |
論文名稱(中文) | 基於ROS在靜態環境之自主機器人的模糊導航系統 |
論文名稱(英文) | Fuzzy Navigation System for ROS Based Autonomous Robot in Static Environment |
第三語言論文名稱 | |
校院名稱 | 淡江大學 |
系所名稱(中文) | 電機工程學系機器人工程碩士班 |
系所名稱(英文) | Master's Program In Robotics Engineering, Department Of Electrical And Computer Engineering |
外國學位學校名稱 | |
外國學位學院名稱 | |
外國學位研究所名稱 | |
學年度 | 107 |
學期 | 2 |
出版年 | 108 |
研究生(中文) | 辛柏凱 |
研究生(英文) | Pushkar Kumar Singh |
學號 | 606465010 |
學位類別 | 碩士 |
語言別 | 英文 |
第二語言別 | |
口試日期 | 2019-07-18 |
論文頁數 | 70頁 |
口試委員 |
指導教授
-
李祖添
指導教授 - 翁慶昌(iclabee@gmail.com) 委員 - 龔宗鈞 委員 - 翁慶昌(iclabee@gmail.com) 委員 - 劉智誠 |
關鍵字(中) |
模糊邏輯 Gazebo 人形機器人 導航 機器人作業系統 軌跡規劃 |
關鍵字(英) |
Fuzzy Logic Gazebo Humanoid Robot Navigation Robot Operating System (ROS) Trajectory Planning |
第三語言關鍵字 | |
學科別分類 | |
中文摘要 |
本論文設計和實現軌跡追蹤和規劃控制器,為使用模糊邏輯來用於移動型與人形機器人之自動化機器人,並在靜態的環境中導航。透過建立自動化機器人之差動驅動滾輪的運動學方程實現運動學模型。當機器人使用攝影機獲取即時影像時,透過影像處理中使用色彩模型的色彩表來進行物件分割來顯示影像二值化。最後,機器人使用模糊邏輯控制器來追蹤預設路徑並透過控制驅動的速度和轉向角度來避開未知的障礙物。已經考慮了線路追蹤與避障的方法。控制器為雙輸入和雙輸出的系統,其是更適合室內使用的追蹤式車輛。模糊控制系統於Ubuntu 16.01之機器人作業系統中設計與實現,並且在Gazebo模擬中進行測試。最後,一些實驗與結果證明了模糊邏輯控制系統對自動化機器人的有效性。 |
英文摘要 |
This paper describes the design and implementation of a trajectory tracking and planning controller using Fuzzy logic for autonomous robots including both mobile and humanoid to navigate in the static environment. The kinematic model has been created for the autonomous robot using the kinematics equations of the differential driving rolling wheel. As the robot uses webcam to get the live image, image binarization has been shown using the object segmentation method by using the color code table of color model in the image processing. Finally, the robot uses a fuzzy logic controller to follow a planned path and avoid unknown obstacles by controlling the velocity and steering angle of the drive unit. Both line following and obstacle avoidance approach has been considered. The controller is a two input and two output system. It is a tracked vehicle which is more suitable for indoor use. The fuzzy control system has been designed and implemented in Robot Operating System (ROS) under Ubuntu 16.01 operating system and tested under Gazebo simulation. Finally, several experiments and results have been presented to demonstrate the effectiveness of fuzzy logic control system on the autonomous robots. |
第三語言摘要 | |
論文目次 |
Table of Content I List of Figures III Table Directory V Chapter I Introduction 1 1.1 Research background 1 1.2 Research motivation 4 1.3 Research purposes 8 1.4 Thesis structure 9 Chapter II Introduction of Humanoid Robot Platform 10 2.1 Foreword 10 2.2 Humanoid robot organization 11 2.3 Humanoid robot core control board introduction 17 2.3.1 Industrial personal computer(IPC) 18 2.3.2 FPGA Development board 19 Chapter III Kinematic Model of Humanoid Robot and Mobile Robot 21 3.1 Kinematic Model 21 3.1.1 Foreword 10 3.1.1 Denavit-Hartenberg System(DH System 21 3.2 Kinematic Model of the mobile robot 23 3.2.1 Kinematics equation of the differential drive rolling wheel……26 3.2.2 Kinematics equation of the humanoid robot 29 3.2.2.1 Positioning System 30 3.2.2.2 Data delivery Module 31 3.2.2.3 Image Binarization 32 3.2.2.4 Humanoid robot software architectur …………......………....35 Chapter IV Fuzzy Logic Controller (FLC)…………………………………..37 4.1 Fuzzy Logic Controller (FLC) and its type………………....…….37 4.2 Fuzzy Inference System………………………………….…………41 4.2.1 Fuzzy Logic Controller Design 43 4.2.2 FLC Design for Line following (Without obstacle) 44 4.2.2.1 Rule base for FLC Design for Line following robot…………...45 4.2.3 FLC Design for Line following (With obstacle) 47 Chapter V Experiment and Result……………………………………….…..50 5.1 Observation mode………………………....……………….….…..51 5.2 Mobile robot model setup…………………………....…………....56 5.3 Marathon setup ……………………………………………….…...58 5.4 Humanoid robot setup……………………………………….…….61 5.5 Obstacle path setup…………………………………………….….63 Chapter VI Conclusions and Future Prospects 67 References 69 Figure 1.1 Hierarchy of robot behavior in marathon 6 Figure 1.2 Hierachy of robot behaviour in obstacle……………...................7 Figure 2.1 Humanoid Robot Diagram 11 Figure 2.2 Humanoid Robot DOF Plan 13 Figure 2.3 Humanoid Robot mechanism design and dimension 13 Figure 2.4 Mechanism design and DOF configuration 16 Figure 2.5 Joint space of the feet 17 Figure 2.6 IPC industrial computer entity map 18 Figure 2.7 FPGA development board entity diagram 20 Figure 3.1 Ideal Rolling Wheel 24 Figure 3.2 Kinematics model of the differential drive rolling wheel……...25 Figure 3.3 Kinematics model of the mobile robot 25 Figure 3.4 Waist and footsteps 30 Figure 3.5 Robot state speculation 31 Figure 3.6 Image modeling: (a) original image, (b) binarization 33 Figure 3.7 Object segmentation diagram 34 Figure 3.8 Humanoid robot software architecture 36 Figure 4.1 Flow chart for FLC 39 Figure 4.2 Fuzzy Logic Controller 40 Figure 4.3 Fuzzy Control system 43 Figure 4.4 FLC for line following robot 44 Figure 4.5 Control surfaces for (a) Left motor (b) Right motor 46 Figure 4.6 FLC for obstacle avoidance robot 47 Figure 5.1 Image Coordinate 51 Figure 5.2 Axis distance calculation diagram……… …………………….52 Figure 5.3 Axis distance calculation diagram 53 Figure 5.4 Image Processing(a)100cm(b) 90cm (c) 80cm (d) 70cm (e) 60cm (f) 50cm 54 Figure 5.5 Error graph 55 Figure 5.6 Mobile robot movement...………………………………….…..56 Figure 5.7 (a)Left and right movement vs time (b) Forward movement vs time (c) Speed vs time graph 57 Figure 5.8 Marathon environment 59 Figure 5.9 Series of the movement of mobile robot in marathon………….60 Figure 5.10 (a)SDF model of robot (b) interface of the robot 61 Figure 5.11 Robot Movement 62 Figure 5.12 setup of the obstacle path…………..……………………….…..63 Figure 5.13 (a)(b)(c)(d)(e)(f)Testing of humanoid robot 64 Table 2.1 IPC Industrial Computer Specifications 19 Table 2.2 System Specifications of FPGA Development Board 20 Table 3.1 Color code table 33 Table 4.1 Fuzzy set for input 45 Table 4.2 Fuzzy set for output……………………………………………..45 Table 4.3 Fuzzy rule base for line following 46 Table 4.4 fuzzy rule base for obstacle avoidance 48 Table 4.5 Parameter Difference 49 Table 5.1 Measured distance error table …………………………55 |
參考文獻 |
[1] URL: https://en.wikipedia.org/wiki/Robot [2] Intelligent identification and control for autonomous guided vehicles using adaptive fuzzy-based algorithms; C. J. Harris & C. G. Moore, Eng. Application of AI, Vol. 2, December '8 [3] R. Frizera Vassallo, H. J. Schneebeli, J. Santos-Victor, Visual navigation: combining visual servoing and appearance based methods, 6th International Symposium on Intelligent Robotic Systems, SIRS’98, Edinburgh, Scotland, July 1998 [4] J. Santos-Victor, G. Sandini, F. Curotto, S. Garibaldi, Divergent stereo in autonomous navigation: from bees to robots, International Journal of Computer Vision 14 (1995) 159–177. [5] R. Carelli, C. Soria, O. Nasisi, E. Freire, Stable AGV corridor navigation with fused vision-based control signals, Conference of the IEEE Industrial Electronics Society, IECON, Sevilla, Spain, November 5–8, 2002 [6] A. Dev, B. Kröse, F. Groen, Navigation of a mobile robot on the temporal development of the optic flow, IEEE/RSJ/GI International Conference on Intelligent Robots and Systems IROS’97, Grenoble, September 1997, pp. 558–563 [7] https://docs.google.com/document/d/11dfuKMQvzFcbTlFgz6OBNYFeh7RHyVuHptdivkjnzyE/pub [8] http://www.fira.net/main/ [9] Z. Zhong, J. Yi, D. Zhao, Y. Hong, and X. Li, “Motion vision for mobile robot localization,” IEEE Internationalconference on Control, Automation, Robotics and Vision, vol. 1, pp. 261-266, 2004. [10] J. K. David, T. Ernst, and O. B. Thomas, “Stereovision and navigation in building for mobilerobots,” IEEE Transaction on Robotics and Automation,vol. 5, pp. 792-803, 1989. [11] H. -S. Baek, J. –M. Choi, and B. –S. Lee, “Improvement of distance measurement algorithm on stereo vision system(SVS),” CUTE International Conference on Ubiquitous Information Technologies and Applications, no. 5678176, 2010. [12] S. D. Blostein, and T.S. Huang, “Error analysis instereo determination of 3-d point position,” IEEETransactionon Pattern Analysis and Machine Intelligence,vol. 9, pp. 752-765, 1987. [13] Y. Matsumoto, K. Ikeda, M. Inaba, and H. Inoue, “Visual navigation using omnidirectional view sequence,” IEEE/RSJ International Conference on Intelligent Robots and System, pp. 317-322, 1999. [14] J. Huber, and V. Graefe, “Motion Stereo for Mobile Robots,” IEEE Transactions on Industrial Electronics, vol. 41, pp. 378-383, 1994. [15] M. S. Arulampalam, S. Maskell, N. Gordon, and T. Clapp, “A tutorial on particle filters for online nonlinear/non-gaussian bayesian tracking,”IEEE Transaction onSignal Processing, vol. 50, no. 2, pp.174-188, 2002. [16] J. Baltes, C. T. Cheng, M. C. Lau, and A. Espinola, “Real-time navigation for a humanoid robot using particle filter,” ICETI Applied Mechanics and Materials, vol. 284-287, pp. 1914-1918, 2012. [17] M. Fu, and B. Xue, “A path planning algorithm based on dynamic networks and restricted searching area,” IEEE International Conference on Automation and Logistics, pp.1193-1197, 2007. [18] I. Chabini, and L. Shan, “Adaptations of the A* algorithm for the computation of fastest paths in deterministic discrete-time dynamic networks,” IEEE Transactions on Intelligent Transportation Systems, vol.3, no.1, pp.60-74, 2002. [19] https://slideplayer.com/slide/16444022/ [20] https://robotics.stackexchange.com/questions/15013/calculating-differential-drive-robot-icc-position [21] https://en.wikipedia.org/wiki/Fuzzy_logic |
論文全文使用權限 |
如有問題,歡迎洽詢!
圖書館數位資訊組 (02)2621-5656 轉 2487 或 來信