臺灣博碩士論文加值系統

近年來，機器人研究已經成為國內外最熱門的研究之一，隨著電腦運算速度的提昇，科技的進步，機器人已經能夠為人們處理更複雜的運算與執行艱難的任務，目前機器人已經廣泛應用在:醫療照護、保全系統、工業、救援、探勘…等。且機器人為台灣產業帶來莫大商機，更是未來台灣發展的重點之一。
本論文目標為發展”保全武士”之運動規劃，機器人以融合多重感測器為架構，可以提供居家照顧與保全服務，機器人利用本身所配備的儀器裝置可以完成複雜任務，提供使用者更多的服務，作者重點在機器人的室內定位以及運動規劃，利用雷射測距儀整合掃描環境資訊並將其資訊跟事先預設好的地圖作比對進而達到定位的弁遄A在完成定位之後使用者能根據機器人的位置操控機器人，使機器人完成所下達的指令，在執行任務的同時機器人能自動閃避動態或是靜態障礙物。
在論文最後，為了使用者操作方便也利用圖形畫的介面，機器人位置可以在地圖上顯示，讓使用者能更正確掌握機器人位置，在操作上將更為方便, 我們亦規劃了運動控制系統，使機器人在移動過程中能根據現在的位置計算出與終點之間的最短路徑，讓機器人更具人工智慧，也成永狻

In recent year mobile robot become more and more popular, mobile robot becomes one of the hot researches in robotics. With recent rapid growth of computer and robotic technology, robot can help people to execute more difficult and dangerous missions. Mobile robot extensively application in service, security industry, rescue,…etc. robot bring significant business opportunities and will become one of the main development in Taiwan.
The objective of this thesis is to develop the motion planning for “Security Warrior” , robot based on multi-sensor fusion system, it can provide home care and security service , robot equipped many devices so it can complete difficult mission and provide more services for user , the objective of this thesis focus on indoor localization and motion planning, we use laser range finder to scan environment and matching with predefined map to achieve localization, when robot complete localization user can base on robot position to control robot , when robot execute task it can avoid static obstacle and dynamic obstacle.
Finally, in order to operate more convenient we designed graphic user interface to feedback robot position, we also planned motion system so robot can move smoother and robot can compute the optimal path between robot initial position and goal ,our robot display a high degree artificial intelligent, Motion planning system has successfully proved the feasibility and reliability.

中 文 摘 要 iii
Abstract i
List of Figures v
List of Tables vii
Chapter 1. Introduction 8
1.1 Motivation 8
1.2 Introduction 9
1.3 Objectives 10
1.4 Major Issues and Challenges 10
1.5 Thesis Organization 11
Chapter 2. Literature Review 12
2.1 Review of Indoor Localization 12
2.1.1 Feature-based Map 13
2.1.2 Grid-based Map 14
2.1.3 Topological Map 16
2.1.4 Sensor-based Map: 18
2.2 Vision Based Localization 20
2.2.1 Monte-Carlo Localization 22
2.2.2 Feature based localization 26
2.3 Review of motion planning 31
2.3.1 The Vertex Graph Method 35
2.3.2 The Potential Function Method 36
2.3.3 The Grid Method 37
2.3.4 Review of Path Planning 38
Chapter 3. System Architecture of Security Warrior 42
3.1 Introduction 42
3.2 Hardware architecture 43
3.2.1 Ultrasonic sensors and laser range finder 44
3.2.2 CCD camera 46
3.2.3 Fire sensor and Body sensor 47
3.2.4 Communication System 49
3.3 System architecture 50
3.3.1 IPC Communication 52
3.3.2 Motion system 53
3.3.3 Power system 56
3.3.4 Vision system 59
3.3.5 Arm system 61
3.3.6 Sensor system 62
Chapter 4. Indoor Localization and Motion Planning of Security Warrior 64
4.1 Introduction 64
4.2 Localization algorithm[31, 33] 65
4.2.1 Clustering scan data 65
4.2.2 Feature Extraction from laser range finder[37-39] 70
4.2.3 Matching with line basedd map[40] 71
4.2.4 Position prediction 71
4.3 Path planning method [41] 73
Chapter 5. Experimental Result 77
5.1 Introduction 77
5.2 Indoor localization experimental result 77
5.3 Path planning experiment result 82
Chapter 6. Conclusion and Contributions 85

[1]S. T. Pfister, "Algorithms for Mobile Robot Localization and Mapping, Incorporating Detailed Noise Modeling and Multi-Scale Feature Extraction," California Institute of Technology Pasadena, 2006.
[2]K.C.Lin, "The Development of Behavior Control of Intelligent Security Robot." vol. master Taiwan: ccu, 2005.
[3]C.-C. Tsai, "Navigation System Design of Autonomous Mobile Robots," Taiwan.
[4]http://en.wikipedia.org/wiki/Topological_map.
[5]M. A. Penna and J. Wu, "Models for map building and navigation," Systems, Man and Cybernetics, IEEE Transactions on, vol. 23, pp. 1276-1301, 1993.
[6]L. Delahoche, C. Pegard, E. M. Mouaddib, and P. Vasseur, "Incremental map building for mobile robot navigation in an indoorenvironment," Robotics and Automation, 1998. Proceedings. 1998 IEEE International Conference on, vol. 3, 1998.
[7]F. Blanes, G. Benet, J. F. Simo, and P. Perez, "Enhancing the real-time response of an ultrasonic sensor for mapbuilding tasks," Industrial Electronics, 1999. ISIE''99. Proceedings of the IEEE International Symposium on, vol. 3, 1999.
[8]M. Asada, "Map building for a mobile robot from sensory data," Systems, Man and Cybernetics, IEEE Transactions on, vol. 20, pp. 1326-1336, 1990.
[9]S. C. Wei, Y. Yagi, and M. Yachida, "Online map building based on ultrasonic and image sensor," Systems, Man, and Cybernetics, 1996., IEEE International Conference on, vol. 2, 1996.
[10]M. Tomono and S. Yuta, "Mobile robot navigation in indoor environments using object andcharacter recognition," Robotics and Automation, 2000. Proceedings. ICRA''00. IEEE International Conference on, vol. 1, 2000.
[11]J. Wolf, W. Burgard, and H. Burkhardt, "Robust vision-based localization by combining an image-retrieval system with Monte Carlo localization," Robotics, IEEE Transactions on [see also Robotics and Automation, IEEE Transactions on], vol. 21, pp. 208-216, 2005.
[12]http://en.wikipedia.org/wiki/Monte_Carlo_method.
[13]http://en.wikipedia.org/wiki/Kalman_filter.
[14]S. Datta, D. Banerji, and R. Mukherjee, "Mobile Robot Localization with Map Building and Obstacle Avoidance for Indoor Navigation," in IEEE, 2006.
[15]H. S. Dulimart and A. K. Jain, "Mobile robot localization in indoor environment," Pattern Recognition, vol. 30, pp. 99-111, 1997.
[16]A. Howard, "Multi-robot Simultaneous Localization and Mapping using Particle Filters," The International Journal of Robotics Research, vol. 25, p. 1243, 2006.
[17]M. Sharir, "Algorithmic motion planning in robotics," Computer, vol. 22, pp. 9-19, 1989.
[18]G. Dozier, A. Homaifar, S. Bryson, and L. Moore, "Artificial potential field based robot navigation, dynamicconstrained optimization and simple genetic hill-climbing," Evolutionary Computation Proceedings, 1998. IEEE World Congress on Computational Intelligence., The 1998 IEEE International Conference on, pp. 189-194, 1998.
[19]Y. Makita, M. Hagiwara, and M. Nakagawa, "A simple path planning system using fuzzy rules and a potentialfield," Fuzzy Systems, 1994. IEEE World Congress on Computational Intelligence., Proceedings of the Third IEEE Conference on, pp. 994-999, 1994.
[20]J. J. Leonard, H. F. Durrant-Whyte, and I. J. Cox, "Dynamic Map Building for an Autonomous Mobile Robot," The International Journal of Robotics Research, vol. 11, p. 286, 1992.
[21]L. Lapierre, R. Zapata, and P. Lepinay, "Combined Path-following and Obstacle Avoidance Control of a Wheeled Robot," The International Journal of Robotics Research, vol. 26, p. 361, 2007.
[22]T. P. Fries, "Autonomous Robot Motion Planning in Diverse Terrain Using Soft Computing," Adaptive and Learning Systems, 2006 IEEE Mountain Workshop on, pp. 177-182, 2006.
[23]http://www.sensorcentral.com/photoelectric/ultrasonic01.php.
[24]http://en.wikipedia.org/wiki/Laser_range_finder#Operation.
[25]http://www.goelectronic.com/store/sony_evi-d70.html.
[26]http://www.drrobot.com/products/item_downloads/DAT5280_1.pdf.
[27]http://www.acroname.com/robotics/parts/R66-R2868.pdf.
[28]G. Cen, H. Nakamoto, N. Matsuhira, and I. Hagiwara, "Effective Application of Monte Carlo Localization for Service Robot," in International Conference on Intelligent Robots and Systems, San Diego, 2005.
[29]S. Thrun, D. Fox, W. Burgard, and F. Dellaert, "Robust Monte Carlo localization for mobile robots," Artificial Intelligence, vol. 128, pp. 99-141, 2001.
[30]F. Dellaert, D. Fox, W. Burgard, and S. Thrun, "Monte Carlo localization for mobile robots," Robotics and Automation, 1999. Proceedings. 1999 IEEE International Conference on, vol. 2, 1999.
[31]D. Fox, "Adapting the Sample Size in Particle Filters Through KLD-Sampling," The International Journal of Robotics Research, vol. 22, p. 985, 2003.
[32]H. Surmann, A. Nuchter, and J. Hertzberg, "An autonomous mobile robot with a 3D laser range finder for 3D exploration and digitalization of indoor environments," Robotics and Autonomous Systems, vol. 45, pp. 181-198, 2003.
[33]H. J. Sohn and B. K. Kim, "A Robust Localization Algorithm for Mobile Robots with Laser Range Finders," in International Conference on Robotics and Automation, Spain, 2005.
[34]L. Zhang and B. K. Ghosh, "Line segment based map building and localization using 2D laserrangefinder," Robotics and Automation, 2000. Proceedings. ICRA''00. IEEE International Conference on, vol. 3, 2000.
[35]Y. H. Choi, T. K. Lee, and S. Y. Oh, "A line feature based SLAM with low grade range sensors using geometric constraints and active exploration for mobile robot," Autonomous Robots, vol. 24, pp. 13-27, 2008.
[36]F. Lu and E. Milios, "Robot Pose Estimation in Unknown Environments by Matching 2D Range Scans," Journal of Intelligent and Robotic Systems, vol. 18, pp. 249-275, 1997.
[37]C. Pradalier, S. Sekhavat, and F. Inria, "Concurrent matching, localization and map building using invariant features," Intelligent Robots and System, 2002. IEEE/RSJ International Conference on, vol. 1, 2002.
[38]X. Zezhong, L. Jilin, and X. Zhiyu, "Map building and localization using 2D range scanner," Computational Intelligence in Robotics and Automation, 2003. Proceedings. 2003 IEEE International Symposium on, vol. 2, 2003.
[39]G. A. Borges and M. J. Aldon, "Optimal mobile robot pose estimation using geometrical maps," Robotics and Automation, IEEE Transactions on, vol. 18, pp. 87-94, 2002.
[40]J. R. Beveridge and E. M. Riseman, "How easy is matching 2D line models using local search?," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 19, pp. 564-579, 1997.
[41]P. Fiorini and Z. Shiller, "Motion Planning in Dynamic Environments Using Velocity Obstacles," The International Journal of Robotics Research, vol. 17, p. 760, 1998.
[42]A. Stentz, "Optimal and efficient path planning for partially-knownenvironments," Robotics and Automation, 1994. Proceedings., 1994 IEEE International Conference on, pp. 3310-3317, 1994.
[43]L. E. Kavraki, P. Svestka, J. C. Latombe, and M. H. Overmars, "Probabilistic roadmaps for path planning in high-dimensionalconfiguration spaces," Robotics and Automation, IEEE Transactions on, vol. 12, pp. 566-580, 1996.
[44]V. J. Lumelsky and A. A. Stepanov, "Path-planning strategies for a point mobile automaton moving amidst unknown obstacles of arbitrary shape," Algorithmica, vol. 2, pp. 403-430, 1987.
[45]T. Shibata and T. Fukuda, "Intelligent motion planning by genetic algorithm with fuzzy critic," Intelligent Control, 1993., Proceedings of the 1993 IEEE International Symposium on, pp. 565-570, 1993.