自主式機器人已廣泛地發展並應用於不同的環境中，例如工業、軍事、展覽和居家看護等。如何在這些動態環境中規畫路徑和避開障礙遂變成了關鍵性的課題。近年來，大多數研究著重於使用聲納、雷射測距儀等感測周遭環境並能成功地閃避動態障礙物，但是在目標導向為主的任務中此方法卻不是非常有效率的。

本論文建構了只利用廣角攝影機之動態路徑規劃系統，實現背景相減演算法偵測動態障礙物並利用HSV色彩和卡曼/粒子濾波器持續追蹤物體。此外，本系統整合改善之可視圖法和平行處理演算法將執行時間從4秒縮減至低於0.2秒。最後經由主從式架構和閉迴路控制導引移動式機器人循著軌跡至終點。

在本論文中，實驗結果顯示了粒子濾波不單是在追蹤移動物體的速度變化比卡曼濾波有較佳的強健性，並且在物體遮蔽和光影變化的測試項目下也有不錯的正確率。不僅如此，實驗結果也證明了此動態影像伺服系統的可行性與效率。此系統成功地在必要情況下重新規劃路徑並實現閉迴路系統控制移動式機器人閃避動態障礙物(200mm/s)，並能與規劃之路徑保持低於30 mm 的誤差。

Autonomous robots are widely used in various applications such as industrial, military, exhibition and home care. Dynamic path planning including obstacle avoidance in real-time is a critical issue for the success of mobile robots in the above dynamic environments. In recent years, most of researches focus on using local sensors to avoid dynamic obstacles. It performances well in obstacle avoidance, but is not an efficient way of goal-oriented system navigation.

This thesis proposes a dynamic path planning system only using omni-directional camera on the ceiling. Based on the global view, background subtraction method is applied to detect a moving object and Kalman/Particle filter based on HSV (hue, saturation, and value) color space is used to track the moving object. Furthermore, this system integrates reduced visibility graph algorithm and parallel processing in path planning to reduce the computation time from 4115 ms to less than 200 ms in 457x357 cm2 work space. Finally, it navigates the mobile robot with closed loop control through the server-client model.

Our experimental results show that the Particle Filter is not only more robust than Kalman Filter to the speed change of moving object but also has better performance during object occlusion and illumination changes. The results also demonstrate the effectiveness and efficiency of the proposed visual servoing system. The system successfully controls the motion of a robot to avoid dynamic obstacle of speed 200 mm/s and re-plans a new path in real-time when necessary. It also maintains the trajectory following error of less than 30 mm with the closed loop control.

[1]H.-C. Huang, et al., "Omnidirectional Mobile Home Care Robot," Department of Electrical Engineering, National Chung-Hsing University2006.
[2]K.-H. Chi and M. R. Lee, "Obstacle avoidance in mobile robot using Neural Network," in Consumer Electronics, Communications and Networks (CECNet), 2011 International Conference on, 2011, pp. 5082-5085.
[3]C. Ivancsits, "Visual Navigation System for Small Unmanned Aerial Vehicles," Master of Science, Graduate Institute of Automation and Control, National Taiwan University of Science and Technology, Taipei, Taiwan, 2010.
[4]A. Muis and K. Ohnishi, "Eye-to-hand approach on eye-in-hand configuration within real-time visual servoing," Mechatronics, IEEE/ASME Transactions on, vol. 10, pp. 404-410, 2005.
[5]L. Haoxiang, et al., "Visual servoing with LQR control for mobile robots," in Control and Automation (ICCA), 2010 8th IEEE International Conference on, 2010, pp. 317-321.
[6]W. Ying, et al., "Visual servo control and parameter calibration for mobile multi-robot cooperative assembly tasks," in Automation and Logistics, 2008. ICAL 2008. IEEE International Conference on, 2008, pp. 635-639.
[7]Z. Hong and J. P. Ostrowski, "Visual motion planning for mobile robots," Robotics and Automation, IEEE Transactions on, vol. 18, pp. 199-208, 2002.
[8]C. L. Chen and M. R. Lee, "Global path planning in mobile robot using omnidirectional camera," in Consumer Electronics, Communications and Networks (CECNet), 2011 International Conference on, 2011, pp. 4986-4989.
[9]H.-P. Huang and S.-Y. Chung, "Dynamic visibility graph for path planning," in Intelligent Robots and Systems, 2004. (IROS 2004). Proceedings. 2004 IEEE/RSJ International Conference on, 2004, pp. 2813-2818 vol.3.
[10]C. Wei, et al., "Reduction of Visibility Graph on Global Path Planning for Mobile Robot," in Control Conference, 2006. CCC 2006. Chinese, 2006, pp. 1605-1608.
[11]K. Rebai, et al., "Moving obstacles detection and tracking with laser range finder," in Advanced Robotics, 2009. ICAR 2009. International Conference on, 2009, pp. 1-6.
[12]D. Bodhale, et al., "Path planning for a mobile robot in a dynamic environment," in Robotics and Biomimetics, 2008. ROBIO 2008. IEEE International Conference on, 2009, pp. 2115-2120.
[13]C.-C. Tsai, et al., "Autonomous navigation of an indoor tour guide robot," in Advanced robotics and Its Social Impacts, 2008. ARSO 2008. IEEE Workshop on, 2008, pp. 1-6.
[14]M. Piccardi, "Background subtraction techniques: a review," in Systems, Man and Cybernetics, 2004 IEEE International Conference on, 2004, pp. 3099-3104 vol.4.
[15]H.-E. K. Lee, "Target Tracking of Autonomous Mobile Robots," Master of Science, Graduate Institute of Automation and Control, National Taiwan University of Science and Technology, Taipei, Taiwan, 2010.
[16]A. Lepis, "The Use of Optic Flow within Background Subtraction," Engineering, 2005.
[17]K. Srinivasan, et al., "Improved background subtraction techniques for security in video applications," in Anti-counterfeiting, Security, and Identification in Communication, 2009. ASID 2009. 3rd International Conference on, 2009, pp. 114-117.
[18]W. Qin and W. Yaonan, "Background subtraction based on adaptive non-parametric model," in Intelligent Control and Automation, 2008. WCICA 2008. 7th World Congress on, 2008, pp. 5960-5965.
[19]S. Geman and D. Geman, "Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. PAMI-6, pp. 721-741, 1984.
[20]A. Yilmaz, et al., "Object Tracking: A Survey," ACM Computing Surveys, vol. 38, p. 45, 2006.
[21]J. Salvi, et al., "A comparative review of camera calibrating methods with accuracy evaluation," Pattern Recognition 35, vol. 1617–1635, 2002.
[22]C. Harris and M. Stephen, "A Combined Corner and Edge Detector," Proc. Fourth Alvey Vision Conf., vol. 15, pp. 147-151, 1988.
[23]S. Suzuki and K. Abe, "Topological structural analysis of digitized binary images by border following," Computer Vision, Graphics, and Image Processing, vol. 30, pp. 32-46, 1985.
[24]J.-C. Latombe, Robot motion planning. Boston: KluwerAcademic Publishers, 1991.
[25]Z. H. E. Chen, "Bayesian Filtering : From Kalman Filters to Particle Filters , and Beyond VI Sequential Monte Carlo Estimation : Particle Filters," Statistics, pp. 1-69, 2003.