結論與未來工作 - 全向式移動機器人之同步定位與環境地圖建立

5.1 結論

本論文提出了一個全向式移動平台結合全向式攝影機的定位系統設計，以基於EKF-SLAM之演算法，和全向式攝影機對環境做觀測，修正全向式機器人的打滑誤差，並在全向式機器人移動的同時，能夠建立出環境地圖且定位出機器人的位置。

以所推導出之全向式機器人運動模型，及不同地點對特徵點的觀測視角，

推算出特徵點相對於機器人本身的距離關係，以此資訊做為定位系統的輸入。使用SLAM演算法解決機器人之定位及地圖建立的問題，達成EKF-based SLAM演算法。結合影像處理與SLAM演算法，實現在全向式機器人平台上。

論文中以實驗驗證定位演算法：手動遙控機器人來回行走約12公尺後起點與終點誤差平均為0.07公尺，於室內繞方形3圈及走8字形軌跡起點與終點的x及y 方向誤差均在0.10公尺以內。並以情境模擬實驗結果證實機器人藉由此演算法的幫助，為在實驗室622繞行一圈後走出房門，沿走廊移動約11公尺進621門，之後再沿原路回到622。另加入了機器人於長距離移動中同時轉向的實驗，發揮了全向式機器人靈活移動的特性，並同時建立其沿途路徑的特徵點環境地圖，完成全向式移動機器人的室內導航功能。

5.2 未來工作

在本論文中之定位演算法約需耗時2秒左右，此運算時間在較為慢速的測試實驗中雖然可行，但在實際的應用中若是到了更複雜的環境，改變就不能有及時的反應，且若在機器人的移動速度加快的情形下，影像運算也不能作及時的反

應，影響定位結果的正確性。因此在影像處理及定位演算法的設計上可以再加以改善，提升整體定位系統的效能。

全向式攝影機常被用於多機器人系統上，而本論文發展出的基於全向攝影機之機器人定位方法亦可與之整合，並藉由全向式移動平台的高機動性，讓機器人不僅能夠觀測機器人隊伍中的隊友，也讓機器人能對周遭整體的環境做估測，

更迅速地移動至目標點，增加多機器人隊伍的實用與功能。

參考文獻

[1] M. Wada and H.H. Asada, “Design and Control of a Variable Footpoint Mechanism for Holonomic Omni-directional Vehicles and its Application to Wheelchairs,” in IEEE Transactions on Robotics and Automation, Vol.15 No.6, pp.

978-989, 1999.

[2] S. Ziaie-Rad, F. Janabi-Sharifi, M.M. Danesh-Panah, A. Abdollahi, H. Ostadi and H. Samani., “A Practical Approach to Control and Self-Localization of Persia Omni-Directional Mobile Robot,” in Proceedings of 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, Edmonton, Canada, 2005, pp.

3473-3479.

[3] H.R. Moballegh, P. Amini, Y. Pakzad, M. Hashemi and M. Narmiani, “An Improvement of Self-localization for Omni-directional Mobile Robots Using a New Odometry Sensor and Omni-directional Vision,” in Proceedings of Canadian Conference on Electrical and Computer Engineering, Niagara Falls, 2004, pp.

2337-2340.

[4] Y. Liu, R.L. Williams and J.J. Zhu, “Integrated Control and Navigation for Omni-directional Mobile Robot Based on Trajectory,” in Proceedings of American Control Conference, New York City, USA, 2007, pp. 2153-2158.

[5] K. Watanabe, “Control of an Omni-directional Mobile Robot,” in Proceedings of Second International Conference on Knowledge-Based Intelligent Electronic Systems, Adelaide, Australia, 1998, pp. 51-60.

[6] K. Watanabe, K. Izumi and F. Han, “Stochastic Fuzzy Servo Control Using Multiple Linear Dynamic Models,” in Proceedings of KES '98. 1998 Second International Conference on Knowledge-Based Intelligent Electronic Systems, Adelaide, Australia, 1998, pp. 474-482.

[7] C.C. Tsai, L.B. Jiang, T.Y. Wang and T.S. Wang,“Kinematics Control of an Omni-directional Mobile Robot, ” in Proceedings of 2005 CACS Automatic Control Conference, Taiwan, 2005, pp. 18-19.

[8] E.J. Jung, H.Y. Lee and J.H. Lee, “Navigation of an Omni-directional Mobile Robot with Active Caster Wheels,” in Proceedings of IEEE International Conference on Robotics and Automation, Pasadena, USA, 2008, pp. 1659-1665.

[9] J.S. Hu, J.H. Cheng and Y.J. Chang, “Spatial Trajectory Tracking Control of Omni-directional Wheeled Robot Using Optical Flow,” in Proceedings of IEEE 22^nd International Symposium on Intelligent Control, Singapore, 2007, pp.

1462-1467.

[10]H. Durrant-Whyte and T. Bailey, “TUTORIAL : Simultaneous Localization and Mapping: Part I”, IEEE Robotics & Automation Magazine, Vol. 13, No. 2,

pp.99-108, 2006.

[11]H. Durrant-Whyte and T. Bailey, “TUTORIAL：Simultaneous Localization and Mapping (SLAM)：Part II”, IEEE Robotics &Automation Magazine, Vol. 13, No.

2, pp. 108-117, 2006.

[12]J.M.M. Montiel, J. Civera and A. J. Davison, “Unified Inverse Depth Parametrization for Monocular SLAM,” in Proceedings of Robotics Science and Systems Conference, Philadelphia, 2006.

[13]F. Bertolli, P. Jensfelt and H. I. Chistensen, “SLAM Using Visual Scan-Matching with Distinguishable 3D Points,” in Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, Beijing, 2006, pp.4042-4047.

[14]Y. Maeda and D. Idou, “Multiple Omni-directional Vision System and Its Self-Localization Experiment,” in Proceedings of IEEE International Fuzzy Systems Conference, London, UK, 2007, pp. 1-6.

[15]J.H. Kim and M.J. Chung, “SLAM with Omni-directional Stereo Vision Sensor,”

in Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, Las Vegas, Nevada, 2003, pp. 442-447.

[16]M. Saedan, C. W. Lim and M.H. Aug, “Appearance-based SLAM with Map Loop Closing Using an Omni-directional Camera,” in Proceedings of IEEE/ASME International Conference on Advanced Intelligent Mechatronics, Switzerland, 2007, pp. 1-6.

[17]G. Welch and G. Bishop, An Introduction to the Kalman Filter, SIGGRAPH 2001 Course.

[18]T. B. Lauwers, G. A. Kantor and R. L. Hollis, “A Dynamically Stable Single-Wheeled Mobile Robot with Inverse Mouse-Ball Drive,” in Proceedings of IEEE International Conference on Robotics and Automation, Orlando, 2006, pp.

2884-2889.

[19]F.S. Huang and K.T. Song, “Vision SLAM Using Omni-Directional Visual Scan Matching,” Accepted for Publication in Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IEEE/RSJ IROS 2008), Nice, France, 2008.

[20]N. Winters, J. Gaspar, G. Lacey and J. Santos-Victor, “Omni-directional Vision for Robot Navigation,” in Proceedings of IEEE Workshop on Omni-directional Vision, South Carolina, 2000, pp.21-28.

[21]S. Panzieri, F. Pascucci, R. Setola and G. Ulivi, “A Low Cost Vision Based Localization System for Mobile Robots,” in Proceedings of 9^th Mediterranean Conference on Control and Automation, Dubrovnik, Croatia, 2001, pp. 1-6.

[22]H. Andreasson, A. Treptow and T. Duckett, “Localization for Mobile Robots using Panoramic Vision, Local Features and Particle Filter,” in Proceedings of

IEEE International Conference on Robotics and Automation, Barcelona, Spain, 2005, pp. 3348-3353.

[23]J. Shi and C. Tomasi, “Good Features to Track.” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Seattle, USA, 1994, pp.

593-600.

[24]David G. Lowe, “Distinctive Image Feature from Scale-Invariant Keypoints,”

International Journal of Computer Vision, Vol. 60, No. 2, 2004, pp. 91-110.

[25]S. Thrun, “Learning Metric-Topological Maps for Indoor Mobile Robot Navigation,” in Journal of Artificial Intelligence, vol. 99, pp. 21-71, 1998.

[26]S. Thrun, D. Fox and W. Burgard, Probabilistic Robotics, MIT Press, 2005.

[27]S. Thompson and A. Zelinsky, “Accurate Local Positioning Using Visual Landmark from a Panoramic Sensor,” in Proceedings of IEEE International Conference on Robotics and Automation, Washington, DC, 2002, pp. 2656-2661.

[28]J. Kim, K.J. Yoon, J.S. Kim and I. Kweon, “Visual SLAM by Single-Camera Catadioptric Stereo,” in Proceedings of SICE-ICASE International Joint Conference, Busan, Korea, 2006, pp. 2005-2009.

在文檔中全向式移動機器人之同步定位與環境地圖建立 (頁 66-70)