本論文主要在探討FIRA HuroCup人形機器人全能賽所使用的視覺與控制策略系統。本人形機器人系統為一視覺回授控制系統，主要分成影像處理與控制策略兩部份，其控制處理中心是以Pico-820嵌入式主機板的CPU來做運算。以實現短跑、馬拉松、避障、投籃和PK五項競賽項目為重點。在視覺系統方面，將擷取的影像資料由RBG轉至HSV色彩空間後，以快速的區塊切割演算法和均值移動演算法作影像分割，再依不同的競賽項目與特徵物，提出對線、地標、障礙物、球與籃框、球門的辨識方法或資訊判斷，並透過驅動頭部馬達，達到目標追蹤的效果。策略方面，針對短跑、馬拉松的競速競賽，提出相似三角形與模糊控制方法。在投籃方面則以影像回授修正撿球和投籃的角度，再以曲線逼近求出投籃的力道；針對其餘著重精準度與穩定度的項目，以特性分割成不同的階段，設計不同的控制策略。整個影像及策略皆以C++撰寫並透過人機介面作控制。最後經實驗與競賽結果，可以充分展現本人形機器人在視覺與策略上優越的效能與強健性。

This thesis mainly concerns the development of the vision and strategy systems for the FIRA HuroCup competition. The humanoid robot system is regarded as a vision feedback control system and is generally separated into two parts, which are vision system and control strategy. The entire computations of the overall system for controlling and decision making are processed on an embedded CPU board Pico-820. The five challenges of the FIRA HuroCup competition, including sprint, marathon, obstacle run, basketball, and penalty kick, are emphasized and discussed. The image information is captured by a CMOS sensor, and then is sent to the CPU for processing. Converting the image from RGB to HSV color space reduces the effect on the lightness. By applying the fast object segmentation method, objects are quickly separated from the image frame. Then, the demanded objects such as line, landmark, obstacles, ball, and goal are recognized according to the requirements of the challenges. At the same time, features of the objects are extracted for the base of the decisions. Once the correct target is detected, applying the mean shift method and controlling the two motors equipped on the robot’s head with P-control to track the target reduce the possibility of fault detection. The racing events such as sprint and marathon are realized based on a similar triangle method and fuzzy logic control. Also, other strategies of challenges which emphasize the precise movement and stability are discussed and expressed in flowcharts. All functions of image processing and strategy controlling are programmed in C++, and are manipulated via a human-machine interface. Finally, the experimental results demonstrate the capability of vision and strategy systems, as well as the efficiency and validity in the FIRA HuroCup competition.

[1] Y.-T. Su, C.-Y. Hu, and T.-H. S. Li, “FPGA-based fuzzy PK controller and image processing system for small-sized humanoid robot,” in Proc. IEEE International Conference on Systems, Man and Cybernetics, SMC, 2009, pp. 1039-1044.
[2] Y.-T. Su, Development and implementation of visual and control systems for humanoid robot, Master Thesis, Dept. of E.E., N.C.K.U., Taiwan, June 2006.
[3] C.-M. Chang, Design and implementation of vision and strategy system for humanoid robot soccer competition, Master Thesis, Dept. of E.E., N.C.K.U., Taiwan, July 2009
[4] T.-K. Wang, Design and implementation of double passing strategy for humanoid soccer robot, Master Thesis, Dept. of E.E., N.C.K.U., Taiwan, Aug. 2010.
[5] Y. Sumi, Y. Ishiyama, and F. Tomita, “Robot-vision architecture for real-time 6-DOF object localization,” Computer Vision and Image Understanding, vol. 105, pp. 218-230, 2007.
[6] K. Hirota and Y. Kyo, “A target tracking robot based on fuzzy control,” in Proc. IEEE International Workshop on Robot and Human Communication, Sep. 1992, pp. 335-340.
[7] ASIMO, http://world.honda.com/ASIMO/RunWithASIMO/index.html
[8] NAO, http://www.aldebaran-robotics.com/
[9] FIRA, http://www.fira.net/.
[10] P.-C. Huang, Design and implementation of a series of small-sized humanoid robots, Master Thesis, Dept. of E.E., N.C.K.U., Taiwan, Aug 2011
[11] Microsoft visual studio 2010, http://msdn.microsoft.com/zh-tw/vstudio
[12] A. R. Smith, “Color Gamut Transform Pairs,” Computer Graphics, vol. 12, no. 3, pp. 12-19, Aug. 1978.
[13] J. Foley, A. Van Dam, S. Feiner, and J. Hughes. Computer Graphics: Principles and Practice. Reading, MA, USA: Addison-Wesley, 1995.
[14] G. S. Gupta and D. bailey, “Discrete YUV look-up tables for fast colour segmentation for robotic applications,” in Proc. IEEE Int. Conf. on Electrical and Computer Engineering, May 2008, pp. 963-968.
[15] K. T. Holland, R. A. Holman, T. C. Lippmann, and J. Stanley, “Practical use of video imagery in nearshore oceanographic field studies,” IEEE Journal of Oceanic Engineering, vol. 22, no. 1, pp. 81-92, Jan 1997.
[16] Y. I. Abdel-Aziz and H. M. Karara, “Direct linear transformation from comparator coordinates into object space coordinates in close-range photogrammetry,” in Proc. ASP/UI Symp. Close-Range Photogrammetry, Urbana, IL, 1971, pp. 1–18.
[17] A. Pooransingh, C. A. Radix, and A. Kokaram, “The path assigned mean shift algorithm: A new fast mean shift implementation for colour image segmentation,” in Proc. 15th IEEE International Conference on Image Processing, ICIP, 2008, pp. 597-600.
[18] H. Wang, B. Yang, G. Tian, and A. Men, “Object tracking by applying mean-shift algorithm into particle filtering,” in Proc. 2nd IEEE International Conference on Broadband Network & Multimedia Technology, IC-BNMT, 2009, pp. 550-554.
[19] The rule of the FIRA2011 HuroCup ,
http://www.fira.tw/static/RoboWorldCup/Hurosot.jsp
[20] R. O. Duda and P. E. Hart, “Use of the Hough transformation to detect lines and curves in pictures,” Commun. ACM, vol. 15, no. 1, pp. 11-15, 1972.
[21] L. Xu, E. Oja, and P. Kultanan, “A new curve detection method : randomized Hough transform (RHT),” Pattern Recognition Letters, vol. 11, no. 5, pp.331-338, 1990.
[22] R.O. Duda and P.E. Hart. Pattern Classification and Scene Analysis. New York: John Wiley & Sons, 1973.
[23] L.A. Zadeh, “Fuzzy sets,” Information and Control, vol. 8, no. 3, pp. 338-353, 1965.
[24] L.A. Zadeh, “Fuzzy algorithms,” Information and Control, vol. 12, no. 2, pp. 94–102,1968.
[25] T.-H. S. Li, Y.-T. Su, S.-W. Lai, and J.-J. Hu, “Walking Motion Generation, Synthesis, and Control for Biped Robot by Using PGRL, LPI, and Fuzzy Logic,” IEEE Trans. Syst., Man, Cybernetics-Part-B, vol. 41, no. 3, pp. 736-748, June 2011.
[26] Kendell A. Atkinson. An Introduction to Numerical Analysis (2nd ed.). New York: John Wiley & Sons, 1988.
[27] Weisstein, Eric W. Least Squares Fitting [Online].
Available: http://mathworld.wolfram.com/LeastSquaresFitting.html
[28] Matlab, http://www.mathworks.com/products/matlab/