本論文旨在建立大型人形機器人立體視覺影像與控制策略系統，並實際應用於FIRA國際機器人競賽HuroCup大人形組；本大型人形機器人主要分成立體影像系統與控制策略兩部份，其影像處理與策略控制核心採用筆記型電腦為中央運算模組，並連接兩台網路攝影機做為視覺感知器。論文首先介紹本大型人形機器人之硬體系統架構與規格，接著是立體視覺系統的建立與策略系統的流程控制。在視覺系統方面，首要工作是雙眼攝影機的校正，使用區塊匹配演算法計算立體影像的視差得到深度資訊，重建周圍環境的三維座標系統，最後我們提出強健且快速的搜尋法以辨識不同種類的特徵物體，並獲得各物件的相對位置。在策略控制方面，對於較高技術性的避障競賽，提出基於粒子群最佳化的演算法，簡化策略判斷，尋找較短且適合機器人行走的路線。針對其餘著重精準度與穩定度的項目，以其特性區分成不同的階段，設計最適合的控制策略系統，以達成最佳的任務執行時間。最後經實驗與模擬結果，可充分展現本大型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 stereo vision and strategy control systems for the FIRA Adult-sized HuroCup competition. The entire system is regarded as a vision feedback control system. The overall processes of vision and decision-making are processed on a laptop. The stereo visual images are captured by two CMOS webcam sensors. Firstly, the thesis introduces the hardware architecture of adult-sized humanoid robot, aiRobots-AH-I, and overview of software system. In the stereo vision system, we calibrate and rectify stereo cameras, and use Block-Matching algorithm to correspond the images. Then, the three-dimensional coordinate system of the surrounding environment with coordinate transformation are reconstructed. We propose a recursive searching algorithm to recognize and segment the objects such as the line, landmark, obstacles, ball, and goal in the events. Furthermore, a simplified cam-shift concept is adopted to track the found objects by driving the head motors. In the control strategy system, five events, including marathon, sprint, basketball, obstacle run, and penalty kick, are examined and emphasized. For the highly skilled obstacle run contest, particle swarm optimization algorithm is utilized to find a shorter and suitably walkable path for the robot without touching the obstacles. For the other events, we divide the strategy into multi-stages according to the characteristics of each event and design the most appropriate decision-making system to have the best performing time. Finally, experimental results fully demonstrate the superior performance and robustness of vision and strategy systems in our adult-sized humanoid robot.

[1] 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.
[2] 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] C.-H. Li, Design and Implementation of Vision and Strategy Systems for the FIRA HuroCup Competition, Master Thesis, Dept. of E.E., N.C.K.U., Taiwan, Aug 2011.
[7] ASIMO [Online], Available:
http://world.honda.com/ASIMO/RunWithASIMO/index.html
[8] NAO [Online], Available: http://www.aldebaran-robotics.com/
[9] FIRA [Online], Available: http://www.fira.net/
[10] K. Konolige, “Small vision system: Hardware and implementation,” in Proceedings of the International Symposium on Robotics Research, Hayama, Japan, 1997, pp. 111-116.
[11] G. R. Bradski, “Computer Video Face Tracking for use in a Perceptual User Interface,” in Proc. IEEE Workshop Applications of Computer Vision, pp. 214-219, Oct. 1998.
[12] J. Matasa, C. Galambosc, and J. Kittler, “Robust Detection of Lines Using the Progressive Probabilistic Hough Transform,” Computer Vision and Image Understanding, vol. 78, pp. 119-137, 2000.
[13] Robotis [Online], Available: http://www.robotis.com/
[14] Arduino STM32-F103ZET6 [Online], Available:
http://arduinosolutions.com/index.php?route=product/product&product_id=257
[15] TOSHIBA [Online], Available: http://www.toshiba.com/
[16] Logitech [Online], Available: http://www.logitech.com/
[17] Zig-100 [Online], Available:
http://support.robotis.com/en/product/auxdevice/communication/zigbee_manual.htm
[18] DMP [Online], Available: http://www.dmp.com.tw/
[19] Microsoft visual studio 2010 [Online], http://msdn.microsoft.com/zh-tw/vstudio
[20] Microsoft Kinect [Online], http://www.xbox.com/zh-tw/Kinect/Kinect-Effect
[21] D. Brown, “Close-range camera calibration,” Photogrammetric Engineering, vol. 37, pp. 855-866, 1971.
[22] J. Fryer and D. Brown, “Lens distortion for close-range photogrammetry,” Photogrammetric Engineering and Remote Sensing, vol. 52, pp. 51-58, 1986.
[23] R. Lenz, and D. Fritsch, “Accuracy of videometry with CCD sensors,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 45, pp. 90-110, 1990.
[24] S. Lanser and A. Roboter, Modellbasierte Lokalisation gestutzt auf monokulare Videobilder: Techn. Univ. Munchen, 1997.
[25] S. Lanser, C. Zierl, and R. Beutlhauser, “Multibildkalibrierung einer CCD-Kamera,” in Proc. Mustererkennung, Informatik aktuell, 1995, pp. 481-491.
[26] G. Bradski and A. Kaehler, Learning OpenCV: Computer vision with the OpenCV library: O'Reilly Media, 2008.
[27] J. Heikkilä and O. Silvén, “Calibration Procedure for Short Focal Length off-the-shelf CCD Cameras,” in Proc. 13th International Conference on Pattern Recognition, Vienna, Austria, pp. 166-170, 1996.
[28] J. Heikkilä and O. Silvén, “A Four-step Camera Calibration Procedure with Implicit Image Correction,” in Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'97), San Juan, Puerto Rico, pp. 1106-1112, 1997.
[29] Matlab [Online], http://www.mathworks.com/products/matlab/
[30] Camera Calibration Toolbox for Matlab [Online], http://www.vision.caltech.edu/bouguetj/calib_doc/
[31] OpenCV [Online], http://opencv.willowgarage.com/
[32] Vladimir Kolmogorov, and Ramin Zabih, “Computing Visual Correspondence with Occlusions via Graph Cuts, ” in Proc. Eighth IEEE International Conference on Computer Vision, ICCV 2001, pp. 508-515.
[33] L. Di Stefano, M. Marchionni, and S. Mattoccia, “A Fast Area-based Stereo Matching Algorithm,” Image and Vision Computing, vol. 22, no. 12, pp 983-1005, October 2004.
[34] G Welch, and G Bishop, An Introduction to the Kalman Filter, (Technical Report TR95-041), University of North Carolina, Chapel Hill, NC, 1995.
[35] A. R. Smith, “Color Gamut Transform Pairs,” Computer Graphics, vol. 12, no. 3, pp. 12-19, Aug. 1978.
[36] J. Foley, A. Van Dam, S. Feiner, and J. Hughes. Computer Graphics: Principles and Practice. Reading, MA, USA: Addison-Wesley, 1995.
[37] D. Comaniciu, and P. Meer, “Mean Shift Analysis and Applications,” in Proc. 1999 IEEE International Conference on Computer Vision, vol. 2, pp. 1197-1203.
[38] The rule of the FIRA2011 HuroCup [Online],
Available: http://www.fira.tw/static/RoboWorldCup/Hurosot.jsp
[39] 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.
[40] Eric W. Weisstein, Least Squares Fitting [Online],
Available: http://mathworld.wolfram.com/LeastSquaresFitting.html
[41] M. Srinivas, and L. Patnaik, “Adaptive probabilities of crossover and mutation in genetic algorithms,” IEEE Transactions on System, Man and Cybernetics, vol.24, no.4, pp.656–667, 1994.
[42] D. E. Goldberg, Genetic Algorithms in Search Optimization and Machine Learning, Addison Wesley, p. 41, ISBN 0-201-15767-5, 1989.
[43] R. J. Williams, “A class of gradient estimating algorithms for reinforcement learning in neural networks,” in Proc. Int. Joint Conf. Neural Networks, vol. II, 1987, pp. 601–608.
[44] P. Jan, S. Vijayakumar, and S. Schaal, “Reinforcement Learning for Humanoid Robotics”, in Proc. IEEE-RAS International Conference on Humanoid Robots, 2003.
[45] C.-Y. Tsai, and I.-W. Kao, “Particle Swarm Optimization with Selective Particle Regeneration for Data Clustering,” Expert Systems with Applications, Vol. 38, Is. 6, pp. 6565-6576, June 2011.
[46] A. W. Mohemmed, N. C. Sahoo, and T. K. Geok, “Solving Shortest Path Problem using Particle Swarm Optimization,” Applied Soft Computing, Vol. 8, Is. 4, pp. 1643-1653, September 2008.
[47] S. Z. Zhao, J. J. Liang, and P. N. Suganthan1, “Dynamic Multi-Swarm Particle Swarm Optimizer with Local Search for Large Scale Global Optimization,” in Proc. Congress on Evolutionary Computation (CEC 2008), pp. 3845-3852.
[48] J. Kennedy, and R. Eberhart, “Particle swarm optimization,” in Proc. IEEE Int. Conf. Neural Networks, vol. IV, 1995, pp. 1942–1948.
[49] J. Kennedy, “The Particle Swarm: Social Adaptation of Knowledge,” in Proc. IEEE Int. Conf. Evolutionary Computation, 1997, pp. 303–308.
[50] Z-H. Zhan, J. Zhang, Y. Li, and H.S-H. Chung, “Adaptive Particle Swarm Optimization,” IEEE Trans. Systems, Man, and Cybernetics Part B, vol. 39, no.6, 2009, pp. 1362–1381.
[51] Dijkstra's_algorithm [Online], Available: http://en.wikipedia.org/wiki/Dijkstra's_algorithm
[52] A* search_algorithm [Online], Available: http://en.wikipedia.org/wiki/A*_search_algorithm
[53] M. Saska, M. Macas, L. Preucil, and L. Lhotska, “Robot Path Planning using Particle Swarm Optimization of Ferguson Splines,” in Proc. IEEE Emerging Technologies and Factory Automatio, pp. 833-839, 2006.