本論文以RoboCup全尺寸人形機器人競賽為主題，提出一考量陰影干擾之避障導航控制研究；其主要針對一對一足球競賽與帶球避障等兩項比賽項目進行探討。由於在比賽環境中影像系統存在著干擾，如環境照明以及陰影遮避等問題，其造成在影像辨識以及特徵擷取之困難，甚至可能導致誤判的情形發生。雖然影像白平衡之方法可以解決環境照明動態變化之問題，但在面對陰影干擾的問題上大多著重於僅以影像處理方式來解決，但卻無對環境光源配置加以考慮，因此無法有效且快速地解決問題。因此本論文針對室內環境，提出環境光源位置之預估以及初步障礙物位置等資訊，進行光學幾何運算來預估障礙物陰影之位置。並以所預估之障礙物陰影在影像中之位置，進行影像辨識之條件修正。此外，本論文之避障導航系統根據不同之狀態分別使用人工位能場（Artificial Potential Field）以及決策樹（Decision Tree）之方法達成。最後，本論文除了探討在實驗室之測試之外，也以參加於荷蘭所舉辦之RoboCup 2013年比賽之情形進行比賽過程與結果之說明。

This study proposes an obstacle avoidance navigation approach by considering shadow interference for the “obstacle avoidance and dribbling” and the “dribble and kick” matches in RoboCup adult-size humanoid robot competitions. Practically, there exist interferences in image systems such as illumination variation and shadow effects. These interferences result in the problems in recognizing the image targets. Although conventional white balance methods may resolve the problems of illumination variation, shadow interferences also exhibit challenges for image recognitions. Nevertheless, conventional shadow problems were resolved with image processing approaches, and they did not consider the arrangements of lighting systems and obstacles’ shadow positions. Therefore, this thesis proposes the position detection of lighting sources in an indoor environment, and then the obstacle’s position is used to estimate the shadow position in the image in terms of optical geometry. The estimated shadow position in the image is further used to revise the image threshold values in the shadow area. In addition, the artificial potential field (APF) and decision tree approaches are used to achieve the obstacle avoidance navigation. Finally, in addition to the experiments in our laboratory, the participation in the RoboCup 2013 competition in Netherlands was presented to discuss the performance of the proposed approaches.

[1] V. Chikane and C.S. Fuh, “Automatic White Balance for Digital Still Cameras,” Journal of Information Science and Engineering, vol. 22, no. 3, pp. 497 – 509, 2006.
[2] 陳柏翰，「影像亮度變化對白平衡演算法影響之研究」，碩士學位論文，北台灣科學技術學院，民國97年。
[3] M. Fedor, “Approaches to Color Balancing,” Department of Psychology, Stanford University, U.S.A, 1998.
[4] J. Chiang and F.A. Turkait, “Color Balancing Experiments with the HP-Photo Smart-C30 Digital Camera,” PSYCH221/EE362 course project, Department of Psychology, Stanford University, U.S.A., 1999.
[5] 邱贊生，「數位相機之自動白平衡」，碩士學位論文，國立台灣大學，民國89年。
[6] J.Y. Huo, Y.L. Chang, J. Wang, and X.X. Wei, "Robust Automatic White Balance Algorithm Using Gray Color Points in Images," IEEE Transactions on Consumer Electronics, vol. 52, no. 2, pp. 541 – 546, 2006.
[7] H.C. Hung and C.L. Chen, "A Fuzzy Inference Model for Removing the Color Cast of Digitally Captured Images Under Unknown Illuminants," International Conference on Fuzzy Theory and its Applications, pp. 192 – 197, 2012.
[8] E. Land, "An Alternative Technique for the Computation of the Designator in the Retinex Theory of Color Vision," Proceedings of the National Academy of Science, vol. 83, no. 10, pp. 3078 – 3080, 1986.
[9] Z. Rahman, D. Jobson, and G. Woodell, "Retinex Processing for Automatic Image Enhancement," The Human Vision and Electronic Imaging VII Conference, vol. 4662, pp. 390 - 401, 2002.
[10] 盧俊良，「基於光線與臉部表情變化下之人臉辨識」，碩士學位論文，國立中央大學，民國98年。
[11] G.D. Finlayson, S.D. Hordley, C. Lu, and M.S. Drew, "On the Removal of Shadows from Images," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 1, pp. 59 – 68, 2006.
[12] J. Zhu, K.G.G. Samuel, S.Z. Masood, and M.F. Tappen, "Learning to Recognize Shadows in Monochromatic Natural Images," IEEE International Conference on Computer Vision and Pattern Recognition, pp. 223 – 230, 2010.
[13] W.H. Huang, B.R. Fajen, B.R. Fink, and W.H. Warren, "Visual Navigation and Obstacle Avoidance Using a Steering Potential Function," Robotics and Autonomous Systems, vol. 54, pp. 288-299, 2006.
[14] C.C. Wong, C.T. Cheng, K.H. Huang, and Y.T. Yang, "Fuzzy Control of Humanoid Robot for Obstacle Avoidance," International Journal of Fuzzy Systems, vol. 10, no. 1, pp. 1 – 10, 2008.
[15] Z. Su, B. Zeng, G. Liu, F. Ye, and M. Xu, "Application of Fuzzy Neural Network in Parameter Optimization of Mobile Robot Path Planning Using Potential Field," IEEE International Symposium on Industrial Electronics, pp. 2125 – 2128, 2007.
[16] Axiomtek Corporation [Online], Available at: http://www.axiomtek.com.tw/products/ViewProduct.asp?view=680/. (Access: 2013/07/26)
[17] L. He, Y. Chao, K. Suzuki, and K. Wu, "Fast Connected-Component Labeling," Pattern Recognition, vol. 42, no. 9, pp. 1977 – 1987, 2009.
[18] C.H. Kuo, H.C. Chou, S.W. Chi, and Y.D. Lien, "Vision-based Obstacle Avoidance Navigation with Autonomous Humanoid Robots for Structured Competition Problems," International Journal of Humanoid Robotics, vol.10, no. 3, 2013.
[19] P. Veelaert and W. Bogaerts, "Ultrasonic Potential Field Sensor for Obstacle Avoidance," IEEE Transactions on Robotics and Automation, vol. 15, no. 4, pp. 774 – 779, 1999.
[20] 許耀升，「具反應導航之嵌入式電動輪椅控制系統」，碩士學位論文，國立台灣科技大學，民國100年。
[21] PhaseSpace Motion Capture [Online], Available at: http://www.phasespace.com/. (Access: 2013/07/26)
[22] C.H. Kuo, H.C. Chou, Y.D. Lien, M.H. Wu, and S.W. Chi, “Team Description Paper: HuroEvolutionAD Humanoid Robot for RoboCup 2013 Humanoid League,” Department of Electrical Engineering, National Taiwan University of Science and Technology, 2013.
[23] 張書豪，「具自主導航與避障之嵌入式移動機器人控制系統開發」，碩士學位論文，國立台灣科技大學，民國99年。