本論文實現一個具有手臂兩輪自主機器人，其主要架構包含馬達與驅動器、機器手臂、及影像物件追蹤系統。我們採用了四組比例、積分及微分控制器(Proportional-Integral-Derivative，PID)分別為位移、速度、角度與追蹤的PID進行對兩輪機器人整體的控制，其中位移的PID負責控制兩輪機器人與目標物的距離，速度的PID控制兩輪機器人速度，角度PID為了避免兩輪機器人過度傾斜，最後經由追蹤PID取得方位的控制力達成影像物件追蹤。影像物件追蹤是利用平板電腦影像模組取得即時影像，經過辨識後傳送目標中心點位置，計算後取得方位再經由追蹤PID的輸出控制力來達到影像物件追蹤。最後利用機器手臂，實現取得目標物件的功能。
透過以下幾個實驗，包含影像辨識實驗、影像追蹤實驗、追蹤吸取物體實驗，證明此論文的方法是可行的。

This thesis implements a two-wheeled autonomous robot with arms. The main structure of the two-wheeled autonomous robot includes motors and their driver circuits, a robotic arm, and an image tracking system. In order to control the two-wheeled autonomous robot, the four Proportional-Integral-Derivative (PID) controllers are used in the two-wheeled autonomous robot, including the displacement PID, the velocity PID, the angle PID, and the tracking PID. The displacement and speed PID controllers are in charge of controlling the movement and speed of the two-wheeled autonomous robot, respectively. The angle PID controller is used to avoid the excessive tilt of the two-wheeled autonomous robot. The tracking PID is used to obtain the control of the orientation to achieve the image object tracking. The image tracking system uses the tablet image module to obtain real-time images. After the object is identified and some image processing operations are performed, the orientation of the target is obtained and then the robot arm acquires the target object. Some experiments are performed, including image recognition, image tracking, and the acquirement of the target object.
The experimental results demonstrate that the method of this thesis is feasible.

參考文獻
[1] SEGWAY，Retrieved From http://www.segway.com/。
[2] N. Vafamand, M. H. Khooban, T. Dragicevic and F. Blaabjerg, "Networked Fuzzy Predictive Control of Power Buffers for Dynamic Stabilization of DC Microgrids," in IEEE Transactions on Industrial Electronics.
[3] 黃惟誠，“類神經網路於車輛自動駕駛自主避障學習機制之研究”，明道大學資訊工程學系，碩士論文，2009。
[4] 黃國和，“應用類神經網路與超音波感測器於車型機器人之路徑追蹤與避障”，國立成功大學電機工程學系，碩士論文，2006。
[5] Y. Pal, A. Swarup and B. Singh, “Magnetics supported 3P-3W UPQC for the realization of four-wire distribution system, ” 2012 IEEE Fifth Power India Conference, Murthal, 2012, pp. 1-6.
[6] C. A. Faucher-Giguère and A. Loeb, “Pulsar–black hole binaries in the Galactic Centre, ” in Monthly Notices of the Royal Astronomical Society, vol. 415, no. 4, pp. 3951-3961, Aug. 2011.
[7] T. Yamakawa, “Stabilization of an Inverted Pendulum by a High -Speed Fuzzy Logic Controller Hardware System,” Fuzzy Sets and Systems, vol. 32, pp. 161-180, 1989.
[8] O. Matsumoto, S. Kajita and K. Tani, “Estimation and control of the attitude of a dynamic mobile robot using internal sensors,”Advanced Robotics, Vol. 7, No. 2, pp. 159-178, 1993.
[9] F. Grasser, A. D’Arrigo, S. Colombi and A.C. Rufer, “JOE: a Mobile,Inverted Pendulum,” IEEE Trans. Industrial Electronics, vol. 39, no.1, pp. 107–114, February 2002.
[10] Y. Alper, J. Omar, and S. Mubarak, “Object tracking: a survey,” ACM Computing Surveys, vol. 38, 2006.
[11] J.G. Allen, R.Y.D. Xu, J.S. Jin, “Object tracking using camshift algorithm andmultiple quantized feature spaces,” School of Information Technologies ,University of Sydney press, 2006.
[12] J. Rajruangrabin, S. S. Thongvigitmanee, S. Aootaphao and P. Thajchayapong, “Acceleration of filtered back-projection algorithm for 3D cone-beam CT reconstruction using parallel computation, ” 2013 IEEE Nuclear Science Symposium and Medical Imaging Conference (2013 NSS/MIC), Seoul, 2013, pp. 1-4.
[13] S. B. Niku, “Introduction to Robot-Analysis, Systems, Application,” Prentice Hall, 2004.
[14] L. Wang, L. Fu and X. Hu, “A nonlinear complementary filter approach for MAV 3D-attitude estimation with low-cost MARG/ADS, ” 2016 IEEE/ION Position, Location and Navigation Symposium (PLANS), Savannah, GA, 2016, pp. 42-47.
[15] W. A. Mustafa, H. Yazid and S. B. Yaacob, “Illumination normalization of non-uniform images based on double mean filtering, ” 2014 IEEE International Conference on Control System, Computing and Engineering (ICCSCE 2014), Batu Ferringhi, 2014, pp. 366-371.
[16] D. N. Abara and A. Lanzon, “H-infinity-PID controller for an open-loop unstable system, ” 2017 IEEE 3rd International Conference on Electro-Technology for National Development (NIGERCON), Owerri, 2017, pp. 134-138.
[17] 徐柏剛，“六足機器人之步態分析與控制,”國立台灣海洋大學電機工程系碩士論文，2013。
[18] D. Chatterjee and S. Chandran, “Comparative study of camshift and KLT algorithms for real time face detection and tracking applications, ” 2016 Second International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN), Kolkata, 2016, pp. 62-65.
[19] A. Aakerberg, K. Nasrollahi and T. Heder, “Improving a deep learning based RGB-D object recognition model by ensemble learning,”2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA), Montreal, QC, 2017, pp. 1-6.
[20] Y. Dandotiya and A. Atre, “Image retrieval using edge detection, RLBP, color moment method for YCbCr and HSV color space, ” 2017 International conference of Electronics, Communication and Aerospace Technology (ICECA), Coimbatore, 2017, pp. 662-668.