本文以無人搬運車的概念為出發點，傳統的無人搬運車以軌道輸送物料，而較新的無人搬運車則是以無軌方式輸送，在地板上的貼上反光漆使無人搬運車能夠跟著它走。然而要更改軌道路徑所花費的成本與時間浩大；無軌輸送的路徑也缺乏其彈性，假如能夠設計一套系統不須依賴軌道而且能夠隨時更改路徑則能改善此問題。
本文利用機械手臂與移動機器人實現這個概念，提出的方法包含三個動作：目標追蹤、自主避障以及目標物夾取。其中”目標追蹤”和”自主避障”屬於移動機器人的範疇，而”目標物夾取”則屬於機械手臂的範疇。流程一開始由移動機器人等待人下達指令，設定目的地的距離以及方位，利用模糊類神經網路引導移動機器人自主避開障礙物直到到達目的地。再由移動機器人上方的相機搜索目標物，結合機械手臂前的相機修正夾爪與目標的誤差，最後再把目標物搬回初始位置結束並等待下一次的指令。
本文的方法有三大特點：其一，移動機器人以較平滑的軌跡避開障礙物並且到達目的地，能改善對於狹小空間易產生碰撞的問題；其二，解決避障行為容易遇到死循環的問題；其三，手臂夾取的部分採用影像伺服控制，根據影像回傳終端夾爪的位置來調整手臂的姿態以及夾取目標物。

In this thesis, the concept of the automated guided vehicle (AGV) as a starting point. The traditional AGV travels with orbit. The newer way use the reflective paint replace orbit and make AGV can follow the paint. However, changing the path of orbit spends huge cost and time; the trackless is also lack of flexibility. Therefore, this problem can be improved if a system is developed without orbit and path can be changed at any time.
In this thesis, the manipulator and mobile robot are implement. Proposing three behaviors in this system: target seeking, obstacle avoidance and target grasping. Target seeking and obstacle avoidance is the category of mobile robot; target grasping is the category of manipulator. In the beginning, the mobile robot waits the command by human. Set up the distance and orientation. Second, with using neuro-fuzzy controller to navigate mobile robot avoid obstacles until it reach to the destination. Then recognize the target by the camera on the top of mobile robot. And integrate eye-in-hand camera to modify the error between the end-effector and target. Finally, manipulator grasps the target and transport to the initial position and wait the next command.
There are three features in this thesis: first, mobile robot avoid obstacle with smoother trajectory and drive to destination. For narrow space it can be improve. Second, solving the problem of dead-cycle which easily occurs on obstacle avoidance behavior. Third, the target grasping adopts visual servo control. Modify the posture of manipulator and grasping the target by feedback the end-effector position on the image.

[1]H. Andreasson, A. Bouguerra, M. Cirillo, D. N. Dimitrov, D. Driankov, L. Karlsson, et al., "Autonomous Transport Vehicles: Where We Are and What Is Missing," Robotics & Automation Magazine, IEEE, vol. 22, pp. 64-75, 2015.
[2]V. Digani, F. Caramaschi, L. Sabattini, C. Secchi, and C. Fantuzzi, "Obstacle avoidance for industrial AGVs," in 2014 10th IEEE International Conference on Intelligent Computer Communication and Processing, ICCP 2014, September 4, 2014 - September 6, 2014, Cluj-Napoca, Romania, 2014, pp. 227-232.
[3]K. Fan, Q. Yang, P. Li, and W. Yan, "On the design of AGV obstacle avoidance system based on fuzzy-PID dual-mode controller," in 2012 1st IEEE Conference on Control, Systems and Industrial Informatics, ICCSII 2012, September 23, 2012 - September 26, 2012, Bandung, Indonesia, 2012, pp. 54-58.
[4]N.-S. Pai, H.-H. Hsieh, and Y.-C. Lai, "Implementation of obstacle-avoidance control for an autonomous omni-directional mobile robot based on extension theory," Sensors (Switzerland), vol. 12, pp. 13947-13963, 2012.
[5]H. Rodriguez-Cortes and E. Aranda-Bricaire, "Observer based trajectory tracking for a wheeled mobile robot," in 2007 American Control Conference, ACC, July 9, 2007 - July 13, 2007, New York, NY, United states, 2007, pp. 991-996.
[6]N. Soltani, A. Shahmansoorian, and M. A. Khosravi, "Robust distance-angle leader-follower formation control of non-holonomic mobile robots," in 2014 2nd RSI/ISM International Conference on Robotics and Mechatronics, ICRoM 2014, October 15, 2014 - October 17, 2014, Tehran, Iran, 2014, pp. 24-28.
[7]D. Nakhaeinia and B. Karasfi, "A behavior-based approach for collision avoidance of mobile robots in unknown and dynamic environments," Journal of Intelligent and Fuzzy Systems, vol. 24, pp. 299-311, 2013.
[8]M. Vona and N. H. Shekar, "Teaching Robotics Software With the Open Hardware Mobile Manipulator," Education, IEEE Transactions on, vol. 56, pp. 42-47, 2013.
[9]H. Mo, Q. Tang, and L. Meng, "Behavior-Based Fuzzy Control for Mobile Robot Navigation," Mathematical Problems in Engineering, vol. 2013, p. 10, 2013.
[10]J. Jiao, S. Ye, Z. Cao, N. Gu, X. Liu, and M. Tan, "Embedded vision-based autonomous move-to-grasp approach for a mobile manipulator," International Journal of Advanced Robotic Systems, vol. 9, 2012.
[11]R. Johnston, "Fuzzy logic control," Microelectronics Journal, vol. 26, pp. 481-495, 1995.
[12]U. Farooq, K. M. Hasan, G. Abbas, M. U. Asad, and S. O. Saleh, "Design, low cost implementation and comparison of MIMO Mamdani Fuzzy Logic Controllers for wall tracking behavior of mobile robot," in 4th International Conference on Information and Communication Technologies, ICICT 2011, July 23, 2011 - July 24, 2011, Karachi, Pakistan, 2011, pp. 118-126.
[13]U. Farooq, K. M. Hasan, G. Abbas, and M. U. Asad, "Comparative analysis of zero order Sugeno and Mamdani fuzzy logic controllers for obstacle avoidance behavior in mobile robot navigation," in 2011 International Conference and Workshop on the Current Trends in Information Technology, CTIT'11, October 26, 2011 - October 27, 2011, Dubai, United arab emirates, 2011, pp. 113-119.
[14]U. Farooq, J. Gu, and M. L. Seto, "Design and comparison of Takagi-Sugeno type-1 and interval type-2 fuzzy logic controllers for posture stabilization of wheeled mobile robot," in 2013 IEEE International Conference on Robotics and Biomimetics, ROBIO 2013, December 12, 2013 - December 14, 2013, Shenzhen, China, 2013, pp. 2309-2316.
[15]I. Engedy and G. Horvath, "Artificial neural network based mobile robot navigation," in WISP 2009 - 6th IEEE International Symposium on Intelligent Signal Processing, August 26, 2009 - August 28, 2009, Budapest, Hungary, 2009, pp. 241-246.
[16]I. Engedy and G. Horvath, "Artificial neural network based local motion planning of a wheeled mobile robot," in 11th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2010, November 18, 2010 - November 20, 2010, Budapest, Hungary, 2010, pp. 213-218.
[17]A. S. Morris and A. Mansor, "Finding the inverse kinematics of manipulator arm using artificial neural network with lookup table," Robotica, vol. 15, pp. 617-625, 1997.
[18]K. Hashimoto, T. Kimoto, T. Ebine, and H. Kimura, "Manipulator control with image-based visual servo," in Proceedings of the 1991 IEEE International Conference on Robotics and Automation, April 9, 1991 - April 11, 1991, Sacramento, CA, USA, 1991, pp. 2267-2271.
[19]Y. Wang, G.-L. Zhang, H. Lang, B. Zuo, and C. W. De Silva, "A modified image-based visual servo controller with hybrid camera configuration for robust robotic grasping," Robotics and Autonomous Systems, vol. 62, pp. 1398-1407, 2014.
[20]G. Dong and Z. H. Zhu, "Position-based visual servo control of autonomous robotic manipulators," Acta Astronautica, vol. 115, pp. 291-302, 2015.
[21]I. Siradjuddin, L. Behera, T. M. McGinnity, and S. Coleman, "A position based visual tracking system for a 7 DOF robot manipulator using a Kinect camera," in 2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012, June 10, 2012 - June 15, 2012, Brisbane, QLD, Australia, 2012, p. IEEE Computational Intelligence Society (CIS); International Neural Network Society (INNS).
[22]X.-Y. AhYin, "Operators to dilate and erode color impulse noise images based on the morphology," in 2nd International Conference on E-Business and E-Government, ICEE 2011, May 6, 2011 - May 8, 2011, Shanghai, China, 2011, pp. 4286-4288.
[23]X. Ma, B. Li, Y. Zhang, and M. Yan, "The Canny edge detection and its improvement," in 4th International Conference on Artificial Intelligence and Computational Intelligence, AICI 2012, October 26, 2012 - October 28, 2012, Chengdu, China, 2012, pp. 50-58.
[24]W. Weixin and Z. Wei, "Two wheel differential robot kinematic analysis and control," in 3rd International Conference on Material and Manufacturing Technology, ICMMT 2012, May 5, 2012 - May 6, 2012, Chengdu, China, 2012, pp. 848-852.
[25]J. Qin, X. He, Y. Liu, and J. Yang, "Four degree of freedom manipulator's kinematics simulation analysis based on MATLAB," Information Technology Journal, vol. 12, pp. 5058-5063, 2013.