本論文主要係討論具有旋轉腰身的居家服務型機器人物件抓取策略與控制之設計與實現。首先討論居家服務型機器人的硬體架構，本機器人的感測器包含Kinect、麥克風、雷測和超音波感測器並藉由筆記型電腦來連結感測器與6個自由度的機械手臂、2個自由度的頭部、可旋轉的腰、四輪轉動及四輪驅動的移動平台。為了增加機器人的抓取範圍，將利用Q-學習演算法(Q-learning)來學習當機器人抓物品時，腰身需旋轉之最適合的角度。機器人在抓取物品時，當手臂的終端器靠近物品，將透過超音波測距感測器來校正機構重量所造成的位置誤差。此外，當抓取過重的物品時，機器人將會利用另一隻手臂輔助來避免馬達過載。最後，本論文提出的物件抓取策略應用於RoboCup Japan Open 2013 Tokyo 的居家服務型機器人組比賽，並透過實驗結果證明其可行性。

This thesis mainly presents the design and implementation of object grasping and control strategy for home service robot that includes a rotatable waist. Firstly, the hardware architecture of the home service robot, named May, is described. The robot May has several sensors comprising Kinect, microphone, laser range finder, and ultrasonic ranging module. She exploits a notebook computer as central processing unit to connect sensors, 6-DOF arms, 2-DOF neck, rotatable waist, and the four-wheel independent steering and four-wheel independent drive mobile platform. In order to increase the coverage of grasping, this thesis proposes the Q-learning controller to find the most suitable angle of waist for grasping the object. By the grasping strategy, the position of end-effector is calibrated using an ultrasonic ranging module. Moreover, in order to avoid overload of servo motors, the home service robot May is able to utilize the other arm to assist when the object is really heavy. Finally, the applicability and validity of object grasping and control strategy are demonstrated both in laboratory experiments and the competitions of robot@home league at RoboCup Japan Open 2013 Tokyo.

References
[1] J. Fasola and M. J. Mataric, “Robot exercise instructor: A socially assistive robot system to monitor and encourage physical exercise for the elderly,” in Proc. IEEE RO-MAN, pp. 416 - 421, 2010.
[2] Y. Bekiroglu, J. Laaksonen, J. Jorgensen, V. Kyrki, and D. Kragic, “Assessing grasp stability based on learning and haptic data,” IEEE Trans. Robot., vol. 27, no. 3, pp. 616-629, Jun. 2011.
[3] T. Taipalus and Kazuhiro Kosuge, “Development of service robot for fetching objects in home environment,” in Proceedings 2005 IEEE International Symposium on Computational Intelligence in Robotics and Automation, June 27-30, 2005, pp. 451-456.
[4] G. S. Huang, C. K. Tung, H. C. Lin and S. H. Hsiao, “Inverse kinematics analysis trajectory planning for a robot arm,” in Proceedings of 2011 8th Asian Control Conference (ASCC), 2011, pp. 965-970.
[5] Y. Cui, P. Shi, and J. Rua, “Kinematics analysis and simulation of a 6-DOF humanoid robot manipulator,” in Proceedings 2010 2nd International Asia Conference on Informatics in Control, Automation and Robotics (CAR), 2010, pp. 246-249.
[6] Wikipedia for Denavit-Hartenberg convention.
Available: http://en.wikipedia.org/wiki/Denavit-Hartenberg_parameters
[7] RoboCup Japan Open 2013 Tokyo. Available: http://www.robocup.or.jp/
[8] Ultrasonic ranging module, HC-SRO4.
Available: http://www.micropik.com/PDF/HCSR04.pdf
[9] SolidWorks. Available: http://www.solidworks.com/
[10] Wikipedia for Needle roller bearings.
Available: http://en.wikipedia.org/wiki/Needle_roller_bearing
[11] R. Leenen, J. J. Ploeg, H. H. Nijmeijer, L. Moreau, and F. Veldpaus, Motion Control Design for a 4WS and 4WD Overactuated Vehicle, Master Thesis, Department Mechanical Engineering Dynamics and Control Technology Group, Eindhoven University of Technology, Eindhoven, January 2004.
[12] F. Yili, H. Xu, W. Shuguo, and M. Yulin, “A Navigation Robot with Reconfigurable Chassis and Bionic Wheel,” in Proc. 2004 IEEE International Conference Robotics and Biomimetics, ROBIO 2004, 2004 pp. 485-489.
[13] ROBOTIS. Available: http://www.robotis.com/zbxe/intro
[14] SICK. Available: http://www.sick.com/group/EN/home/Pages/Homepage1.aspx
[15] Kinect for Windows.
Available: http://www.microsoft.com/en-us/kinectforwindows/
[16] Wikipedia for Q-learning. Available: http://en.wikipedia.org/wiki/Q-learning
[17] Y. Wang, H. Lang, and C. W. de Silva. “A Hybrid Visual Servo Controller for Robust Grasping by Wheeled Mobile Robots,” IEEE/ASME Transactions on Mechatronics, vol. 15, no. 5, pp. 757-769, Oct. 2010.
[18] R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction. Cambridge, MA: MIT Press, 1998.
[19] E. Alpaydin, Introduction to Machine Learning. Cambridge, MA: MIT Press, 2004.
[20] M. W. Spong and M. Vidyasagar, Robot Dynamics and Control, New York: Wiley, 1989.
[21] C. H. Yeh, Design and Implementation of Grasping Posture and Fuzzy Grip Force Control Scheme for Home Service Robot, Master Thesis, National Cheng Kung University, July, 2012.
[22] J. Xie, S. Yan, and W. Qiang, “A method for solving the inverse kinematics problem of 6-DOF space manipulator,” in Proceedings of International Symposium on Systems and Control in Aerospace and Astronautics, January 2006, pp.379-382.
[23] D. H. Song and S. Jung, “Geometrical analysis of inverse kinematics solutions and fuzzy control of humanoid robot arm under kinematics constraints,” in Proceedings International Conference on Mechatronics and Automation, 2007, pp.1178-1183.
[24] K. Iwata, K. Ikeda, and H. Sakai, “A statistical property of multiagent learning based on Markov decision process,” IEEE Trans. Neural Network, vol. 17, no. 4, pp. 829–842, Jul. 2006.
[25] RoboCup@Home 2013 rule book.
Available: http://www.robocupathome.org/rules