臺灣博碩士論文加值系統

近十年來，由於人形機器人擁有擬人的外形、具親和力的設計及在人類生活環境中的智能等要素，使得人形機器人成為眾所期盼的對象;而為了滿足消費者的需求，近幾年來，已開發出各式各樣的人形機器人。然而，透過機器人來執行球類遊戲，像是足球機器人、桌球機器人等研究，已吸引機器人領域的研究者之注意；在週期性的與環境互動中，這類機器人必須能夠調整其互動的時間及所需之運動。因此，找到一個適合的方法來使機器人執行球類遊戲是相當不容易的。
基於上述之動機，本研究建構了一輪式人形機器人來執行乒乓球賽，所發展之人形機器人由輪式移動平台、安裝於平台之3自由度腰部機構、雙7自由度之機械手臂、雙7自由度之機械手掌及7自由度之雙眼機械頭所組成。並在控制系統上建構了一以DSP為基礎之嵌入式控制系統來達成機器人之即時控制。
模仿人類於乒乓球賽時之學習過程是非常困難的，在本研究中，提出四個步驟來模仿人類玩乒乓球賽。首先，我們建構一光學/慣性混合追蹤之運動捕捉系統，透過此捕捉系統來捕捉人類於乒乓球賽中之打擊運動及分析此運動軌跡，接著將分析後所得之資訊應用於機器人來執行乒乓球賽。第二，我們提出一逆向運動學來解得具贅餘自由度之人形手臂在模仿人類之揮拍運動所需之平滑軸解，最後，由於人類會以直覺之方式來決定適合之姿態來完成乒乓球之打擊，本研究提出兩個新的過程：(a)估測球之狀態及透過模糊適應共振網路來預測軌跡；及(b)透過以自我組織映射為基礎之增強式學習，對每次打擊進行自我學習。實驗結果顯示所提出之方法可有效的應用於真實之人形機器人上來執行乒乓球賽。

In the recent decade, humanoid robots are widely anticipated to emerge owing to factors such as anthropomorphism, friendly design, and intelligence within human living environments. To fulfill these consumer demands, several humanoid robots have been developed in recent years. However, ball game tasks have recently attracted more attention of researchers in robotics fields, such as soccer robots, table tennis robots, and so on. This kind of robot must be able to adjust the motion and timing of interactions during the intermittent interactions between the robot and its environment. Therefore, it is difficult to find general approaches for robots to perform these tasks.
Based on this motivation, this research constructs a wheeled humanoid robot to play ping-pong. The developed humanoid robot comprises mainly a wheeled mobile base, a torso with a 3-DOF waist mounted on the mobile base, two 7-DOF robot arms, two 7-DOF robot hands and one 7-DOF robotic binocular head. An embedded DSP-based control system is also designed and constructed for real-time control.
Imitating the learning process of a human playing ping-pong is extremely complex. In this research, four steps are proposed for imitating a human playing ping-pong. First, we construct an optical/inertial track motion-capture system that captures the strike motion and analyze the motion trajectory, then the analyzed data is applied on the robot to perform the ping-pong play. Second, we propose inverse kinematics to solve the smooth joint spaces of the redundant anthropomorphic arm to imitate a human’s paddle motion. Finally, as humans instinctively determine which posture is suitable for striking a ball, this research proposes two novel processes—(a) estimating ball states and predicting trajectory using a fuzzy Adaptive Resonance Theory (ART) network, and (b) self-learning the behavior for each strike using a Self-Organizing Map (SOM)-based reinforcement learning network that imitates human learning behavior. Experimental results demonstrate that the proposed algorithms work effectively when applied to an actual humanoid robot playing ping-pong.

Abstract (in Chinese) i
Abstract (in English) ii
Acknowledgements iii
Content iv
List of Tables vii
List of Figures viii
Nomenclature xi

1. Introduction 1
1.1 Preface 1
1.2 Motivation and Objective 2
1.3 Literature Survey 2
1.4 Contribution 5
1.5 Structure of This Dissertation 6

2. Design of a Humanoid Robot 8
2.1 Mechanism Design of the Humanoid Robot 8
2.1.1 Design of Robotic Binocular Head 11
2.1.2 Design of Robot Arms and Hands 13
2.1.3 Design of the Robot Waist and Wheeled Mobile Base 18
2.2 Control System of the Humanoid Robot 20
2.2.1 Design of Motor Board for Robotic Servo Control 20
2.2.2 Design of Processor Board for the Decision Maker Part 22
2.2.3 Design of the Image-Processing Subsystem 24
2.3 Whole Control System of the Humanoid Robot 26
2.4 Design of Servo Controller of Humanoid Robot 28

3. Kinematic Model and Simulation System of Humanoid Robot 34
3.1 Coordinate System 35
3.2 Coordinate Frames of the Humanoid Robot 38
3.3 Infinitesimal Translation and Rotation of the Robotic Arm 42
3.4 Inverse Kinematics of the Robotic Arm with Redundant Structure 45
3.5 Inverse/Forward Dynamics of the Humanoid Robot 48
3.6 Simulation System of the Humanoid Robot 55
4. Calibration of Visual System and Motion-capture System 58
4.1 Calibration of Visual System 59
4.1.1 Camera Geometry 59
4.1.2 Camera Model Calibration 60
4.1.3 Stereo Vision and Paddle/Eye Calibration 67
4.2 Coordinate Frame of Motion-capture System 69
4.3 Fusion Filter for Motion-capture System 71
4.4 Analysis and Processing of Data from Motion-capture System 72

5. Self-learning for a Humanoid Robotic Ping-Pong Player 76
5.1 Events and States while Playing Ping-Pong 77
5.2 States Estimation of Ball 79
5.3 Prediction using Fuzzy ART 81
5.4 Self-learning using SOM-based Reinforcement Learning 86
5.4.1 Reinforcement Learning and Q-learning 86
5.4.2 SOM-based Reinforcement Learning 88
5.5 Strike Trajectory Generation 93

6. Experimentation 96
6.1 Experimental Setup 96
6.2 Calibration for the Humanoid Robotic Stereo Vision 98
6.3 Experimentation for the Motion-capture System 98
6.4 Experimentation for the Humanoid Robotic Ping-pong Player 103

7. Conclusion 111
7.1 Summary 111
7.2 Future Work 112

Bibliography 114
Appendix A 119
Appendix B 120
Appendix C 124
Biography 126

[1].Y. I. Abdel-Aziz, H. M. Karara, “Direct Linear Transformation into Object Space Coordinate in Close-Range Photogrammetry, ASP Symposium on Close-Range Photogrammetry, USA, pp.1-18, 1971.
[2].L. Acosta, J. J. Rodrigo, J. A. Mendez, G. N. Marichal and M. Sigut, “Ping-Pong Player Prototype, IEEE Robotics ＆ Automation Magazine, Vol.10, No.4, pp. 44-52, 2003.
[3].B. Adams, C. Breazeal, R. A. Brooks and B. Scassellati, “Humanoid Robots: a New Kind of Tool, Intelligent Systems and Their Applications, pp. 25-31, July-Aug. 2000.
[4].J. K. Aggarwal and Q. Cai, “Human Motion Analysis: A Review, Computer Vision and Image Understanding, Vol.73, No.3, pp. 428-440, 1999.
[5].R. L. Andersson, A Robot Ping-Pong Player: Experiment in Real-Time Intelligent Control, MIT Press, Cambridge, MA, 1988.
[6].H. Asada and Jean-Jacques E. Slotine, Robot Analysis and Control, Wiley. Interscience, 1986.
[7].D. C. Bentivegna and C. G. Atkeson, “A Framework for Learning From Observation Using Primitives, Proceedings of RoboCup International Symposium, Fukuoka, pp. 263-270, 2002.
[8].J. Bortz, “A New Mathematical Formulation for Strapdown Inertial Navigation, IEEE Transactions on Aerospace and Electronic Systems, Vol.AES-7, Issue 17, pp. 61-66, 1971.
[9].R. R. Burridge, A. A. Rizzi, D. E. Koditschek, “Sequential Composition of Dynamically Dexterous Robot Behaviors, International Journal of Robotics Research, Vol.18, No.6, pp. 534-555, 1999.
[10].G. A. Carpenter, S. Grossberg, N. Markuzon, J. H. Reynolds and D. B. Rosen, “Fuzzy ARTMAP: A Neural Network Architecture for Incremental Supervised Learning of Analog Multidimensional Maps, IEEE Transactions on Neural Networks, Vol.3, No.5, pp. 698-713, 1992.
[11].F. T. Cheng, Y. D. Lu and Y. Y. Sun, “Window-shaped Obstacle Avoidance for a Redundant Manipulator, IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, Vol.28, No.6, pp. 806-815, 1998.
[12].J. M. Chiu, Z. Chen and C. M. Wang, “3-D Polyhedral Face Computation from Two Perspective Views with the Aid of a Calibration Plate, IEEE Transactions on robotics and automation, Vol. 13, No. 2, pp.290-295, 1997.
[13].K. S. Fu, R. C. Gonzalez and C. S. G. Lee, Robotics: Control, Sensing, Vision, and Intelligence, McGraw-Hill: New York, 1987.
[14].K. Hirai, M. Hirose, Y. Haikawa and T. Takenaka, “The Development of Honda Humanoid Robot, Proceedings of IEEE International Conference on Robotics and Automation, pp. 1321-1326, 1998.
[15].M. Hirose, “Humanoid Robot, Journal of the Robotics Society of Japan, Vol.15, No.7, pp. 983-985, 1997.
[16].W. Khalil and J. F. Kleinfinger, “A New Geometric Notation for Open and Closed Loop Robots, Proceedings of IEEE International Conference on Robotics and Automation, pp.1174-1180, 1986.
[17].Y. B. Kim, S. H. Han, S. J. Kim, E. J. Kim and C. G. Song, “Multi-Player Virtual Ping-Pong Game, International Conference Artificial Reality and Telexistence, pp. 269-273, 2007.
[18].L. J. Lin, “Self-improving Reactive Agents Based on Reinforcement Learning, Planning and Teaching, Machine Learning, Vol.8, No.3, pp. 293-321, 1992.
[19].J. Y. S. Luh, M. W. Walker and R. P. C. Paul, “On-Line Computational Scheme for Mechanical Manipulators, ASME Journal of Dynamic Systems, Measurement and Control, Vol. 102, pp. 69-76, June, 1980.
[20].M. Matsushima, T. Hashimoto, M. Takeuchi and F. Miyazaki, “A learning approach to robotic table tennis, IEEE Transactions on Robotics, Vol.21, No.4, pp. 767-771, 2005.
[21].T. Morita, H. Iwata and S. Sugano, “Development of Human Symbiotic Robot: WENDY, Proceedings of IEEE International Conference on Robotics and Automation, pp. 3183-3188, 1999.
[22].T. Morita, K. Shbuya and S. Sugano, “Design and Control of Mobile Manipulation System for Human Symbiotic Humanoid: Hadaly-2, Proceedings of IEEE International Conference on Robotics and Automation, pp.1315-1320, May 1998.
[23].K. Nishiwaki, T. Sugihara, S. Kagami, F. Kanehiro, M. Inaba and H. Inoue, “Design and Development of Research Platform for Perception-Action Integration in Humanoid Robot: H6, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 1559-1564, Nov. 2000.
[24].D. Roetenberg, P. J. Slycke and P. H. Veltink, “Ambulatory Position and Orientation Tracking Fusing Magnetic and Inertial Sensing, IEEE Transactions on Biomedical Engineering, Vol.54, issue 5, pp. 883-890, 2007.
[25].S. Rusdorf, G. Brunnett, M. Lorenz and T. Winkler, “Real-Time Interaction with a Humanoid Avatar in an Immersive Table Tennis Simulation, IEEE Transactions on Visualization and Computer Graphics, Vol.13, No.1, pp. 15-25, 2007.
[26].F. Saito and T. Fukuda, “Learning Architecture for Real Robot Systems-extension of Connectionist Q-learning for Continuous Robot Control Domain, Proceedings of IEEE International Conference on Robotics and Automation, pp. 27-32, 1994.
[27].S. Sehad and C. Touzet, “Self-organizing Map for Reinforcement Learning: Obstacle Avoidance with Khepera, Proceedings of From Perception to Action Conference, pp. 420-423, 1994.
[28].S. W. Shih, Y. P. Hung and W. S. Lin, “Calibration of an Active Binocular Head, IEEE Transactions on Systems, Man, and Cybernetics, Vol. 28, No. 4, pp.426-442, 1998.
[29].S. W. Shih, Y. P. Hung, W. S. Lin, “Head/Eye Calibration of a Binocular by Use of Single Calibration Point, Image Analysis and Interpretation, Proceeding of the IEEE Southwest Symposium, pp.154-159, 1994.
[30].Jean-Jacques E. Slotine and Weiping Li, Applied Nonlinear Control, Prentice Hall, 1991.
[31].Jean-Jacques E. Slotine, “Sliding Controller Design for Non-linear Systems, International Journal of Control, Vol. 40, pp. 421-434, 1984.
[32].R. S. Sutton and A.G. Barto, Reinforcement Learning: An Introduction, MIT Press, Cambridge, MA, 1998.
[33].R. Y. Tsai, R. K. Lenz, “A New Technique for Fully Autonomous and Efficient 3D Robotics Hand/Eye Calibration, IEEE Transactions on robotics and automation, Vol.5, No.3, pp.345-358, 1989.
[34].R. Y. Tsai, “An Efficient and Accurate Camera Calibration Technique for 3D Machine Vision, International Conference on Computer Vision and Pattern Recognition, USA, pp.364-374, 1986.
[35].T. I. James Tsay and Jiann-Hwa Huang, “Robust Nonlinear Control of Robot Manipulators, Proceedings of the 1994 IEEE International Conference on Robotics and Automatioon, pp. 2083-2088, 1994.
[36].C. M. Wang and Z. Chen, “Camera Parameter Determination from A Single View of A General Planar Calibration Object, International Conference on Computer Vision and Pattern Recognition, Vol.1, pp.238 –242, 1994.
[37].J. Wang, Q. Hu and D. Jiang, “A Lagrangian network for kinematic control of redundant robot manipulators, IEEE Transactions on Neural Networks, Vol.10, No.5, pp. 1123-1132, 1999.
[38].L. Wang, W. Hu and T. Tan, “Recent Developments in Human Motion Analysis, Pattern Recognition, Vol.36, No.3, pp. 585-601, 2003.
[39].C. J. C.H. Watkins and P. Dayan, “Technical note: Q learning, Machine Learning, Vol.8, No.3, pp. 279-292, 1992.
[40].G. Welch and G. Bishop, “An Introduction to the Kalman Filter, Technical Report 95-041, University of North Carolina at Chapel Hill, 2001.
[41].Z. Zhang, “A Flexible New Technique for Camera Calibration, Technical Report MSR-TR-98-71, Update on Microsoft Corporation, pp.1-21, 1998.