進階搜尋


   電子論文尚未授權公開,紙本請查館藏目錄
(※如查詢不到或館藏狀況顯示「閉架不公開」,表示該本論文不在書庫,無法取用。)
系統識別號 U0026-0507201819241200
論文名稱(中文) 具位置控制模仿學習與自我避障功能之六軸雙臂服務型機器人
論文名稱(英文) 6-DoF Dual-Arm Imitation Learning with Position Control based Self-Collision Avoidance for Service Robot
校院名稱 成功大學
系所名稱(中) 電機工程學系
系所名稱(英) Department of Electrical Engineering
學年度 106
學期 2
出版年 107
研究生(中文) 梁介仲
研究生(英文) Jie-Jhong Liang
學號 n26054184
學位類別 碩士
語文別 英文
論文頁數 101頁
口試委員 指導教授-李祖聖
口試委員-郭昭霖
口試委員-林惠勇
口試委員-王明賢
口試委員-余國瑞
中文關鍵字 居家服務型機器人  模仿學習  動作學習  整合型適應性粒子群演算法  自我避障 
英文關鍵字 home service robot  imitation learning  motion learning  PSO-IAC  self-collision avoidance 
學科別分類
中文摘要 本論文提出一個視覺模仿動作學習系統,並將其應用於服務型機器人上。利用深度攝影機(Kinect 2.0) 所擷取的人體骨架資訊,結合順向運動學與空間向量法,計算人類雙臂的關節角度,對應至機器人手臂的六個關節角度,讓機器人可以即時模仿人類的動作。為了提高動作的安全性,本論文加入自我避障系統,此系統基於位置控制的阻抗模型,評估動作碰撞的可能性,計算避障排斥力,並以此排斥力計算手臂位移量,再以整合型適應性粒子群演算法(PSO-IAC),重新規劃機械手臂關節的角度,使機器人在避障的同時,也可以維持與人類動作的相似性。機器人所學的動作會記錄在動作資料中,並透過動作學習系統,以第一階段適應性粒子群演算法,規劃符合現實狀況的最佳化軌跡。最佳化後的軌跡不但可以讓同一個軌跡因應多種情形,且讓軌跡更加平滑,使動作更加平順。最佳化後的軌跡,再利用第二階段適應性粒子群演算法,計算每個關節的角度。模擬結果顯示,此系統可因不同情況,規劃出合適的動作。除此之外,本論文更架構三個實驗,包含了單手抓取物品放置到特定位置、雙手搬取不同大小的紙箱,以及會議室佈置的情境應用。實驗結果展示透過視覺模仿學習方法,機器人可以學習到人類的動作,而動作學習系統則讓機器人將學到的動作,應用在不同的情境或物品當中,達到舉一反三的學習能力。
英文摘要 This thesis proposes an imitation learning system which consists of an imitation system, a self-collision avoidance system, and a motion learning system. The imitation system captures the human skeleton with an RBG-D camera, Kinect 2.0, to map the human joint angles to the motor angles of the robot, at here an integrating method of the forward kinematics and the space vector method is developed. To improve safety, the self-collision avoidance system is added, so that the robot will not collide with itself while learning human motions. This system is based on the position control method; with an impedance subsystem, it calculates the possibility of collisions and generates a repulsive force to further calculate the corresponding displacement of the robot arm. In order to maintain the similarity to the human motion while avoiding collision, integrated adaptive constricted particle swarm optimization algorithm (PSO-IAC) is used to calculate the corresponding motor angles. The learned motion is then recorded in a motion dataset as a reference motion. To deal with different situations and objects, the learned motion is then adjusted by another 2-stage PSO-IAC. The first PSO-IAC generates a suitable motion trajectory based on the real situation, and the second PSO-IAC calculates the motor angles according to the trajectory. The real experiments demonstrate the efficiency of the whole imitation learning system. The robot can learn a reference motion using its vision, and generate a suitable motion based on the learned one for coping with different objects and situations.
論文目次 Abstract Ⅰ
Acknowledgement Ⅲ
Contents Ⅳ
List of Figures Ⅶ
List of Tables ⅩⅠ
Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Related Work 2
1.2.1 Motion Imitation 2
1.2.2 Self-Collision Avoidance 3
1.2.3 Motion Learning 4
1.3 System Overview 5
1.4 Thesis Organization 6
Chapter 2 Learning from Demonstration 8
2.1 Introduction 8
2.2 Information Captured from Kinect2.0 9
2.3 Jitter Removal Filter 11
2.4 Robot Joint Angle Calculation 14
2.4.1 Definition of Different Coordinate System 15
2.4.2 Forward Kinematics 16
2.4.3 Derivation of Inverse Kinematics Solution from Skeleton Information 21
2.5 Experiment 25
Chapter 3 Self-Collision Avoidance 28
3.1 Introduction 28
3.2 Virtual Dual Arm Model 30
3.3 Calculation Repulsive Force 32
3.4 Impedance Model 36
3.5 PSO-IAC 39
3.6 Experiment 45
3.6.1 Experimental Setup 45
3.6.2 Experimental Result 47
Chapter 4 Two Stages PSO-IAC for Motion Learning 52
4.1 Introduction 52
4.2 Preprocess Trajectory 54
4.3 Two Stages PSO-IAC 57
4.3.1 The First Stage PSO-IAC for Trajectory Learning 59
4.3.2 The Second Stage PSO-IAC 62
4.4 Simulation 63
4.4.1 Parameters Setting 63
4.4.2 Simulation Results 66
Chapter 5 Experiments 70
5.1 Introduction 70
5.2 Experiment Ⅰ: Grasping and Placing Task 72
5.2.1 Experiment Ⅰ: Learning from Demonstration 72
5.2.2 Experiment Ⅰ: Motion Learning 73
5.3 Experiment Ⅱ: Moving Box Task 83
5.3.1 Experiment Ⅱ: Learning from Demonstration 84
5.3.2 Experiment Ⅱ: Motion Learning 86
5.4 Experiment Ⅲ: Preparing Meeting Task 90
5.4.1 Experimental Setting 90
5.4.2 Experimental Results 91
Chapter 6 Conclusion and Future Works 95
6.1 Conclusion 95
6.2 Future Works 97
References 98
參考文獻 [1]The depth camera, Kinect II. [Online] Available: http://www.xbox.com/en-SG/xbox-one/accessories/kinect-for-xbox-one#fbid=PKBhrjxJICP
[2]I. Almetwally and M. Mallem, “Real-Time Tele-Operation and Tele-Walking of Humanoid Robot Nao Using Kinect Depth Camera,” in Proceedings of 2013 10th IEEE International Conference on Networking, Sensing and Control, pp. 463-466, 2013.
[3]Y. Ou, J. Hu, Z. Wang, Y. Fu, X. Wu, and X. Li, “A Real-Time Human Imitation System Using Kinect,” International Journal of Social Robotics, vol. 7, no. 5, pp. 587-600, 2015.
[4]A. Muis and W. Indrajit, “Realistic Motion Preservation-Imitation Development Through Kinect and Humanoid Robot,” TELKOMNIKA (Telecommunication, Computing, Electronics and Control), vol. 10, no. 4, pp. 599-608, 2012.
[5]J. H. Lee, “Full-Body Imitation of Human Motions with Kinect and Heterogeneous Kinematic Structure of Humanoid Robot,” in Proceedings of 2012 IEEE/SICE International Symposium on System Integration, pp. 91-98, 2012.
[6]N. Yang, F. Duan, Y. Wei, C. Liu, J. T. C. Tan, B. Xu, and J. Zhang, “A Study of the Human-Robot Synchronous Control System Based on Skeletal Tracking Technology,” in Proceedings of 2013 IEEE International Conference on Robotics and Biomimetics, pp. 2191-2196, 2013.
[7]H. Youngmo, “2D-to-3D Visual Human Motion Converting System for Home Optical Motion Capture Tool and 3-D Smart TV,” IEEE Systems Journal, vol. 9, no. 1, pp. 131-140, 2015.
[8]A. G. Kirk, J. F. O'Brien, and D. A. Forsyth, “Skeletal Parameter Estimation from Optical Motion Capture Data,” in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 782-788, 2005.
[9]V. B. Zordan and N. C. Van Der Horst, “Mapping Optical Motion Capture Data to Skeletal Motion Using a Physical Model,” in Proceedings of the 2003 ACM SIGGRAPH/Eurographics Symposium on Computer Animation, pp. 245-250, 2013.
[10]S. Kim, C. H. Kim, and J. H. Park, “Human-Like Arm Motion Generation for Humanoid Robots Using Motion Capture Database,” in Proceedings of 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 3486-3491, 2006.
[11]A. Agarwal and B. Triggs, “Monocular Human Motion Capture with a Mixture of Regressors,” in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition-Workshops, pp. 72-72, 2005.
[12]B. Kurt, Imitation of Human Arm Movements by a Humanoid Robot Using Monocular Vision, Bogaziçi University, Master of Science, 2009.
[13]V. Ganapathi, C. Plagemann, D. Koller, and S. Thrun, “Real Time Motion Capture Using a Single Time-of-Flight Camera,” in Proceedings of 2010 IEEE Conference on Computer Vision and Pattern Recognition, pp. 755-762, 2010.
[14]M. Riley, A. Ude, K. Wade, and C. G. Atkeson, “Enabling Real-Time Full-Body Imitation: a Natural Way of Transferring Human Movement to Humanoids,” in Proceedings of IEEE International Conference on Robotics and Automation, vol. 2, pp. 2368-2374, 2003.
[15]M. Alibeigi, S. Rabiee, and M. Ahmadabadi, “Inverse Kinematics Based Human Mimicking System Using Skeletal Tracking Technology,” Journal of Intelligent & Robotic Systems, vol. 85, no. 1, pp. 27-45, 2016.
[16]S. J. Kwon, W. K. Chung, Y. Youm, and M. S. Kim, “Self-Collision Avoidance for N-Link Redundant Manipulators,” in Proceedings of IEEE International Conference on Systems, Man, and Cybernetics, Decision Aiding for Complex Systems, pp. 937–942, 1991.
[17]J. Oh, H. Bae, and, J. H. Oh, “Analytic Inverse Kinematics Considering the Joint Constraints and Self-Collision for Redundant 7DOF Manipulator,” in Proceedings of IEEE International Conference on Robotic Computing, pp.123-128, 2017.
[18]A. Dietrich, T. Wimbock, A. Albu-Schaffer, and G. Hirzinger, “Integration of Reactive, Torque-Based Self-Collision Avoidance into a Task Hierarchy,” IEEE Transactions on Robotics, vol. 28, no. 6, pp. 1278-1293, 2012.
[19]F. Seto, K. Kosuge, and Y. Hirata, “Self-Collision Avoidance Motion Control for Human Robot Cooperation System Using RoBE.” in Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, pp.3143-3148, 2005.
[20]P. Tadej and L. Žlajpah, “Smooth Transition between Tasks on a Kinematic Control Level: Application to Self Collision Avoidance for Two Kuka LWR Robots,” in Proceedings of IEEE International Conference on Robotics and Biomimetics, pp. 162-167, 2011.
[21]A. Dietrich, T. Wimböck, H. Täubig, A. Albu-Schäffer, and G. Hirzinger, “Extensions to Reactive Self-Collision Avoidance for Torque and Position Controlled Humanoids,” in Proceedings of 2011 IEEE International Conference on Robotics and Automation, pp. 3455-3462, 2011.
[22]H. Täubig, B. Bäuml, and U. Frese, “Real-Time Swept Volume and Distance Computation for Self Collision Detection,” in Proceedings of 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 1585-1592, 2011.
[23]A. De Santis, A. Albu-Schaffer, C. Ott, B. Siciliano, and G. Hirzinger, “The Skeleton Algorithm for Self-Collision Avoidance of a Humanoid Manipulator,” in Proceedings of 2007 IEEE/ASME international conference on Advanced intelligent mechatronics, pp. 1-6, 2007.
[24]Y. Chua, K. P. Tee, and R. Yan, “Robust Optimal Inverse Kinematics with Self-Collision Avoidance for a Humanoid Robot,” in Proceedings of RO-MAN, pp. 496-502, 2013.
[25]B. Akgun and K. Subramanian, “Robot Learning from Demonstration: Kinesthetic Teaching vs. Teleoperation,” Unpublished manuscript, 2011. [Online] Available:
https://www.cc.gatech.edu/~ksubrama/files/HRIFinalBK.pdf
[26]B. Akgun, M. Cakmak, J. W. Yoo, and A. L. Thomaz, “Trajectories and Keyframes for Kinesthetic Teaching: a Human-Robot Interaction Perspective,” in Proceedings of the seventh annual ACM/IEEE international conference on Human-Robot Interaction, pp. 391-398, 2012.
[27]S. Wrede, C. Emmerich, R. Grünberg, A. Nordmann, A. Swadzba, and J. Steil, “A User Study on Kinesthetic Teaching of Redundant Robots in Task and Configuration Space,” Journal of Human-Robot Interaction, vol. 2, no. 1, pp. 56-81, 2013.
[28]C. Chen, C. Yang, C. Zeng, N. Wang, and Z. Li, “Robot Learning from Multiple Demonstrations with Dynamic Movement Primitive,” in Proceedings of 2017 2nd International Conference on Advanced Robotics and Mechatronics, pp. 523-528, 2017.
[29]S. Calinon, F. Guenter, and A. Billard, “On Learning, Representing, and Generalizing a Task in a Humanoid Robot,” IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics), vol. 37, no. 2, pp. 286-298, 2007.
[30]B. Huang, J. Bryson, and T. Inamura, “Learning Motion Primitives of Object Manipulation Using Mimesis Model,” in Proceedings of 2013 IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 1144-1150, 2013.
[31]M. Muhlig, M. Gienger, S. Hellbach, J. J. Steil, and C. Goerick, “Task-Level Imitation Learning Using Variance-Based Movement Optimization,” in Proceedings of IEEE International Conference on Robotics and Automation, pp. 1177-1184, 2009.
[32]S. Calinon, F. D'halluin, D. G. Caldwell, and A. G. Billard, “Handling of Multiple Constraints and Motion Alternatives in a Robot Programming by Demonstration Framework,” in Proceedings of 9th IEEE-RAS International Conference on Humanoid Robots, pp. 582-588, 2009.
[33]Y. Shi and R. C. Eberhart, “Empirical study of particle swarm optimization,” in Proceedings of the 1999 Congress on Evolutionary Computation, vol. 3, pp. 1945-1950, 1999.
[34]M. Clerc, “The Swarm and the Queen: Towards a Deterministic and Adaptive Particle Swarm Optimization,” in Proceedings of the 1999 Congress on Evolutionary Computation, vol. 3, pp. 1951-1957, 1999.
[35]D. Mandal, S. P. Ghoshal, and A. K. Bhattacharjee, “Design of Concentric Circular Antenna Array with Central Element Feeding Using Particle Swarm Optimization with Constriction Factor and Inertia Weight Approach and Evolutionary Programing Technique,” Journal of Infrared, Millimeter, and Terahertz Waves, vol. 31 no. 6, pp. 667-680, 2010.
[36]A. Nickabadi, M. M. Ebadzadeh, and R. Safabakhsh, “A Novel Particle Swarm Optimization Algorithm with Adaptive Inertia Weight,” Applied Soft Computing, vol. 11, no. 4, pp. 3658–3670, 2011.
[37]C. J. Lin, T.-H. S. Li, P. H. Kuo, and Y. H. Wang, “Integrated Particle Swarm Optimization Algorithm Based Obstacle Avoidance Control Design for Home Service Robot,” Computers & Electrical Engineering, vol. 56, pp. 748-762, 2016.
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2023-06-01起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2023-06-01起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw