簡易檢索 / 詳目顯示

回結果列表
研究生： 李鎧帆
Lee, Kai-Fan
論文名稱： 大型人形機器人之粒子群最佳化步態學習法之設計與實驗
Design and Implementation of Particle Swarm Optimization Gait Learning Method for Adult-sized Humanoid Robots
指導教授： 李祖聖
Li, Tzuu-Hseng S.
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 電機工程學系
Department of Electrical Engineering
論文出版年： 2012
畢業學年度： 100
語文別： 英文
論文頁數： 85
中文關鍵詞： 大型人形機器人 、粒子群最佳化步態學習法
外文關鍵詞： Adult-sized Humanoid Robots, Particle Swarm Optimization Gait Learning Method
相關次數： 點閱：187  下載：22 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 本論文使用粒子群最佳化步態學習法為概念設計並實現大型人形機器人的步態學習。論文首先介紹大型人形機器人aiRobots-AH-I上的軟硬體系統架構、硬體規格與設計概念。為了減少機器人馬達的壽命的損耗與增加動作學習的便利性，本論文設計了一套人形機器人動作模擬系統。此機器人模擬系統是基於開源軟體Open Dynamics Engine(ODE)所開發而成的模擬系統，利用剛體與關節的組合建立aiRobots-AH-I模型。人形機器人使用粒子群最佳化步態學習法在機器人模擬系統上進行學習，將機器人質心移動的路徑作為適應值，自動去尋找可能的最佳解以達到穩定且快速的步態。經實驗證明，機器人模擬系統所模擬出來的動作與實際動作相似度極高，可以做為動作學習的平台。粒子群最佳化步態學習的結果在模擬系統上有優異的表現，機器人從原地踏步的動作成功的學習出了重心的轉移與抬腳的動作。最後，學習的結果在模擬器上，移動速度可以達到14.5 cm/s的行走速度。

    The design and implementation of particle swarm optimization (PSO) gait learning method for adult-sized humanoid robots is proposed in this thesis. Firstly, the architecture of the system hardware and software, the specifications of the hardware, and the design concepts about adult-sized humanoid robot of aiRobots laboratory (aiRobots-AH-I) are addressed in details. In order to reduce the motor damage and train motions more convenient, a robotics simulator system for humanoid robots is developed in the thesis, where an open source software--Open Dynamics Engine (ODE) is adopted. The model of aiRobots-AH-I is a combination of rigid bodies and joints. The humanoid robot is trained on the robotics simulator system with PSO method which chooses the trajectory of robot’s centroid as the fitness value to learn faster and stable gaits automatically. Two-stage gait patterns are proposed in the PSO gait learning, one is the stage of marking time to moving centroid and another is the stage of swinging legs. The experiments illustrate that the motions perform on the robotics simulator system are very similar to those of real humanoid robot. Thus, the developed robotics simulator can be indeed employed as the motion training platform. The result of the PSO gait learning method offers great performance on the robotics simulator system. Finally, the proposed PSO based gait learning results make the robot walk forward speed 14.5 cm/s on the simulator system.

    Chapter 1. Introduction 1 1.1 Motivation 1 1.2 Thesis Organization 4 Chapter 2. Hardware Specifications of aiRobots-AH-I 5 2.1 Introduction 5 2.2 The Configurations of aiRobots-AH-I 7 2.3 Hardware Specifications of aiRobots-AH-I 10 2.3.1 Actuators 10 2.3.2 Motion Controller 13 2.3.3 Computer 16 2.3.4 Camera 18 2.3.5 Zigbee Module 20 2.3.6 9-axes IMU 21 2.3.7 LCD Display 22 2.3.8 Li-poly Batteries 23 2.4 Special Design for aiRobots-AH-I 24 2.4.1 The Routes of Signal Lines 24 2.4.1.1 The Block of Several Motors 24 2.4.1.2 Signal Lines in Tube 27 2.4.2 The Design on the Waist of aiRobots-AH-I 28 2.4.3 The Way to Place the Computer and motion controller 31 2.5 Summary 32 Chapter 3. Development of Robotics Simulator System 33 3.1 Introduction 33 3.2 Important Concepts of ODE 35 3.2.1 Rigid Bodies 35 3.2.2 The types of joints 36 3.2.3 Typical simulator code 40 3.3 Model of aiRobots-AH-I 42 3.3.1 Bodies of aiRobots-AH-I 42 3.3.2 Joints of aiRobots-AH-I 44 3.3.3 The Model of aiRobots-AH-I in Simulator System 46 3.4 The Interface of Robotics Simulator System 47 3.5 Summary 49 Chapter 4. Particle Swarm Optimization Gait Learning Method 50 4.1 Introduction 50 4.2 Concept of Particle Swarm Optimization 51 4.3 Gait Patterns for aiRobots-AH-I 53 4.4 Parameters of Gait Patterns 56 4.5 Particle Swarm Optimization Gait Learning 60 4.6 Particle Swarm Optimization Gait Learning with Simulator 61 4.7 The Interface of Gait Learning 63 4.8 Summary 64 Chapter 5. Experiment Results 65 5.1 Introduction 65 5.2 Experimental Results 66 5.2.1 Comparison of Motions between aiRobots-AH-I and Simulator 66 5.2.2 PSO Gait Learning 71 5.2.2.1 Gait Pattern of the First Stage 71 5.2.2.2 Gait Pattern of the Second Stage 74 5.2.2.3 Gait Patterns on aiRobots-AH-I 76 Chapter 6. Conclusions and Future Works 78 6.1 Conclusions 78 6.2 Future Works 80 References 81 Biography 85

    [1] FIRA, http://www.fira.net/
    [2] RoboCup, http://www.robocup.org/
    [3] K. Harada, S. Kajita, K. Kaneko, and H. Hirukawa, “Dynamics and balance of a humanoid robot during manipulation tasks,” IEEE Trans. Robotics, vol. 22, no. 3, pp. 568-575, Jun. 2006.
    [4] S. Kajita, T. Nagasaki, K. Kaneko, and H. Hirukawa, “ZMP-based biped running control,” IEEE Trans. Robotics, vol. 14, no. 2, pp. 63-72, Jun. 2007.
    [5] E. Ohashi, T. Aiko, T. Tsuji, H. Nishi, and K. Ohnishi, “Collision avoidance method of humanoid robot with arm force,” IEEE Trans. Industrial Electronics, vol. 54, no. 3, pp. 1632-1641, Jun. 2007.
    [6] C. Fu and K. Chen, “Gait synthesis and sensory control of stair climbing for a humanoid robot,” IEEE Trans. Industrial Electronics, vol. 55, no. 5, pp. 2111-2120, May. 2008.
    [7] K. Erbatur and O. Kurt, “Natural ZMP trajectories for biped robot reference generation,” IEEE Trans. Industrial Electronics, vol. 56, no. 3, pp. 835-845, Mar. 2009.
    [8] P. Sardain and G. Bessonnet, “Zero moment point-measurements from a human walker wearing robot feet as shoes,” IEEE Trans. Systems, Man and Cybernetics, Part A: Systems and Humans, vol. 34, no. 5, pp. 638-648, Sep. 2004.
    [9] Q. Huang, K. Kaneko, K. Yokoi, S. Kajita, T. Kotoku, N. Koyachi, H. Arai, N. Imamura, K. Komoriya, and K. Tanie, “Balance control of a biped robot combining off-line pattern with real-time modification,” in Proc. IEEE Int. Conf. Robotics and Automation, 2000, pp. 3346-3352.
    [10] P. Sardain and G. Bessonnet, “Forces acting on a biped robot. Center of pressure-zero moment point,” IEEE Trans. Systems, Man and Cybernetics, Part A: Systems and Humans, vol. 34, pp. 630–372, Sep. 2004.
    [11] F. Asano, M. Yamakita, N. Kamamichi, and Z. W. Luo, “A novel gait generation for biped walking robots based on mechanical energy constraint,” IEEE Trans. Robotics and Automation, vol. 20, no. 3, pp. 565-573, Jun. 2004.
    [12] Q. Huang and Y. Nakamura, “Sensory reflex control for humanoid walking,” IEEE Trans. Robotics, vol. 21, no. 5, pp. 977-984, Oct. 2005.
    [13] K. Harada, S. Kajita, F. Kanehiro, K. Fujiwara, K. Kanedo, K. Yokoi, and H. Hirukawa, “Real-time planning of humanoid robot’s gait for force-controlled manipulation,” IEEE/ASME Trans. Mechatronics, vol. 12, no. 1, pp. 53-62, Feb. 2007.
    [14] P. Sardain, M. Rostami, and G. Bessonnet, “An anthropomorphic biped robot: dynamic concepts and technological design,” IEEE Trans. Systems, Man and Cybernetics, Part A: Systems and Humans, vol. 28, no. 6, pp.823-838, Nov. 1998.
    [15] Y. D. Kim, B. J. Lee, J. H. Ryu, and J. H. Kim, “Landing force control for humanoid robot by time-domain passivity approach,” IEEE Trans. Robotics, vol. 23, no. 6, pp. 1294-1301, Dec. 2007.
    [16] H. Minakata, H. Seki, and S. Tadakuma, “A study of energy-saving shoes for robot considering lateral plane motion,” IEEE Trans. Industrial Electronics, vol. 55, no. 3, pp. 1271-1276, Mar. 2008.
    [17] J. Morimoto, G. Endo, J. Nakanishi, and G. Cheng, “A biologically inspired biped locomotion strategy for humanoid robots: Modulation of sinusoidal patterns by a coupled oscillator model,” IEEE Trans. Robotics, vol. 24, no. 1, pp. 185-191, Feb. 2008.
    [18] T. Zielinska, “Biological inspiration used for robots motion synthesis,” Journal of Physiology - Paris, vol. 103, pp. 133-140, Jul. 2009.
    [19] Open Dynaimics Engine, http://www.ode.org/
    [20] C-Y. Tsai and I-W. Kao, “Particle swarm optimization with selective particle regeneration for data clustering,” Expert Systems with Applications, vol. 38, is. 6, pp. 6565-6576, June 2011.
    [21] A. W. Mohemmed, N. C. Sahoo and T. K. Geok, “Solving shortest path problem using particle swarm optimization,” Applied Soft Computing, vol. 8, is. 4, pp. 1643-1653, September 2008.
    [22] S. Z. Zhao, J. J. Liang and P. N. Suganthan, “Dynamic Multi-Swarm Particle Swarm Optimizer with Local Search for Large Scale Global Optimization,” in Proc. Congress on Evolutionary Computation (CEC 2008), pp. 3845-3852.
    [23] J. Kennedy and R. Eberhart, “Particle swarm optimization,” in Proc. IEEE Int. Conf. Neural Networks, vol. IV, 1995, pp. 1942-1948.
    [24] J. Kennedy, “The particle swarm: social adaptation of knowledge,” in Proc. IEEE Int. Conf. Evolutionary Computation, 1997, pp. 303-308.
    [25] Z-H. Zhan, J. Zhang, Y. Li, and H.S-H. Chung, “Adaptive particle swarm optimization,” IEEE Trans. Systems, Man, and Cybernetics - Part B, vol. 39, no.6, pp. 1362-1381, 2009.
    [26] Robotis [Online], Available: http://www.robotis.com/
    [27] STM32-F103ZET6, http://www.st.com/internet/com/home/home.jsp
    [28] TOSHIBA [Online], Available: http://www.toshiba.com/
    [29] Solid-state drive, http://en.wikipedia.org/wiki/Solid-state_drive
    [30] Logitech [Online], Available: http://www.logitech.com/
    [31] Zigbee-100, http://support.robotis.com/en/product/auxdevice/communication/zigbee_manual.htm
    [32] DMP, http://www.dmp.com.tw/
    [33] J. Hale, B. Hohl, S-H. Hyon, T. Matsubara, E. M. Moraud, G. Cheng. “Highly precise dynamic simulation environment for humanoid robots,” Advanced Robotics, vol. 22, no. 1, pp. 1075-1105, 2008.
    [34] T. Reichenbach. “A dynamic simulator for humanoid robots,” Artificial Life and Robotics, vol. 13, no. 2, pp. 561-565, 2009.
    [35] S. Nakaoka, S. Hattori, F. Kanehiro, S. Kajita, H. Hirukawa. “Constraint-based dynamics simulator for humanoid robots with shock absorbing mechanisms,” in Proc. 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 3641-3647.
    [36] Gazebo, http://gazebosim.org/
    [37] Marilou, http://www.anykode.com/index.php
    [38] Webots, http://www.cyberbotics.com/
    [39] Virtual Robot Experimentation Platform, http://www.v-rep.eu/
    [40] OpenGL, http://www.opengl.org/
    [41] Po-Chun Huang, Design and Implementation of a Series of Small-sized Humanoid Robots, Master Thesis, National Cheng Kung University, July, 2011.
    [42] R. S. Hartenberg and J. Denavit, Kinematic Synthesis of Linkages, New York: McGraw-Hill, 1964.
    [43] M. Srinivas, L. Patnaik, “Adaptive probabilities of crossover and mutation in genetic algorithms,” IEEE Transactions on System, Man and Cybernetics, vol.24, no.4, pp.656–667, 1994.
    [44] D.E. Goldberg. Genetic Algorithms in Search Optimization and Machine Learning. Addison Wesley. ISBN 0-201-15767-5, 1989.
    [45] R. J. Williams, “A Cass of Gradient Estimating Algorithms for Reinforcement Learning in Neural Networks,” in Proc. Int. Joint Conf. Neural Networks, vol. II, 1987, pp. 601–608.
    [46] P. Jan, S. Vijayakumar and S. Schaal, “Reinforcement Learning for Humanoid Robotics,” in Proc. IEEE-RAS International Conference on Humanoid Robots, 2003.
    [47] S. H. Liu, Design And Implementation of a Gait Pattern Generator based on Genetic Algorithms and Fuzzy Control for Small-sized Humanoid Robot by using SOPC, Master Thesis, National Cheng Kung University, July, 2008.
    [48] S. W. Lai, Design and Implementation of Reinforce Learning based Fuzzy Gait Controller for Humanoid Robot, Master Thesis, National Cheng Kung University, July, 2009.
    [49] K. Y. Chong, Design and Implememtation of Fuzzy Policy Gradient Gait Learning Method for Humanoid Robot, Master Thesis, National Cheng Kung University, July, 2010.

    下載圖示 校內：2017-08-16公開
    校外：2017-08-16公開
    QR CODE