簡易檢索 / 詳目顯示

回結果列表
研究生： 戴立恒
Tai, Li-Heng
論文名稱： 運用CPG與ABC演算法於人形機器人步態產生器之模擬器開發
Development of Simulator for Humanoid Robot Gait Pattern Generation by using CPG and ABC Algorithm
指導教授： 李祖聖
Li, Tzuu-Hseng
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： 2013
畢業學年度： 101
語文別： 英文
論文頁數： 86
中文關鍵詞： 模擬器 、ODE 、CPG 、步態學習 、人形機器人
外文關鍵詞： Simulator, ODE, CPG, Gait Learning, Humanoid Robot
相關次數： 點閱：93  下載：2 
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

    • 本論文旨在開發具有高度實用性與整合性之人形機器人動作模擬系統，該模擬系統不僅具有人形機器人之步態學習與模擬功能，亦包含RoboCup競賽環境，並可接收來自影像處理及決策系統之指令，達成比賽策略之模擬。該模擬系統建構於免費的源代碼Open Graphics Library (OpenGL)與Open Dynamics Engine (ODE)，所使用的機器人架構模型為本實驗室aiRobots所開發之第二代大人形機器人David II。步態學習方面，使用Central Pattern Generator (CPG)演算法以建構快速且穩定的步態動作，透過兩組神經振盪器控制腳踝位置以產生步態軌跡，並應用Artificial Bee Colony (ABC)學習法以訓練CPG之參數。選用加速度計及陀螺儀之量測值做為回授訊號，並結合Dynamic Time Warping (DTW)波形配對技術，用以計算步態學習之適應值。實驗結果顯示，經過學習後機器人能得到一個最好的行走步態，前進速度可達到18.5cm/s，也成功地模擬RoboCup一對一大型人形機器人足球競賽的比賽策略。

    This thesis focuses on developing a simulator with high integration ability and practicality. It can be applied to test the competitions of RoboCup, adjust motion of robots, and realize gait learning method in a virtual environment. By transmitting and receiving data such as visual image, commands of motors, and judgments of strategy between programs, simulator can easily be combined with other software. This simulator is mainly constructed with two free open sources, Open Graphics Library (OpenGL) and Open Dynamic Engine (ODE). The architecture model of the robot named David II, which is the second generation adult sized humanoid robot developed by our laboratory, the aiRobots. In terms of gait learning, we use central pattern generator (CPG) to build a fast and stable walking locomotion. Two pairs of neural oscillators are arranged to control positions of the robot's ankles. Furthermore, artificial bee colony (ABC) algorithm is chosen to train the parameters of CPG with feedback signals of accelerometer and gyro. Dynamic time warping technique is utilized to synthesize an appropriate fitness function. Finally, the developed simulator can successfully learn the best gait pattern for an adult sized humanoid robot to achieve 18.5cm/s forward walking speed by proposed method. Furthermore, the one-on-one soccer competition in humanoid league of RoboCup can be effectively demonstrated in the investigated simulator.

    Contents Abstract I Acknowledgment III Contents IV List of Figures VII List of Tables X Chapter 1. Introduction 1 1.1 Motivation 1 1.2 Thesis Organization 5 Chapter 2. Overview of the Robot Simulation System 6 2.1 Introduction 6 2.2 User Interface of Simulator 7 2.3 Basics of Open Dynamic Engine 11 2.4 Combination with Self-Developed Software 14 2.4.1 Robot Model 15 2.4.2 RoboCup Humanoid Soccer Strategy Program 17 2.4.3 Human Machine Interface of Motion Editor 28 2.5 Summary 29 Chapter 3. Concept of Central Pattern Generator Used in Gait Locomotion 30 3.1 Introduction 30 3.2 Sorts of Gait Pattern 31 3.2.1 Zero Moment Point Method 31 3.2.2 Central Pattern Generator Method 36 3.2.2.1 Matsuoka Oscillator 36 3.2.2.2 Application of Matsuoka Oscillator 38 3.2.3 Comparisons between ZMP and CPG 39 3.3 Gait Pattern Generation 39 3.3.1 Rules of Adjusting CPG parameter 39 3.3.2 Inverse Kinematics of the Robot 43 3.4 Summary 50 Chapter 4. ABC Gait Learning with DTW 51 4.1 Introduction 51 4.2 Concept of ABC Algorithm 53 4.3 Concept of DTW 56 4.4 Gait Pattern 59 4.5 ABC Gait Learning with DTW in Simulator 61 4.6 Summary 66 Chapter 5. Experiment Results 67 5.1 Introduction 67 5.2 Settings of Gait Learning 68 5.3 Fitness Functions 69 5.4 Experimental Results 73 Chapter 6. Conclusions and Future Works 81 6.1 Conclusions 81 6.2 Future Works 83 References 84

    [1]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.
    [2]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.
    [3]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.
    [4]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, 2006.
    [5]Q. Huang et al., "Balance Control of a Biped Robot Combining Off-line Pattern with Real-time Modification," in Proc. IEEE Int. Conf. Robotics and Automation, pp. 3346-3352, 2000.
    [6]S. Kajita, T. Nagasaki, K. Kaneko, and H. Hirukawa, "ZMP-based Biped Running Control," IEEE Trans. Robotics, vol. 14, no. 2, pp. 63-72, June 2007.
    [7]E. Ohashi, T. Tsuji T. Aiko, 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, June 2007.
    [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]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.
    [10]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.
    [11]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.
    [12]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. 21, no. 3, pp. 565-573, June 2004.
    [13]K. Harada, S. Kajita, F. Kanehiro, K. Fujiwara, K. Kaneko, K. Yokoi, 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]Q. Huang and Y. Nakamura, "Sensory Reflex Control for Humanoid Walking," IEEE Trans. Robotics, vol. 21, no. 5, pp. 977-984, Oct. 2005.
    [15]T. Zielinska, "Biological Inspiration Used for Robots Motion Synthesis," Journal of Physiology - Paris, vol. 103, pp. 133-140, July 2009.
    [16]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.
    [17]K. Matsuoka, "Sustained Oscillations Generated by Mutually Inhibiting Neurons with Adaptation," Biological Cybernetics, vol. 52, pp. 367-376, 1985.
    [18]K. Matsuoka, "Mechanisms of Frequency and Pattern Control in the Neural Rhythm Generators," Biological Cybernetics, vol. 56, pp. 345-353, 1987.
    [19]G. Taga, Y. Yamaguehi, and H. Shimizu, "Self-organized Control of Bipedal Locomotion by Neural Oscillators in Unpredictable Environment," Biological Cybernetics, vol. 65, pp. 147-159, Apr. 1991.
    [20]D. Karaboga and B. Basturk, "A Powerful and Efficient Algorithm for Numerical Function Optimization: Artificial Bee Colony (ABC) Algorithm," Journal of Global Optimization, vol. 39, no. 3, pp. 459–471, Apr. 2007.
    [21]M. Müller, Information Retrieval for Music and Motion: Springer-Verlag New York Inc, 2007.
    [22]OpenGL. [Online]. http://www.opengl.org/sdk/libs/
    [23]Russell Smith. Open Dynamics Engine. [Online]. http://www.ode.org/
    [24]RoboCup. [Online]. http://www.robocup.org/
    [25]Webots. [Online]. http://www.cyberbotics.com/
    [26]Marilou. [Online]. http://www.anykode.com/index.php
    [27]V-REP (Virtual Robot Experimentation Platform). [Online]. http://www.v-rep.eu/
    [28]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, 2008.
    [29]G. Endo, J. Morimoto, T. Matsubara, J. Nakanishi, and G. Cheng, "Learning CPG-based Biped Locomotion with a Policy Gradient Method: Application to a Humanoid Robot," The International Journal of Robotics Research, vol. 27, no. 2, pp. 213–228, Feb. 2008.
    [30]M. M. Williamson, "Neural Control of Rhythmic Arm Movements," Neural Networks, vol. 11, no. 7-8, pp. 1379–1394, 10-11 1998.
    [31]G. Endo, J. Nakanish, J. Morimoto, and G. Cheng, "Experimental Studies of a Neural Oscillator for Biped Locomotion with QRIO," IEEE International Conference on Robotics and Automation, pp. 598–604, Apr. 2005.
    [32]K. S. Fu, R.C. Gonzalez, and C.S.G. Lee, Robotics: Control, Sensing, Vision, and Intelligence., 1987.
    [33]P.-C. Huang, Design and Implementation of a Series of Small-sized Humanoid Robots.: Master Thesis, National Cheng Kung University, 2011.
    [34]K.-F. Lee, Design and Implementation of Particle Swarm Optimization Gait Learning Method for Adult-sized Humanoid Robots.: Master Thesis, National Cheng Kung University, 2012.
    [35]Y.-T. Su, K.-Y. Chong, and T.-H. S. Li, "Design and Implementation of Fuzzy Policy Gradient Gait Learning Method for Walking Pattern Generation of Humanoid Robots," International Journal of Fuzzy Systems, vol. 13, no. 4, pp. 369-382, Dec. 2011.

    下載圖示 校內：2018-08-21公開
    校外：2018-08-21公開
    QR CODE