Basic Search / Detailed Display

Author: 許閔傑
Hsu, Min-Jie
Thesis Title: 基於深度學習類神經網路之機器人動作決策認知系統
Cognitive Systems with Robotic Motion Policies Based on Deep Learning Neural Networks
Advisor: 王偉彥
Wang, Wei-Yen
許陳鑑
Hsu, Chen-Chien
Committee: 蘇順豐
Su, Shun-Feng
王文俊
Wang, Wen-June
吳政郎
Wu, Jenq-Lang
蔡清池
Tsai, Ching-Chih
李祖聖
Li, Tzuu-Hseng
許陳鑑
Hsu, Chen-Chien
王偉彥
Wang, Wei-Yen
Approval Date: 2022/12/28
Degree: 博士
Doctor
Department: 電機工程學系
Department of Electrical Engineering
Thesis Publication Year: 2023
Academic Year: 111
Language: 英文
Number of pages: 104
Keywords (in English): cognitive system, deep learning, hypothesis generation model, memory model, perception model, Chinese calligraphy
Research Methods: 實驗設計法
DOI URL: http://doi.org/10.6345/NTNU202300150
Thesis Type: Academic thesis/ dissertation
Reference times: Clicks: 105Downloads: 0
Share:
School Collection Retrieve National Library Collection Retrieve Error Report
  • High-dimensional complex motion generation is an interesting research topic. Most action generation methods in robotics research use a single pose as the model output. However, in some scenarios, only a series of motions can be output at one time. The calligraphy writing task belongs to a complex motion generation challenge which needs to output a series of motions at one time. The calligraphy writing task can be divided into position learning and posture learning. For position learning, human can directly form a properly rational statement of where to write. In Taylor’s problem categories, the position learning problem in calligraphy learning belongs to Q3 and Q4 types which are formal statement. That is, human can easily design an algorithm to generate a policy to robot. In the contrast, humans are not able to describe the relationship between the writing posture and the writing result. Therefore, the posture learning problem in calligraphy learning belongs to Q1 and Q2 types in Taylor's problem categories. In order to solve the problems of Q1 and Q2, this dissertation will propose the fundamental cognitive system with self-learning ability. This dissertation integrates the framework of human perception, memory, and decision-making into the robot system through the cognitive psychology. We use the top-down and bottom-up processing of the human perceptual system to design a perception model of the cognitive system, which enables encoder networks to learn online. In the memory model, we implement the psychological multi-store model with a deep neural network, so that robots can remember past events like humans. We use the hypothesis generation model of psychology in the decision-making model, so that the robot has a human-like thinking process. Integrating these cognitive models, robots can generate action strategies based on their goals through their own experience. Finally, we use a practical robot as experimental platform to verify the learning ability of the proposed cognitive system.

    Abstract i Acknowledgment iii Table of Contents iv List of Figures vi List of Tables ix Chapter 1. Introduction 1 Chapter 2. The Chinese Calligraphy Writing Model 4 2.1 The Challenge of the Calligraphy Writing Task 4 2.2 The Brush Model for Calligraphy Writing Task 6 2.2.1 Brush Geometry 6 2.2.2 Writing Projection Model 8 2.2.3 Combination of Droplets 10 2.3 Simulation Results 12 Chapter 3. Hypothesis Generation Model for Calligraphy Writing Task 22 3.1 Definition of Robot Framework 22 3.2 Hypothesis Generation Processing 25 3.2.1 Psychological Hypothesis Generation Processing 26 3.2.2 Deep Learning Based Hypothesis Generation Processing 30 3.3 Formulation of the Hypothesis Model and Motor System 33 3.4 Formulation of the Evaluation Model 36 3.5 Hypothesis Net and Memory Net for Calligraphy Tasks 37 3.6 Simulation Results 40 3.7 Conclusions 44 Chapter 4. A Fundamental Cognitive System for Robots 45 4.1 Systematic Designed Robotic System for Cognitive Computing 46 4.2 Memory Model of the Cognitive System 48 4.2.1 Psychological Memory Processing 48 4.2.2 Short-Term Memory 50 4.2.3 Long-Term Memory 51 4.2.3.1 The Episodic Memory of the Cognitive System 52 4.2.3.2 The Procedural Memory of the Cognitive System 54 4.3 Architecture of the Cognitive System 55 4.4 Perception Model of the Cognitive System 59 4.4.1 Formulation of the Perception Model 61 4.5 Mental Processing of the Cognitive System 64 Chapter 5. Deep Learning Based Cognitive System in Chinese Calligraphy Writing Task 73 5.1 Perception Model Designed for Calligraphy Learning Task 73 5.2 Hypothesis Model Designed for Calligraphy Learning Task 75 5.3 Memory Model Designed for Calligraphy Learning Task 76 5.4 Simulation Results 77 5.5 Practical Experimental Results 85 5.6 Analysis and Discussion 90 5.6.1 Behavior Analysis 90 5.6.2 Advantage of the Cognitive System 94 Chapter 6. Conclusions and Future Work 97 6.1 Conclusions 97 6.2 Future Work 98 References 99 Autobiography 102 Academic Achievement 103

    L. Gan, W. Fang, F. Chao, C. Zhou, L. Yang, C.-M. Lin, and C. Shang, “Towards a Robotic Chinese Calligraphy Writing Framework,” Proceedings of the IEEE International Conference on Robotics and Biomimetics, pp. 493-498, Dec. 2018.
    F. Chao, Y. Huang, C.-M. Lin, L. Yang, H. Hu, and C. Zhou, “Use of Automatic Chinese Character Decomposition and Human Gestures for Chinese Calligraphy Robots,” IEEE Trans. on Human-Machine System, vol. 49, no. 1, pp. 47-58, 2019.
    F. Chao, J. Lv, D. Zhou, L. Yang, C.-M. Lin, C. Shang, and C. Zhou, “Generative Adversarial Nets in Robotic Chinese Calligraphy,” Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pp. 1104-1110, May, 2018.
    F. Yao, G. Shao, and J. Yi, “Extracting the Trajectory of Writing Brush in Chinese Character Calligraphy,” Engineering Applications of Artificial Intelligence, vol. 17, no. 6, pp. 631-644, 2004.
    F. Yao and G. Shao, “Modeling of Ancient-style Chinese Character and Its Application to CCC Robot,” Proceedings of the IEEE International Conference on Networking, Sensing and Control, pp. 72-77, Aug. 2006.
    J. Li, W. Sun, M.-C. Zhou, and X. Dai, “Teaching a Calligraphy Robot via a Touch Screen,” Proceedings of the IEEE International Conference on Automation Science and Engineering (CASE), pp. 221-226, Aug. 2014.
    V. Mnih, et al. “Playing atari with deep reinforcement learning,” arXiv preprint arXiv:1312.5602, 2013.
    T.P. Lillicrap, et al. “Continuous control with deep reinforcement learning,” arXiv preprint arXiv:1509.02971, 2015.
    R. C. Atkinson and R. Shiffrin, “Human memory: A proposed system and its control processes. In K. W. Spence & J. T. Spence,” The psychology of learning and motivation, vol. 2, pp. 89-195, Jan. 1968.
    F. I. M. Craik and R. S. Lockhart, “Levels of processing: A framework for memory research,” Journal of Verbal Learning and Verbal behavior, vol. 11, no 6, pp. 671-684, Dec. 1972.
    N. Cowan, “What are the differences between long term, short term, and working memory?,” Brain Research, vol. 169, pp. 323-338, 2008.
    E. Camina, and G. Francisco, “The Neuroanatomical, Neurophysiological and Psychological Basis of Memory: Current Models and Their Origins,” Frontiers in pharmacology, vol. 8, pp. 438, 2017.
    R. Akrour, D. Tateo, and J. Peters, “Continuous Action Reinforcement Learning from a Mixture of Interpretable Experts,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
    R. S. TAYLOR, “The process of asking questions.” American documentation, vol.13, no.4,:pp. 391-396, 1962.
    Z. Ma and J. Su, “Aesthetics Evaluation for Robotic Chinese Calligraphy,” IEEE Transactions on Cognitive and Developmental Systems,” vol. 9, no. 1, pp. 80-90, Mar. 2017.
    X. Gao, C. Zhou, F. Chao, L. Yang, C.-M. Lin, T. Xu, C. Shang, and Q. Shen, “A data-driven robotic chinese calligraphy system using convolutionalauto-encoder and differential evolution,” Knowledge-Based System, vol.182, Oct. 2019.
    S. T. S. Wong, H. Leung, and H. H. S. Ip, “Model-based Analysis of Chinese Calligraphy Images,” Computer Vision and Image Understanding, vol. 109, pp. 69-85, Jan. 2008.
    H. T. F. Wong and H. H. S. Ip, “Virtual Brush: A Model-Based Synthesis of Chinese Calligraphy,” Computers & Graphics, vol. 24, no. 1, pp. 99-113, Feb. 2000.
    C. R. Boër, L. Molinari-Tosatti, and K. S. Smith, “Parallel Kinematic Machines: Theoretical Aspects and Industrial Requirements,” Springer Verlag, Sept. 1999.
    L.-W. Tsai, “Robot analysis: the mechanics of serial and parallel manipulators,” Wiley-Interscience, Feb. 1999.
    C.-Y. Tzou, M.-J. Hsu, J.-Z. Jian, Y.-H. Chien, W.-Y. Wang, and C.-C. Hsu, “Mathematical analysis and practical applications of a serial-parallel robot with delta-like architecture,” International Journal of Engineering Research & Science, vol. 2, no. 5, pp. 80-91, May. 2016.
    Wikipedia, Chinese character classification, Available: https://en.wikipedia.org/wiki/Chinese_character_classification. [Accessed: January 16, 2022].
    Wikipedia, Eight Principles of Yong, Available: https://en.wikipedia.org/wiki/Eight_Principles_of_Yong. [Accessed: January 16, 2022].
    C. Gettys, et al. “Hypothesis Generation: A Final Report of Three Years of Research.” Decision Processes Lab. University of Oklahoma, https://apps.dtic.mil/sti/pdfs/ADA091681.pdf, 1980.
    E. S. Dasgupta and S. J. Gershman, “Where do hypotheses come from,” Cognitive Psychology, vol. 96, pp. 1-25, Aug. 2017.
    T. L. Griffiths and J. B. Tenenbaum, “Optimal predictions in everyday cognition,” Psychological Science, vol. 17, no. 9, Sep, pp. 767-773, 2006.
    B. Gawronski; L. A. Creighton, “Dual process theories,” The Oxford handbook of social cognition, pp. 282-312, 2013.
    R. Rojas, “The Backpropagation Algorithm,” Neural Networks. Springer, pp 149-182,1996.
    W. -Y. Wang, M. -J. Hsu, L. -A. Yu, Y. -H. Chien and C. -C. Hsu, “Deep Learning-Based Hypothesis Generation Model and Its Application on Virtual Chinese Calligraphy-Writing Robot,” IEEE Access, vol. 8, pp. 87243-87251,2020.
    W.-Y. Wang, Y.-H. Chien, Y.-G. Leu, and T.-T. Lee, “Adaptive T-S fuzzy-neural modeling and control for general MIMO unknown nonaffine nonlinear systems using projection update laws,” Automatica, vol. 46, pp.852-863, 2010.
    T. Tieleman and G. Hinton, “Lecture 6.5-RmsProp: Divide the gradientby a running average of its recent magnitude,” COURSERA, Neural Netw. Mach. Learn., vol. 4, no. 2, pp. 2631, Oct. 2012.
    G. Olague, E. Clemente, D. E. Hernández, A. Barrera, M. Chan-Ley and S. Bakshi, “Artificial Visual Cortex and Random Search for Object Categorization,” IEEE Access, vol. 7, pp. 54054-54072, 2019.
    X. -S. Tang, H. Wei and K. Hao, “Using a Vertical-Stream Variational Auto-Encoder to Generate Segment-Based Images and Its Biological Plausibility for Modelling the Visual Pathways,” IEEE Access, vol. 7, pp. 99-110, 2019.
    H. Reynolds, S. Feldman, “Cognitive computing: Beyond the hype,” KM World, http://www.kmworld.com/Articles/News /News-Analysis/Cognitive-computing-Beyond-the-hype-97685.aspx. 2014.
    M. Chen, F. Herrera and K. Hwang, “Cognitive Computing: Architecture, Technologies and Intelligent Applications,” IEEE Access, vol. 6, pp. 19774-19783, 2018.
    A. K. Noor, “Potential of Cognitive Computing and Cognitive Systems,” Open Engineering, vol. 5, no. 1, Nov. 2014.
    E. Akagunduz, A. G. Bors and K. K. Evans, “Defining Image Memorability Using the Visual Memory Schema,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 9, pp. 2165-2178, Sept. 2020.
    R. L. Solso, “Cognitive psychology (5th ed.),” Needham Heights, MA: Allyn and Bacon, 1998.
    J. G. Richard, “Psychology and life (20th edition),” Boston, Pearson, 2013.
    R. C. Atkinson and R. M. Shiffrin, “Human memory: A proposed system and its control processes. In K. W. Spence & J. T. Spence,” The psychology of learning and motivation, vol. 2, pp. 89-195, Jan. 1968.
    F. I. M. Craik and R. S. Lockhart, “Levels of processing: A frame-work for memory research,” Journal of Verbal Learning and Verbal behavior, vol. 11, no. 6, pp. 671-684, Dec. 1972.
    N. Cowan, “What are the differences between long-term, short-term, and working memory?” Brain Research, vol. 169, pp. 323-338, 2008.
    E. Camina, and G. Francisco, “The Neuroanatomical, Neurophysiological and Psychological Basis of Memory: Current Models and Their Origins,” Frontiers in pharmacology, vol. 8, pp. 438, 2017.
    E. Tulving and W. Donaldson, “Episodic and semantic memory,” Organization of memory. Academic Press, 1972.
    J. W. PAPEZ, “A proposed mechanism of emotion.” Archives of Neurology & Psychiatry, vol. 38, no. 4, pp. 725-743, 1937.
    N. Balak, et al. “Mammillothalamic and Mammillotegmental Tracts as New Targets for Dementia and Epilepsy Treatment.” World Neurosurg., no. 110, pp. 133-144, Feb. 2018
    T. Y. Zhang and C. Y. Suen, “A fast parallel algorithm for thinning digital patterns,” Commun. ACM, vol. 27, no. 3, pp. 236-239, Mar. 1984.

    無法下載圖示 Public on Internet date:
    2028/02/09
    QR CODE