個人化機器人被設計來在居家環境中能協助或娛樂人們，並且被期待
能夠與人們互動，因此，越來越吸引來自各領域的人們的注意力，而機器
人能夠模仿人類動作則被視為能與人類在動作上互動的第一步。本篇論文
提出一個以類神經網路為基礎的機制，得以讓機器人即時模仿人類動作。
主要由三個步驟組成：1)建立人體基本動作單元、2)針對每個人體基本動
作單元，利用最佳化演算法找出相對應的機械人關節的馬達角度、3)利用
前述步驟之結果，設計以類神經網路為基礎的機械人關節角度控制器。
首先由收集的多種人體動作序列，利用分群演算法找出基本動作單
元。由於人體基本動作單元數未知，我們採用非監督式的自我組織特徵映
射圖(SOM)方法，藉由人體動作資料的拓樸分佈，找出基本人體動作單元。
第二步是針對這些基本動作單元，找出對應的機械人關節馬達角度，使得
機器人的能作出與人體基本動作最相似的動作，此問題可被視為一個在高
維度空間中尋找一個最佳解(亦即最佳之馬達角度組合)的最佳化問題，會
隨著機器人之馬達數目的增加而大大增加其複雜度。針對此最佳化問題，
本論文特別發展了一個以鴿子覓食機制為構想的最佳化演算法─鴿子群體
最佳化演算法(Dove Swarm Optimization)，希望透過此鴿子群體最佳化演
算法得以快速找到好的機械人馬達關節角度組合。第三步則是以上述找到
之機械人馬達關節角度對應之資料集作為訓練資料，訓練一個監督式的類
神經網路做為機械人關節角度控制器。本論文比較多層感知機網路以及放
射狀基底函數網路的結果，最後選用多層感知機網路作為控制器。
在實驗結果部份，本論文與線性對應(linear mapping)的方法比對差
異度、方均根誤差以及時間，結果發現整體效能平均提升約10%，而對於在
線性對應方式中表現特別不好的人體姿態，其改進比例則為13%，而在線性
對應方式中已表現很好的姿態則無太大之改進。

Personal service robots are designed to assist or entertain people in
domestic environments and expected to engage in social-human interactions;
therefore, they are gaining more and more attentions from many different fields.
A robot that can imitate human actions can be regarded as the first step for
interacting with humans from the viewpoint of actions. This dissertation presents
a neural-network-based imitation mechanism for teaching a robot to imitate
human actions. The proposed mechanism involves in the following three steps: 1)
the generation of basic human motion units, 2) the mapping between basic
human motion units and robot joint motor angles, and 3) the construction of a
NN-based controller.
First of all, we collected several human motion sequences consisted of
many different human activities and then used a clustering algorithm to cluster
the collected human actions into a set of basic human motion units. Since the
number of basic human motion units is unknown, we decided to adopt the
self-organized feature map (SOM) as the clustering tool to generate basic human
motion units. Secondly, for each basic human action unit, we need to find a
combination of robot joint motor angles to make the robot pose be similar to the
corresponding human pose. The problem can be regarded as an optimization
problem of which goal is to find an optimized solution (i.e., the best
combination of robot joint motor angles) in a multi-dimensional space. The
complexity of the optimization problem greatly increases as the number of robot
joint motors. To provide a good solution to the optimization problem, this
dissertation also proposes the new optimal algorithm called dove swarm
optimization (DSO), which is motivated by the doves’ foraging behavior. The
proposed DSO is adopted to affectively find the best combination of robot joint
motor angles corresponding to each basic human motion unit. In the third step,
the data set generated in the previous step is adopted as the training data set to
construct a NN-based controller. From our simulations, we found that controller
performance achieved by the multilayer perceptrons (MLP) outperformed the
radial basis function network (RBFN); therefore, we decided to adopt the MLP
to construct the NN-based controller.
The proposed mechanism was compared with the most straightforward
linear mapping method based on the root mean squared error and computational
time. In simulation results, we found that the proposed imitation mechanism
could promote the performance about 10% on average. The worst one hundred
basic human actions achieved by the linear mapping method, the imitation
performance could be improved to 13% by our mechanism. As for the best one
hundred basic human actions achieved by the linear mapping method, our
imitation mechanism did not clearly improve the imitation performance.

[1] S. Thrun, “Toward a Framework for Human-Robot Interaction,” Human
Computer Interaction, vol. 19, no. 1, pp. 9-24, 2004.
[2] K. Dautenhahn, S. C. Woods, M. Kaouri, L. Walters, K. L. Koay, and I.
Werry, “What is a robot companion - friend, assistant or butler?” in
IEEE/RSJ International Conference on Intelligent Robots and Systems, pp.
1192-1197, 2005.
[3] C. Breazeal and B. Scassellati, “Robots that imitate humans,” TRENDS in
Cognitive Sciences, vol.6, no.11, Nov. 2002.
[4] Tingoy, A. Gunefler, E. Ongun, A. Demirag, and O. Koroglu, “Using
storytelling in education,” in 4th International Symposium of Interactive
Media Design, 2006.
[5] B. Robins, K. Dautenhahn, R. te Boekhorst, and A. Billard, “Effects of
repeated exposure to a humanoid robot on children with autism,” in
Designing a More Inclusive World, Springer Verlag, London, pp. 225-236,
2004.
[6] B. Robins, K. Dautenhahn, R. Te Boekhorst, and A. Billard “Robotic
assistants in therapy and education of children with autism: can a small
humanoid robot help encourage social interaction skills?” Access in the
Information Society (UAIS), vol. 4, no. 2, pp. 105-120, 2005.
[7] K. Dautenhahn , C. L. Nehaniv , M. L. Walters , B. Robins , H. Kose-Bagci ,
N. A. Mirza , and M. Blow, “KASPAR -- A Minimally Expressive
Humanoid Robot for Human-Robot Interaction Research,” Appl. Bionics
Biomech, vol. 6 no. 3-4, pp. 369-97, 2009.
[8] E. S. Kim, R. Paul, F. Shic, and B. Scassellati, “Bridging the Research Gap:
Making HRI Useful to Individuals with Autism,” Journal of Human-Robot
interaction, vol. 1, no. 1, pp. 26-54, 2012.
[9] F Michaud, J.F. Laplante, H. Larouche, A. Duquette, and S. Caron, et al.,
“Autonomous spherical mobile robot for child-development studies,” IEEE
Trans. Syst. Man Cybern. Part A, vol. 35, no. 4, pp. 471-480, 2005.
[10]A. Duquette, F. Michaud, and H. Mercier, “Exploring the use of a mobile
robot as an imitation agent with children with low-functioning autism,”
Auton. Robot, vol. 24, pp.147-157, 2008.
[11]H. Kozima, C. Nakagawa, and Y. Yasuda, “Children-robot interaction: a
pilot study in autism therapy,” Prog. Brain Res, vol. 164, pp. 385-400,
2007.
[12]B. Scassellati, H. Admoni, and M. Matari, “Robots for Use in Autism
73
Research,” Annual Review of Biomedical Engineering, vol. 14, pp. 275-294,
2012.
[13] L. Boutin, A. Eon, S. Zeghloul, and P. Lacouture, “From human motion
capture to humanoid locomotion imitation Application to the robots HRP-2
and HOAP-3,” Robotica, vol. 29, no. 54, Cambridge, MA: MIT Press, 2010.
[14] X. ZHAO, Q. HUANG, Z. PENG, and K. LI, “Kinematics Mapping and
Similarity Evaluation of Humanoid Motion Based on Human Motion
Capture,” in Proc. of 2004 International Conference on Intelligent Robots
and Systems, Sep. 28 - Oct. 2, 2004, Sendai, Japan.
[15] S. Nakaoka, A. Nakazawa, F. Kanehiro, K. Kaneko, M. Morisawa, and K.
Ikeuchi, “Task Model of Lower Body Motion for a Biped Humanoid Robot
to Imitate Human Dances,” in 2005 IEEE/RSJ International Conference on
Intelligent Robots and Systems, pp. 2770-2774, 2005.
[16] W. Suleiman, E. Yoshida, F. Kanehiro, J. P. Laumond, and A. Monin, “On
Human Motion Imitation by Humanoid Robot,” in 2008 IEEE International
Conference on Robotics and Automation Pasadena, CA, USA, May 19-23,
2008
[17] D. Lee, C. Ott, Y. Nakamura, and G. Hirzinger, “Physical Human Robot
Interaction in Imitation Learning,” in 2011 IEEE International Conference
on Robotics and Automation, May 9-13, 2011, Shanghai, China.
[18] T. Kaneko, T. Ono, and N. Munakata, “Implementation of
context-adaptive Physical Imitation between Humans and Robots,” in 20th
IEEE International Symposium on Robot and Human Interactive
Communication, July 31 - August 3, 2011, Atlanta, GA, USA.
[19] F. Montecillo-Puente, M. N. Sreenivasa, and J. Laumond, “On Real-time
Whole-body Human to Humanoid Motion Transfer,” in Proc. of ICINCO,
pp. 22-31, 2010.
[20] A. Bogdanovych, C. Stanton, X. Wang, and M. A. Williams, “Real-Time
Human-Robot Interactive Coaching System with Full-Body Control
Interface,” Lecture Notes in Computer Science, vol. 7416, pp 562-573,
2012.
[21] J. Koenemann and M. Bennewitz, “Whole-Body Imitation of Human
Motions with a Nao Humanoid,” in HRI 2012, Boston, Massachusetts, USA,
March 5–8, 2012.
[22] F. Zuher and R. Romero, “Recognition of human motions for imitation and
control of a humanoid robot,” in 2012 Brazilian Robotics Symposium and
Latin American Robotics Symposium, 2012.
[23] T. Veltrop, “Brushing the Cat Remotely with a Robot Avatar” Avaliable:
74
http://www.youtube.com/watch?v=pxoL4bnLp0g 2013/6/24[data access]
[24] C. Plaisant, A. Druin, C. Lathan,K. Dakhane, K. Edwards, J. Maxwell Vice,
and J. Montemayor, “A Storytelling Robot for Pediatric Rehabilitation,” in
Proc. of ASSETS'00, Washington, ACM, New York, Nov. 2000.
[25] T. Kohonen, Self-Organization Maps, Springer-Verlag, 1995.
[26] D. C. Lay, “Change Of Basis,” Linear Algebra and Its Applications,
Maryland, 3rd ed., 2006.
[27] M. C. Su and H. C. Chang, “Fast self-organizing feature map algorithm,”
IEEE Transactions on Neural Networks, vol. 13, no. 3, pp. 721-733, May
2000.
[28] M. C. Su, Y. X. Zhao, and J. Lee, “SOM-based Optimization,” in IEEE
International Joint Conference on Neural Networks (IJCNN), Budapest,
Hungary, pp. 781-786, July 2004.
[29] J. S. R. Jang, C. T. Sun, and E. Mizutani, “Neuro-Fuzzy and Soft
Computing: A Computational Approach to Learning and Machine
Intelligence,” Prentice Hall, 1997.
[30] D. E. Goldberg, Genetic Algorithms in Search, Optimization, and Machine
Learning, Addison-Wesley Publishing Company, Reading, MA, 1989.
[31] J. H. Holland, Adaptation in Natural and Artificial Systems, University of
Michigan Press, Ann Arbor, 1975.
[32] S. Kirkpatrick, C. D. Gelatt, and M. P. Vecchi, “Optimization by simulated
annealing,” Science, vol. 220, no. 4598, pp. 671-680, May 1983.
[33] R. H. J. M. Otten and L. P. P. P. Ginneken, The annealing algorithm,
Kluwer Academic, 1989.
[34] L. J. Fogel, “Evolutionary Programming in Perspective: the Top-down
View,” in Computational Intelligence: Imitating Life, Piscataway, NJ, 1994.
[35] R. Mallipeddi , S. Mallipeddi , and P.N. Suganthan, “Ensemble strategies
with adaptive evolutionary programming,” Information Sciences, vol. 180,
no. 9, pp. 1571-1581, May 2010.
[36] I. Rechenberg, “Cybernetic solution path of an experimental problem,”
Royal Aircraft Establishment, Library translation 1122, Farnborough, Hants,
U.K. 1965.
[37] I. Rechenberg, “Evolutiosstrategie: optimierung technischer system nach
prinzipien der biologischen evolution,” Stuttgart, Germany:
Frommann-Holzboog Verlag, 1973.
[38] M. Dorigo, V. Maniezzo, and A. Colorni, “Ant system: optimization by a
colony of cooperating agents,” IEEE Trans. Systems, Man, and Cybernetics,
B. vol. 26, no. 1, pp. 29-41, 1996.
75
[39] M. Dorigo and T. Stutzle, Ant Colony Optimization, Cambridge, M: MIT,
2004.
[40] A. Colorni, M. Dorigo, and V. Maniezzo, “Distributed Optimization by
Ant Colonies,” in Proc. of First European Conference on Artifical Life,
edited by F. Varela and P. Bourgine, Cambridge, MA: MIT Press, pp.
134-142. 1991.
[41] J. Kennedy and R. Eberhart, “Particle swarm optimization, “in IEEE
International Conference on Neural Networks, vol.4, pp.1942-1948, Dec.
1995.
[42] R. Eberhart and J. Kennedy, “A new optimizer using particle swarm theory,
“in Proc. of the Sixth International Symposium on Micro Machine and
Human Science, pp. 39-43, Oct. 1995.
[43] J. Kennedy, R. C. Eberhart, and Y. Shi, Swarm Intelligence, New York:
Academic Press, 2001.
[44] S. Boyd and L. Vandenberghe, Convex Optimization, Cambridge
University Press, 2004.
[45] J. Nocedal and S. J. Wright, Numerical Optimization, Springer, 2006.
[46] E. Bonabeau, M. Dorigo, and G. Theraulaz, Swarm Intelligence: From
Natural to Artificial Systems, Oxford University Press, New York, 1999.
[47] K.N. Krishnanand and D. Ghose, “Glowworm swarm optimisation: a new
method for optimising multi-modal functions,” International Journal
Computational Intelligence Studies, vol. 1, no. 1, 2009.
[48] C. W. Reynolds, “Flocks, herds, and schools: a distributed behavioral
model,” Computer Graphics, vol. 21, pp. 25-34, 1987.
[49] F. Heppner and U. Grenander, “A stochastic nonlinear model for
coordinated bird flocks,” in S. Krasner (Ed.), The Ubiquity of Chaos,
Washington, DC: AAAS Publications, 1990.
[50] J. Denavit and R. S. Hartenberg, “A kinematic notation for lower
pairmechanisms,” Applied Mechanics, vol. 22, pp. 215-221, 1955.
[51] M. W. Spong, S. Hutchinson, and M. Vidyasagar, Robot Modeling and
Control, JOHN WILEY & SONS, INC, New York, U.S.A., 2005.
[52] S. Kucuk and Z. Bingul, “Chapter 4:Robot Kinematics: Forward and
Inverse Kinematics,” in Industrial Robotics: Theory, Modeling and Control,
S. Cubero Ed., Pro Literatur Verlag, Germany / ARS, Austria, pp. 117-148,
2006.
[53] M. C. Su and H. T. Chang, Machine Learning: Neural Networks, Fuzzy
Systems, and Genetic Algorithms 3rd edit (in Chinese), Chuan-Hwa Pub.,
2004.
76
[54] J. T. Tou and R. C. Gonzalez, Pattern Recognition Principles,
Addison-Wesley Publishing Company, London, 1974.
[55]K. A. De Jong, “An analysis of the behavior of a class of genetic adaptive
systems,” University of Michigan, Ann Arbor, Tech. Rep. No:185, 1975.
(University Microfilms No. 76-9381)
[56] G. B. Fogel, G. W. Greenwood, and K. Chellapilla, “Evolutionary
computation with extinction: Experiments and analysis,” in Proc. of the
2000 Congress on Evolutionary Computation, pp. 1415-1420, 2000.
[57] R. Salomon, “Reevaluating Genetic Algorithm Performance under
Coordinate Rotation of Benchmark Functions,” Elsevier Science on
BioSystems, vol. 39, pp. 263-278, 1995.
[58] M. Locatelli, “A Note on the Griewank Test Function,” Journal of Global
Optimization, vol. 25, no. 2, Feb. 2003.
[59] 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, pp.459-471, Feb. 2007.
[60] H. H. Rosenbrock, “An Automatic Method for Finding the Greatest or
Least Value of a Function,” The Computer Journal, vol. 3, no. 3, pp.
175-184, 1960.
[61] T. Krink and R. Thomsen, “Self-organized criticality and mass extinction
in evolutionary algorithms,” in IEEE International Conf. on Evolutionary
Computation, pp. 1155-1161, 2001.
[62] M. Richards and D. Ventura, “Dynamic sociometry in particle swarm
optimization,” in International Conference on Computational Intelligence
and Natural Computing, pp. 1557-1560, 2003.
[63] Y. Shi and R. Eberhart, “Fuzzy adaptive particle swarm optimization,” in
Proc. of the Congress on Evolutionary Computation, pp. 101-106, 2001.
[64] J. Vesterstrom and R. Thomsen, “A comparative study of differential
evolution, particle swarm optimization, and evolutionary algorithms on
numerical benchmark problems,” in Proc. of the 2004 Congress on
Evolutionary Computation, vol. 2, pp. 1980-1987, 2004.