Browse > Article
http://dx.doi.org/10.5302/J.ICROS.2008.14.10.1038

Motion Imitation Learning and Real-time Movement Generation of Humanoid Using Evolutionary Algorithm  

Park, Ga-Lam (고려대학교 기계공학과, 한국과학기술연구원(KIST))
Ra, Syung-Kwon (한국과학기술연구원(KIST) 인지로봇연구단)
Kim, Chang-Hwan (한국과학기술연구원(KIST) 인지로봇연구단)
Song, Jae-Bok (고려대학교 기계공학과)
Publication Information
Journal of Institute of Control, Robotics and Systems / v.14, no.10, 2008 , pp. 1038-1046 More about this Journal
Abstract
This paper presents a framework to generate human-like movements of a humanoid in real time using the movement primitive database of a human. The framework consists of two processes: 1) the offline motion imitation learning based on an Evolutionary Algorithm and 2) the online motion generation of a humanoid using the database updated bγ the motion imitation teaming. For the offline process, the initial database contains the kinetic characteristics of a human, since it is full of human's captured motions. The database then develops through the proposed framework of motion teaming based on an Evolutionary Algorithm, having the kinetic characteristics of a humanoid in aspect of minimal torque or joint jerk. The humanoid generates human-like movements far a given purpose in real time by linearly interpolating the primitive motions in the developed database. The movement of catching a ball was examined in simulation.
Keywords
humanoid; evolutionary algorithm; imitation learning; human-like movement;
Citations & Related Records

Times Cited By SCOPUS : 0
연도 인용수 순위
  • Reference
1 J. M. Hollerbach and T. Flash, 'Dynamic interactions between limb segments during planar arm movement,' Biological Cybernetics, vol. 44, pp. 67-77, 1982   DOI
2 F. A. Mussa-Ivaldi, S. F. Giszter, and E. Bizzi, 'Linear combinations of primitives in vertebrate motor control,' Proc. of the National Academy of Sciences of the United States of America, 91, pp. 7534-7538, 1994
3 T. D. Sanger, 'Human arm movements described by a lowdimensional superposition of principal components,' The J. of Neuroscience, vol. 20, no. 3, pp. 1066-1072, 2000   DOI
4 C. Kim, D. kim, and Y. Oh, 'Solving an inverse kinematics problem for a humanoid robot's imitation of human motions using optimization,' in Proc. Of Int. Conf. on Informatics in Control, Automation and Robotics, pp. 85-92, 2005
5 S. Schaal, 'Learning robot control, in the handbook of brain theory and neural networks, 2nd ed,' M. A. Arbib, Ed. MIT Press, pp. 983-987, 2002
6 S. Schaal, 'Is imitation learning the route to humanoid robots?,' Trends in Cognitive Sciences, 3, pp. 233-242, 1999   DOI   ScienceOn
7 E. Nakano, H. Imamizu, R. Osu, Y. Uno, H. Gomi, T. Yoshioka, & M, Kawato, 'Quantitative examinations of internal representations for arm trajectory planning: minimum commanded torque change model,' Journal of Neurophysiology, vol. 81 (5), pp. 2140-2155, 1999   DOI
8 R. A. Schmidt, Motor Control and Learning: A Behavioral Emphasis. 2nd ed. champaign, IL: Human Kinetics, 1988
9 R. M. Alexander, 'A minimum energy cost hypothesis for human arm trajectories,' Biol. Cybern., vol. 76, pp. 97-105, 1997   DOI
10 Y. Uno, M. Kawato, & R. Suzuki, 'Formation and control of optimal trajectory in human arm movement -minimum torquechange model,' Biol. Cybernetics, vol. 61, pp. 89-101, 1989
11 J. E. Bobrow, B. Martin, G. Sohl, E. C. Wang, F. C. Park, and J. Kim, 'Optimal robot motions for physical criteria,' J. of Robotic Systems, vol. 18, no. 12, pp. 785-795, 2001   DOI   ScienceOn
12 S. Lee, J. Kim, F. C. Park, M. Kim, and J. E. Bobrow, 'Newtontype algorithms for dynamics-based robot motion optimization,' IEEE Trans. Robotics, vol. 21, no. 4, pp. 657-667, 2005   DOI   ScienceOn
13 F. A. Mussa-Ivaldi FA and E. Bizzi, 'Motor learning through the combination of primitive,' Philosophical Trans. of the Royal Society of London, Series B, 355:1755-1769, 2000   DOI   ScienceOn
14 M. M. Williamson, 'Postural primitives: interactive behavior for a humanoid robot arm,' In Proc. of the Fourth International Conference on Simulation of Adaptive Behavior (SAB-96), 1996
15 A. E. Eiben and J. E. Smith, Introduction to Evolutionary Computing, Springer, pp. 15-24, 2003
16 G. J. Garvin, M. Zefran, E. A. Henis, and V. Kumarm, 'Two-arm trajectory planning in a manipulation task,' Biol. Cybern., vol. 76, pp. 53-62, 1997   DOI
17 M. Raibert and B. Horn, 'A model for sensorimotor control and learning,' Biological Cybernetics, vol. 29, pp. 29-36, 1978   DOI
18 G. R. Tack, B. S. Lee, S. C. Chung, J. H. Yi, G. M. Eom, C. H. Kim, and J. S. Choi, 'Effect of shoe and walking speed on the smoothness of movement during walking,' Int. Conf. Mechanics in Medicine and Biology, pp. 354-357, 2006
19 L. I. Smith, 'A tutorial on principal components analysis,' http://csnet.otago.ac.nz /cosc453/, 2002
20 B. Lim, S. Ra, and F. C. Park, 'Movement primitives, principal component analysis, and the efficient generation of natural motions,' in Proc. 2005 IEEE Int. Conf. Intelligent Robots and Systems, pp. 4630-4635, 2005
21 Y. Wada, Y. Kaneko, E. Nakano, R. Osu, and M. Kawato, 'Quantitative examinations for multi joint arm trajectory planning - using a robust calculation algorithm of the inimum commanded torque change trajectory,' Neural Networks, vol. 14, pp. 381-393, 2001   DOI   ScienceOn
22 A. Fod, M. J. Mataric, and O. C. Jenkins, 'Automated derivation of Primitives for movement classification,' Autonomous Robots, vol. 12, no. 1, pp. 39-54, 2002   DOI   ScienceOn
23 J. Nakanishi, J. Morimoto, G. Endo, G. Cheng, S. Schaal, and M. Kawato, 'Learning from demonstration and adaptation of biped locomotion,' Robotics and Autonomous System, vol. 47, pp. 79-91, 2004   DOI   ScienceOn