Abstract
This paper proposes a new algorithm for the automatic segmentation of motion data from a humanoid soccer playing robot that allows feed-forward neural networks to generalize and reproduce various kinematic patterns, including walking, turning, and sidestepping. Data from a 20 degree-of-freedom Fujitsu hoap-1 robot is reduced to its intrinsic dimensionality, as determined by the isomap procedure, by means of nonlinear principal component analysis (nlpca). The proposed algorithm then automatically segments motion patterns by incrementally generating periodic temporally-constrained nonlinear pca neural networks and assigning data points to these networks in a conquer-and-divide fashion, that is, each network’s ability to learn the data influences the data’s division among the networks. The learned networks abstract five out of six types of motion without any prior information about the number or type of motion patterns. The multiple decoding subnetworks that result can serve to generate abstract actions for playing soccer and other complex tasks.
Chapter PDF
Similar content being viewed by others
Keywords
- Periodic Motion
- Humanoid Robot
- Automatic Segmentation
- Intrinsic Dimensionality
- Nonlinear Principal Component Analysis
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Inamura, T., Toshima, I., Nakamura, Y.: Acquiring motion elements for bidirectional computation of motion recognition and generation. In: Siciliano, B., Dario, P. (eds.) Experimental Robotics VIII, pp. 372–381. Springer, Heidelberg (2003)
Fujii, T.: A new approach to the LQ design from the viewpoint of the inverse regulator problem. IEEE Transactions on Automatic Control 32, 995–1004 (1987)
Zatsiorsky, V.M.: Kinematics of Human Motion. Human Kinetics, Urbana Champaign (2002)
Okada, M., Tatani, K., Nakamura, Y.: Polynomial design of the nonlinear dynamics for the brain-like information processing of whole body motion. In: IEEE International Conference on Robotics and Automation, pp. 1410–1415 (2002)
Kramer, M.A.: Nonlinear principal component analysis using autoassociative neural networks. Journal of the American Institute of Chemical Engineers 37, 233–243 (1991)
Tatani, K., Nakamura, Y.: Dimensionality reduction and reproduction with hierarchical NLPCA neural networks extracting common space of multiple humanoid motion patterns. In: Proceedings of the IEEE International Conference on Robotics and Automation, Taipei, Taiwan, pp. 1927–1932 (2003)
Malthouse, E.C.: Limitations of nonlinear PCA as performed with generic neural networks. IEEE Transactions on Neural Networks 9, 165–173 (1998)
Ridella, S., Rovetta, S., Zunino, R.: Adaptive internal representation in circular backpropagation networks. Neural Computing and Applications 3, 222–333 (1995)
Ridella, S., Rovetta, S., Zunino, R.: Circular backpropagation networks for classification. IEEE Transaction on Neural Networks 8, 84–97 (1997)
Kirby, M.J., Miranda, R.: Circular nodes in neural networks. Neural Computation 8, 390–402 (1996)
LeCun, Y., Bottou, L., Orr, G.B., Müller, K.R.: Efficient BackProp. In: Orr, G.B., Müller, K.R. (eds.) Neural Networks: Tricks of the Trade, pp. 1–44. Springer, Heidelberg (1998)
MacKay, D.J.: Probable networks and plausible predictions: A review of practical Bayesian methods for supervised neural networks. Network: Computation in Neural Systems 6, 469–505 (1995)
Chalodhorn, R., Aono, M., Ooga, J., Ogino, M., Asada, M.: Osaka University “Senchans 2003”. In Browning, B., Polani, D., Bonarini, A., Yoshida, K., eds.: RoboCup-2003: Robot Soccer World Cup VII, Springer Verlag (2003)
Tenenbaum, J.B., de Silva, V., Langford, J.C.: A global geometric framework for nonlinear dimensionality reduction. Science 290, 2319–2323 (2000)
Chalodhorn, R., MacDorman, K., Asada, M.: Automatic extraction of abstract actions from humanoid motion data. In: IROS 2004: IEEE/RSJ International Conference on Intelligent Robots and Systems, Sendai, Japan (Submitted)
MacDorman, K., Chalodhorn, R., Ishiguro, H., Asada, M.: Protosymbols that integrate recognition and response. In: EpiRob 2004: Fourth International Workshop on Epigenetic Robotics, Genoa, Italy (2004)
MacDorman, K., Chalodhorn, R., Asada, M.: Periodic nonlinear principal component neural networks for humanoid motion segmentation, generalization, and generation. In: ICPR 2004: International Conference on Pattern Recognition, Cambridge, UK (2004)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chalodhorn, R., MacDorman, K., Asada, M. (2005). An Algorithm That Recognizes and Reproduces Distinct Types of Humanoid Motion Based on Periodically-Constrained Nonlinear PCA. In: Nardi, D., Riedmiller, M., Sammut, C., Santos-Victor, J. (eds) RoboCup 2004: Robot Soccer World Cup VIII. RoboCup 2004. Lecture Notes in Computer Science(), vol 3276. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-32256-6_30
Download citation
DOI: https://doi.org/10.1007/978-3-540-32256-6_30
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-25046-3
Online ISBN: 978-3-540-32256-6
eBook Packages: Computer ScienceComputer Science (R0)