JRM Vol.25 No.1 pp. 80-88
doi: 10.20965/jrm.2013.p0080


Abstraction Multimodal Low-Dimensional Representation from High-Dimensional Posture Information and Visual Images

Tatsuya Hirose* and Tadahiro Taniguchi**

*Kyoto University, Oiwake-cho, Kitashirakawa, Sakyo-ku, Kyoto, Japan

**Ritsumeikan University, 1-1-1 Nojihigashi, Kusatsu, Shiga, Japan

February 16, 2012
May 7, 2012
February 20, 2013
kernel canonical correlation analysis, imitation learning, body schema
Imitative learning is an effective method for robots to obtain a novel movement from a person demonstrating many kinds of movement. Many problems need to be solved, however, before a robot can achieve imitative learning. One problem is how to convert visual information on the demonstrator’s motion to kinematic posture information for the learner. This is referred to as a correspondence problem and we have focused on this problem in this study. To solve it, we focus on the formation of a low-dimensional representation that integrates sensory information from two different modalities. We propose a computation method for constructing the low-dimensional representation combining posture information and visual images by using Kernel Canonical Correlation Analysis (KCCA). Using this method, a robot becomes able to estimate posture information from visual images in a bottom-up way. Using several experiments we show how effective our proposed method is in estimating kinematic information.
Cite this article as:
T. Hirose and T. Taniguchi, “Abstraction Multimodal Low-Dimensional Representation from High-Dimensional Posture Information and Visual Images,” J. Robot. Mechatron., Vol.25 No.1, pp. 80-88, 2013.
Data files:
  1. [1] C. Breazeal and B. Scassellati, “Robots that imitate humans,” TRENDS in Cognitive Sciences, Vol.6, p. 11, November 2002.
  2. [2] T. Taniguchi, N. Iwahashi, K. Sugiura, and T. Sawaragi, “Constructive Approach to Role-Reversal Imitation Through Unsegmented Interactions,” J. of Robotics and Mechatronics, Vol.20, No.4, pp. 567-577, 2008.
  3. [3] C. Breazeal and B. Scassellati, “A context-dependent attention system for a social robot,” In Proc. Sixteenth Int. Joint Conf. Artif. Intell. (IJCAI99), pp. 1146-1151, 1999.
  4. [4] A. Alissandrakis, C. L. Nehaniv, and K. Dautenhahn, “Imitation With ALICE: Learning to Imitate Corresponding Actions Across Dissimilar Embodiments,” IEEE Trans. on Systems, Man, and Cybernetics Part A: Systems and Humans, Vol.32, pp. 482-496, 2002.
  5. [5] C. L. Nehaniv and K. Dautenhahn, “Imitation in Animals and Artifacts,” The MIT Press, pp. 41-61, 2002.
  6. [6] M.W. Lee, I. Cohen, and S. K. Jung, “Particle Filter with Analytical Inference for Human Body Tracking,” IEEE Workshop on Motion and Video Computing, 2002.
  7. [7] J. Shotton, A. Fitzgibbon, M. Cook, T. Sharp, M. Finocchio, R. Moore, A. Kipman, and A. Blake, “Real-Time Human Pose Recognition in Parts from Single Depth Images,” CVPR, 2011.
  8. [8] K. Yamane, D. Fukuda, and Y. Nakamura, “Markerless Motion Capture with Structure Estimation Capability,” J. of Robotics and Mechatronics, Vol.20, No.2, pp. 322-331, 2008.
  9. [9] A. Agarwal and B. Triggs, “Recovering 3d human pose from monocular images,” IEEE Trans. Pattern Anal. Mach. Intell., Vol.28, pp. 44-58, 2006.
  10. [10] K. Grauman, G. Shakhnarovich, and T. Darrell, “Inferring 3d structure with a statistical image-based shape model,” ICCV, pp. 641-648, 2003.
  11. [11] C. H. Ek, P. H. S. Torr, and N. D. Lawrence, “Gaussian Process Latent Variable Models for Human Pose Estimation,” MLMI, pp. 132-143, 2007.
  12. [12] C. E. Rasmussen and C. K. Williams, “Gaussian Processes for Machine Learning,” The MIT Press, 2006.
  13. [13] A. Maravita, C. Spence, and Driver, “Multisensory integration and the body schema: Close to hand and within reach,” Current Biology, Vol.13, 2003.
  14. [14] N. A. Borghese, L. Bianchi, and F. Lacquaniti, “Kinematic determinants of human locomotion,” J. Physiology, 1996.
  15. [15] C. M. Bishop, “Pattern Recognition And Machine Learning,” Springer-Verlag, 2006.
  16. [16] H. Hotelling, “Relations between two sets of variates,” Biometrika, Vol.28, pp. 321-377, 1936.
  17. [17] D. R. Hardoon, S. Szedmak, and J. Shawe-Taylor, “Canonical correlation analysis: an overview with application to learning methods,” Neural Computation, Vol.16, pp. 2639-2664, 2004.
  18. [18] C. Wang, “Variational Bayesian approach to Canonical Correlation Analysis,” In IEEE Trans. on Neural Networks, 2007.
  19. [19] P. Rai and H. Daume, “Multi-label prediction via sparse infinite CCA,” Advances in Neural Information Processing Systems, Vol.22, pp. 1518-1526, 2009.
  20. [20] K. Morita and H. Ishihara, “Four-Legged Mechanism for Realizing Dynamic Running – Design of Prototype with Drive System that Enables Dynamic Locomotion Change –,” J. of Robotics and Mechatronics, Vol.20, No.2, pp. 234-240, 2008.
  21. [21] T. Doi, K.Miyata, T. Sasagawa, and K. Tadakuma, “Multi-Leg System for Aerial Vehicles,” J. of Robotics and Mechatronics, Vol.24, No.1, pp. 174-179, 2012.
  22. [22] K. Hoshino and M. Tomida, “3D Hand Pose Estimation Using a Single Camera for Unspecified Users,” J. of Robotics and Mechatronics, Vol.21, No.6, pp. 749-757, 2009.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Jul. 12, 2024