Manifold Learning Approach toward Image Feature-based State Space Construction

Yuichi Kobayashi, Ryosuke Matsui, Toru Kaneko

Abstract

This paper presents a bottom-up approach to building internal representation of an autonomous robot under a stand point that the robot create its state space for planning and generating actions only by itself. For this purpose, image-feature-based state space construction method is proposed using LLE (locally linear embedding). The visual feature is extracted from sample images by SIFT (scale invariant feature transform). SOM (Self Organizing Map) is introduced to find appropriate labels of image features throughout images with different configurations of robot. The vector of visual feature points mapped to low dimensional space express relation between the robot and its environment. The proposed method was evaluated by experiment with a humanoid robot collision classification.

References

  1. Aldebaran Robotics (2009). Nao. http://www.aldebaranrobotics.com/. Technical Specifications Document.
  2. Argall, B. D., Chernova, S., Veloso, M., and Browning, B. (2009). A survey of robot learning from demonstration. Robot. Auton. Syst., 57(5):469-483.
  3. Ke, Y. and Sukthankar, R. (2004). Pca-sift: A more distinctive representation for local image descriptors. Computer Vision and Pattern Recognition.
  4. Kobayashi, Y., Okamoto, T., and Onishi, M. (2012). Generation of obstacle avoidance based on image features and embodiment. International Journal of Robotics and Automation, 24(4):364-376.
  5. Kohonen, T. (1995). Self-Organizing Maps. Springer Press.
  6. Lowe, D. G. (1999). Object recognition from local scaleinvariant features. In Proc. of IEEE International Conference on Computer Vision, volume 2, pages 1150- 1157.
  7. Lungarella, M., Metta, G., Pfeifer, R., and Sandini, G. (2003). Developmental robotics: A survey. Connection Science, 15:151-190.
  8. Morimoto, J., Nakanishi, J., Endo, G., Cheng, G., Atkeson, C. G., and Zeglin, G. (2005). Poincaré-MapBased Reinforcement Learning For Biped Walking. In Proc. of IEEE International Conference on Robotics and Automation.
  9. Oudeyer, P. Y., Kaplan, F., and Hafner, V. (2007). Intrinsic motivation systems for autonomous mental development. IEEE Transactions on Evolutionary Computation, 11(2):265-286.
  10. Prankl, J., Zillich, M., and Vincze, M. (2011). 3d piecewise planar object model for robotics manipulation. In Robotics and Automation (ICRA), 2011 IEEE International Conference on, pages 1784 -1790.
  11. Saul, L. K. and Roweis, S. T. (2003). Think globally,fit locally : Unsupervised learning of low dimensional manifolds. Journal of Machine Learning Research, 4:119-155.
  12. Stoytchev, A. (2009). Some basic principles of developmental robotics. IEEE Transactions on Autonomous Mental Development, 1(2):122-130.
  13. Sutton, R. S. and Barto, A. G. (1998). Reinforcement Learning: An Introduction (Adaptive Computation and Machine Learning). A Bradford Book.
  14. Weng, J., McClelland, J., Pentland, A., Sporns, O., Stockman, I., Sur, M., and Thelen, E. (2001). Autonomous mental development by robots and animals. Science, 291:599-600.
Download


Paper Citation


in Harvard Style

Kobayashi Y., Matsui R. and Kaneko T. (2013). Manifold Learning Approach toward Image Feature-based State Space Construction . In Proceedings of the 5th International Joint Conference on Computational Intelligence - Volume 1: NCTA, (IJCCI 2013) ISBN 978-989-8565-77-8, pages 529-534. DOI: 10.5220/0004630305290534


in Bibtex Style

@conference{ncta13,
author={Yuichi Kobayashi and Ryosuke Matsui and Toru Kaneko},
title={Manifold Learning Approach toward Image Feature-based State Space Construction},
booktitle={Proceedings of the 5th International Joint Conference on Computational Intelligence - Volume 1: NCTA, (IJCCI 2013)},
year={2013},
pages={529-534},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004630305290534},
isbn={978-989-8565-77-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Joint Conference on Computational Intelligence - Volume 1: NCTA, (IJCCI 2013)
TI - Manifold Learning Approach toward Image Feature-based State Space Construction
SN - 978-989-8565-77-8
AU - Kobayashi Y.
AU - Matsui R.
AU - Kaneko T.
PY - 2013
SP - 529
EP - 534
DO - 10.5220/0004630305290534