Abstract
This paper presents a bottom-up approach to building internal representation of an autonomous robot. The robot creates its state space for planning and generating actions adaptively based on collected information of image features without pre-programmed physical model of the world. For this purpose, image-feature-based state space construction method is proposed using manifold learning approach. 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 with LLE (locally linear embedding). The proposed method was evaluated by experiment with a humanoid robot collision classification and motion generation in an obstacle avoidance task.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aldebaran Robotics. Technical Specifications Document (2009). http://www.aldebaran-robotics.com/
Argall, B.D., Chernova, S., Veloso, M., Browning, B.: A survey of robot learning from demonstration. Robot. Auton. Syst. 57(5), 469–483 (2009)
Minato, T., Thomas, D., Yoshikawa, Y., Ishiguro, H.: A model to explain the emergence of imitation development based on predictability preference. IEEE Trans. Autonomous Mental Develop. 4(1), 17–28 (2012)
Theodorou, E., Buchli, J., Schaal, S.: A path integral approach. In: Proceedings of IEEE International Conference on Robotics and Automation, pp. 2397–2403 (2010)
Sugimoto, N., Morimoto, J.: Application to humanoid robot motor learning in the real environment. In: Proceedings of IEEE International Conference on Robotics and Automation, pp. 1311–1316 (2013)
Minato, T., Asada, M.: Towards selective attention: generating image features by learning a visuo-motor map. Robot. Auton. Syst. 45(3–4), 211–221 (2006)
Prankl, J., Zillich, M., Vincze, M.: 3d piecewise planar object model for robotics manipulation. In: 2011 IEEE International Conference on Robotics and Automation (ICRA), pp. 1784–1790 (2011)
Ke, Y., Sukthankar, R.: A more distinctive representation for local image descriptors. In: Computer Vision and Pattern Recognition (2004)
Kobayashi, Y., Okamoto, T., Onishi, M.: Generation of obstacle avoidance based on image features and embodiment. Intl. J. Robot. Autom. 24(4), 364–376 (2012)
Somei, T., Kobayashi, Y., Shimizu, A., Kaneko, T.: Clustering of image features based on contact and occlusion among robot body and objects. In: Proceedings of the 2013 IEEE Workshop on Robot Vision (WoRV2013), pp. 203–208 (2013)
Kohonen, T.: Self-Organizing Maps. Springer, Heidelberg (1995)
Lowe, D.G.: Object recognition from local scale-invariant features. In: Proceedings of IEEE International Conference on Computer Vision, vol. 2, pp. 1150–1157 (1999)
Lungarella, M., Metta, G., Pfeifer, R., Sandini, G.: Developmental robotics: a survey. Connect. Sci. 15, 151–190 (2003)
Morimoto, J., Nakanishi, J., Endo, G., Cheng, G., Atkeson, C.G., Zeglin, G.: Poincaré-map-based reinforcement learning for biped walking. In: Proceedings of IEEE International Conference on Robotics and Automation (2005)
Oudeyer, P.Y., Kaplan, F., Hafner, V.: Intrinsic motivation systems for autonomous mental development. IEEE Trans. Evol. Comput. 11(2), 265–286 (2007)
Saul, L.K., Roweis, S.T.: Think globally, fit locally: unsupervised learning of low dimensional manifolds. J. Mach. Learn. Res. 4, 119–155 (2003)
Stoytchev, A.: Some basic principles of developmental robotics. IEEE Trans. Autonomous Mental Develop. 1(2), 122–130 (2009)
Sutton, R.S., Barto, A.G.: Reinforcement learning: an introduction (Adaptive Computation and Machine Learning). In: A Bradford Book (1998)
Kober, J., Bagnell, D., Peters, J.: Reinforcement learning in robotics: a survey. Intl. J. Robot. Res. 11, 1238–1274 (2013)
Weng, J., McClelland, J., Pentland, A., Sporns, O., Stockman, I., Sur, M., Thelen, E.: Autonomous mental development by robots and animals. Science 291, 599–600 (2001)
Fitzpatrick, P., Metta, G., Natalc, L., Rao, S., Sandini, G.: Learning about objects through action - initial steps towards artificial cognition. In: Proceedings of IEEE International Conference on Robotics and Automation, pp. 3140–3145 (2003)
Stoytchev, A.: Toward video-guided robot behaviors. In: Proceedings of the 7th International Conference on Epigenetic Robotics, pp. 165–172 (2007)
Kobayashi, Y., Hosoe, S.: Planning-space shift motion generation: variable-space motion planning toward flexible extension of body schema. J. Intell. Robot. Syst. 62(3), 467–500 (2011)
Acknowledgment
This work was partly supported by Kayamori Foundation of Informational Science Advancement.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Kobayashi, Y., Matsui, R. (2016). Manifold Learning Approach Toward Constructing State Representation for Robot Motion Generation. In: Nguyen, N., Kowalczyk, R., Filipe, J. (eds) Transactions on Computational Collective Intelligence XXIV. Lecture Notes in Computer Science(), vol 9770. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-53525-7_6
Download citation
DOI: https://doi.org/10.1007/978-3-662-53525-7_6
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-53524-0
Online ISBN: 978-3-662-53525-7
eBook Packages: Computer ScienceComputer Science (R0)