Abstract
Humans tend to organize their knowledge into hierarchies, because searches are efficient when proceeding downward in the tree-like structures. Similarly, many autonomous robots also contain some form of hierarchical knowledge. They may learn knowledge from their experiences through interaction with human users. However, it is difficult to find a common ground between robots and humans in a low level experience. Thus, their interaction must take place at the semantic level rather than at the perceptual level, and robots need to organize perceptual experiences into hierarchies for themselves. This paper presents an unsupervised method to build view-based perceptual hierarchies using hierarchical Nearest Neighbor Graphs (hNNGs), which combine most of the interesting features of both Nearest Neighbor Graphs (NNGs) and self-balancing trees. An incremental construction algorithm is developed to build and maintain the perceptual hierarchies. The paper describes the details of the data representations and the algorithms of hNNGs.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The labels are provided just for evaluation.
References
Austerweil, J.L., Griffiths, T.L.: A nonparametric bayesian framework for constructing flexible feature representations. Psychol. Rev. 120(4), 817 (2013)
Bentley, J.L.: Multidimensional binary search trees used for associative searching. Commun. ACM 18(9), 509–517 (1975)
Collet, A., Xiong, B., Gurau, C., Hebert, M., Srinivasa, S.S.: Exploiting domain knowledge for object discovery. In: 2013 IEEE International Conference on Robotics and Automation (ICRA), pp. 2118–2125. IEEE (2013)
Franti, P., Virmajoki, O., Hautamaki, V.: Fast agglomerative clustering using a k-nearest neighbor graph. IEEE Trans. Pattern Anal. Mach. Intell. 28(11), 1875–1881 (2006)
Friedman, J.H., Bentley, J.L., Finkel, R.A.: An algorithm for finding best matches in logarithmic expected time. ACM Trans. Math. Softw. (TOMS) 3(3), 209–226 (1977)
Guttman, A.: R-trees: A dynamic index structure for spatial searching, vol. 14. ACM (1984)
Hautamäki, V., Kinnunen, T., Fränti, P.: Text-independent speaker recognition using graph matching. Pattern Recogn. Lett. 29(9), 1427–1432 (2008)
Hertzberg, J., Zhang, J., Zhang, L., Rockel, S., Neumann, B., Lehmann, J., Dubba, K.S.R., Cohn, A.G., Saffiotti, A., Pecora, F., Mansouri, M.: The RACE project. KI - Künstliche Intelligenz 28(4), 297–304 (2014). http://dx.doi.org/10.1007/s13218-014-0327-y
Johnson, A., Hebert, M.: Using spin images for efficient object recognition in cluttered 3D scenes. IEEE Trans. Pattern Anal. Mach. Intell. 21(5), 433–449 (1999)
Kasaei, S.H., Oliveira, M., Lim, G.H., Lopes, L.S., Tomé, A.M.: Interactive open-ended learning for 3d object recognition: An approach and experiments. J. Intell. Robotic Syst., 1–17 (2015)
Kriegeskorte, N., Mur, M., Ruff, D.A., Kiani, R., Bodurka, J., Esteky, H., Tanaka, K., Bandettini, P.A.: Matching categorical object representations in inferior temporal cortex of man and monkey. Neuron 60(6), 1126–1141 (2008)
Lai, K., Bo, L., Ren, X., Fox, D.: A large-scale hierarchical multi-view rgb-d object dataset. In: 2011 IEEE International Conference on Robotics and Automation (ICRA), pp. 1817–1824. IEEE (2011)
Lim, G.H., Kim, K.W., Suh, H., Suh, I.H., Beetz, M.: Knowledge-based incremental bayesian learning for object recognition. In: Autonomous Learning Workshop, ICRA (2013)
Lim, G.H., Oliveira, M., Mokhtari Hassanabad, V., Kasaei, S.H., Seabra Lopes, L., Maria Tomé, A.: Interactive teaching and experience extraction for learning about objects and robot activities. In: RO-MAN 2014. IEEE (2014)
Lim, G.H., Suh, I.H., Suh, H.: Ontology-based unified robot knowledge for service robots in indoor environments. IEEE Trans. Syst., Man Cybern., Part A: Syst. Humans 41(3), 492–509 (2011)
Oliveira, M., Lim, G.H., Seabra Lopes, L., Kasaei, S.H., Maria Tomé, A., Chauhan, A.: A perceptual memory system for grounding semantic representations in intelligent service robots. In: IROS 2014. IEEE (2014)
Riesenhuber, M., Poggio, T.: Models of object recognition. Nature Neurosci. 3, 1199–1204 (2000)
Rockel, S., Neumann, B., Zhang, J., Dubba, K.S.R., Cohn, A.G., Konec̆ný, S̆., Mansouri, M., Pecora, F., Saffiotti, A., Günther, M., Stock, S., Hertzberg, J., Tomé, A.M., Pinho, A.J., Lopes, L.S., von Riegen, S., Hotz, L.: An ontology-based multi-level robot architecture for learning from experiences. In: Designing Intelligent Robots: Reintegrating AI II, AAAI Spring Symposium, Stanford, USA, March 2013
Roussopoulos, N., Kelley, S., Vincent, F.: Nearest neighbor queries. In: ACM Sigmod Record. vol. 24, pp. 71–79. ACM (1995)
Seabra Lopes, L., Chauhan, A.: Open-ended category learning for language acquisition. Connection Sci. 20(4), 277–297 (2008)
Sivic, J., Russell, B.C., Zisserman, A., Freeman, W.T., Efros, A.A.: Unsupervised discovery of visual object class hierarchies. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2008, pp. 1–8. IEEE (2008)
Steels, L.: Grounding language through evolutionary language games. In: Steels, L., Hild, M. (eds.) Language Grounding in Robots, pp. 1–22. Springer, US (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Lim, G.H., Oliveira, M., Kasaei, S.H., Lopes, L.S. (2015). Hierarchical Nearest Neighbor Graphs for Building Perceptual Hierarchies. In: Arik, S., Huang, T., Lai, W., Liu, Q. (eds) Neural Information Processing. ICONIP 2015. Lecture Notes in Computer Science(), vol 9490. Springer, Cham. https://doi.org/10.1007/978-3-319-26535-3_74
Download citation
DOI: https://doi.org/10.1007/978-3-319-26535-3_74
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-26534-6
Online ISBN: 978-3-319-26535-3
eBook Packages: Computer ScienceComputer Science (R0)