Abstract
The paper proposes a method for visual based self-localisation of a mobile agent in indoor environment. The images acquired by the camera constitute an implicit topological representation of the environment. The environment is a priori unknown and so the implemented architecture is entirely unsupervised. To compare the performance of some self-organising neural networks, a similar neural network architecture of both Self-Organizing Map (SOM) and Growing Neural Gas (GNG) has been realized. Extensive simulations are provided to characterise the effectiveness of the GNG model in recognition speed, classification tasks and in particular topology preserving as compared to the SOM model. This behaviour depends on the following fact: a network (GNG) that adds nodes into map space can approximate the input space more accurately than a network with a predefined structure and size (SOM). The work shows that the GNG network is able to correctly reconstruct the environment topological map.
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
Preview
Unable to display preview. Download preview PDF.
References
M. Daszykowski, B. Walczak and D.L. Massart, “On the Optimal Partitioning of Data with k-Means, Growing K-Means, Neural Gas”, J. Chem. Tnf. Comput. Sci., 42 (2002) 1378–1389.
F. Florez, J.M. Garcia, J. Garcia, A. Hernandez, “Representing 2D objects. Comparison of several self-organizing networks”, 3th WSES Conference on Neural Networks and Applications, Interlaken (2002).
B. Fritzke, “A Growing Neural Gas Networks Learns Topologies”, Advances in Neural Information Processing Systems, 7, Brussels (1995), 625–632
B. Fritzke, “Growing Self-organizing Networks-Why?”, European Symposium on Artificial Neural Network, (1996), 61–72.
GJ. Goodhill and T.J. Sejnowski, “A Unifying Objective Function for Topographic Mapping”, Neural Computation, vol. 9, (1997) 1291–1304.
T. Kohonen, “Self-Organizing Maps”, Springer Verlag, (1995).
S. Marsland, J. Shapiro and U. Nehmzow, “A Self-Organizing Network That Grows When Required”, Neural Networks, vol. 15, (2002), 1041–1058.
T. Martinetz, “Competitive Hebbian Learning Rules Forms Perfectly Topology Preserving Maps”, In the Proceeding of International Conference on Artificial Neural Networks (ICANN’ 93), (1993), 426–438.
T. Martinetz and K. Schulten, “Topology Representing Networks”, Neural Networks, vol. 7, No. 3, (1994), 507–522.
J. Si, S. Lin and M.A. Vuong, “Dynamic Topology Representing Networks”, Neural Networks, vol. 13, (2000), 617–627.
T. Vilmann, R. Der, M. Herrmann and T.M. Martinetz, “Topology Preservation in Self-Organizing Maps: Exact Definition and Measurement”, IEEE Transactions on Neural Networks, vol. 8, No. 2, (March 1997), 256–266.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Baldassarri, P., Puliti, P., Montesanto, A., Tascini, G. (2003). Self-Organizing Maps versus Growing Neural Gas in a Robotic Application. In: Mira, J., Álvarez, J.R. (eds) Artificial Neural Nets Problem Solving Methods. IWANN 2003. Lecture Notes in Computer Science, vol 2687. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44869-1_26
Download citation
DOI: https://doi.org/10.1007/3-540-44869-1_26
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40211-4
Online ISBN: 978-3-540-44869-3
eBook Packages: Springer Book Archive