Sensory Flow Segmentation Using a Resource Allocating Vector Quantizer

  • Fredrik Linåker
  • Lars Niklasson
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1876)


We present a very simple unsupervised vector quantizer which extracts higher order concepts from time series generated from sensors on a mobile robot as it moves through an environment. The vector quantizer is constructive, i.e. it adds new model vectors, each one encoding a separate higher order concept, to account for any novel situation the robot encounters. The number of higher order concepts is determined dynamically, depending on the complexity of the sensed environment, without the need of any user intervention. We show how the vector quantizer elegantly handles many of the problems faced by an existing architecture by Nolfi and Tani, and note some directions for future work.


  1. 1.
    Carpenter G. A., Grossberg S.: ART 2: Self-organization of stable category recognition codes for analog input patterns, Applied Optics (1987) 26: 4919–4930.CrossRefGoogle Scholar
  2. 2.
    Chan C., Vetterli M.: Lossy compression of individual signals based on string matching and one pass codebook design, In Proceedings ICASSP (1995) 2491–2494.Google Scholar
  3. 3.
    Fritzke B.: Vector quantization with a growing and splitting elastic network, In ICANN’93: International Conference on Artificial Neural Networks, Springer (1993) 580–585.Google Scholar
  4. 4.
    Kohonen T.: Self-Organizing Maps (second edition), Springer (1995).Google Scholar
  5. 5.
    Michel O.: Khepera simulator package version 2.0: Freeware mobile robot simulator (1996),
  6. 6.
    Nehmzow U.: Mobile Robotics: A Practical Introduction, Springer (2000).Google Scholar
  7. 7.
    Nolfi S., Tani J.: Extracting Regularities in Space and Time Through a Cascade of Prediction Networks: The Case of a Mobile Robot Navigating in a Structured Environment, Connection Science (1999), 11(2).Google Scholar
  8. 8.
    Platt J.: A Resource-Allocating Network for Function Interpolation, Neural Computation (1991) 3(2): 213–225.CrossRefMathSciNetGoogle Scholar
  9. 9.
    Tani J., Nolfi S.: Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems, In Proc. of the Fifth Int. Conf. on Simulation of Adaptive Behavior, R. Pfeifer, B. Blumberg, J.A. Meyer and S.W. Wilson (Eds.), MIT Press (1998) 270–279.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Fredrik Linåker
    • 1
    • 2
  • Lars Niklasson
    • 1
  1. 1.Department of Computer ScienceUniversity of SkövdeSkövdeSweden
  2. 2.Department of Computer ScienceUniversity of SheffieldSheffieldUK

Personalised recommendations