Skip to main content
Springer Nature Link
Log in

Mathematical Approach to Sensory Motor Control and Memory

  • Chapter
Spatial Temporal Patterns for Action-Oriented Perception in Roving Robots

Part of the book series: Cognitive Systems Monographs ((COSMOS,volume 1))

  • 1067 Accesses

Abstract

In this chapter we provide mathematical models for a general memory structure and for sensory-motor control via perception, detailing on some of the Recurrent Neural Networks (RNNs) introduced in Chapter 4. In the first section we study how individual memory items are stored assuming that situations given in the environment can be represented in the form of synaptic-like couplings in recurrent neural networks (RNN). We provide a theoretical basis concerning the learning process convergence and the network response to novel stimuli. We show that a nD network can learn static and dynamic patterns and can also replicate a sequence of up to n different vectors or frames. Such networks can also perform arithmetic calculations by means of pattern completion. In the second section we introduce a robot platform including the simplest probabilistic sensory and motor layers. Then we use the platform as a test-bed for evaluating the capabilities of robot navigation with different neural networks. We show that the basic robot element, the short-time memory, is the key element in obstacle avoidance. However, in the simplest conditions of no obstacles the straightforward memoryless robot is usually superior in performance. Accordingly, we suggest that small organisms (or agents) with short life-time do not require complex brains and even can benefit from simple brain-like (reflex) structures. In section 3 we propose a memotaxis strategy for target searching, which requires minimal computational resources and can be easily implemented in hardware. The strategy makes use of a dynamical system modeling short time memory which “collects” information on successful steps and corrects decisions made by a gradient strategy. Thus a memotactic robot can take steps against the chemotactic-like sensory gradient. We show (theoretically and experimentally) that the memotaxis strategy effectively suppresses stochasticity observed in the behavior of chemotactic robots in the region of low SNR and provides from 50 to 200% performance gain.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Arras, K., Tomaris, T., Jensen, B., Siegwart, R.: Multisensor on-thefly localization: Precision and reliability for applications. Robotics and Autonomous Systems 34, 131–143 (2001)

    Article  MATH  Google Scholar 

  2. Atick, J., Redlich, N.: Towards a theory of early visual processing. Neural Comput. 2, 308–320 (1990)

    Article  Google Scholar 

  3. Atick, J.: Could information theory provide an ecological theory of sensory processing? Network 3, 213–251 (1992)

    Article  MATH  Google Scholar 

  4. Atick, J., Bialek, W.: Princeton Lectures on Biophysics. World Scientific, Singapore (1992)

    Google Scholar 

  5. Atrash, A., Koening, S.: Probabilistic Planning for Behavior-Based Robot. In: Proc. Flairs Conference, pp. 531–535 (2001)

    Google Scholar 

  6. Atteneave, F.: Some informational aspect of visual perception. Psychol. Rev. 61, 183–193 (1954)

    Article  Google Scholar 

  7. Barlow, H.: Sensory communication. MIT Press, Cambridge (1961)

    Google Scholar 

  8. Beer, R.D.: Toward the evolution of dynamical neural networks for minimally cognitive behavior. In: Maas, P., Mataric, M., Meyer, J., Pollack, J., Wilson, S. (eds.) From animals to animats 4: Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior, pp. 421–429. MIT Press, Cambridge (1996)

    Google Scholar 

  9. Beer, R.D.: The dynamics of active categorical perception in an evolved model agent. Adaptive Behavior 11, 209–243 (2003)

    Article  Google Scholar 

  10. Beer, R.D.: Parameter space structure of continuous-time recurrent neural networks. Neural Computation 18, 3009–3051 (2006)

    Article  MATH  MathSciNet  Google Scholar 

  11. Berg, B.C.: Random Walks in Biology. Princeton Univ. Press, Princeton (1993)

    Google Scholar 

  12. Berg, B.C., Purcell, E.M.: Physics of chemoreception. Biophys. J. 20, 193–219 (1977)

    Article  Google Scholar 

  13. Borenstein, J., Konen, Y.: The vector field histogram - fast obstacle avoidance for mobile robots. IEEE Journal of Robotics and Automation 7(3), 278–288 (1991)

    Article  Google Scholar 

  14. Brooks, R.: A robust layered control system for a mobile robot. IEEE J. Rob. Autom. 2, 14–23 (1986)

    MathSciNet  Google Scholar 

  15. Brooks, A.: Hardware retargetable distributed layered architecture for mobile robot control. In: Proceedings IEEE Robotics and Automation, pp. 106–110 (1987)

    Google Scholar 

  16. Castellanos, N.P., Makarov, V.A., Patane, L., Velarde, M.G.: Sensory-motor neural loop discovering statistical dependences among imperfect sensory perception and motor response. In: Proc. of SPIE, vol. 6592 (2007) doi:10.1117/12.724327

    Google Scholar 

  17. Cruse, H., Hübner, D.: Selforganizing memory: active learning of landmarks used for navigation (in Preparation)

    Google Scholar 

  18. Cruse, H., Sievers, K.: A general network structure for learning Pavlovian paradigms (in Preparation)

    Google Scholar 

  19. Elman, J.L.: Finding structure in time. Cognitive Science 14, 179–211 (1990)

    Article  Google Scholar 

  20. Engelson, S., McDermott, D.: Error correction in mobile robot map learning. In: Proc. of the 1992 IEEE Int. Conf. on Robotics and Automation, pp. 2555–2560 (1992)

    Google Scholar 

  21. Fuster, J.M.: Memory in the Cerebral Cortex: an Empirical Approach to Neural Networks in the Human and Nonhuman Primate. MIT Press, Cambridge (1995)

    Google Scholar 

  22. Grasso, F.W., Consi, T.R., Mountain, D.C., Atema, J.: Biomimetic robot lobster performs chemoorientation in turbulence using a pair of spatially separated sensors: Progress and challenges. Robotics and Autonomous Systems 30, 115–131 (2000)

    Article  Google Scholar 

  23. Hamza, M.H.: Robotics and Applications. In: RA 2006, vol. 210. ACTA Press (2006)

    Google Scholar 

  24. Herrero, M.A.: The mathematics of chemotaxis. Handbook of differential equations 3, 137–1993 (2007)

    Article  MathSciNet  Google Scholar 

  25. Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. 79, 2554–2558 (1982)

    Article  MathSciNet  Google Scholar 

  26. Hopfield, J.J.: Neurons with graded response have collective computational properties like those of two state neurons. Proc. Natl. Acad. Sci. 81, 3088–3092 (1984)

    Article  Google Scholar 

  27. Ishida, H., Kagawa, Y., Nakamoto, T., Moriizumi, T.: Odor-source localization in the clean room by an autonomous mobile sensing system. Sens. Actuators B 33, 115–121 (1996)

    Article  Google Scholar 

  28. Jaeger, H., Haas, H.: Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication. Science 2, 78–80 (2004)

    Article  Google Scholar 

  29. Jaulmes, R., Pineau, J., Precup, D.: Probabilistic robot planning under model uncertainty: an active learning approach. In: NIPS Workshop on Machine Learning Based Robotics in Unstructured Environments (2005)

    Google Scholar 

  30. Kindermann, T., Cruse, H.: MMC – a new numerical approach to the kinematics of complex manipulators. Mechanism and Machine Theory 37, 375–394 (2002)

    Article  MATH  Google Scholar 

  31. Kortenkamp, D., Weymouth, T.: Topological mapping for obile robots using a combination of sonar and vision sensing. In: Proceedings of the AI, pp. 979–984 (1994)

    Google Scholar 

  32. Kühn, S., Beyn, W.J., Cruse, H.: Modelling memory functions with recurrent neural networks consisting of input compensation units: I. Static situations. Biological Cybernetics 96, 455–470 (2007)

    Article  MATH  Google Scholar 

  33. Kühn, S., Cruse, H.: Modelling memory functions with recurrent neural networks consisting of input compensation units: II. Dynamic situations. Biological Cybernetics 96, 471–486 (2007)

    Article  MATH  MathSciNet  Google Scholar 

  34. Kuwana, Y., Nagasawa, S., Shimoyama, I., Kanzaki, R.: Synthesis of the pheromone oriented behaviour of silkworm moths by a mobile robot with moth antennae as pheromone sensors. Biosens. Bioelectron. 14, 195–202 (1999)

    Article  Google Scholar 

  35. Makarov, V.A., Castellanos, N.P., Velarde, M.G.: Simple agents benefits only from simple brains. Trans. Engn., Computing and Tech. 15, 25–30 (2006)

    Google Scholar 

  36. Makarov, V.A., Song, Y., Velarde, M.G., Huber, D., Cruse, H.: Elements for a general memory structure: Properties of recurrent neural networks used to form situation models. Biological Cybern (2008)

    Google Scholar 

  37. Palm, G., Sommer, F.T.: Associative data storage and retrieval in neural networks. In: Domany, E., van Hemmen, J.L., Schulten, K. (eds.) Models of Neural Networks III. Association, Generalization, and Representation, pp. 79–118. Springer, New York (1996)

    Google Scholar 

  38. Pasemann, F.: Complex dynamics and the structure of small neural networks. Network: Computation in Neural Systems 13, 195–216 (2002)

    Article  MATH  Google Scholar 

  39. Russell, R.A., Bab-Hadiashar, A., Shepherd, R., Wallace, G.G.: A comparison of reactive robot chemotaxis algorithms. Rob. Auton. Syst. 45, 83–97 (2003)

    Article  Google Scholar 

  40. Schilling, M., Cruse, H.: The evolution of cognition, from first order to second order embodiment. In: Wachsmuth, I. (ed.) (2008)

    Google Scholar 

  41. Steinkühler, C.H.: A holistic model for an internal representation to control the movement of a manipulator with redundant degrees of freedom. Biol. Cybernetics 79, 457–466 (1998)

    Article  Google Scholar 

  42. Strang, G.: Introduction to Linear Algebra. Wellesley-Cambridge Press (2003)

    Google Scholar 

  43. Tani, J.: Learning to generate articulated behavior through the bottom-up and the top-down interaction processes. Neural Networks 16, 11–23 (2003)

    Article  Google Scholar 

  44. Thrun, S.: Probabilistic algorithms in robotics. AI Magazine 21, 93–109 (2000)

    Google Scholar 

  45. Ulrich, U., Borenstein, J.: Reliable obstacle avoidance for fast mobile robots. In: IEEE Int. Conf. on Robotics and Automation, pp. 1572–1577 (1998)

    Google Scholar 

  46. Vergassola, M., Villermaux, E., Shraiman, B.I.: Infotaxis as a strategy for searching without gradients. Nature 445, 406–409 (2007)

    Article  Google Scholar 

  47. Wessnitzer, J., Webb, B.: Multimodal sensory integration in insects - towards insect brain control architectures. Bioinspiration and Biomimetics 1, 63–75 (2006)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Instituto Pluridisciplinar, Universidad Complutense de Madrid, Paseo Juan XXII 1, 28040, Madrid, Spain

    M. G. Velarde, V. A. Makarov, N. P. Castellanos & Y. L. Song

  2. Dip. di Ingegneria Elettrica, Elettronica e dei Sistemi, Universitá degli Studi di Catania, Viale A. Doria 6, 95125, Catania, Italy

    D. Lombardo

Authors
  1. M. G. Velarde
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. V. A. Makarov
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. N. P. Castellanos
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Y. L. Song
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. D. Lombardo
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Università di Catania, Catania, Italy

    Paolo Arena  & Luca Patanè  & 

Rights and permissions

Reprints and permissions

Copyright information

© 2009 Springer-Verlag Berlin Heidelberg

About this chapter

Cite this chapter

Velarde, M.G., Makarov, V.A., Castellanos, N.P., Song, Y.L., Lombardo, D. (2009). Mathematical Approach to Sensory Motor Control and Memory. In: Arena, P., Patanè, L. (eds) Spatial Temporal Patterns for Action-Oriented Perception in Roving Robots. Cognitive Systems Monographs, vol 1. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-88464-4_5

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-88464-4_5

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-88463-7

  • Online ISBN: 978-3-540-88464-4

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics