chapter

Adaptive behavior control with self-regulating neurons

Authors:

Frank PasemannAuthors Info & Claims

50 years of artificial intelligence: essays dedicated to the 50th anniversary of artificial intelligence

January 2007

Pages 196 - 205

Published: 01 January 2007 Publication History

Abstract

It is claimed that synaptic plasticity of neural controllers for autonomous robots can enhance the behavioral properties of these systems. Based on homeostatic properties of so called self-regulating neurons, the presented mechanism will vary the synaptic strength during the robot interaction with the environment, due to driving sensor inputs and motor outputs. This is exemplarily shown for an obstacle avoidance behavior in simulation.

References

[1]

Ashby, W.R.: Design for a Brain: The Origin of Adaptive Behavior, 2nd edn. Chapman and Hall, London (1960)

[2]

Braitenberg, V.: Vehicles: Experiments in Synthetic Psychology. MIT Press, Cambridge, MA (1984)

[3]

Beer, R.: A dynamical systems perspective on agent environment interaction. Artificial Intelligence 72, 173-215 (1995)

Digital Library

[4]

Cannon, W.: The Wisdom of the Body. Norton, New York (1932)

[5]

Der, R., Liebscher, R.: True autonomy from self-organized adaptivity. In: Proceedings of the EPSRC/BBSRC International Workshop on Biologically-Inspired Robotics: The Legacy of Grey Walter, Bristol (2002)

[6]

Di Paolo, E.A.: Organismically-inspired robotics: Homeostatic adaptation and natural teleology beyond the closed sensorimotor loop. In: Murase, K., Asakura, T. (eds.) Dynamical Systems Approach to Embodiment and Sociality, Advanced Knowledge International, Adelaide, pp. 19-42 (2003)

[7]

Hülse, M., Pasemann, F.: Dynamical neural Schmitt trigger for robot control. In: Dorronsoro, J.R. (ed.) ICANN 2002. LNCS, vol. 2415, pp. 783-788. Springer, Heidelberg (2002)

Digital Library

[8]

Hülse, M., Wischmann, S., Pasemann, F.: Structure and function of evolved neurocontrollers for autonomous robots, Special Issue on Evolutionary Robotics. Connection Science 16, 249-266 (2004)

[9]

Michel, O.: Khepera Simulator Package version 2.0: Freeware Khepera simulator, downloadable at http://wwwi3s.unice.fr/~om/khep-sim.html

[10]

Nolfi, S., Floreano, D.: Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines. MIT Press, Cambridge, MA (2000)

Digital Library

[11]

Pasemann, F.: Dynamics of a single model neuron. International Journal of Bifurcation and Chaos 2, 271-278 (1993)

[12]

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

[13]

Pfeifer, R., Bongard, J.: How the body shapes the way we think. MIT Press, Cambridge, MA (2007)

Digital Library

[14]

Turrigiano, G.G.: Homeostatic plasticity in neuronal networks: the more things change, the more they stay the same. Trends in Neuroscience 22, 221-227 (1999)

[15]

Williams, H.: Homeostatic plasticity in recurrent neuronal networks. In: Schaal, S., et al. (eds.) From Animals to Animats 8, MIT Press, Cambridge, MA (2004)

Cited By

Pasemann F(2013)Self-regulating neurons in the sensorimotor loopProceedings of the 12th international conference on Artificial Neural Networks: advances in computational intelligence - Volume Part I10.1007/978-3-642-38679-4_48(481-491)Online publication date: 12-Jun-2013
https://dl.acm.org/doi/10.1007/978-3-642-38679-4_48

Adaptive behavior control with self-regulating neurons

Recommendations

Self-organized two-state membrane potential transitions in a network of realistically modeled cortical neurons

Recent studies have revealed that in vivo cortical neurons show spontaneous transitions between two subthreshold levels of the membrane potentials, 'up' and 'down' states. The neural mechanism of generating those spontaneous states transitions, however, ...
Model of oscillatory activity in thalamic neurons: Role of voltage- and calcium-dependent ionic conductances

This paper describes a computer modeling study of the generation of 10 Hz oscillations in the electrical activity of guinea pig thalamic neurons in vitro. The computer model was based on experimental evidence suggesting that single thalamic neurons in ...
Self-organization of Hebbian synapses in Hippocampal neurons
NIPS'90: Proceedings of the 4th International Conference on Neural Information Processing Systems

We are exploring the significance of biological complexity for neuronal computation. Here we demonstrate that Hebbian synapses in realistically-modeled hippocampal pyramidal cells may give rise to two novel forms of self-organization in response to ...

Comments

Information & Contributors

Information

Published In

cover image Guide books

50 years of artificial intelligence: essays dedicated to the 50th anniversary of artificial intelligence

January 2007

398 pages

ISBN:3540772952

Editors:
Max Lungarella
University of Zurich, Artificial Intelligence Laboratory, Zurich, Switzerland
,
Rolf Pfeifer
University of Zurich, Artificial Intelligence Laboratory, Zurich, Switzerland
,
Fumiya Iida
Massachusetts Institute of Technology, Robot Locomotion Group Computer Science and Artificial Intelligence Laboratory, Cambridge, MA
,
Josh Bongard
University of Vermont, Department of Computer Science, Burlington, VT

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 01 January 2007

Qualifiers

Chapter

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
3
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 18 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Pasemann F(2013)Self-regulating neurons in the sensorimotor loopProceedings of the 12th international conference on Artificial Neural Networks: advances in computational intelligence - Volume Part I10.1007/978-3-642-38679-4_48(481-491)Online publication date: 12-Jun-2013
https://dl.acm.org/doi/10.1007/978-3-642-38679-4_48

View Options

View options

Figures

Tables

Media

View Table of Conten