Abstract
The question of how biological learning and instinctive neural mechanisms interact with each other in the course of development to produce novel, adaptive behaviors was explored via a robotic simulation. Instinctive behavior in the agent was implemented in a hard-wired network which produced obstacle avoidance. Phototactic behavior was produced in two serially connected plastic layers. A self-organizing feature map was combined with a reinforcement learning layer to produce a learning network. The reinforcement came from an internally generated signal. Both the adaptive and fixed networks supplied motor control signals to the robot motors. The sizes of the self-organizing layer, reinforcement layer, and the complexity of the environment were varied and effects on robot phototactic efficiency and accuracy in the mature networks were measured. A significant interaction of the three independent variables was found, supporting the idea that organisms evolve distinct combinations of instinctive and plastic neural mechanisms which are tailored to the demands of the environment in which their species evolved.
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
Skinner, B.: Why I Am Not a Cognitive Psychologist. Behaviorism 5(2), 1–10 (1977)
Watson, J.B.: What is Behaviorism? In: Behaviorism, pp. 6–19. W. W. Norton, New York (1924)
Tinbergen, N.: The hierarchical organization of nervous mechanisms underlying instinctive behaviour. Physiological Mechanisms in Animal Behavior (1950)
Tinbergen, N.: On aims and methods of ethology, pp. 114–137 (1963)
Arkin, R.C.: Behavior-based robotics, p. 491. The MIT Press (1998)
Brooks, R.A.: Cambrian Intelligence the early history of the new aI, p. 199. A bradford book. The MIT press (1999)
Brooks, R.A.: Flesh and machines how robots will change us, vol. 260. Pantheon books (2002)
Hogan, J.A.: Developmental psychobiology and behavioral ecology. In: Blass, E.M. (ed.) Handbook of Behavioral Neurobiology, pp. 63–106. Plenum Publishing, Philadelphia (1988)
Hinde, R.A. (ed.): Animal Behavior, a synthesis of ethology and comparative psychology, 2nd edn. McGraw-Hill Book Company, New York (1970)
Shettleworth, S.J.: Cognition, Evolution, and Behavior. Oxford University Press (2010)
Dunlap, A.S., Stephens, D.W.: Components of change in the evolution of learning and unlearned preference. Proceedings of the Royals Society B, London (2009)
Anastasio, T.J.: Tutorial on neural systems modeling, 1st edn. Sinauer Associates Inc., Sunderland (2010)
Touretzky, D.S., Saksida, L.M.: Skinnerbots. In: Maes, M.M.P., Meyer, J.A., Pollack, J., Wilson, S.W. (eds.) Animals to Animats 4: Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior, pp. 285–294. MIT Press, Cambridge (1996)
Touretzky, D.S., Saksida, L.M.: Operant conditioning in skinnerbots. Adaptive Behavior 5(3/4), 219–247 (1997)
McCelland, J.L., Rumelhart, D.: Parallel distributed processing: explorations in the microstructure of cognition. In: Psychological and Biological Models, vol. 2, p. 611. A bradford book–the MIT press, London, Cambridge (1986)
Gurney, K., Redgrave, P., Prescott, T.J.: A computational model of action selection in the basal ganglia II. Analysis and simulation of behaviour. Biological Cybernetics 84, 411–423 (2001)
Gurney, K., Redgrave, P., Prescott, T.J.: A computational model of action selection in the basal ganglia I. A new functional anatomy. Biological Cybernetics 84, 411–423 (2001)
Lengyel, M., Dayan, P.: Hippocampal contributions to control: The third way. In: Platt, J.C., et al. (eds.) Neural Information Processing Systems Foundation, NIPS 2007, Vancouver, Canada (2007)
Barto, A.G., Sutton, R.S., Anderson, C.W.: Neuronlike adaptive elements can solve difficult learning control problems. IEEE Transactions on Systems, Man and Cybernetics 13, 834–846 (1983)
Kohonen, T.: Self-organized formation of topologically correct feature maps. Biological Cybernetics 43, 59–69 (1982)
Kohonen, T.: Self-organizing maps. Springer, Berlin (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Young, B., Ghirlanda, S., Grasso, F.W. (2012). Parallel Implementation of Instinctual and Learning Neural Mechanisms in a Simulated Mobile Robot. In: Prescott, T.J., Lepora, N.F., Mura, A., Verschure, P.F.M.J. (eds) Biomimetic and Biohybrid Systems. Living Machines 2012. Lecture Notes in Computer Science(), vol 7375. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-31525-1_26
Download citation
DOI: https://doi.org/10.1007/978-3-642-31525-1_26
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-31524-4
Online ISBN: 978-3-642-31525-1
eBook Packages: Computer ScienceComputer Science (R0)