Evolution of bilateral symmetry in agents controlled by spiking neural networks

We present in this paper three novel developmental models allowing information to be encoded in space and time, using spiking neurons placed on a 2D substrate. In two of these models, we introduce neural development that can use bilateral symmetry. We show that these models can create neural controllers for agents evolved to perform chemotaxis. Neural bilateral symmetry can be evolved and be beneficial for an agent. This work is the first, as far as we know, to present developmental models where spiking neurons are generated in space and where bilateral symmetry can be evolved and proved to be beneficial in this context.

[1]  V. Braitenberg.  Vehicles, Experiments in Synthetic Psychology , 1984 .

[2]  A. R. Palmer.  Symmetry Breaking and the Evolution of Development , 2004, Science.

[3]  D. Parisi,et al.  Phenotypic plasticity in evolving neural networks , 1994, Proceedings of PerAc '94. From Perception to Action.

[4]  Alastair Channon,et al.  A virtual creatures model for studies in artificial evolution , 2005, 2005 IEEE Congress on Evolutionary Computation.

[5]  G. Uhlenbeck,et al.  On the Theory of the Brownian Motion , 1930 .

[6]  Fumiya Iida,et al.  New Robotics: Design Principles for Intelligent Systems , 2005, Artificial Life.

[7]  P. Mazur.  On the theory of brownian motion , 1959 .

[8]  Risto Miikkulainen,et al.  A Taxonomy for Artificial Embryogeny , 2003, Artificial Life.

[9]  Lewis Wolpert.  Development of the asymmetric human , 2005, European Review.

[10]  R. Mazo.  On the theory of brownian motion , 1973 .

[11]  Auke Jan Ijspeert,et al.  Evolution and Development of a Central Pattern Generator for the Swimming of a Lamprey , 1999, Artificial Life.

[12]  erôme Kodjabachian,et al.  Evolution of a Robust Obstacle-AvoidanceBehavior in Khepera : A Comparison ofIncremental and Direct StrategiesJ , 1998 .

[13]  Kyle R. Zander.  Developmental Biology. Eighth edition , 2007, The Yale Journal of Biology and Medicine.

[14]  M. Alexander,et al.  Principles of Neural Science , 1981 .

[15]  Thomas Miconi,et al.  An Improved System for Artificial Creatures Evolution , 2006 .

[16]  Neil Davey,et al.  Adaptive Olfactory Encoding in Agents Controlled by Spiking Neural Networks , 2008, SAB.

[17]  Rufus A. Johnstone,et al.  Generalization and the evolution of symmetry preferences , 1997, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[18]  Robert I. Damper,et al.  The evolutionary emergence of socially intelligent agents , 1998 .

[19]  Frédéric Gruau,et al.  Genetic Synthesis of Modular Neural Networks , 1993, ICGA.

[20]  H. Meinhardt.  Models of biological pattern formation , 1982 .

[21]  Karl Sims,et al.  Evolving 3d morphology and behavior by competition , 1994 .

[22]  Maciej Komosinski,et al.  Comparison of Different Genotype Encodings for Simulated Three-Dimensional Agents , 2002, Artificial Life.

[23]  Xin Yao,et al.  Evolving artificial neural networks , 1999, Proc. IEEE.

[24]  Jean-Arcady Meyer,et al.  Evolution and Development of Modular Control Architectures for 1D Locomotion in Six-legged Animats , 1998, Connect. Sci..

[25]  E. Ruppin.  Evolutionary autonomous agents: A neuroscience perspective , 2002, Nature Reviews Neuroscience.

[26]  J. Thompson,et al.  MOVPE growth for the fabrication of OEICs , 1992 .

[27]  Kenneth O. Stanley,et al.  Compositional Pattern Producing Networks : A Novel Abstraction of Development , 2007 .

[28]  Dario Floreano,et al.  Evolution of Spiking Neural Controllers for Autonomous Vision-Based Robots , 2001, EvoRobots.

[29]  William T. Arthur,et al.  The Origin of Animal Body Plans: A Study in Evolutionary Developmental Biology , 1997 .

[30]  Neil Davey,et al.  Optimal noise in spiking neural networks for the detection of chemicals by simulated agents , 2008, ALIFE.

[31]  Yang Dongyong,et al.  Evolving mobile robot controllers using evolutionary algorithms , 2002, Proceedings of the 41st SICE Annual Conference. SICE 2002..

[32]  D'arcy W. Thompson.  On Growth and Form , 1945 .

[33]  Kenneth O. Stanley,et al.  Generating large-scale neural networks through discovering geometric regularities , 2007, GECCO '07.

[34]  Phil Husbands,et al.  Evolutionary robotics , 2014, Evolutionary Intelligence.

[35]  David Filliat,et al.  Incremental Evolution of Neural Controllers for Navigation in a 6-legged Robot , 1999 .

[36]  Jean-Arcady Meyer,et al.  Evolution and development of neural controllers for locomotion, gradient-following, and obstacle-avoidance in artificial insects , 1998, IEEE Trans. Neural Networks.

[37]  R. I. DamperImage.  Evolving Novel Behaviors via Natural Selection , 1998 .

[38]  Dario Floreano,et al.  Neuroevolution: from architectures to learning , 2008, Evol. Intell..

[39]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.

[40]  Gregory S. Hornby,et al.  Body-brain co-evolution using L-systems as a generative encoding , 2001 .