A Model of Artificial Genotype and Norm of Reaction in a Robotic System

The genes of living organisms serve as large stores of information for replicating their behavior and morphology over generations. The evolutionary view of genetics that has inspired artificial systems with a Mendelian approach does not take into account the interaction between species and with the environment to generate a particular phenotype. In this paper, a genotype model is suggested to shape the relationship with the phenotype and the environment in an artificial system. A method to obtain a genotype from a population of a particular robotic system is also proposed. Finally, we show that this model presents a similar behavior to that of living organisms in what regards the concept of norm of reaction.

[1]  Giorgio Metta,et al.  Real-time model learning using Incremental Sparse Spectrum Gaussian Process Regression. , 2013, Neural networks : the official journal of the International Neural Network Society.

[2]  Andrew M. Sutton,et al.  Genetic Algorithms - A Survey of Models and Methods , 2012, Handbook of Natural Computing.

[3]  Benjamin Recht,et al.  Random Features for Large-Scale Kernel Machines , 2007, NIPS.

[4]  Massimo Pigliucci,et al.  Phenotypic Plasticity: Beyond Nature and Nurture , 2001 .

[5]  L. Cook.  The Genetical Theory of Natural Selection — A Complete Variorum Edition , 2000, Heredity.

[6]  M. Pigliucci.  Genotype–phenotype mapping and the end of the ‘genes as blueprint’ metaphor , 2010, Philosophical Transactions of the Royal Society B: Biological Sciences.

[7]  Martin Fodslette Meiller.  A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning , 1993 .

[8]  P. Alberch.  From genes to phenotype: dynamical systems and evolvability , 2004, Genetica.

[9]  Martin Fodslette Møller,et al.  A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.

[10]  Lalit M. Patnaik,et al.  Genetic algorithms: a survey , 1994, Computer.

[11]  Marko Pfeifer,et al.  An Introduction To Genetic Analysis , 2016 .

[12]  Marco Antonelli,et al.  Learning the visual-oculomotor transformation: Effects on saccade control and space representation , 2015, Robotics Auton. Syst..

[13]  Mitsuo Kawato,et al.  Feedback-Error-Learning Neural Network for Supervised Motor Learning , 1990 .

[14]  Stéphane Doncieux,et al.  Beyond black-box optimization: a review of selective pressures for evolutionary robotics , 2014, Evol. Intell..