Impact of neuron models and network structure on evolving modular robot neural network controllers

This paper investigates the properties required to evolve Artificial Neural Networks for distributed control in modular robotics, which typically involves non-linear dynamics and complex interactions in the sensori-motor space. We investigate the relation between macro-scale properties (such as modularity and regularity) and micro-scale properties in Neural Network controllers. We show how neurons capable of multiplicative-like arithmetic operations may increase the performance of controllers in several ways whenever challenging control problems with non-linear dynamics are involved. This paper provides evidence that performance and robustness of evolved controllers can be improved by a combination of carefully chosen micro- and macro-scale neural network properties.

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

[2]  Kenneth O. Stanley,et al.  On the Performance of Indirect Encoding Across the Continuum of Regularity , 2011, IEEE Transactions on Evolutionary Computation.

[3]  Frédéric Gruau,et al.  Modular Genetic Neural Networks for Six-Legged Locomotion , 1995, Artificial Evolution.

[4]  Christof Koch,et al.  Biophysics of Computation: Information Processing in Single Neurons (Computational Neuroscience Series) , 1998 .

[5]  David E. Rumelhart,et al.  Product Units: A Computationally Powerful and Biologically Plausible Extension to Backpropagation Networks , 1989, Neural Computation.

[6]  Karl Sims,et al.  Evolving virtual creatures , 1994, SIGGRAPH.

[7]  Vivien A. Casagrande,et al.  Biophysics of Computation: Information Processing in Single Neurons , 1999 .

[8]  L. Buşoniu.  Evolutionary function approximation for reinforcement learning , 2006 .

[9]  Gregory Hornby,et al.  Measuring, enabling and comparing modularity, regularity and hierarchy in evolutionary design , 2005, GECCO '05.

[10]  Josh C. Bongard.  Spontaneous evolution of structural modularity in robot neural network controllers: artificial life/robotics/evolvable hardware , 2011, GECCO '11.

[11]  Kenneth O. Stanley,et al.  A Hypercube-Based Encoding for Evolving Large-Scale Neural Networks , 2009, Artificial Life.

[12]  Nikolaus Hansen,et al.  A restart CMA evolution strategy with increasing population size , 2005, 2005 IEEE Congress on Evolutionary Computation.

[13]  Kenneth O. Stanley,et al.  Constraining connectivity to encourage modularity in HyperNEAT , 2011, GECCO '11.

[14]  Masoud Nikravesh,et al.  Feature Extraction: Foundations and Applications (Studies in Fuzziness and Soft Computing) , 2006 .

[15]  Michael Schmitt,et al.  On the Complexity of Computing and Learning with Multiplicative Neural Networks , 2002, Neural Computation.

[16]  Geoffrey E. Hinton,et al.  A general framework for parallel distributed processing , 1986 .

[17]  U. Alon,et al.  Spontaneous evolution of modularity and network motifs. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[18]  Herbert Jaeger,et al.  A tutorial on training recurrent neural networks , covering BPPT , RTRL , EKF and the " echo state network " approach - Semantic Scholar , 2005 .

[19]  Hod Lipson,et al.  Principles of modularity, regularity, and hierarchy for scalable systems , 2007 .

[20]  Masoud Nikravesh,et al.  Feature Extraction - Foundations and Applications , 2006, Feature Extraction.

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

[22]  Thomas Schmickl,et al.  A Hormone-Based Controller for Evaluation-Minimal Evolution in Decentrally Controlled Systems , 2012, Artificial Life.

[23]  Julian Francis Miller,et al.  Cartesian genetic programming , 2010, GECCO.

[24]  Thomas Schmickl,et al.  Coupled inverted pendulums: a benchmark for evolving decentral controllers in modular robotics , 2011, GECCO '11.

[25]  Serge Kernbach,et al.  Symbiotic Multi-Robot Organisms - Reliability, Adaptability, Evolution , 2010, Cognitive Systems Monographs.