NMODE - Neuro-MODule Evolution.

Modularisation, repetition, and symmetry are structural features shared by almost all biological neural networks. These features are very unlikely to be found by the means of structural evolution of artificial neural networks. This paper introduces NMODE, which is specifically designed to operate on neuro-modules. NMODE addresses a second problem in the context of evolutionary robotics, which is incremental evolution of complex behaviours for complex machines, by offering a way to interface neuro-modules. The scenario in mind is a complex walking machine, for which a locomotion module is evolved first, that is then extended by other modules in later stages. We show that NMODE is able to evolve a locomotion behaviour for a standard six-legged walking machine in approximately 10 generations and show how it can be used for incremental evolution of a complex walking machine. The entire source code used in this paper is publicly available through GitHub.

[1]  Auke Jan Ijspeert,et al.  Central pattern generators for locomotion control in animals and robots: A review , 2008, Neural Networks.

[2]  Frank Pasemann,et al.  NERD Neurodynamics and Evolutionary Robotics Development Kit , 2010, SIMPAR.

[3]  Erwin Coumans,et al.  Bullet physics simulation , 2015, SIGGRAPH Courses.

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

[5]  A. Büschges,et al.  Dynamic simulation of insect walking. , 2004, Arthropod structure & development.

[6]  Frank Pasemann,et al.  Neural control of a modular multi-legged walking machine: Simulation and hardware , 2012, Robotics Auton. Syst..

[7]  Hod Lipson,et al.  Evolved Electrophysiological Soft Robots , 2014, ALIFE.

[8]  Keyan Zahedi,et al.  Linear combination of one-step predictive information with an external reward in an episodic policy gradient setting: a critical analysis , 2013, Front. Psychol..

[9]  Keyan Zahedi,et al.  A Theory of Cheap Control in Embodied Systems , 2014, PLoS Comput. Biol..

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

[11]  Keyan Zahedi,et al.  Self-regulating neurons: a model for synaptic plasticity in artificial recurrent neural networks , 2009 .

[12]  ULF DIECKMANN.  COEVOLUTION AS AN AUTONOMOUS LEARNING STRATEGY FOR NEUROMODULES , 2003 .

[13]  Kenneth O. Stanley,et al.  Picbreeder: A Case Study in Collaborative Evolutionary Exploration of Design Space , 2011, Evolutionary Computation.

[14]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[15]  Joshua Evan Auerbach,et al.  Environmental Influence on the Evolution of Morphological Complexity in Machines , 2014, PLoS Comput. Biol..

[16]  Charles Ofria,et al.  Evolving coordinated quadruped gaits with the HyperNEAT generative encoding , 2009, 2009 IEEE Congress on Evolutionary Computation.

[17]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[18]  Ansgar Büschges,et al.  Deriving neural network controllers from neuro-biological data: implementation of a single-leg stick insect controller , 2011, Biological Cybernetics.

[19]  Thomas Kindermann,et al.  Walknet--a biologically inspired network to control six-legged walking , 1998, Neural Networks.

[20]  Karl Sims,et al.  Evolving 3D Morphology and Behavior by Competition , 1994, Artificial Life.

[21]  J. Clune,et al.  Evolving 3D objects with a generative encoding inspired by developmental biology , 2011, SEVO.

[22]  Sebastian Risi,et al.  An Enhanced Hypercube-Based Encoding for Evolving the Placement, Density, and Connectivity of Neurons , 2012, Artificial Life.

[23]  H. Cruse.  What mechanisms coordinate leg movement in walking arthropods? , 1990, Trends in Neurosciences.

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

[25]  Keyan Zahedi,et al.  AN EVOLVED NEURAL NETWORK FOR FAST QUADRUPEDAL LOCOMOTION , 2007 .