Dynamic Resolution in the Co-Evolution of Morphology and Control

Evolutionary robotics is a promising approach to overcoming the limitations and biases of human designers in producing control strategies for autonomous robots. However, most work in evolutionary robotics remains solely concerned with optimizing control strategies for existing morphologies. By contrast, natural evolution, the only process that has produced intelligent agents to date, may modify both the control (brain) and morphology (body) of organisms. Therefore, co-evolving morphology along with control may provide a better path towards realizing intelligent robots. This paper presents a novel method for co-evolving morphology and control using CPPN-NEAT. This method is capable of dynamically adjusting the resolution at which components of the robot are created: a large number of small sized components may be present in some body locations while a smaller number of larger sized components is present in other locations. Advantages of this capability are demonstrated on a simple task, and implications for using this methodology to create more complex robots are discussed.

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

[2]  Frank Dellaert,et al.  Toward an evolvable model of development for autonomous agent synthesis , 1994 .

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

[4]  John Hallam,et al.  Evolving robot morphology , 1997, Proceedings of 1997 IEEE International Conference on Evolutionary Computation (ICEC '97).

[5]  Inman Harvey,et al.  Evolutionary robotics: the Sussex approach , 1997, Robotics Auton. Syst..

[6]  Peter Eggenberger,et al.  Evolving Morphologies of Simulated 3d Organisms Based on Differential Gene Expression , 1997 .

[7]  Jordan B. Pollack,et al.  Automatic design and manufacture of robotic lifeforms , 2000, Nature.

[8]  D. Floreano,et al.  Evolutionary Robotics: The Biology,Intelligence,and Technology , 2000 .

[9]  Jordan B. Pollack,et al.  Evolving L-systems to generate virtual creatures , 2001, Comput. Graph..

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

[11]  R. Pfeifer,et al.  Repeated structure and dissociation of genotypic and phenotypic complexity in artificial ontogeny , 2001 .

[12]  Josh Bongard,et al.  Evolving modular genetic regulatory networks , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

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

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

[15]  Michael L. Anderson.  Embodied Cognition: A field guide , 2003, Artif. Intell..

[16]  R. Pfeifer,et al.  Evolving Complete Agents using Artificial Ontogeny , 2003 .

[17]  Rolf Pfeifer,et al.  How the body shapes the way we think - a new view on intelligence , 2006 .

[18]  Richard K. Belew,et al.  Evolving robot morphology and control , 2006, Artificial Life and Robotics.

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

[20]  Peter Eggenberger-Hotz.  Evolving Morphologies of Simulated 3d Organisms Based on Differential Gene Expression , 2007 .

[21]  Randall D. Beer,et al.  The Dynamics of Brain–Body–Environment Systems , 2008 .

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

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

[24]  Charles Ofria,et al.  The sensitivity of HyperNEAT to different geometric representations of a problem , 2009, GECCO.

[25]  Joshua Evan Auerbach,et al.  Evolving CPPNs to grow three-dimensional physical structures , 2010, GECCO '10.