ALife in the Galapagos: Migration Effects on Neuro-Controller Design

The parallelization of evolutionary computation tasks using a coarse-grained approach can be efficiently achieved using the island migration model. Strongly influenced by the theory of punctuated equilibria, such a scheme guarantees an efficient exchange of genetic material between niches, not only accelerating but also improving the evolutionary process. We study the island model computational paradigm in relation to the evolutionary robotics methodology. We let populations of robots evolve in different islands of an archipelago and exchange individuals along allowed migration paths. We show, for the test-case selected, how the exchange of genetic material coming from different islands improves the overall design efficiency and speed, effectively taking advantage of a parallel computing environment to improve the methodology of evolutionary robotics, often criticized for its computational cost.

[1]  John J. Grefenstette,et al.  Genetic algorithms and their applications , 1987 .

[2]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[3]  Erick Cantú-Paz,et al.  Efficient and Accurate Parallel Genetic Algorithms , 2000, Genetic Algorithms and Evolutionary Computation.

[4]  James P. Cohoon,et al.  C6.3 Island (migration) models: evolutionary algorithms based on punctuated equilibria , 1997 .

[5]  S. Gould,et al.  Punctuated equilibria: an alternative to phyletic gradualism , 1972 .

[6]  W. Martin,et al.  Population Structures C 6 . 3 Island ( migration ) models : evolutionary algorithms based on punctuated equilibria , 1997 .

[7]  Dave Cliff,et al.  Challenges in evolving controllers for physical robots , 1996, Robotics Auton. Syst..

[8]  Dario Izzo,et al.  Parallel global optimisation meta-heuristics using an asynchronous island-model , 2009, 2009 IEEE Congress on Evolutionary Computation.

[9]  Randall D. Beer,et al.  Evolving Dynamical Neural Networks for Adaptive Behavior , 1992, Adapt. Behav..

[10]  Marco Dorigo,et al.  Evolving Self-Assembly in Autonomous Homogeneous Robots: Experiments with Two Physical Robots , 2009, Artificial Life.

[11]  Marco Dorigo,et al.  Self-Assembly in Physical Autonomous Robots - the Evolutionary Robotics Approach , 2008, ALIFE.

[12]  Dana S. Richards,et al.  Punctuated Equilibria: A Parallel Genetic Algorithm , 1987, ICGA.

[13]  Dimitris K. Tasoulis,et al.  Parallel differential evolution , 2004, Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753).

[14]  Jeffrey L. Krichmar,et al.  Evolutionary robotics: The biology, intelligence, and technology of self-organizing machines , 2001, Complex..

[15]  Alexander Shapiro,et al.  The Sample Average Approximation Method for Stochastic Discrete Optimization , 2002, SIAM J. Optim..