Evolving Variants of Neuro-Control Using Constraint Masks

The search for variants of effective neural behavior is a major requirement for the identification of novel neuro-dynamical control principles. Evolutionary algorithms are successfully used to search for such controllers. But neuro-evolution tends to find similar, well performing solutions when run multiple times, instead of many, perhaps also weaker performing, but neuro-dynamically highly interesting variants. Furthermore, variants only develop by chance, so that a systematic exploration of different neural control strategies is difficult. With the ICONE method the search space can be shaped by so-called constraint masks (CM) to bias the evolving networks towards specific configurations. On the basis of an animat experiment we demonstrate that the number of evolved distinct variants can be significantly increased using different CMs.

[1]  Helge J. Ritter,et al.  Evolving neural fields for problems with large input and output spaces , 2012, Neural Networks.

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

[3]  Jean-Arcady Meyer,et al.  Simulation of adaptive behavior in animats: review and prospect , 1991 .

[4]  Bruno Sareni,et al.  Fitness sharing and niching methods revisited , 1998, IEEE Trans. Evol. Comput..

[5]  Jean-Arcady Meyer,et al.  Evolution and development of neural controllers for locomotion, gradient-following, and obstacle-avoidance in artificial insects , 1998, IEEE Trans. Neural Networks.

[6]  Kenneth O. Stanley,et al.  Abandoning Objectives: Evolution Through the Search for Novelty Alone , 2011, Evolutionary Computation.

[7]  Dario Floreano,et al.  Neuroevolution: from architectures to learning , 2008, Evol. Intell..

[8]  Stefano Nolfi,et al.  Evolutionary robotics , 2014, Evolutionary Intelligence.

[9]  Risto Miikkulainen,et al.  Robust non-linear control through neuroevolution , 2003 .

[10]  Frank Pasemann,et al.  Structure and function of evolved neuro-controllers for autonomous robots , 2004, Connect. Sci..

[11]  Stéphane Doncieux,et al.  Overcoming the bootstrap problem in evolutionary robotics using behavioral diversity , 2009, 2009 IEEE Congress on Evolutionary Computation.

[12]  Zbigniew Michalewicz,et al.  Variants of Evolutionary Algorithms for Real-World Applications , 2011, Variants of Evolutionary Algorithms for Real-World Applications.

[13]  Frank Pasemann,et al.  An Interactively Constrained Neuro-Evolution Approach for Behavior Control of Complex Robots , 2012, Variants of Evolutionary Algorithms for Real-World Applications.

[14]  D. Parisi,et al.  Growing neural networks , 1991 .

[15]  Stefano Nolfi,et al.  Evolutionary robotics , 1998, Lecture Notes in Computer Science.

[16]  Kenneth O. Stanley,et al.  A novel generative encoding for exploiting neural network sensor and output geometry , 2007, GECCO '07.

[17]  Christian W. Rempis.  Evolving complex neuro-controllers with interactively constrained neuro-evolution , 2012 .

[18]  Jordan B. Pollack,et al.  TITLE : Generative Representations for the Automated Design of Modular Physical Robots , 2003 .

[19]  Samir W. Mahfoud.  Niching methods for genetic algorithms , 1996 .