As part of GEVA Week ’08 James Murphy evolved a controller for a Hamster Ball by applying forces to the ball to steer its path through a maze of falling blocks. The number, order, size and direction of the forces to apply were evolved using Grammatical Evolution and ODE adopted as the Physics Engine. The short video demos the application.
Hamster Run with GEVA
Development Team: Michael O'Neill, Erik Hemberg, Conor Gilligan, Eliott Bartley, James McDermott, Jonathan Byrne, Anthony Brabazon
GEVA is an implementation of Grammatical Evolution in Java developed at UCD's Natural Computing Research & Applications group. As well as providing the characteristic genotype-phenotype mapper of GE a search algorithm engine, and GUI are also provided. Currently a variable-length integer encoding Evolutionary Algorithm search engine is provided.
•Download v1.1 Release (Released under GNU GPL)
•GEVA Documentation & Technical Report. Published as a UCD School of Computer Science & Informatics Technical Report UCD-CSI-2008-09
•GEVA Community Google Group and Email list
•GEVA Source Code Code repository
Download Blender Shape Grammar
•Article in SIGEVOlution on GEVA
As part of ODCSSS ’08 John Reddin developed the Elevated Pitch software which used GEVA to automatically compose music. A sample of evolved music is provided.
Elevated Pitch with GEVA
The NCRA group logo was evolved using Grammatical Evolution using a Lindenmayer system grammar and output in the Postscript language. The resulting work was published in IEEE Congress on Evolutionary Computation in 2008. An alternative implementation is provided as a demo problem in GEVA. A poster describing the Logo evolution is provided.
Evolving a Logo Design with GEVA
DrumBalls was the winning project of GEVA Week ’09 by James Murphy. When a Sounder Ball strikes a Drum Ball a drum sound is generated. GE was used to evolve ball motion patterns to generate a desired rhythm. The short video demos the application.
DrumBalls with GEVA
