A main problem in engineering self-organizing systems is to find the respective behavior for the interaction of the components so that the intented behavior emerges. We address this problem in the DEMESOS project. As an outcome of the project, we have just released a first version of our Framework for Evolutionary Design (FREVO). The tool is very generic and can be applied to find a (possibly distributed) solution (i.e. a configuration for a controller) for a defined problem (i.e. a simulation giving a fitness function) using an optimization algorithm. An example of its use was to breed the neural network controllers for an agent-based robot soccer team (see http://wwwu.uni-klu.ac.at/welmenre/papers/fehervari-2009-evolutionary-methods-in-self-organizing-system-design.pdf). FREVO is released under the GPL open source license. The framework, some sample components, and a tutorial can be accessed at the project webpage http://www.frevotool.tk.
No comments:
Post a Comment