Evolving Parametric Models Using Genetic Programming with Artificial Selection

Evolutionary methods with artificial selection have been shown to be an effective human-computer technique for exploring design spaces with unknown goals. This paper investigates an interactive evolution of visual programs currently used in popular parametric modelling software. Although parametric models provide a useful cognitive artifact for designers to interact with, they are often bound by their topological structure with the designer left to adjusting (or optimising) metric variables as part of a design search. By allowing the topological structure of the graph to be evolved as well as the parameters, artificial selection can be employed to explore a wider design space more suited to the early design stage.