Comparing encodings for performance and phenotypic exploration in evolving modular robots

Frank Veenstra, Emma Hart, Edgar Buchanan, Wei Li, Matteo De Carlo, Ágoston E. Eiben

Abstract: To investigate how encodings influence evolving the morphology and control of modular robots, we compared three encodings: a direct encoding and two generative encodings---a compositional pattern producing network (CPPN) and a Lindenmayer System (L-System). The evolutionary progression and final performance of the direct encoding and the L-System was significantly better than the CPPN. The generative encodings converge quicker than the direct encoding in terms of morphological and controller diversity.