How Different Encodings Affect Performance and Diversification when Evolving the Morphology and Control of 2D Virtual Creatures

Abstract

A challenge in evolutionary robotics is the in parallel adaptation of morphologies and controllers. Here, we considered encoding methods for morphogenesis of 2D virtual creatures that can be created from directed trees. Using an evolutionary algorithm, we optimized locomotion in these virtual creatures and compared a direct encoding, an L-System, and two types of encodings that produce neural networks—a Compositional Pattern Producing Network (CPPN) and a Cellular Encoding (CE). We evaluated these encodings based on performance and diversification, and we introduced an OpenAI gym environment as a computationally inexpensive benchmark for exploring morphological evolution. The direct encoding and L-System generated more fit solutions compared to the network strategies. Considering morphological diversity, the direct encoding finds solutions more locally in the morphological search space, the L-System made larger jumps across this search space, and both network approaches also make larger jumps though find fewer solutions in this space. With these results we show how encodings exhibit different characteristics as developmental approaches. Since the genotype-phenotype mapping plays a major role in evolutionary robotics, further modifications using more complex tasks and environments can lead to a better understanding of morphogenesis and thereby improve how morphologies and controllers of robots are evolved.

Topics & Concepts