Measuring properties of movement in populations of evolved 3D agents

Abstract

Although determining the similarity of genotypes is often employed in artificial life experiments to measure or control diversity, in practical applications we may often be more interested in similarities of phenotypes. The latter may provide information about the effective diversity in a population, and thus it may be more suitable for diversity estimations and diversity-based search algorithms. A phenotype of a simulated creature can be understood as creature's physiology or its behavior-e.g., body kinematics, movement patterns, or gaits. In this paper, we introduce a set of efficient measures which allow for describing the movement of simulated 3D stick creatures. We use these measures to analyze the results of evolutionary optimization of virtual creatures towards four unique behavioral goals. We show that most solutions obtained for each goal occupy distinct areas of the phenotype space. This suggests that measures defined in this paper create a useful behavioral space for movement-related fitness functions. Finally, we use the introduced measures to visualize how the properties of movement change in populations during the course of evolution.

Diversity Control in Evolution of Movement

“…Experiments reported in this paper use the properties of movement from (Komosinski and Miazga, 2019) as the behavioral descriptors of the creatures.…”

“…Unfortunately, traditional measures of movement -which could be used to encourage diversity of movement strategies -are often tied to specific morphologies, such as tetrapods (Biewener, 2006) or hexapods (Full et al, 1991). In our previous work we introduced a set of behavioral measures that can be applied to agents or robots with bodies modeled as graphs (Komosinski and Miazga, 2019), and can also be calculated for solid or soft morphologies. In this paper we use these behavioral measures for the purpose of evolving various behaviors.…”