Phenotypic complexity and evolvability in evolving robots

Abstract

The propensity of evolutionary algorithms to generate compact solutions have advantages and disadvantages. On one side, compact solutions can be cheaper, lighter, and faster than less compact ones. On the other hand, compact solutions might lack evolvability, i.e. might have a lower probability to improve as a result of genetic variations. In this work we study the relation between phenotypic complexity and evolvability in the case of soft-robots with varying morphology. We demonstrate a correlation between phenotypic complexity and evolvability. We demonstrate that the tendency to select compact solutions originates from the fact that the fittest robots often correspond to phenotypically simple robots which are robust to genetic variations but lack evolvability. Finally, we demonstrate that the efficacy of the evolutionary process can be improved by increasing the probability of genetic variations which produce a complexification of the agents’ phenotype or by using absolute mutation rates.

Human Control of Simulated Modular Soft Robots May Predict the Performance of Optimized AI-Based Controllers

“…Whereas the literature has delved into what factors make a physical configuration more or less successful [9,10,11], no work to date has considered how to augment the robot optimization with knowledge from external sources, despite it being common in other fields [12], like test [13] and content generation [14]. Just like most animal lifeforms, humans evolved powerful mental ''world models'' for predicting the future states of the world [15].…”