EvoRobogami: Co-designing with Humans in Evolutionary Robotics Experiments

TL;DR

This paper investigates how human-designed robot configurations influence evolutionary algorithms in robotics, finding that combining human intuition with random solutions enhances performance, especially in intuitive problem spaces.

Contribution

It introduces a method for injecting human-generated designs into evolutionary robotics and assesses their impact on optimization outcomes.

Findings

Balanced initial populations improve results

Human designs benefit intuitive problems

Combining human and random solutions yields best performance

Abstract

We study the effects of injecting human-generated designs into the initial population of an evolutionary robotics experiment, where subsequent population of robots are optimised via a Genetic Algorithm and MAP-Elites. First, human participants interact via a graphical front-end to explore a directly-parameterised legged robot design space and attempt to produce robots via a combination of intuition and trial-and-error that perform well in a range of environments. Environments are generated whose corresponding high-performance robot designs range from intuitive to complex and hard to grasp. Once the human designs have been collected, their impact on the evolutionary process is assessed by replacing a varying number of designs in the initial population with human designs and subsequently running the evolutionary algorithm. Our results suggest that a balance of random and hand-designed initial solutions provides the best performance for the problems considered, and that human designs are most valuable when the problem is intuitive. The influence of human design in an evolutionary algorithm is a highly understudied area, and the insights in this paper may be valuable to the area of AI-based design more generally.