Seeking Quality Diversity in Evolutionary Co-design of Morphology and Control of Soft Tensegrity Modular Robots

TL;DR

This paper explores algorithmic strategies to enhance the quality and diversity of co-evolved morphologies and controllers in soft tensegrity modular robots, aiming to improve task performance and design variety.

Contribution

It introduces a novel Double Map MAP-Elites algorithm that co-evolves morphologies and controllers with enhanced diversity, outperforming existing methods in design illumination.

Findings

DM-ME provides a richer pool of robotic designs.

ViE-NEAT outperforms MAP-Elites in goal-reaching.

DM-ME excels in diversity across tasks.

Abstract

Designing optimal soft modular robots is difficult, due to non-trivial interactions between morphology and controller. Evolutionary algorithms (EAs), combined with physical simulators, represent a valid tool to overcome this issue. In this work, we investigate algorithmic solutions to improve the Quality Diversity of co-evolved designs of Tensegrity Soft Modular Robots (TSMRs) for two robotic tasks, namely goal reaching and squeezing trough a narrow passage. To this aim, we use three different EAs, i.e., MAP-Elites and two custom algorithms: one based on Viability Evolution (ViE) and NEAT (ViE-NEAT), the other named Double Map MAP-Elites (DM-ME) and devised to seek diversity while co-evolving robot morphologies and neural network (NN)-based controllers. In detail, DM-ME extends MAP-Elites in that it uses two distinct feature maps, referring to morphologies and controllers respectively, and integrates a mechanism to automatically define the NN-related feature descriptor. Considering the fitness, in the goal-reaching task ViE-NEAT outperforms MAP-Elites and results equivalent to DM-ME. Instead, when considering diversity in terms of "illumination" of the feature space, DM-ME outperforms the other two algorithms on both tasks, providing a richer pool of possible robotic designs, whereas ViE-NEAT shows comparable performance to MAP-Elites on goal reaching, although it does not exploit any map.