NEAT and HyperNEAT based Design for Soft Actuator Controllers

TL;DR

This paper presents an automated controller design method for soft actuators using Neuroevolution techniques, demonstrating NEAT's superior performance and simplicity over traditional genetic algorithms across various morphologies.

Contribution

It introduces a novel application of NEAT and HyperNEAT for soft actuator controller design, comparing their effectiveness against standard genetic algorithms.

Findings

NEAT outperformed HyperNEAT and SGA in all tested scenarios.

Neuroevolution methods produced simpler, more implementable networks.

The approach was effective for both high- and low-performing morphologies.

Abstract

Since soft robotics are composed of compliant materials, they perform better than conventional rigid robotics in specific fields, such as medical applications. However, the field of soft robotics is fairly new, and the design process of their morphology and their controller strategies has not yet been thoroughly studied. Consequently, here, an automated design method for the controller of soft actuators based on Neuroevolution is proposed. Specifically, the suggested techniques employ Neuroevolution of Augmenting Topologies (NEAT) and Hypercube-based NEAT (HyperNEAT) to generate the synchronization profile of the components of a simulated soft actuator by employing Compositional Pattern Producing Networks (CPPNs). As a baseline methodology, a Standard Genetic Algorithm (SGA) was used. Moreover, to test the robustness of the proposed methodologies, both high- and low-performing morphologies of soft actuators were utilized as testbeds. Moreover, the use of an affluent and a more limited set of activation functions for the Neuroevolution targets was tested throughout the experiments. The results support the hypothesis that Neuroevolution based methodologies are more appropriate for designing controllers that align with both types of morphologies. In specific, NEAT performed better for all different scenarios tested and produced more simplistic networks that are easier to implement in real life applications.