Evaluating Fitness Averaging Strategies in Cooperative NeuroCoEvolution for Automated Soft Actuator Design

TL;DR

This paper evaluates different fitness averaging strategies in cooperative NeuroCoEvolution to optimize soft robot actuators, demonstrating improved morphology quality and efficiency over previous methods in a drug delivery application.

Contribution

It introduces and tests various fitness averaging methods within cooperative NeuroCoEvolution, showing that weighted mean averaging of top individuals enhances soft actuator design.

Findings

CPPN-NEAT outperforms previous multi-objective optimization in morphology quality.

Weighted mean fitness averaging yields the best results.

The approach reduces computational effort and time.

Abstract

Soft robotics are increasingly favoured in specific applications such as healthcare, due to their adaptability, which stems from the non-linear properties of their building materials. However, these properties also pose significant challenges in designing the morphologies and controllers of soft robots. The relatively short history of this field has not yet produced sufficient knowledge to consistently derive optimal solutions. Consequently, an automated process for the design of soft robot morphologies can be extremely helpful. This study focusses on the cooperative NeuroCoEvolution of networks that are indirect representations of soft robot actuators. Both the morphologies and controllers represented by Compositional Pattern Producing Networks are evolved using the well-established method NeuroEvolution of Augmented Topologies (CPPN-NEAT). The CoEvolution of controllers and morphologies is implemented using the top n individuals from the cooperating population, with various averaging methods tested to determine the fitness of the evaluated individuals. The test-case application for this research is the optimisation of a soft actuator for a drug delivery system. The primary metric used is the maximum displacement of one end of the actuator in a specified direction. Additionally, the robustness of the evolved morphologies is assessed against a range of randomly generated controllers to simulate potential noise in real-world applications. The results of this investigation indicate that CPPN-NEAT produces superior morphologies compared to previously published results from multi-objective optimisation, with reduced computational effort and time. Moreover, the best configuration is found to be CoEvolution with the two best individuals from the cooperative population and the averaging of their fitness using the weighted mean method.