Designing morphologies of soft medical devices using cooperative neuro coevolution

TL;DR

This paper introduces a cooperative neuro coevolution method for designing soft robot morphologies and controllers, demonstrating improved performance over baseline optimization in drug delivery applications.

Contribution

It presents a novel cooperative neuro coevolution approach that encodes morphologies and controllers as neural networks, exploring different collaboration strategies for soft robot design.

Findings

Cooperative neuro coevolution outperforms AFPO in morphology suitability.

Different collaboration methods impact design robustness.

Method achieves higher displacement in soft actuator prototypes.

Abstract

Soft robots have proven to outperform traditional robots in applications related to propagation in geometrically constrained environments. Designing these robots and their controllers is an intricate task, since their building materials exhibit non-linear properties. Human designs may be biased; hence, alternative designing processes should be considered. We present a cooperative neuro coevolution approach to designing the morphologies of soft actuators and their controllers for applications in drug delivery apparatus. Morphologies and controllers are encoded as compositional pattern-producing networks evolved by Neuroevolution of Augmented Topologies (NEAT) and in cooperative coevolution methodology, taking into account different collaboration methods. Four collaboration methods are studied: n best individuals, n worst individuals, n best and worst individuals, and n random individuals. As a performance baseline, the results from the implementation of Age-Fitness Pareto Optimisation (AFPO) are considered. The metrics used are the maximum displacement in upward bending and the robustness of the devices in terms of applying to the same evolved morphology a diverse set of controllers. Results suggest that the cooperative neuro coevolution approach can produce more suitable morphologies for the intended devices than AFPO.