Evolving generalist controllers to handle a wide range of morphological variations

TL;DR

This paper introduces a neuro-evolutionary algorithm that produces generalist controllers capable of handling diverse morphological variations in robots, enhancing robustness and adaptability without prior morphological information.

Contribution

It proposes a novel evolutionary method that trains controllers across morphological variations, improving robustness and generalizability in neural network controllers.

Findings

Generalist controllers can manage various morphologies effectively.

Trade-off observed: generalists underperform specialists on specific morphologies.

Method enhances robustness without needing morphological details.

Abstract

Neuro-evolutionary methods have proven effective in addressing a wide range of tasks. However, the study of the robustness and generalizability of evolved artificial neural networks (ANNs) has remained limited. This has immense implications in the fields like robotics where such controllers are used in control tasks. Unexpected morphological or environmental changes during operation can risk failure if the ANN controllers are unable to handle these changes. This paper proposes an algorithm that aims to enhance the robustness and generalizability of the controllers. This is achieved by introducing morphological variations during the evolutionary training process. As a results, it is possible to discover generalist controllers that can handle a wide range of morphological variations sufficiently without the need of the information regarding their morphologies or adaptation of their parameters. We perform an extensive experimental analysis on simulation that demonstrates the trade-off between specialist and generalist controllers. The results show that generalists are able to control a range of morphological variations with a cost of underperforming on a specific morphology relative to a specialist. This research contributes to the field by addressing the limited understanding of robustness and generalizability and proposes a method by which to improve these properties.