Neuroevolution of Decentralized Decision-Making in N-Bead Swimmers Leads to Scalable and Robust Collective Locomotion

TL;DR

This paper uses neuroevolution to develop decentralized decision-making policies for microswimmers, resulting in scalable, robust, and efficient locomotion strategies applicable to biological and artificial systems.

Contribution

It introduces a neuroevolution-based method to optimize decentralized control policies for microswimmers, demonstrating emergent efficient swimming gaits and robustness to morphological changes.

Findings

Emergence of long-wavelength body deformations for efficient swimming

Decentralized policies are robust to defects and morphological variations

Applicable to artificial microswimmers for cargo transport and drug delivery

Abstract

Many microorganisms swim by performing larger non-reciprocal shape deformations that are initiated locally by molecular motors. However, it remains unclear how decentralized shape control determines the movement of the entire organism. Here, we investigate how efficient locomotion emerges from coordinated yet simple and decentralized decision-making of the body parts using neuroevolution techniques. Our approach allows us to investigate optimal locomotion policies for increasingly large microswimmer bodies, with emerging long-wavelength body shape deformations corresponding to surprisingly efficient swimming gaits. The obtained decentralized policies are robust and tolerant concerning morphological changes or defects and can be applied to artificial microswimmers for cargo transport or drug delivery applications without further optimization "out of the box". Our work is of relevance to understanding and developing robust navigation strategies of biological and artificial microswimmers and, in a broader context, for understanding emergent levels of individuality and the role of collective intelligence in Artificial Life.