Machine learning for active matter

Self-assembly enables nature to build complex forms, from multicellular organisms to complex animal structures such as flocks of birds, through the interaction of vast numbers of limited and unreliable individuals. Creating this ability in engineered systems poses challenges in the design of both algorithms and physical systems that can operate at such scales. We report a system that demonstrates programmable self-assembly of complex two-dimensional shapes with a thousand-robot swarm. This was enabled by creating autonomous robots designed to operate in large groups and to cooperate through local interactions and by developing a collective algorithm for shape formation that is highly robust to the variability and error characteristic of large-scale decentralized systems. This work advances the aim of creating artificial swarms with the capabilities of natural ones.

The field of fluid mechanics is rapidly advancing, driven by unprecedented volumes of data from experiments, field measurements, and large-scale simulations at multiple spatiotemporal scales. Machine learning (ML) offers a wealth of techniques to extract information from data that can be translated into knowledge about the underlying fluid mechanics. Moreover, ML algorithms can augment domain knowledge and automate tasks related to flow control and optimization. This article presents an overview of past history, current developments, and emerging opportunities of ML for fluid mechanics. We outline fundamental ML methodologies and discuss their uses for understanding, modeling, optimizing, and controlling fluid flows. The strengths and limitations of these methods are addressed from the perspective of scientific inquiry that considers data as an inherent part of modeling, experiments, and simulations. ML provides a powerful information-processing framework that can augment, and possibly even transform, current lines of fluid mechanics research and industrial applications.