Navigating micro- and nano-motors/swimmers with machine learning: Challenges and future directions

Abstract

Micro-/nano-motors (MNMs) or swimmers are minuscule machines that can convert various forms of energy, such as chemical, electrical, or magnetic energy, into motion. These devices have attracted significant attention owing to their potential application in a wide range of fields such as drug delivery, sensing, and microfabrication. However, owing to their diverse shapes, sizes, and structural/chemical compositions, the development of MNMs faces several challenges, such as understanding their structure-function relationships, which is crucial for achieving precise control over their motion within complex environments. In recent years, machine learning techniques have shown promise in addressing these challenges and improving the performance of MNMs. Machine learning techniques can analyze large amounts of data, learn from patterns, and make predictions, thereby enabling MNMs to navigate complex environments, avoid obstacles, and perform tasks with higher efficiency and reliability. This review introduces the current state-of-the-art machine learning techniques in MNM research, with a particular focus on employing machine learning to understand and manipulate the navigation and locomotion of MNMs. Finally, we discuss the challenges and opportunities in this field and suggest future research directions.