Autonomous robotic searching and assembly of two-dimensional crystals to build van der Waals superlattices

Abstract

Van der Waals heterostructures are comprised of stacked atomically thin two-dimensional crystals and serve as novel materials providing unprecedented properties. However, the random natures in positions and shapes of exfoliated two-dimensional crystals have required the repetitive manual tasks of optical microscopy-based searching and mechanical transferring, thereby severely limiting the complexity of heterostructures. To solve the problem, here we develop a robotic system that searches exfoliated two-dimensional crystals and assembles them into superlattices inside the glovebox. The system can autonomously detect 400 monolayer graphene flakes per hour with a small error rate (<7%) and stack four cycles of the designated two-dimensional crystals per hour with few minutes of human intervention for each stack cycle. The system enabled fabrication of the superlattice consisting of 29 alternating layers of the graphene and the hexagonal boron nitride. This capacity provides a scalable approach for prototyping a variety of van der Waals superlattices.

Various Structures of 2D Transition‐Metal Dichalcogenides and Their Applications

“…On the basis of an analogous idea, Li et al have also developed a simple “photolithographic‐pattern‐transfer” technique that is able to fabricate complicated FET devices under the assistance of only an ordinary light source and an optical microscope . In addition, Masubuchi et al reported a fully automatic setup to stack heterostructures that possess higher stability than the artificial assembly …”

Determining optical constants of 2D materials with neural networks from multi-angle reflectometry data

“…The developed neural-network based refractive estimator can easily be extended to 2D materials with multiple layers. In that case, the learning system can also predict the number of layers of those 2D materials, similar to [3][4][5][6].…”

“…With the availability of open-source and easy to use libraries [1,2] and graphics processing units at affordable prices, researchers from various disciplines of science and engineering are using artificial neural networks to learn from and make predictions on data in various forms. Optical material characterization based on reflectometry (or ellipsometry) data is one of these applications, where deep learning has been implemented to identify two-dimensional (2D) nanostructures [3][4][5][6] and to obtain optical constants of particles [7], thin films [8,9], solutions [10], tissues [11], and soils [12]. This work focuses on determining optical constants of atomically thin layered materials as follows.…”

“…Hence, the method used for optical property extraction should be not only accurate but also efficient. As previously mentioned [3][4][5][6][7][8][9][10][11], deep learning is a promising field for this very purpose, which can be used in two different ways: regression [8] or classification [12,19]. Since previous regression based Original content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence.…”

Deep-learning-based image segmentation integrated with optical microscopy for automatically searching for two-dimensional materials

“…In the field of two-dimensional (2D) materials 20,21,22,23 , the recent advent of autonomous robotic assembly systems has enabled high-throughput searching for exfoliated 2D materials and their subsequent assembly into van der Waals heterostructures 24 . These developments were bolstered by an image recognition algorithm for detecting 2D materials on SiO2/Si substrates 24,25 ; however, current implementations have been developed on the framework of conventional rule-based image processing 26,27 , which uses traditional handcrafted image features such as color contrast, edges, and entropy 24,25 . Although these algorithms are computationally inexpensive, the detection parameters need to be adjusted by experts, with retuning required when the microscopy conditions change.…”