Autonomous Robotic Mechanical Exfoliation of Two-Dimensional Semiconductors Combined with Bayesian Optimization

Abstract

Simple mechanical exfoliation of layered materials is the most frequently employed method for producing high-quality monolayers of two-dimensional semiconducting materials. However, mechanical exfoliation by human hands is a microscopically sophisticated process with a large number of microscopic parameters, which requires significant operator efforts and limits the reproducibility in achieving high-quality and large-area monolayer semiconducting materials. Herein, we have proposed a strategy for mechanical exfoliation by combining a developed robotic system and Bayesian optimization. We demonstrated that it is possible to explore the optimized experimental conditions among a large number of parameter combinations for mechanical exfoliation in a relatively small number of experimental trials. The entire mechanical exfoliation process, from preparation to detection of monolayer semiconductors, can be performed by a developed robotic system. Moreover, the robot system can autonomously explore the optimized experimental conditions among a huge number of parameter sets implanted on the Bayesian optimization algorithm. The optimized experimental condition was determined through only 30 trials of mechanical exfoliation experiments, representing 0.25% of all experimental parameter conditions. As a result, the critical parameters for the efficient fabrication of large-area monolayer WSe2 were elucidated.