There are multiple challenges to developing autonomous microscopy. It requires a balance between the workflows, development of task-specific machine-learning methods, understanding of the interplay between physics discovery and machine learning and end-to-end definition of the discovery workflows. Researchers at Oak Ridge National Laboratory have developed a physics-informed, active learning (AL)-driven autonomous microscopy, which enables active autonomous discovery of physics during real-time experiments. This product is universal to any microscopic technique and can be adapted for application in other experiments, such as chemical syntheses and battery lifetime testing. The software suite comprises active learning algorithms and control software for microscopes and other experimental tools that expedite scientific discovery.
