Tokyo Institute of Technology, Japan
Autonomous Materials Synthesis by Machine Learning and Robotics
Abstract: Future materials-science research will involve autonomous synthesis and characterization, requiring an approach that combines machine learning, robotics, and big data. Here, we highlight our recent experiments in autonomous materials exploration. We show the synthesis and resistance minimization of Nb-doped TiO2 thin films as a proof of concept. The system fully automates sample transfer, thin film deposition, and growth condition optimization—all addressing the physical aspects of fabrication. Combining Bayesian optimization with robotics illustrates how the required speed and volume of a future big-data collection in materials science will be achieved and demonstrate the potential of this approach. We briefly discuss the outlook and significance of these results and discuss a new materials research style to accelerate materials science.
Dr. Taro Hitosugi is a Professor in the School of Materials and Chemical Technology at the Tokyo Institute of Technology (Tokyo Tech). He also serves as a Deputy Director of the Tokyo Tech Academy for Convergence of Materials and Informatics (TAC-MI).
His research interests involve surfaces and interfaces of materials for electronics and energy applications. He has recently succeeded in autonomous materials synthesis by machine learning and robotics, aiming to accelerate materials science research. He is an editorial advisory board member of APL Materials and an associate editor of Science and Technology of Advanced Materials (STAM). He has published more than 150 refereed papers in leading academic journals.