Computational materials science and the use of artificial intelligence (AI) and machine learning (ML) methods to mine existing databases have significantly accelerated materials design and discovery in the past few years. In addition, high throughput experiments which involve the use of automated systems and technologies to perform laboratory experiments and data collection without direct human intervention have increased the speed, reproducibility, and cost efficiency for materials synthesis and characterization. With these advances, an emerging challenge concerns the close integration of AI-assisted computation and automated experimentation in a closed loop manner, and how this data might be analyzed and interpreted for subsequent experiment planning. This symposium will provide a platform to discuss the specific opportunities and challenges in building autonomous laboratories and their underlying computational frameworks to make fully autonomous materials discovery a reality. Topics will include the development of novel AI/ML methods, experimental automation for both hardware and software, and high-throughput experimental and computational frameworks. Materials for energy-related applications such as batteries, catalysts, optoelectronics, solar cells, and fuel cells will be highlighted. This symposium intends to inform the broad materials community of the current status and future directions of developing the very promising AI-driven autonomous laboratory.

autonomous research