High-Throughput Automation and AI Accelerate New Material Development

High-throughput lab automation systems are well established for dramatically accelerating the development of novel pharmaceutical treatments and other functional chemicals. More recently, this technology has been directed to energy storage applications, including synthesis and characterization of electrode materials, electrolytes, catalyst inks, and more. These advances have involved the evolution of existing technologies and creation of new capabilities specific to material development applications.<br/><br/>By combining the inherent characteristics of lab automation, including high accuracy and precision, and capture of structured data with advances in software interoperability, such as open APIs and widespread use of Python, researchers are now able to develop and train ML/AI models more easily for their specific research goals. These models have also been used to direct automated systems to perform the desired experiments, including in fully autonomous systems.<br/><br/>This presentation will include examples of key hardware and software capabilities that have been applied to high-throughput material development workflows. It will also address challenges and important factors to consider when implementing new automated systems, such as self-driving labs.