In the Aspuru-Guzik group, our mission is to drastically reduce the cost and time associated with discovering and optimizing functional materials by a factor of ten, transforming a process that typically requires over ten million dollars and ten years into one that can be achieved with one million dollars and in just one year. Our approach to addressing this challenge is the development of fully autonomous, self-driving laboratories.

Self-driving laboratories integrate advanced artificial intelligence (AI) with robotic platforms for the autonomous discovery and optimization of materials. These systems have the potential to dramatically increase the speed of experimentation, fundamentally changing the scientific method. By leveraging interconnected robotic platforms equipped with specialized tools to fine-tune material properties, we aim to unlock novel fabrication strategies and enter previously inaccessible areas of materials discovery.

Developing fully autonomous laboratories is an inherently multidisciplinary endeavor, combining machine learning, materials modeling, robotics, automation, and computer vision. Machine learning algorithms predict material properties and inform new experimental designs, while robotic systems and automated characterization techniques execute experiments and analyze outcomes in real time. Crucially, closing the loop between computational modeling and experimental validation enables the seamless integration of these technologies into a unified platform.

Our Self-driving Lab subgroup explores a wide range of topics, including AI-driven optimization techniques, autonomous robotics systems for performing experiments, and automated characterization methods for data analysis. A growing area of research is the application of computer vision in creating visually-aware robotic systems capable of conducting complex chemical and materials science experiments autonomously.

‍