Advanced materials hold the potential to improve our lives and our world, but traditional methods of discovery are slow and expensive. “Self-driving” laboratories (SDLs) have the power to fast-track materials discovery by using AI and robotics to run lab experiments autonomously. State-of-the-art SDLs require interdisciplinary teams and skillsets that traditional degree-based programs do not provide. To address this gap, the Acceleration Consortium at the University of Toronto presents the Autonomous Systems for Discovery certificate containing short, hands-on courses that will provide familiarity with the terminology, principles, and tools of SDLs.
Participants will start by creating a basic project in self-driving labs using hardware and Python programming. Later courses delve deeper into data science, robotics, and software development, equipping learners to use AI for experiment suggestions, manage materials data, and coordinate complex workflow. They will also learn to apply best practices in software development to create robust, maintainable solutions and minimize frustration.
The program concludes with a project proposal developed and executed at the Acceleration Consortium's training lab, where participants gain hands-on experience with both educational and research-grade equipment. Overall, the certificate provides comprehensive knowledge and skills for multidisciplinary teams in building advanced self-driving labs.