AI, Automation, and Autonomous Experimentation for Materials Discovery

Undergraduate / Graduate

This course introduces students to the principles and practice of AI-guided, automated, and autonomous experimentation for materials discovery. As materials research faces urgent challenges in sustainability, energy, and health, traditional trial-and-error approaches are often too slow and inefficient. Advances in laboratory automation, data-driven decision-making, and closed-loop experimentation provide new ways to explore experimental spaces more systematically, efficiently, and reproducibly. The course teaches the core foundations and practical toolbox for AI-driven experimentation, including laboratory automation, integration, design of experiments, representation of experiments and data, and AI/ML methods for experimental decision-making. Representative case studies drawn from molecular engineering, spanning polymers, chemistry, energy materials, and characterization workflows, are used to guide students through real AI-enabled experimental scenarios. Rather than focusing on building robotic systems or developing new machine learning architectures, the course emphasizes experimental judgment, decision logic, and effective human-in-the-loop control in AI-driven automated workflows for materials discovery.