An Introduction to Autonomous Science

February 7-11, 2026

Thomas Michael Menino Convention & Exhibition Center (MCEC)

Boston, MA, USA

An Introduction to Autonomous Science

Autonomous science uses AI to plan, execute and interpret experiments without human intervention. Autonomous science platforms combine three technologies: laboratory robots that perform physical experiments, a machine learning model that predicts results and an AI agent that plans future experiments. This course introduces all three technologies and shows how they fit together into a closed-loop, autonomous system. The course also emphasizes the interfaces between technologies, e.g., how to modify machine learning models for use with a planning agent or the liquid handling challenges that arise from AI-planned experiments. Case studies in biology and chemistry will highlight state-of-the-art automated science systems.

Attendees will learn from instructors who have assembled autonomous science pipelines in biology and chemistry. The course requires only a basic understanding of statistics and laboratory automation. Practitioners with expertise in one technology (e.g., machine learning or lab automation) are encouraged to attend and learn how to combine their knowledge with other parts of an automated science platform.

Who Should Attend?

Bench scientists
Computational scientists
Automation engineers
Team leaders and project managers
Students, postdocs, and faculty

Course Benefits

Learn to combine AI, automation, and machine learning to perform autonomous experiments.
Expand technical leadership skills needed for multidisciplinary teams using autonomous science.
Explore recent developments in AI-driven experimentation.

Course Topics

The “Levels of Autonomy” and the "Plan -> Experiment -> Model" Strategy for AI-Driven Experiments
The Bayesian Optimization Framework for Identifying Optimal Experiments, Including the Explore vs. Exploit Tradeoff
Machine Learning Models Used for Autonomous Science
Automation Challenges Unique to Closed-Loop Experimentation
How to Improve Experiment Planning with Big Data (e.g. genomics or cheminformatics)
Recent Advances in Automated Biology and Chemistry

Instructors

Paul Jensen, PhD
University of Michigan

Paul Jensen is an associate professor of biomedical engineering at the University of Michigan. He leads a research group that builds robot scientists using artificial intelligence, laboratory automation and high-throughput genomics. The Jensen Lab has completed over one million autonomous experiments to understand the oral microbiome. Jensen teaches undergraduate and graduate courses in linear algebra, machine learning, and automated experiment design.

Mark Hendricks, PhD
Whitman College

Mark Hendricks is an associate professor in the Department of Chemistry at Whitman College. His research aims to understand the synthesis of nanomaterials and develop automation tools and artificial intelligence to gain insights into the synthesis of metallic nanocrystals. Hendricks also teaches physical, materials, and general chemistry at Whitman and has developed lab automation modules for the undergraduate chemistry curriculum.

Benjamin David, PhD
University of Michigan

Ben David is an assistant research scientist at the University of Michigan. His research combines laboratory automation, artificial intelligence, and experimental design to build autonomous laboratories. David oversees an automated microbial phenotyping platform within the Jensen Lab in the Department of Biomedical Engineering.