Skip to main content
People Spotlight | Institutional Partnerships

Staff Spotlight - Casey Stone

Casey Stone

Computer Scientist (DSL)

Education:
Bachelor of Science in Biology with minor in Chemistry and Psychology (Indiana University Bloomington), M.S. in Computer Science (University of Chicago)

Hobbies: Painting, workout classes, bowling with friends on her bowling team, weekend hikes and camping trips in the outdoors

Casey Stone, a computer scientist in Argonne National Laboratory’s Data Science & Learning (DSL) division, oversees several robotics projects connected to the Autonomous Discovery Initiative, including overseeing the Rapid Prototyping Laboratory (RPL) for self-driving lab projects.

There was no specific moment where I decided I wanted to be who I am today,” Casey said. I always enjoyed math and science growing up, so I knew I wanted to study something scientific in college.”

Casey explored multiple fields in biology, including nursing, premed, and microbiology, before deciding to study computer science. A Master’s program at the University of Chicago enabled her to combine computer science with her biology background, while also taking new courses such as bioinformatics.

Computer science and biology seemed like a powerful combination which would allow me to still contribute to biological discoveries without having to do all the bench work myself,” she explained.

Casey’s bioinformatics professor at UChicago previously worked at Argonne and helped her make the connections that led to her job today. Her work with Autonomous Discovery Initiative projects involves integrating robotics, scientific instruments, and AI to execute various experiments in a fully autonomous closed-loop. She also runs the Biosciences building’s robotics experimentation platform.

Casey takes the most pride, however, in managing the RPL, which provides a prototyping space for all of Argonne’s self-driving-lab projects. She intends to develop standards for the self-driving labs of the future, believing that self-driving labs and autonomous experimentation can combine AI and robotics to speed up large-scale research. For example, they can train AI to recognize patterns in large data sets, so it can pick experiments with the highest chance of success.

There are many scientific problems today that are too large or too complex for humans to solve through traditional scientific experimentation or work spaces,” Casey said. But setting up a self-driving laboratory can be difficult, especially if you don’t specialize in the skills required to integrate different robots and scientific instruments so they can execute an experimental protocol in a high-throughput manner. That’s the challenge we hope to solve in the Rapid Prototyping Lab.”

Just as she tried multiple options in her STEM journey, Casey advises students to be open to trying different careers before they decide on what they will focus.

It’s normal to be interested in several different subjects and to not know exactly what you want to do with your life at first,” she said. The path to success is often not linear, and it’s OK to try and fail at several things before settling into a career. Along those same lines, it’s also OK to switch careers and continuously search for something that interests you and suits your talents the best. Be open to trying new experiences, do your best, and it will all fall into place.”