Argonne’s Rapid Prototyping Laboratory helps students prepare for science careers

Efforts paving way for automating lab work with robotics and AI in autonomous discovery

The Rapid Prototyping Laboratory at Argonne National Laboratory is a bright, high-ceilinged room alive with the whir of robotic arms, the hum of 3D printers, and the gust of cooling fans. Young researchers huddle around laptops and workbenches. They program robots, test cameras and sensors, build virtual-reality models of workspaces and print new mechanical attachments.

These college interns, master’s students and Ph.D. candidates are laying the groundwork not only for their own future careers in laboratory science, but for the future of science itself. That’s because the Rapid Prototyping Laboratory is at the heart of an Argonne effort called autonomous discovery, which incorporates robotics, machine learning and artificial intelligence.

Scientists hope that autonomous discovery will speed the rate of scientific discovery while freeing up scientists’ hands and brains to work on tasks that only humans can accomplish.

Interns collaborating, tinkering and prototyping in the Rapid Prototyping Laboratory might design and print a custom attachment so a robotic arm can pick up a delicate petri dish without smashing it, or test cameras that help robots see and avoid obstacles in a lab.

Rafael Vescovi calls these steps ​“microtasks.” Vescovi is a data scientist with the Data Science and Learning division at Argonne, a U.S. Department of Energy laboratory which is managed by the University of Chicago. Vescovi and computational scientist Casey Stone are responsible for helping interns learn and grow during their time at Argonne. They work on ways to implement autonomous systems alongside existing instruments in Argonne’s labs and experiments. Vescovi says that chaining micro-projects together makes the long-term vision of autonomous discovery possible.

He acknowledges that it can be challenging for interns to parachute into such a big project. ​“But working in a group and working on a scientific or on a research and development environment,” he said, ​“I think they get a lot from that.”

Vescovi should know. He joined Argonne as an undergraduate physics student conducting research at the Advanced Photon Source in 2010 and started automating aspects of his experiments to improve efficiency.

Along with teaching students the practical aspects of being a working researcher — like polishing their CVs, turning in weekly reports on time and posting their portfolios online — Vescovi and Stone also encourage students to follow their passion.

The student researchers come from a variety of backgrounds, from biology to computer science to e-sports. They’ve been inspired by everything from great teachers to video games to TV shows like Myth Busters. And their interests show in their research.

If you break it, know how to fix it

Kendrick Xie is a junior at the University of Chicago majoring in computer science. He’s also a competitive gamer. One of his first projects was to program a LoCoBot so he could control it with a PlayStation 4 controller.

Xie notes that if you break something in real life, you have to figure out how to fix it. ​“There are no safeguards to keep you from crashing or accidentally jamming the arm into the floor.” His real-life crash test of the robot caused a crack in the robot’s gripper, so he came to the Rapid Prototyping Laboratory to 3D print a new one.

Xie, like many of the interns, was new to 3D printing. But breaking things and learning new skills to fix them are part of the learning process.

Rory Butler says that’s part of the fun of working at the Rapid Prototyping Laboratory. Butler is a computer science Ph.D. candidate doing master’s research in applied robotics at UChicago.

Butler was always interested in robotics. Now he uses virtual reality to build laboratory environments where his teammates test robot functions.

“Having this group of people with a very diverse set of experiences and education allows us to work with each other and accomplish things more quickly,” said Butler. ​“And it’s also a whole lot of fun because if there’s no set way of doing things, then you’re free to explore and try just wild and crazy ideas and see what sticks.”

In pivotal discovery, there is no road map

Casey Stone oversees the Rapid Prototyping Laboratory and works with Vescovi mentoring the interns. With a background in biological sciences, Stone is familiar with the precise and methodical aspects of laboratory research. As an undergraduate, she majored in biology but realized she didn’t enjoy bench science, especially repetitive tasks like pipetting: using a small suction device to transfer liquid samples during experiments. This hand cramping, repetitive motion can occupy a biologist for several hours each day.

“It’s just not my idea of fun,” Stone said. ​“I went back to school for computer science, so that I could also do biology, but maybe not hands-on all day. That’s how I got into automating biology.”

Stone loves the enthusiasm and teamwork she sees when the student researchers attack a challenge. She points out that they rarely find the solution or create the perfect prototype on the first try. ​“Maybe it’s the right solution the fifth time. That’s what the Rapid Prototyping Laboratory is all about. Figuring out that solution.”

Stretching themselves

Although the students’ projects are paving the way for larger discoveries with autonomous discovery, they do have ​“Eureka” moments of their own. Over the summer, Gillian Camacho, Arleen Hidalgo and Halona Dantes worked together to test the findings of a paper on automating experiments for growing E. coli in different nutrient environments.

Camacho is a junior at Penn State studying chemistry and forensics. Hidalgo is a senior at the University of Puerto Rico at Mayaguez studying industrial microbiology. Dantes is a senior at the University of North Carolina at Chapel Hill studying physics. Before coming to Argonne, none of them had significant experience with robotics or programming, but they loved the challenge of stretching outside of their focus areas.

“We all had different areas that we were stronger in. And I think that helped a lot,” said Camacho. ​“We ended up moving pretty quickly once we learned how to communicate with each other.”

They were thrilled the first time they saw their robot run their commands to successfully complete a task. That thrill came not just from witnessing their first successful run, but also from knowing that what they were doing would help researchers achieve a lab-wide goal.

“It’s exciting and it’s something new and we’re contributing for it to get better,” said Hidalgo.

Rafael Vescovi says that the investment that Argonne makes in interns pays off. He has watched several interns grow from beginners to specialists. ​“Once they are trained, there’s always the chance that one of them will stay.”

Argonne is accepting applications for the Robotics & instrumentation Internship Program and other undergraduate and graduate level positions across the lab.

This story originally appeared on the Argonne National Laboratory website.