This article is written by Tyler Irving and originally appeared on U of T's Engineering News.

At the University of Toronto and elsewhere, self-driving labs are promising to dramatically speed up the search for new materials. Now, a new robotic system designed and built by U of T Engineering undergraduate students could help lower the barriers to this kind of research.

“As these million-dollar tools spin up, we run the risk of freezing out those who want to participate in the scientific process, but who aren’t fortunate enough to be at a top-tier research institution,” says Professor Jason Hattrick-Simpers (MSE), who supervised the project.

“Our focus was: can we create a self-driving lab that is affordable and could be distributed to as many individuals as possible, so that we can ensure equity in science?”

Graduating student Kyrylo Kalashnikov (MechE 2T5) started working on the project in the summer after his first year. He ended up continuing work on the project throughout his entire undergraduate degree, and was joined later on by fellow student Robert Hou (Year 3 MechE).

“The first iteration was actually built out of Lego,” says Kalashnikov.

“Obviously we had to move on from that for the next three iterations, but we kept the idea of making it modular, with components that can be swapped in or out depending on what you are trying to do.”

Self-driving labs are an emerging paradigm designed to automate and accelerate the process of searching through large numbers of potential materials to find the ones that are best suited to a given task.

They rely on computer models and algorithms that can virtually crawl through huge libraries of known or possible materials, identifying those most likely to have the desired properties.

The best candidates are then synthesized and tested in real life — not by hand, but by sophisticated robotic systems that can run around the clock. The results of those high-throughput tests are then fed back into the model for another iteration, until eventually the system converges on an optimal solution.

Self-driving labs are central to the mission of U of T’s Acceleration Consortium (AC), a global community dedicated to accelerating scientific discovery with AI and automation. In fact, it was an innovation from one of the AC’s labs that inspired the student project.

“Our focus with this system was on electrochemistry, which is relevant for designing things like new materials that can resist corrosion, or new electrolytes for batteries or fuel cells,” says Hattrick-Simpers, who is a member of the Acceleration Consortium’s scientific leadership team.

“One of the most expensive components of a system like that is a tool called a potentiostat, which can cost tens of thousands of dollars just by itself. But Professor Alán Aspuru-Guzik and his team at the Acceleration Consortium have designed an innovative, low-cost potentiostat, which we were then able to use in our version.”

The rest of the system the students designed was built from off-the-shelf parts; Kalashnikov estimates its total cost at under $500. The system repurposes a consumer 3-D-printer gantry, adds aquarium-grade pumps for liquid handling, a dual-servo gripper for electrode transfer, and a handful of 3-D-printed brackets and baths.

All of these actions are controlled by custom, open-source software. That software, along with the computer-aided design files, electrical schematics and firmware are posted for free on GitHub.

“The target audience for something like this is people who are really excited to get into science and engineering, but who don’t have access to expensive tools,” says Kalashnikov.

“That basically describes me in high school. I remember trying to build my own self-driving car and finding a lot of what I needed in open-source repositories online. It was the only way for me to learn, because I didn’t know anyone else could teach me.  

“Throughout the three years of this project, I just kept thinking that there was somebody else like me out there who might want to learn and build these cool things, and who would benefit from this project. Now, they can do that.”

For his part, Hattrick-Simpers says that he is integrating the new system as part of a course he teaches: MSE 403/1003 Advanced AI for Self-Driving Labs. But he’s also excited for the larger community to take the idea and run with it.

“There is a potential that if we can have a couple of these tools floating around in the world, we could create even little ‘internet of scientific things’ around them,” he says.

“Having these distributed tools and their users interact with one another can help build up a really robust community around self-driving labs, which in turn will drive forward scientific innovation.”