North Carolina State University will lead a four-year, $20 million National Science Foundation effort to build a nationwide network of artificial-intelligence-enabled automated laboratories, with partner institutions UNC-Chapel Hill and the Massachusetts Institute of Technology. The project, called Self-Driving Platforms for Experimental co-Design in Chemistry and Materials Science (SPEED), aims to give researchers remote access to robotic experiments that can sharply accelerate chemical and materials discovery.
The SPEED lab falls under the NSF's Programmable Cloud Laboratories program and is led by NC State engineering professor Milad Abolhasani. At UNC-Chapel Hill, chemistry professor Alex Miller heads a team that includes chemistry professors Jillian Dempsey and Erik Alexanian, along with computer science professor Ron Alterovitz. Their work is part of UNC's Sustainable Energy Research Consortium, which Miller directs within the College of Arts and Science.
The initiative extends the growing reach of AI for Science & Research, where autonomous laboratories and machine learning are reshaping how experiments are designed and run. A core goal of SPEED is to make self-driving labs - in which human scientists direct research goals while smart robotics carry out procedures - remotely controllable from anywhere in the country.
Remote Access and Expanding Chemical Reactions
A major UNC contribution will be building the access and control interfaces that let outside researchers use the automated instrumentation at NC State, while also piloting a wider range of chemical reactions than previously attempted in self-driving labs. The idea, according to Miller, is to make advanced research questions accessible to scientists who don't have their own high-end robotic equipment.
"The development of hardware and software tools that enable users that don't have access to advanced instrumentation to test their research ideas could be revolutionary," Miller said. "The individual self-driving lab modules within SPEED can accelerate the process of moving from lead discovery to optimized outcome dramatically - by 100 times or more - by performing experiments in parallel and using machine learning methods to predict the most promising next set of experiments. This combination of accelerated discovery and broad accessibility is really exciting."
The UNC team will also work on the project's science drivers, which include creating more efficient synthetic pathways for high-value specialty chemicals and speeding the translation of next-generation materials into manufacturing for energy-efficient digital displays and other technologies.
Why this matters for Science and Research
Self-driving labs stand to change the pace and geography of experimental science. By allowing researchers to design tests and have them run remotely on robotic platforms, projects that once required in-person access to rare instruments can move forward from anywhere. When those automated workflows are paired with machine learning that selects the most promising next experiments, entire discovery cycles can compress from months to days. For working scientists, this means more time spent on hypothesis-driven inquiry and less on manual benchwork - and the potential to tackle research questions that were previously out of reach.
Your membership also unlocks:
