“AI advisor” helps self-driving labs share control
Peer-Reviewed Publication
Updates every hour. Last Updated: 18-Dec-2025 23:11 ET (19-Dec-2025 04:11 GMT/UTC)
In a paper published today in Nature Chemical Engineering, a team of researchers from the University of Chicago Pritzker School of Molecular Engineering and Argonne National Laboratory outlined an “AI advisor” model that helps humans and machines share the driver’s seat in self-driving labs. Inspired by the software used to help investors trade stocks, the model leverages AI’s data-processing prowess but keeps decisions in the hands of experienced researchers accustomed to making real-time choices using limited datasets. The team demonstrated this approach through synthesizing a mixed ion-electron conducting polymer (MIECP) that showed a 150% increase in mix conducting performance over MIECPs synthesized in traditional labs.
A flutter of blue and yellow darts through a field in late May. Trees, shrubs and summer flowers fill the landscape. A blue-winged warbler is just within reach, with one swift motion it can be gently grasped, banded and studied to understand the health and evolution of one of North America’s most colorful birds. A practice once reserved for scientists, this moment is now possible anywhere in the world thanks to a virtual reality experience developed by scientists at Penn State.