Lawrence Berkeley National Laboratory has built and opened an autonomous artificial intelligence research facility to accelerate materials science discovery.
The A-Lab is focused on finding new materials for sustainable energy, and can process 50 to 100 times more samples than human scientists every day, LBL said Monday.
The closed-loop laboratory uses three robotic arms that work 24/7 to test novel materials and identify which of them should be scientifically pursued further. The robots can can select from and mix nearly 200 powder precursors, such as metal oxides with lithium, iron and nickel.
Data from the automated system is sent to human researchers, as well as the Materials Project, a consortium of multiple countries and institutions that aim to significantly shorten the timeline for inventing new inorganic elements.
“We need materials solutions for things like the climate crisis that we can build and deploy now, because we can’t wait – so we’re trying to break this cycle that is so slow by having machines that correct themselves,” said Gerd Ceder, A-Lab’s principal investigator. “The important thing is not working in parallel, but instead to iterate rapidly, the way scientists operate.”
