Researchers from North Carolina State University and the University at Buffalo have developed a technology called 'Artificial Chemist,' which incorporates artificial intelligence (AI) and robotics to perform chemical reactions to accelerate the research and development of new commercially desirable materials.
The scientists describe the technology as "a fully autonomous materials development technology" that "helps you find the ideal solution-processed material more quickly than any techniques currently in use."
RELATED: A NEW AI TOOL CAN HELP US FIGHT AI-WRITTEN FAKE NEWS AND REVIEWS
An autonomous robot navigating the "chemical universe"
The researchers behind the 'Artificial Chemist' demonstrated, through proof-of-concept experiments that their machine could identify and produce the best possible quantum dots — colloidal semiconductor nanocrystals typically used in LED screens — for any color in 15 minutes or less. The scope of the machine's work can go far beyond quantum dots, the researchers say.
“Artificial Chemist is a truly autonomous system that can intelligently navigate through the chemical universe,” Milad Abolhasani, the corresponding author of a paper on the work and an assistant professor of chemical and biomolecular engineering at NC State explained in a press release.
“Currently, Artificial Chemist is designed for solution-processed materials – meaning it works for materials that can be made using liquid chemical precursors. Solution-processed materials include high-value materials such as quantum dots, metal/metal oxide nanoparticles, metal organic frameworks (MOFs), and so on.
The Artificial Chemist has a "body", a robotic arm for performing experiments and sensing results, and a "brain" that records the data and then makes a decision, based on that data, of what the next experiment will be.
Mimicking the human thought process with greater efficiency
For their proof-of-concept tests, the researchers demonstrated that the Artificial Chemist platform can run 500 quantum dot synthesis experiments per day, though Abolhasani believes it could run as many as 1,000.
The Artificial Chemist’s AI "brain" determines what chemical reactions will most efficiently allow for the desired material compositions, with specified properties and performance metrics.
“We tried to mimic the process that humans use when making decisions, but more efficiently,” Abolhasani says.
The team's paper is titled, “Artificial Chemist: An Autonomous Quantum Dot Synthesis Bot,” and is published in the journal Advanced Materials.
Ultimately, Abolhasani says that he believes "Artificial Chemist can re-shape the future of materials development and manufacturing". His team is currently looking for partners to help transfer the technique from the lab to the industrial sector.