Communications of the ACM
AI-Driven Robots Are Improving Solar Cells, Other Technologies
University of British Columbia researchers have developed a robotic system to perform materials science design tests.
Credit: Fraser Parlane
Researchers at the University of British Columbia in Canada have developed a single-armed robotic system equipped with an artificial intelligence (AI) algorithm to perform materials science design tests.
The Ada system can mix different solutions, cast them into films, perform heat treatments and other processing steps, test the films' conductivity, evaluate their microstructure, and log the results.
The AI interprets each experiment and determines what to synthesize next.
The team found Ada was able to quickly create a recipe and heating conditions that created defect-free films ideal for solar cells.
Other researchers have reported successes with similar "closed loop" systems that combine the latest advances in automation with AI that directs how the experiments should proceed in real time, including researchers at Lawrence Berkeley National Laboratory, Boston University, the Massachusetts Institute of Technology, Carnegie Mellon University, and the University of Liverpool in the U.K.
From Science
View Full Article
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA
No entries found