Scientist Robert Wolkow & Team Are Kick-Starting A Revolution Using AI To Automate Atomic-Scale Manufacturing

Scientists at the University of Alberta have managed to perfect and automate atomic-scale manufacturing. This has never been done before.

University of Alberta researchers have published their newest findings in ACS Nano, a monthly, peer-reviewed scientific journal. In a press release supplied to Science Daily, Robert Wolkow, professor of physics at the University of Alberta, explained the importance of his and Research Associate Moe Rashidi’s findings.

“Until now, we printed with atoms about as efficiently as medieval monks produced books. For a long while, we have had the equivalent of a pen for writing with atoms, but we had to write manually. So we couldn’t mass produce atom-scale devices, and we couldn’t commercialize anything.

“Now that has all changed, much like the disruption following the arrival of the printing press for those medieval monks. Machine learning has automated the atom fabrication process, and an atom-scale manufacturing revolution is sure to follow.”

Wolkow, who has spent much of his career developing and perfecting atomic-scale manufacturing, claims his and his associate’s findings will not only revolutionize atom-scale manufacturing but also do wonders for the environment and satisfy the ever-increasing demands of the information age.

According to Wired, Wolkow has spent years trying to improve the scanning probe microscope – the sharpest object ever made, invented nearly 40 years ago by IBM scientists. A thin metal wire, as fine as a human hair at one end, is usually used to position atoms. Over the years, scientists have, Wired noted, used this machine to create groundbreaking things, including the tiniest transistor of all time, made out of a single atom.

This delicate machine requires precision and patience, and taming this tool has been a daunting task for many. Wolkow has spent years doing just that. Now, closer than ever to fulfilling his dream, the Canadian scientist has managed to find a way to use the machine for making new types of chips. These chips, he claims, could revolutionize atom-scale manufacturing.

robert wolkow microscope

“Most of us thought we’d never be able to automate atomic writing and editing, but stubborn persistence has paid off, and now Research Associate Moe Rashidi has done it,” Wolkow said, praising his colleague.

As Wired noted, transistors in computer chips currently either “hold onto” electrons or dump them. In layman’s terms, this means that our computers, as they record and memorize data, have to move a lot of electrons around. Needless to say, this consumes a lot of energy.

Wolkow’s team has found a way to bypass this – they have developed a circuit design capable of encoding information in the atoms’ patterns. This means that atoms, arranged in various ways, correspond to different binary numbers. This, in turn, means all a computer using Wolkow’s chips would need to record data would be the minimum of energy needed to rearrange the atoms. In any case, they would require substantially less energy than now.

robert wolkow chips

Perhaps more importantly, Wolkow’s team has managed to bypass other issues scientists have faced over the years. He has made progress with the machine, the scanning probe microscope, itself. Wolkow’s group has developed and perfected a technique which relies on machine learning and artificial intelligence. The technique, Wolkow’s team refer to it as “the atomic whiteout,” uses AI to sharpen the machine’s wire tip, correcting errors when laying atoms.

This, in Wolkow’s opinion, is a turning point. Companies could start making products, atom by atom, using the AI-infused scanning probe microscope.

Using his technology, Wolkow said, we could do everything that we are currently capable of better, and create entirely new functions; achieve what conventional technology is incapable of achieving.

“Combining that with a practical path to manufacturing will be game changing,” the scientist said, adding that this “allows us to create a new, extremely efficient basis for computing using the natural properties of individual atoms.”

Robert Wolkow’s ultimate goal is to produce more scanning probe microscopes, which, he claims, would allow him to manufacture millions of chips a year.