"AI has more or less acquired the sense of sight, through advances in computer vision and object recognition," said Stevens physics professor Yong Meng Sua. "It has not, however, yet developed a human-like sense of touch that can discern, for example, a rough sheet of newspaper paper from a smooth and glossy sheet of magazine paper."
Now, researchers at Stevens Institute's Center for Quantum Science and Engineering (CQSE) have introduced a groundbreaking approach enabling AI to measure and sense surfaces.
High-precision metrology for diverse applications
In collaboration with CQSE Director Yuping Huang and doctoral students Daniel Tafone and Luke McEvoy '22 M.S. '23, Sua devised a lab setup that merges a photon-emitting scanning laser with new AI models capable of distinguishing between surfaces based on laser imagery.
"This is a marriage of AI and quantum," Tafone explained.
Detailed in the journal 'Applied Optics' [Vol. 63, No. 30], their system employs a precisely engineered light beam that pulses at surfaces to "feel" them. Reflected photons return, bearing speckle noise - normally a nuisance in imaging - which their AI processes as significant data, revealing the object's topography.
"We use the variation in photon counts over different illumination points across the surface," said Tafone.
The team tested their system on 31 different industrial sandpapers with surface roughness ranging from 1 to 100 microns, akin to the thickness of a human hair. Pulsed mode-locked lasers transmitted light onto the samples, and rebounding pulses were analyzed by the AI model.
Initial trials showed the system achieving an average root-mean-square error (RMSE) of approximately 8 microns. With further refinements and averaging multiple samples, the accuracy increased to within 4 microns - matching top industrial profilometers.
"Interestingly, our system worked best for the finest-grained surfaces, such as diamond lapping film and aluminum oxide," Tafone noted.
Promising uses in healthcare and industry
This new method holds potential for multiple fields. Skin cancer diagnostics, for instance, often suffer from errors when benign moles are mistaken for harmful melanomas.
"Tiny differences in mole roughness, too small to see with the human eye but measurable with our proposed quantum system, could differentiate between those conditions," Huang explained.
Huang also emphasized its relevance for manufacturing, where minuscule imperfections in components can affect product quality and safety.
"Since LiDAR technology is already implemented widely in devices such as autonomous cars, smartphones and robots," Huang concluded, "our method enriches their capabilities with surface property measurement at very small scales."
Research Report:Surface roughness metrology with a raster scanning single photon LiDAR
Related Links
Center for Quantum Science and Engineering
All about the robots on Earth and beyond!
| Subscribe Free To Our Daily Newsletters |
| Subscribe Free To Our Daily Newsletters |
