A groundbreaking achievement in the realm of artificial intelligence (AI) has opened up exciting new possibilities for its real-world application. For the first time, scientists have successfully enabled AI to ‘feel’ surfaces, marking a significant step forward in technological capabilities. This innovative approach, detailed in a recent study published in the journal *Applied Optics*, leverages the principles of quantum science to achieve unprecedented levels of surface analysis.
The system ingeniously combines a photon-firing scanning laser with a sophisticated AI model. This AI model is specifically trained to differentiate between various surfaces imaged using the laser’s light pulses. The process begins with the laser emitting short bursts of light at the target surface. Upon interaction, back-scattered photons, or light particles, return to the system, carrying with them ‘speckle noise’—typically considered an imaging flaw. However, the researchers cleverly exploited this noise, utilizing the AI to process the artifacts and accurately determine the object’s topography.
This fusion of quantum mechanics and artificial intelligence is described by study co-author Daniel Tafone, a doctoral candidate at Stevens Institute of Technology, as a ‘marriage of AI and quantum’. The team validated the system’s efficacy using a series of experiments involving 31 variations of industrial sandpaper, exhibiting roughness ranging from 1 to 100 micrometers—the thickest being approximately the width of a human hair. The lidar system employed in the study uses a laser beam fired in picosecond pulses (one trillionth of a second), with light pulses traveling through transceivers, striking the sandpaper, and then rebounding for AI analysis. A single photon detector counts the returning back-scattered photons from various surface points.
The results were astonishing. The system achieved an average error of roughly 8 micrometers, which was further refined to just 4 micrometers after the AI processed data from multiple samples. This accuracy is comparable to existing profilometer devices, demonstrating the system’s potential as a viable alternative. Intriguingly, the researchers noted that the system performed exceptionally well on fine-grained surfaces like diamond lapping film and aluminum oxide, frequently used in specialized sandpaper applications.
Beyond the initial experiments, the implications of this groundbreaking technology are far-reaching. The researchers envision a multitude of applications, particularly in medical diagnostics. The system’s sensitivity could prove invaluable in detecting subtle differences in the roughness of moles, potentially aiding in the early detection of skin cancer. As Yuping Huang, director of Stevens’ Center for Quantum Science and Engineering (CQSE), explains, “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. Quantum interactions provide a wealth of information, using AI to quickly understand and process it is the next logical step.”
This remarkable advancement pushes the boundaries of AI and quantum science, opening doors to innovative technologies in diverse fields. From precise manufacturing quality control to sophisticated medical imaging, this AI-powered surface sensing promises a future where machines possess not just sight and sound, but also the capacity to ‘feel’ and interpret the world around them with unprecedented accuracy and detail. This technological leap represents a significant step towards the development of truly advanced, intelligent systems capable of interacting with the physical world on a profoundly nuanced level.
