New technology gives AI human-like eyes

Researchers from the University of Central Florida have created artificial intelligence technology that mimics the human eye.

The technology could lead to highly advanced artificial intelligence that can instantly understand what it sees and use it in robotics and self-driving cars.

Researchers of University of Central Florida (UCF) created an artificial intelligence device that replicates the retina of the eye.

The research could lead to the creation of cutting-edge artificial intelligence that can immediately identify what it sees, such as automated descriptions of photos taken with a camera or phone. The technology could also be used in robots and self-driving cars.

The technology is described in a recent study published in the journal ACS Nano, also performs better than the eye in terms of the range of wavelengths it can perceive, from ultraviolet to visible light and the infrared spectrum.

Its ability to combine three different operations into one further contributes to its uniqueness. Currently available intelligent imaging technology, such as in self-driving cars, requires separate data processing, storage, and sensing.

By integrating the three procedures, the UCF-developed device works much faster than existing technologies, the researchers say. With hundreds of devices on a one-inch-wide chip, the technology is also quite compact.

“This will change the way artificial intelligence is implemented today,” says the study’s principal investigator Tanya Roy, an associate professor in UCF’s Department of Materials Science and Engineering and the Nanoscience Technology Center. “Today, everything consists of discrete components and runs on conventional hardware. And here we have the ability to do intrasensory computing with one device on one small platform.”

The technology expands on previous work by the research team, which created brain-like devices that allow AI to operate in remote regions and space.

“We had devices that behaved like the synapses of the human brain, but we still weren’t feeding them an image directly,” says Roy. “Now, by adding image sensing capability to these, we have synapse-like devices that act as ‘smart pixels’ in the camera, simultaneously sensing, processing and recognizing images.”

Mullah Manjurul Islam

Mola Manjurul Islam, lead author of the study and a doctoral student in the UCF Department of Physics, is studying retina-like devices on a chip. Author: University of Central Florida

For unmanned vehicles, the device’s versatility will allow for safer driving in a variety of conditions, including at night, says Mola Manjurul Islam ’17MS, lead author of the study and a doctoral student in the UCF Department of Physics.

“If you’re in your self-driving car at night and the car’s imaging system only works on a certain wavelength, say the visible wavelength, it won’t see what’s in front of it,” Islam says. “But in our case, with our device, it can actually see in the whole state.”

“There is no reported device that can simultaneously operate in the ultraviolet and visible wavelengths as well as infrared wavelengths, so this is the most unique selling point of this device,” he says.

Key to this technology is the development of nanoscale surfaces made of molybdenum disulfide and platinum ditelluride to enable multi-wavelength sensing and memory. This work was done in close collaboration with YongWung Jung, an associate professor with joint appointments in the UCF NanoScience Technology Center and the Department of Materials Science and Engineering, which is part of the UCF College of Engineering and Computer Science.

Researchers tested the device[{” attribute=””>accuracy by having it sense and recognize a mixed wavelength image — an ultraviolet number “3” and an infrared part that is the mirror image of the digit that were placed together to form an “8.” They demonstrated that the technology could discern the patterns and identify them both as a “3” in ultraviolet and an “8” in infrared.

“We got 70 to 80% accuracy, which means they have very good chances that they can be realized in hardware,” says study co-author Adithi Krishnaprasad ’18MS, a doctoral student in UCF’s Department of Electrical and Computer Engineering.

The researchers say the technology could become available for use in the next five to 10 years.

Reference: “Multiwavelength Optoelectronic Synapse with 2D Materials for Mixed-Color Pattern Recognition” by Molla Manjurul Islam, Adithi Krishnaprasad, Durjoy Dev, Ricardo Martinez-Martinez, Victor Okonkwo, Benjamin Wu, Sang Sub Han, Tae-Sung Bae, Hee-Suk Chung, Jimmy Touma, Yeonwoong Jung and Tania Roy, 25 May 2022, ACS Nano.
DOI: 10.1021/acsnano.2c01035

The work was funded by the U.S. Air Force Research Laboratory through the Air Force Office of Scientific Research, and the U.S. National Science Foundation through its CAREER program. New technology gives AI human-like eyes

Back to top button