Smartphone ATMs Purchase And Exchange Old Devices
Lee Rannals for redOrbit.com — Your Universe Online
Got a few of those old school Nokia 5120 phones lying around? Try depositing them inside an ecoATM kiosk and see if you can’t get at least some parking meter change out of it.
A new artificial intelligence system is able to differentiate various consumer electronics products and determine a market value, then exchange some cash for the product.
Users will be able to walk up to the ecoATM kiosks and accept either cash or store credit for the value the machine gives them.
The ecoATM helps to find second homes for three-fourths of the phones it collects, sending the remaining ones to environmentally responsible recycling channels to reclaim any rare earth elements and keep toxic components from landfills.
“The basic technologies of machine vision, artificial intelligence and robotics that we use have existed for many years, but none have been applied to the particular problem of consumer recycling,” ecoATM co-founder and NSF principal investigator Mark Bowles said in a statement. “But we’ve done much more than just apply existing technology to an old problem–we developed significant innovations for each of those basic elements to make the system commercially viable.”
The ecoATM system began as a wood-box prototype that required a representative to ensure that users were being honest about their trades.
With funding from the NSF Small Business Innovation Research grant, researchers were able to develop artificial intelligence and diagnostics that delivered 97.5% accuracy for device recognition, allowing the ecoATMs to operate unsupervised.
Bowles said traditional machine vision relies on pattern matching, which is pairing a new image to a known one. This approach isn’t useful for the ecoATM’s evaluation process, which includes eight separate grades based on a device’s level of damage.
“We are now able to tell the difference between cracked glass on a phone, which is an inexpensive fix, versus a broken display or bleeding pixels, which is generally fatal for the device,” Bowles said in the statement. “We were warned by leading machine-vision experts that solving the inspecting/grading problem-with an infinite variety of possible flaws-was an impossible problem to solve. Yet with our NSF support, we solved it through several years of research and development, trial and error, use of artificial intelligence and neural network techniques.”
The company’s databases are loaded with images of more than 4,000 devices. When an identification mistake occurs, the system learns from the mistake.
If a user places their device into an ecoATM kiosk, the artificial intelligence system conducts a visual inspection, identifies the device model and then provides one of 23 possible connector cables for linking it to the ecoATM network.
The system uses proprietary algorithms to determine a value for the device based on the company’s real-time, worldwide, pre-auction system. This pre-auction system uses a network of buyers that have already bid in advance on the 4,000 different models in eight possible grades.
Some robotic elements allow the kiosk to safely collect, evaluate and then store each of the devices within just a few minutes.
“The ecoATM project is an extremely innovative way to motivate the public with an incentive to ‘do the right thing’ with discarded electronics, both socially and environmentally,” Glenn Larsen, the NSF SBIR program officer overseeing the ecoATM grants, said in the statement. “This may change behavior from simply dumping unwanted electronics to a focus on recycling, while helping put more hi-tech devices in the hands of others that might not otherwise be able to afford or acquire them.”