London, Sep 18 (IANS) A recycling ATM offers gadget freaks the option to trade in their discarded mobile phones for cash, rather than dumping them when they go in for the latest model.
Californian company ecoATM has rolled out the machine that is sophisticated enough to see if a screen is cracked, evaluate unwanted goods for resale and recycling – hoping to inspire people to go green.
Old gadgets still have a value as either an affordable alternative, spare parts, or even melted down for the residual value of the metals inside. ecoATM has developed the device with support from the US National Science Foundation (NSF).
The ecoATM finds 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. More than 300 kiosks are hoped to be rolled out across the US by the year-end, the Daily Mail reported.
Company co-founder Mark Bowles said: “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.”
“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,” Bowles said.
Using artificial intelligence (AI) ecoATM kiosks can differentiate varied consumer electronics products and determine a market value. If the value is acceptable, users have the option of receiving cash or store credit for their trade – or donating all or part of the compensation to one of several charities.
The system began as a wooden-box prototype that required the presence of an ecoATM representative to ensure that users were being honest with their trades.
The team therefore developed AI that delivered 97.5 percent accuracy for device recognition, removing human oversight and making the system viable. They are currently trying to eliminate the accuracy gap.
“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 added.
The company’s databases are now trained with images of more than 4,000 devices, and when an identification mistake occurs, the system learns from that mistake.
When a phone is presented, the AI system conducts a visual inspection, identifies the device model and provides one of 23 possible connector cables to link it to the network.
A value is then determined based on the company’s real-time, worldwide, pre-auction system in which a broad network of buyers have already bid on the old technology, so the kiosk can immediately provide compensation.