The AI ‘bin assistant’ aims to take the stress out of recycling | Credit: EduLeite
A zoo near Winchester is trialing a recycling solution that scans rubbish and tells visitors what bin to put it in
It is a frustratingly common sight to peer into a public recycling bin and find it contaminated with all sorts of rubbish that does not belong, from food waste to greasy cardboard and crinkly plastics.
But four students from tech giant IBM’s Extreme Blue Internship programme may have come up with an answer to the problem of recycling contamination having developed a new rubbish sorting system that uses artificial intelligence (AI) technology to nudge people towards the correct bins.
The students’ describe their Wastenet prototype as a “bin assistant”. Users can hold an item up to a scanner next to recycling bins or use an accompanying mobile phone app to show the system what they want to recycle.
The system then uses IBM Watson AI technology – including visual recognition, machine learning, and cloud computing functionality – to identify what bin the rubbish should go in. The more the system is used, the better it gets at recognising items and correctly identifying where they should go.
Wastenet is now being trialled at Marwell Wildlife centre near Winchester, where the IBM students found contaminated recycling bins were a regular occurrence.
“You’d think throwing rubbish in a bin would be easy,” said Arthur Berkley, a materials science student from the University of Oxford. “But when we studied how zoo visitors used the bins, we saw that they got confused about what they can recycle. And if they throw stuff in the wrong bin, or if it’s soiled, then recycling companies can decide the whole binload is contaminated.”
“We found that out for ourselves the hard way,” added Robert Scowen, a computer science and AI student at the University of Sheffield. “We spent a grim day sorting through some of the binbags and saw what a mess people made of recycling – literally.”
Marwelll Wildlife said it wanted to encourage its visitors to consider their environmental impact when visiting the zoo, and take better care of disposing the waste they produce.
It added that government policy is making it more expensive to send waste to landfill, so contaminated recycling bins is costing the attraction more each year.
The system will also gather data from across the zoo for Marwell Wildlife operations staff to help them quickly spot how bins are being used across the site and adapt facilities accordingly.
“We’re very excited to be working with IBM to take the stress out of recycling and make it quick, easy and fun,” said Duncan East, head of sustainability at Marwell Wildlife.
IBM’s Extreme Blue internship gives student teams three months to design, develop, and test a solution to a “real world problem”, using IBM clients as test beds. Marwell Wildlife has previously hosted an Extreme Blue project using data from sensors in zoo enclosures to reduce energy used for heating.
IBM said once the Extreme Blue participants resume their studies, a team from IBM will take over the project and continue developing the technology, both at Marwell Wildlife and IBM’s Hursley labs.