Garbage or recycling? U of T students invent 'RoboBin' to make the decision for you

Five University of Toronto masters students invented a disposal system that uses AI technology to separate waste into garbage, recycling and organics.

System separates waste into garbage, recyclables and organics for the user

RoboBin eliminates users' guesswork by using AI to sort waste at the source into garbage, recyclables and organics. (Sabrina Jonas/CBC News)

You're standing in front of a public waste bin holding a takeaway cup, puzzled by the three options in front of you: garbage, recycling or organic.

Sometimes it's a tough decision, but could it be easier with help from artificial intelligence (AI)?

Five University of Toronto masters students think so, and so to combat bin confusion — which they say leads to a quarter of Toronto's recycling becoming contaminated — they invented RoboBin. 

"One in three citizens contaminate their recycling waste ... Even if you make an educated guess, we go wrong all the time," said Nikunj Viramgamaj, CEO of Paramount AI, the company the students created.

Paramount AI's RoboBin won first place in KPMG's second annual Ideation Challenge, a worldwide competition to develop solutions to problems facing businesses using AI. 

The U of T team beat out 600 other applicants from 65 universities across nine countries in May.

How it works

The AI-powered waste management system uses photos to help sort out what waste is what.

Vaibhav Gupta, CTO of Paramount AI, says they uploaded over 35,000 images of waste into the system in order to train it to identify characteristics of garbage, recyclables and organics. 

"So what it is doing is basically analyzing each and every pixel separately and then [RoboBin] finds out what's the best description for the content," says Gupta. 

The user places a piece of waste into RoboBin, they push a button, and the system uses AI to scan the item before mechanically moving it into the correct bin. 

Team Paramount AI, creators of RoboBin: (From left to right) Ganesh Vedula, Aakash Iyer, Nikunj Viramgama and Vaibhav Gupta. Another member, Maharshi Trivedi, could not attend the demonstration. (Paul Borkwood/CBC News)

The team says they will incorporate feedback from the images to improve and increase the machine's accuracy. 

Toronto could save up to $1M annually 

Paramount AI says the machine not only helps to combat climate change, it also counters the economic consequences of improper recycling. 

In 2018, then general manager of waste management services for the City of Toronto Jim McKay told CBC Toronto he estimated that each percentage point decrease in contamination could lower recycling costs in the city by $600,000 to $1 million a year. 

The team says their company kept this information in mind when creating their prototype and they say they are confident their invention could help with those savings. 

Viramgamaj says they created the prototype as an accessory for public waste bins to reduce costs "so that the government or whoever the client is don't have to replace the entire bin."

Anthony Coops, KPMG partner and Ideation Challenge judge, says the business aspect in Paramount AI's pitch was what really attracted him to their idea.

"This team in particular brought to life the business case for their idea by... talking about the number of bins at a theme park and the amount of waste that is then generated," he says.

Coops says he felt it was a really clever way of making their idea real.

"This idea has legs. They're in discussions with some organizations about taking it further," says Coops.

'We want to save the environment'

Paramount AI says they recognize that the problem of rising landfills is a global problem. 

"We want to save the environment as well as create a business model," says Viramgamaj.

The team says they are planning to implement the system around their neighbourhoods to see if it is "feasible and scalable."

If so, they say they will approach the City of Toronto with their pitch.

The team demonstrated their prototype at KPMG's Global Lighthouse Summit for over 300 KPMG clients and partners on Oct. 17-18 in hopes of securing venture capital. 

But the team says their biggest goal is to hone the future of AI in an ethical, multicultural and unbiased way.

"This win was not only important for us but also for Canada as a whole and to reassure that we are at the forefront of AI development," says Viramgamaj. 

With files from Natalie Nanowski


To encourage thoughtful and respectful conversations, first and last names will appear with each submission to CBC/Radio-Canada's online communities (except in children and youth-oriented communities). Pseudonyms will no longer be permitted.

By submitting a comment, you accept that CBC has the right to reproduce and publish that comment in whole or in part, in any manner CBC chooses. Please note that CBC does not endorse the opinions expressed in comments. Comments on this story are moderated according to our Submission Guidelines. Comments are welcome while open. We reserve the right to close comments at any time.