PITTSBURGH — At a mall in Sydney, Australia, “the world’s first smart trash can” is fastidiously photographing, weighing, and sorting garbage. The industrious TrashBot is a long way from home.
Trashbot was born in Pittsburgh at the AlphaLab Gear startup accelerator. There, the CleanRobotics team has been developing a machine that uses cameras, sensors, and machine learning to ensure that garbage ends up in the landfill and recyclables don’t. They’re tackling a problem that most environmentalists would agree needs to be solved: only about 20 percent of what goes in those blue bins actually ends up recycled, according to CleanRobotics co-founder Tanner Cook.
“That’s super pathetic, if you ask us,” he said. “That’s due to contamination and confusion and multiple different reasons. You can’t always blame it on the person. You drive 100 miles and what’s recyclable changes”
Here’s how it works: A piece of garbage is thrown into the TrashBot, then a small door slides closed over the opening. Under that door is a camera that analyzes the type of waste. The item is also weighed on a Teflon-coated plastic shelf that drains off liquid if there is any. CleanRobotics software determines whether the item is destined for the landfill or recycling facility and directs it into the appropriate bin below.
CleanRobotics is targeting big facilities that produce a lot of waste: airports, malls, stadiums, etc. The company is also starting to market TrashBot to office buildings and other businesses that handle large quantities of garbage.
In addition to the smart trash bin, CleanRobotics offers a monthly software service that allows waste management facilities to track the types of materials they throw away and the amount of garbage they produce. The metrics are valuable because trash isn’t cheap.
“In Australia, it costs $350 per ton of landfill versus getting a tax credit for recycling,” Cook said. “When you have a facility that’s going through 10,000 tons of trash every year, it makes sense for them to try and divert as much of it into that high-quality recycling space as possible.”
Cook serves as CleanRobotics’s VP of engineering. It’s his second startup aimed at reducing our carbon footprint. Before launching CleanRobotics, he co-founded Higea Technologies to clean up oil spills using nanotechnology. Cook co-founded CleanRobotics with CEO Charles Yhap, who previously led a non-profit dedicated to fighting human trafficking.
CleanRobotics is an alumnus of AlphaLab, an influential accelerator in Pittsburgh’s East Liberty neighborhood that helps early-stage startups get off the ground with a four-month mentorship program. Pittsburgh has become a hub for robotics and machine learning, with startups using the technology to tackle everything from self-driving cars to eco-cleanup.
With an undisclosed amount of funding from AlphaLab and angel investors, CleanRobotics is prototyping TrashBot and selling the system to early customers, including Pittsburgh International Airport.
“Our early adopters are buildings that are located in municipalities that have heavily waste conscious laws put into place,” Cook said. “Seattle, Boulder, North Carolina, Australia. A lot of these places, they’ll actually give you a tax credit for having recyclables. So instead of paying you’re getting a tax credit.”
TrashBot uses machine learning to improve its ability to detect and sort garbage over time. CleanRobotics custom codes the brains of TrashBot depending on the recycling rules and regulations in each market. Cook says Trashbot is comparable in price to the bespoke garbage bins you see at airports and stadiums.
TrashBot is a finalist in the $5 million IBM Watson AI XPRIZE, an international competition for AI innovations tackling some of the world’s greatest challenges.
CleanRobotics is also planning to develop a personal garbage sorting device for homes. The startup doesn’t plan to stop there.
“We all started this company because we care about the environment and the impact that we’re having on it,” Cook said. “We also see ourselves branching out into other sorting spaces and applying our technology to other sorting applications … We definitely tackled one of the messiest and most difficult things first.”