Recycling is complicated, and not just for consumers, but especially for recycling companies. But as with many other fields, artificial intelligence may be able to help.
Until now, determining what exactly is in the vast mess of garbage that arrives at recycling plants has been a dirty and difficult job. Humans can only see so much so fast, but it is necessary to differentiate a milk container from a beer can or a jug of detergent to recycle all of them properly.
Now, companies such as AMP Robotics, Machinex, Recycleye and a California-based startup called EverestLabs are using AI and robotics to do just that. They aim to simplify, expedite and improve the process.
“Because of AI, because of the robotic arms, we have seen plants recover 10, 20, 30% more than what they have been doing previously,” said JD Ambati, CEO of EverestLabs. “They have been losing millions of dollars to the landfill, and because of AI, they were able to identify the value of the losses and deploy robotic arms to capture that.”
EverestLabs puts 3D depth-sensing cameras on recycling conveyor lines. The cameras can identify up to 200 items in each frame. Within 12 milliseconds, the AI software can tell what those objects are and what types of packaging they contain.
“We get data around brands, types of packaging, types of material and how much of that is getting recovered and reused, and how much of that material is being sent to the landfill,” said Ambati.
That helps increase the potential recovery of recyclable items. Add to that robotic arms, which he says recover the packaging three to four times more effectively than humans. That means big cost savings for major recyclers such as SMR.
“Labor is a big challenge in our business, like in lots of the economy,” said Tom Outerbridge, president of SMR. “We can replace some portion of the positions that we would otherwise have to fill with human beings with a robot that can do that in a cost-effective way, that’s obviously good for the business and it’s good for the operation.”
EverestLabs is backed by Translink Capital, NEC Orchestrating Future Fund, BGV, Sierra Ventures, Morado Ventures and Xplorer Capital. It has raised $24.6 million so far.
— CNBC producer Lisa Rizzolo contributed to this story.