Image Credits: CleanRobotics

Better Than Humans: CleanRobotics Units Clear Trash with 90% Accuracy

When it comes to trash, Americans are top producers. The average American generates 1,704 pounds of garbage per year, roughly three times the global average, according to a new report by the research firm Verisk Maplecroft. That’s more waste than any other nation in the world with 4.5 pounds of municipal solid waste (MSW) per person per day, 55 percent of which is residential garbage.

A company in Colorado has created a new approach to removing trash called Trashbot.

A number of startups are working to improve trash sorting with robots. AMP Robotics is near the top of the list, coupling a picker and a conveyor belt to sort materials in large, automated facilities. The technology aims to correct human shortcomings when it comes to recycling. Too often people either don’t bother to separate trash or simply don’t understand where things go.

Founded in 2015, CleanRobotics hopes to correct the issue at the point of disposal. The Colorado firm’s flagship trashbot system uses onboard machine learning and robotic systems to sort materials from a single disposal point. It claims the machines are able to do so with roughly 90% accuracy — not perfect, but certainly better than what humans generally do.

“Recycling rules are confusing and consumers are often so confused that their recycling accuracy is less than chance, leading to highly contaminated recyclables, which no one is buying,” CEO Charles Yhap said in a release. “Our system improves material diversion from landfills, resulting in more recyclables and less waste.”

This week, the company announced a $4.5 million Series A led by Melco International Development Limited and featuring SOSV/HAX, Undivided VC, and Longmont Evergreen Opportunity Fund. The funding will go toward CleanRobotics’ plans to produce “hundreds” of systems, in addition to those already installed in high-traffic areas like shopping malls and airports