COP31 Zero Waste Push
Globally, less than 7% of the materials entering the economy come from recycled or reused sources, creating a stark deficit as world leaders gather for COP31 in Türkiye.
Municipal solid waste generation accounts for over 2 billion tons of trash per year.
That volume could nearly double by 2050.
AI and Robotics on the Line
Blogs.nvidia.com reported that artificial intelligence and robotics are helping change this trajectory by automating the sorting of waste streams.
NVIDIA Inception program startups are deploying computer vision to recover valuable materials.
“A more circular economy relies on making better use of what we already have,” said Josh Parker, head of sustainability at NVIDIA.
“AI can help us understand what’s in a waste stream, identify what can be recovered and automate the work of sorting it,” Parker stated.
Vision AI for Plastic Sorting
AIRECO, a startup based in Taiwan, uses vision AI to sort plastics more finely from mixed scrap piles.
“The finer you sort, the more you can recycle,” said Chun-Feng Liu, founder and CEO of AIRECO.
Liu noted that finely sorted material enables closed-loop recycling where used items become new versions of the same product.
The company uses NVIDIA Jetson Orin NX modules to run inference across a pilot line in Tainan.
Recognition accuracy on that test line tops 95%.
Real-Time Material Recovery
EverestLabs AI deploys computer vision-guided robots on fast-moving conveyor belts in North America and Australia.
“Other robots have infinite time to finish their tasks,” said R. Paul Singh, CEO of EverestLabs AI.
“We don’t have that luxury because our conveyor belts are coming in at a certain speed,” Singh added.
EverestLabs runs AI inference on NVIDIA RTX GPUs at the edge.
Tracking the Waste Stream
Greyparrot built its Analyzer platform to monitor waste across conveyor belts moving up to 4 meters a second.
“Waste changes all the time,” said Ambarish Mitra, cofounder of Greyparrot.
“Before, operators guessed based on a tiny sample, and now they can see exactly what’s on the belt,” Mitra stated.
Over 300 Analyzer systems operate in more than 20 countries.
Automating Textile Sorting
Europe generates nearly 7 million tons of used textiles a year.
Berlin-based startup reverse.fashion is automating textile sorting using high-resolution computer vision.
“Compared to classical waste sorting, our AI models have to run at very high resolution because humans are picky with textiles,” said Karsten Pufahl, cofounder and chief technology officer of reverse.fashion.
Pufahl estimated that the system sorts in an hour what previously took a week.
