Sonoco, a packaging manufacturer based in Hartsville, South Carolina, has formed a partnership with Amp Robotics, a Denver-based artificial intelligence (AI) and robotics manufacturer for the waste and recycling industry. The two companies plan to create a new material category within Amp’s neural network specific to rigid paperboard cans.
According to a news release from Sonoco, the partnership will result in increased recycling rates for spiral-wound paper canisters with steel bottoms produced by Sonoco and other packaging manufacturers.
The use of recycled steel has a 45 percent lower environmental impact than producing the equivalent amount from virgin material, reducing the need to mine for virgin iron ore. Additionally, when compared with landfilling, recycling the paper container with steel bottom through the steel or other streams has a greater than 40 percent lower environmental impact than landfilling. Sonoco reports that any material recovery facility that uses an Amp Cortex robotics system can now accurately and efficiently sort Sonoco’s paper can to the desired stream.
“Sonoco is uniquely positioned as a leading recycler to help deliver end-of-life solutions across our consumer and industrial packaging platforms,” says Elizabeth Rhue, staff vice president of sustainability at Sonoco. “This partnership represents another step forward in our growing portfolio of sustainable packaging solutions.”
“Our AI is unique in its strength, precision and flexibility to learn new packaging to the specificity of a manufacturer or brand, and Sonoco was early to recognize the implications of AI in the sorting process,” says Matanya Horowitz, founder and CEO of Amp Robotics. “Manufacturers like Sonoco are directly influencing what is recoverable in recycling facilities and taking advantage of the ability to capture more of their specific packaging. Recyclers across the world with Amp Cortex gain this sorting capability, as they have many others. And because our AI is continuously learning, we’ll only improve the recovery of this and other materials over time.”
Amp says its AI platform, Amp Neuron, encompasses a large, real-world dataset of recyclable materials for machine learning. With an object recognition rate of more than 10 billion items annually, the technology can classify more than 100 different categories and characteristics of recyclables across single-stream recycling, e-scrap and construction and demolition debris.