TOMRA Recycling has revealed its new AI platform from PolyPerception and three deep learning applications for its GAINnext technology, coinciding with TOMRA increasing its investment in PolyPerception to a 51% majority stake.
PolyPerception’s new platform marks the evolution of its AI-powered Waste Analyser solution, designed to improve sorting performance through end‑to‑end material tracking. Apparently, the platform’s natural language interface allows operators to ‘chat’ with their plant data in plain language, asking questions such as ‘How did changing the settings on the recovery line affect our purity?’. The platform understands the context and provides immediate natural language answers accompanied by data breakdowns.
The platform is said to have ‘writing’ capabilities, enabling it to act like an agent within the plant. TOMRA says that as well as observing material streams, it can actively create custom quality reports and set operational alerts based on its deep domain knowledge of the recycling process. It also allows managers to query waste statistics or purity levels through their own dashboards without needing to log into a separate system.
The platform also features two search methods to help plants respond to changing material streams. With the similarity search, operators can right-click a problematic object to instantly identify every other visually similar item in the stream, which can be used for spotting fire hazards like batteries without the need to train a new AI model. Through the text and brand search, users can search for specific brands or object types to see what is passing through the facility in real time.
TOMRA is also introducing three new deep learning applications for its GAINnext ecosystem. The first application aims to address rising demand for food-grade PET trays, with the system able to distinguish between takeaway or supermarket trays and consumer or medical packaging based on shape and use, reportedly achieving purity levels over 95%.
In the metals sector, TOMRA is launching a high-precision application for ‘copper meatballs’ with the new GAINnext automatically identifying complex copper-steel composites such as motor armatures, even in oxidized or dirty streams, delivering ‘outstanding’ selectivity and helping recyclers upgrade rebar-grade scrap to premium furnace feedstock.
The third application is a high-throughput solution for used beverage can aluminium recovery from packaging streams, launched in North America and now adapted for the European market. According to TOMRA, the GAINnext UBC application offers up to 33 times more throughput than manual sorting, delivering 98% purity or higher, and instantly detects and ejects non-UBC materials.
In related news, over the last 16 months Nestlé has taken part in a consortium alongside 8 other partners to pilot Zest’s AI-led solutions to visualize and reduce food waste and redistribute surplus to people, supporting an estimated 94,133 people across various charities and organisations. Nestlé says the pilot demonstrated how AI can enable connecting siloed data points on a manufacturing line, to map where food waste and surplus is generated in real time and identify actions to reduce and redistribute it.
This month Avery Dennison announced a $75 million minority investment in Wiliot, aiming to scale investment in physical AI for supply chains. The two companies plan to ‘significantly strengthen and expand’ their joint go-to-market efforts to accelerate the adoption of digital identities on physical items across industries including retail, logistics and food. In addition to its existing Board Observer position, Avery Dennison will receive a seat on Wiliot’s Board of Directors.
If you liked this story, you might also enjoy:
The ultimate guide to packaging innovation in 2026
Packaging and Packaging Waste Regulation: what to know in 2026
Everything you need to know about global packaging sustainability regulation
No comments yet