Two Latvian companies are using artificial intelligence to increase the efficiency of plastic waste and make a significant contribution to the implementation of upcoming EU single plastic directive.
Latvian process engineering and equipment manufacturing company, Peruza, in partnership with technology company Dots, has developed a prototype of a packaging deposit-refund system.
The artificial intelligence (AI) recognition system can identify different types of packaging materials, and is not limited to certain types of drinks packaging only.
Deposit return schemes are considered a good way to involve people in waste collection and thus help to reach the recycling goals of the entire European Union (EU).
According to Peruza, 10 European countries have implemented deposit return schemes and the number is increasing. However, the EU’s aim is that by 2030 all plastic packaging placed on the market should be reusable or recyclable.
A PlasticsEurope study conducted in 2014 shows Europe produces 25 million tonnes of plastic waste. Only 30 per cent of this is recycled, while 39 per cent is incinerated and 31 per cent goes to landfill.
“The problem of existing devices is that they can collect individual types of packaging. They use a barcode for recognition. Our system can currently recognise, collect and sort 0.5 litre and/or 1.5 litre Pet bottles, and 5 litre plastic bottles, 1.5 litre plastic canisters, as well as aluminium cans, cardboard Tetra Pak, glass bottles and jars,” said Robert Dlohi, CEO of Peruza.
“We have also foreseen situations when packaging appears in the system that it cannot recognise. For that we have created a separate bin for unsorted waste.”
A second project has gone further. A demo device has been created by Baltic AI developer, Apply, in partnership with a group of companies offering solutions for sustainable and smart cities.
“We have also foreseen situations when packaging appears in the system that it cannot recognise”
This device uses AI, computer vision, machine learning and deep learning technologies to recognise and sort various kinds of waste regardless of how much the packaging is flattened, deformed or if it has no barcode.
“In future, the system will be developed to be able to separate glass packaging that can be used repeatedly from recyclable glass. Later, we are planning to add spectral analysis to detect high-density polyethylene (HDPE) and separate it from the other types of polymers or other materials such as metals,” added Vismands Menjoks, chief commercial officer of Apply.
You might also like: