The AI-PRISM project is oriented towards a human-centred AI-based solutions ecosystem targeted to manufacturing scenarios with tasks difficult to automate and where speed and versatility are essential. To facilitate the assessment of the performance, transferability, scalability, and large-scale deployment of AI-PRISM solutions, we will conduct research under real operational environments in five pilots involving key manufacturing sectors: furniture, food/beverage, built-in appliances, Electronics and one generic discrete manufacturing.
Regarding the food and beverages demonstrator, researchers from WINGS ICT Solutions, Cranfield University (CRAN), Łukasiewicz – PIAP, Robotnik Automation and VIGO Photonics had the opportunity to check the malting and brewing process, tasks of sorting returnable bottles, preparing for filtration, cleaning the packaging area and preparing beers for export in the facilities of partner Athenian Brewery (AB) in Thessaloniki, Greece. This partner is Greece’s largest beer production and distribution company, with an active presence in the country for over 55 years. In this pilot, AB, together with WINGS, will implement and demonstrate several use case scenarios in which there is a need for an AI-enhanced robotic solution that can adapt its operation to dynamic needs.
The challenge of digitising beer brewing
During the visit, the AI-PRISM learned about some use cases that will be conducted, raising questions, taking photos and videos and discussing the possibilities of human-robot collaborations. AB partner prepared the visit and explained different processes and tasks where there is room for improvement, considering that, as they say, “our main asset is our people and our WoW.”
One process where AB envisages robots performing tasks and improving its workers’ safety is filtration powder preparation. Operators lift sacks of 22,7kg of powder, a carcinogenic and dangerous substance, and place them upon a conveyor for further processing. AB will avoid the negative impact on workers’ health by using AI-PRISM robots that perform this task.
Another task where AB foresees human-robot collaboration is sorting returned bottles from the market. The AI-PRISM team observed it in the plant, consisting of crates filled with different brands of returnable bottles returned from the need to AB’s premises. These bottles must be sorted into the corresponding crates. Moreover, there is a process where bottles and cans intended for the export market have a sticker on top of them (tax tag). Currently, the operation is done manually with a stickering gun. Implementing AI-PRISM innovations will positively impact productivity and costs as a robot would perform these two processes.
Cleaning the packaging floor of broken glass, dirt, and labels is one of the processes where AI-PRISM solutions can be applied. As the packaging operates, there are broken bottles from the process, the debris of which fall on the floor and are a hazard to the people and operators. Once more, the support of robots can reduce operational expenditures and increase cost-efficiency.
By now, no robots exist for any of the processes presented by AB; these are all performed by humans, which makes the pilot cases challenging as there are no data or sensors for any of them. Ideally, robots must work independently for AB use cases, so there is no direct interaction with humans, although humans could teach them. In principle, there would be humans in the area, not in proximity.
The AB pilot project perfectly exemplifies human – robot collaboration for shifting focus of humans towards more mind-driven tasks. AI-PRISM team is excited to see where this project will take us. We will apply the same methods and technologies in the other industries that conform to our five pilot use cases, requiring high manual dexterity and expertise.
Do you want to learn more about AI-PRISM and the team behind the project? Subscribe to our newsletter and follow us on LinkedIn and Twitter, so you don’t miss a thing!