AI Powered human-centred Robot Interactions for Smart Manufacturing

AI-PRISM is an industrial-end-user driven project that will provide a human-centred AI-based solutions ecosystem targeted to manufacturing scenarios with tasks difficult to automate and where speed and versatility are essential. The result will be an integrated and scalable ecosystem with installation-specific solutions for semi-automated and collaborative manufacturing in flexible production processes and for which specific robotic programming skills will not be required, thanks to its programming-by-demonstration modules. The ecosystem will be composed by four main pillars including 1) Human Centred Collaborative Robotic Platform, 2) Human Robot Cooperation Ambient, 3) Social Human-Agent-Robots Teams Collaboration and 4) Open Access Network Portal. In order to facilitate the assessment of the performance, transferability, scalability and large-scale deployment of these solutions, the demonstrations will be conducted under real operational environments in four pilot involving key manufacturing sectors - Furniture (ES), Food/Beverage (GR), Built-in Appliances (TR) and Electronics (PL) -, plus one generic demonstration facility (AT). The project is not just aiming at quantitative improvements in a specific sector, but to use technology innovation to support a change of paradigm where AI, robotics and Social Sciences and Humanities (SSH) integrated in the manufacturing domain for the improvement of flexible production processes, become a feasible and widespread alternative for European factories, especially SMEs. To achieve this, the project relies on a strong consortium of 25 partners from 12 countries including international cooperation with Korea. The consortium brings together all the actors of the Human Robot Collaboration (HRC) value chain including relevant competence centres, technology providers, equipment providers, integrators, and manufacturers/end users; and involves key expert partners in SSH, standardisation, exploitation, and dissemination.