CoLLaboratE

The CoLLaboratE project has been formed to enable genuine human–robot collaboration for performing assembly tasks in a production cell designed to provide a safe collaborative environment. The project will build upon state-of-the-art methods for teaching the robot assembly tasks using human demonstration, extending them to facilitate human-robot collaboration. To this end, a framework for equipping the robots and Autonomous Guided Vehicle (AGV) mobile platforms with basic collaboration skills will also be developed, coupled with deep reinforcement learning algorithms for increasing adaptability. Special attention will be paid in providing efficient safety strategies allowing the use of a fenceless approach within the production cell. As a result, closer collaboration will be achievable and efficient production plans making optimal use of the available resources can be designed and executed. Targeted collaboration abilities will be demonstrated in real-world industrial scenarios including a car starter assembly, a windshield assembly, an LCD TV assembly, and CNC cutting tools assembly, showing the system’s capability to learn different types of assembly at different levels of collaboration.

Consortium

• Aristotle University of Thessaloniki [AUTH] – Greece

• Centre for Research and Technology Hellas [CERTH] – Greece

• Association pour la Recherche et le Developpement des Methodes et Processus Industriels [ARMINES] – France

• Jozef Stefan Institute [JSI] – Slovenia

• Idiap Research Institute [IDIAP] – Switzerland

• Universita degli studi di Genova [UNIGE] – Italy

• Katholieke Universiteit Leuven [KU LEUVEN] – Belgium

• Panepistimio Patron [LMS] – Greece

• Centro Ricerche FIAT SCPA [CRF] – Italy

• Blue Ocean Robotics [BOR] – Denmark

• Automatismos y Sistemas de Transporte Interno SA [ASTI] – Spain

• Kolektor Orodjarna d.o.o. [KOL] – Slovenia

• Arcelic A.S. [ARCELIC] – Turkey