HARTU (Handling with AI-enhanced Robotic Technologies for flexible ManUfacturing) will provide components for automatic planning and control of gripping, release and contact assembly tasks and propose innovative gripping concepts based on electroroadhesion for handling many different products. These components will make production lines more efficient, flexible and reconfigurable. The main technological goals are.
- self-monitored identification and control of gripping strategies 2. learning and controlling assembly techniques based on human demonstrations 3. developing AI-based multimodal perception for visual control and continuous monitoring during handling operations 4. developing versatile and dexterous soft grippers with electro-active fingertips.
The technologies are evaluated in 5 different industrial scenarios, 4 in manufacturing and 1 in logistics: packaging, assembly, sorting, packing and machine operation.
In HARTU, DFKI is primarily concerned with learning and controlling assembly skills that involve a variety of different contact situations. Therefore, motion sequences and contact forces are to be learned through human demonstration and generalized with respect to novel situations. These skills shall be generic and adapt the control parameters to the current contact situation.
The developed methods shall be demonstrated in mass production of consumer goods, in this case electric razors, at Philips Consumer lifestyle B.V.. They are intended to make assembly lines more flexible and easier to reconfigure.
Partners
Fundacion Tekniker (ESP), AIMEN Centro Tecnológico (ESP), Industrial Technology Research Institute (TWN), Politecnico di Bari (ITA), Omnigrasp (ITA), Engineering Ingegneria Informatica (ITA), FMI Drachten B.V. (NLD), ULMA Manutención S. Coop (ESP), Tofaş Türk Otomobil Fabrikası (TUR), Philips Consumer Lifestyle BV (NLD), Tecnoalimenti SCPA (ITA), INFAR Industrial Co., Ltd. (TWN), Deep Blue SRL (ITA)
