The partners in the 'Rob-akademi' research project, including the Fraunhofer IPA and the Institute of Industrial Manufacturing and Factory Operation IFF at the University of Stuttgart, are developing technologies that will simplify and automate robot programming for assembly tasks. The basis for this is a purely digital image of the production environment, a digital twin. This image, combined with a special programming framework, is used in a physical simulation environment so that robots learn skills for flexible assembly. They autonomously explore their environment in the simulation environment, plan their behaviour based on this and optimize it independently or learn continuously. Artificial intelligence (AI) is used for this - more precisely, machine learning and its sub-area of reinforcement learning (RL). This means that an algorithm learns according to the principle of trial and error, similar to humans. The algorithm receives a reward signal for a successful action in order to gradually improve.

The project is creating three application-related learning modules that encapsulate expert knowledge about robot programming and the assembly operation to be carried out: The 'Perception module' for object recognition, the 'Force-controlled joining' learning module for robust joining strategies and the 'Snap-fit connections' learning module with a detailed physical joining model. These technologies are used to create robust robot programs for transferring the simulation results to reality. The project partners are validating their results with the help of three practical use cases - control cabinet, switch and PCB assembly. The modules for force-controlled joining and snap-fit connections are based on the already available IPA software 'pitasc' for force-controlled assembly tasks and will expand its capabilities.
With its project objectives, 'Rob-akademi' addresses the needs of increasingly personalized production in particular. Assembly applications currently still place high demands on robot programming. These include diverse and simultaneously demanding, often force-controlled processes, a high number of variants and short cycle times. For many companies, and especially SMEs with their customer-specific products, it is therefore often not yet worthwhile using robots for assembly, especially as only an expert can carry out the programming. Robots offer advantages such as taking over non-ergonomic, dangerous or monotonous tasks and consistent quality in the execution of tasks.

The project is part of the major funding measure 'KI01 KI in der Praxis' of the Federal Ministry of Education and Research. Another Fraunhofer IPA research project is part of the same funding measure: 'Deep Picking' uses AI to optimize robot-based picking. The IFF is involved in the 'AI-based robot calibration' (KIRK) project.