Talk 1: RobOptiCut – High-performance hardwood veneers for sustainable lightweight construction, Benjamin Breiling, JOANNEUM RESEARCH ROBOTICS

RobOptiCut develops a novel process chain to unlock the potential of hardwood veneers for high-performance lightweight applications. With hardwood resources, particularly beech, expected to increase as forests adapt to climate change, the project addresses the challenge of using this valuable material more efficiently. Today, veneer production for structural applications suffers from high material losses due to defects and insufficient information on fiber orientation. RobOptiCut combines advanced imaging, automated defect detection and robotic processing to identify fiber orientation, remove local defects and repair veneers using scarfed patches. The approach is expected to more than double the yield of top-grade veneers while achieving mechanical properties close to flawless material. In this way, RobOptiCut enables the automated production of high-quality veneer layers and provides a technological basis for advanced hardwood lightweight components.

Talk 2: Simulated First, Live Later: When AI Agents Take Control of the Machine, Michael Eberle, digifai

Digital twins have arrived in mechanical engineering. They enable machines and control software to be developed and tested in a safe virtual environment before the actual system is built and commissioned. However, creating these digital twins takes time. This is where AI agents come in: they support the creation of simulation models and significantly shorten the path to a fully functional digital twin. And then what? Another agent takes over control. First in the simulation, where mistakes come at no cost. Then on the real machine, where they certainly do. Michael Eberle from digifai demonstrates this approach using twin as an example and explains why robust, reliable simulations are essential before AI agents can be allowed anywhere near a real machine.