Click here to download the session cfp.

The selection of proper automation components for a given task is a complex and time-consuming challenge. As customer requirements tend to change more and more frequently, it becomes necessary to pursue flexible and changeable automation approaches. Recent research has introduced approaches based on capabilities and skills using holistic data models (i.e. ontologies, DSLs, variability models …). While capabilities are seen as an abstract description of the (manufacturing) processes a system is able to perform, skills are often described as their executable counterparts (i.e. modelling an invocation interface such as OPC UA). In order to automatically find solutions for a customer requirement, required tasks as well as domain specific constraints have to be matched with capabilities provided by automation components. This can be achieved by various techniques such as AI planning or knowledge graph exploration and reasoning. Skill based process plans can then be orchestrated by combining the skills which are related to the capabilities found in the previous step. Finally, simulation and optimization of such process plans can be performed before executing them.