Towards planning and control in cognitive factories - A generic model including learning effects and knowledge transfer across system entities

Abstract Cognitive abilities allow robots to learn and reason from their environment. The gained knowledge can then be incorporated into the robot’s actions which in turn affect Therefore, a cognitive robot is no longer static system that performs based on pre-defined set of rules but complex entity dynamically adjusts over time. With this, challenges arise for production systems need observe ideally anticipate behavior. Often, digital twins are employed test optimize control systems. This paper presents generic approach characterize, model simulate learning processes formalized hybrid assuming different station types with effects. Thereby, quantitative qualitative mapped including sharing transfer across entities. A modular parameterizable design enables adjustment use cases. Eventually, instantiated as twin real product disassembly employing cognitive-autonomous among human operators rigidly automated machines. shows great potential integrated beds planning factories.