Model predictive control as a service - concept and architecture for use in cloud-based robot control

This paper presents the concept and architecture of a model predictive feedback control system to be used for compensating communication delays in networked industrial robot control. This approach follows the ideas given by the paradigms of Industrie 4.0 that demand for highly networked production devices and functions on different machine layers and IT hierarchy levels. We push the concept of fully outsourced control systems to a point, where even real-time critical feedback processes are driven from cloud-based services over uncertain public networks.