Cross-layer cognitive optimization tools & methods for the lifecycle support of dependable CPSoS

Cyber-physical Systems of Systems (CPSoS) are large complex systems where physical elements interact with and are controlled by a large number of distributed and networked computing elements and human users. Their increasingly stringent demands on reduction of emissions, efficient use of resources,  high service and product quality levels and, of course, low cost and competitiveness in the world market introduce big challenges related to the design operation continuum of dependable connected CPSs. CPSoSaware project aims at developing the models and software tools to allocate computational power/resources to the CPS end devices of the System by determining and generating autonomously what cyber-physical processes will be handled by a device’s heterogeneous component (processor cores, GPUs, FPGA fabric, software stacks).  The CPSoSaware solution will rely on Artificial Intelligence support in order to strengthen the reliability, fault tolerance, and security at the system level but also will be able to lead to CPS designs that work in a decentralized way, collaboratively, in an equilibrium, by sharing tasks and data with minimal central intervention. Also, the CPSaware system will interact with the human users/operators through extended reality visual and touchable interfaces increasing situational awareness. The CPSoSaware system will be evaluated:

1. in the automotive sector, in mixed traffic environments with semi-autonomous connected vehicles proactively passing the dynamic driving task back to the human driver, whenever system limits are approached and
2. in the manufacturing industry, we consider inspection and repair scenarios using collaborative robots passing the control tasks to the operator, in critical situations.

The impact of such a holistic and innovative approach is huge and the foundations laid here are expected to result in widespread adoption of CPSoS in a larger number of technology sectors.