From Embedded to AI-powered Cyberphysical Systems and Beyond

E. Faliagka, A. Spournias, C. Antonopoulos, N. Voros (Univ. of Peloponnese, Greece)

During the recent years we are experiencing the emergence of an interconnected world. Domains like electronics, embedded systems and telecommunications are now converging, leading to new generation of systems: Cyber-physical systems (CPS). New requirements from demanding applications call for new system architectures for interconnected systems that exploit state of the art communication technologies like 5G, 6G and beyond. The internet of everything paradigm is dominated by AI and ML for providing more efficient and more green applications strengthening reliability, fault tolerance, and security. It also leads to CPS designs that work in a decentralized way, collaboratively, in an equilibrium, by sharing tasks and data with minimal central intervention. Also, systems are able to interact with the CPS/CPSoS (Cyber-physical system of systems) human users/operators through extended reality modules (e.g., through AR glasses and haptics interfaces) to increase human situational awareness, but also to include human behavior in the CPSoS design and operation phase (using human-based reinforced learning). A prominent example of next generation of networked embedded systems using AI is the domain of autonomous driving, where malfunctions and security vulnerabilities can lead to serious incidents causing physical harm to humans or their environment. Therefore, approaches to minimize the risk caused by faults of such intelligent systems while minimizing development costs are essential in order to maintain vital services and public confidence in them. Finally, these domains have a crucial role in healthcare systems. Ambient Assisted Living environments use CPS/CPSoS systems combined with AI to make decisions for the vital signs of the residents and provide remote monitoring. They have also impact on the domain of smart surgery, that includes live data in surgery, novel visualization systems and tissue sensing. The common thread is improved decision making by surgeons and other healthcare professionals, enabled by the novel provision of information.