6G-INTENSE project: Press Release

Press Release

During the Plenary Meeting of the 6G-INTENSE project, held in Barcelona on January 27–28, 2026, CNIT presented the key results it has achieved within the project, once again demonstrating CNIT’s leadership at the forefront of 6G research and innovation. 6G-INTENSE, funded by the Smart Networks and Services (SNS) program under Horizon Europe (HORIZON-JU-SNS-2023), is coordinated by Professor Christos Verikoukis (Institute of Industrial Systems, Athena Research Center) and benefits from the outstanding technical support of Professor Adlen Ksentini (EURECOM). Its goal is to create a novel AI-based system architecture for future 6G smart networks, with the ambition to revolutionize industrial sectors, foster digital transformation, and enable smart societies with an enhanced quality of life. The innovative automated network management mechanisms developed within the project pave the way for advanced services and applications, including immersive end-user experiences enabled by the Metaverse. The 6G-INTENSE architecture is based on the advanced integration of resources and services through AI techniques natively embedded into the network architecture. Communication and computation are seamlessly fused into a virtualized continuum, ensuring the efficient and reliable delivery of next-generation services that require tight coordination between networking and computing capabilities.

Within the project, the CNIT Collaborative Research team, led by Professor Carla Fabiana Chiasserini (CNIT–Politecnico di Torino) and Professor Renato Lo Cigno (CNIT–University of Brescia), has developed Joint Communication and Sensing (JCAS)services for mobile user localization and tracking, along with algorithms for the efficient orchestration of these services and of the underlying network and computational resources. Furthermore, CNIT has designed explainable AI solutions for the detection and mitigation of conflicts arising from machine-learning–based network services. Finally, it developed a framework for distributed machine-learning processing at the network edge. CNIT is currently supporting the integration of the project results, with the specific focus on JCAS-enabled services for the Metaverse use case.