R&I group

AI-driven Systems

The AI-driven Systems research group focuses on leveraging artificial intelligence and machine learning to address critical challenges in the sustainability and performance of next-generation networks, focusing on 6G virtualized RANs and Integrated Sensing and Communications (ISAC). By combining AI, energy optimization, and innovative sensing solutions, the AI-driven Systems research group contributes to making 6G networks sustainable, scalable, and capable of meeting the demands of advanced use cases in sensing and communications.

Research lines

AI-RAN: This research line aims to explore the limits of AI-driven network automation in future 6G systems. It aims to design sustainable 6G Virtualized Radio Access Networks by leveraging open and cloud-native technologies, possibly supported by smart surfaces. Researchers rely on analytical evaluations and experimental testing on real testbeds to validate their solutions.
ISAC: Integrated Sensing and Communications 6G Systems: This research aims to overcome current limitations in localization accuracy and the high cost of dedicated sensing systems. It leverages Digital Twins and focuses on the design of cost-efficient, in-band joint solutions to enhance both sensing and communication capabilities. Smart surfaces emerge as key technology enablers in this research line, supporting ISAC scenarios. Methodologies include analytical evaluation, simulations, and experimental testing, using mobile robots and drones.

Innovation lines

3DSAR
5GNSS
HachiGO

Technologies

Sustainable 6G virtualized RANs
6G Integrated Sensing and Communications (ISAC)
Gen AI for RANs
AI/ML-driven 6G RAN Automation
vRANs Cost/Energy-efficiency
vRAN+Smart Surfaces
Cellular/RIS-based localization
Collaborative Mobile Robotics
Smart surfaces
Wireless XR/VR
Precision Medicine

Group leader

Xavier Costa

Areas

Smart Networks & Services 5G/6G Artificial Intelligence (AI) Cybersecurity Social Impact

AI-driven Systems

Projects

AI-driven Systems

Publications

Energy-aware Joint Orchestration of 5G and Robots: Experimental Testbed and Field Validation

M. Groshev, L. Zanzi, C. Delgado, X. Li, A. d. l. Oliva and X. Costa-Pérez, “Energy-Aware Joint Orchestration of 5G and Robots: Experimental Testbed and Field Validation,” in IEEE Transactions on Network and Service Management, vol. 22, no. 4, pp. 3046-3059, Aug. 2025, doi: 10.1109/TNSM.2025.3555126. keywords: {Robots;Robot kinematics;5G mobile communication;Robot sensing systems;Sensors;Resource management;Real-time systems;Energy consumption;Testing;Peer-to-peer computing;5G;orchestration;robotics;optimization;offloading;energy efficient},

Quantum Computing in the RAN with Qu4Fec: Closing Gaps Towards Quantum-based FEC processors

Nikolaos Apostolakis, Marta Sierra-Obea, Marco Gramaglia, Jose A. Ayala-Romero, Andres Garcia-Saavedra, Marco Fiore, Albert Banchs, and Xavier Costa-Perez. 2025. Quantum Computing in the RAN with Qu4Fec: Closing Gaps Towards Quantum-based FEC processors. Proc. ACM Meas. Anal. Comput. Syst. 9, 2, Article 36 (June 2025), 25 pages. https://doi.org/10.1145/3727128

Curved Apertures for Customized Wave Trajectories: Beyond Flat Aperture Limitations

J. M. Canals, F. Devoti, V. Sciancalepore, M. D. Renzo and X. Costa-Pérez, “Curved Apertures for Customized Wave Trajectories: Beyond Flat Aperture Limitations,” in IEEE Wireless Communications Letters (2025).

AI-driven Systems