MUNICH and BARCELONA — In an announcement released Tuesday, February 24, 2026, Rohde & Schwarz, in collaboration with NVIDIA, revealed a new milestone in AI-driven wireless system testing. The latest testbed, scheduled for live demonstration at MWC Barcelona 2026, integrates site-specific channel emulation with the NVIDIA Sionna Research Kit to enable high-fidelity digital twin-based hardware-in-the-loop (HIL) testing for 5G-Advanced and 6G architectures.
The collaboration represents a transition from link-level validation to full system-level verification, utilizing the complete 5G NR protocol stack to bridge the gap between AI simulations and real-world network deployments.
Technical Integration and Digital Twin Specs
The integrated testbed addresses the “sparse data” challenge in AI training by generating synthetic, physics-accurate datasets. The hardware configuration leverages Rohde & Schwarz’s high-performance instrumentation to recreate dynamic RF environments without requiring field testing:
- Signal Generation: The R&S SMW200A vector signal generator emulates complex, site-specific radio channels.
- Signal Analysis: The FSW signal and spectrum analyzer provides real-time verification of AI-driven link adaptation.
- NVIDIA Sionna Research Kit: Powered by a single NVIDIA DGX Spark, the kit runs a software-defined 5G RAN based on OpenAirInterface (OAI).
- Ray Tracing: Differentiable ray-tracing software simulates real-world signal propagation, allowing the AI to learn site-specific characteristics and user equipment-specific behavior on the fly.
Executive Perspective
“We’re excited to continue our ongoing collaboration with NVIDIA with this latest proof-of-concept for testing AI-enhanced base stations under realistic propagation conditions,” said Gerald Tietscher, Vice President Signal Generators, Power Supplies and Meters at Rohde & Schwarz. “Leveraging digital twin technology and ray tracing, this approach facilitates more efficient and accurate testing of next-generation receiver architectures.“
Soma Velayutham, Global Industry Business Development Lead for Telecommunications at NVIDIA, added: “Synthetic data generation is transforming the way we train and validate AI-RAN systems by ensuring accuracy, scalability, and privacy. Rohde & Schwarz, leveraging the NVIDIA Sionna Research Kit, exemplifies how industry-leading expertise can accelerate progress in this critical field.”
