A major advancement in AI-driven wireless communication research has been achieved by Rohde & Schwarz and NVIDIA. The most recent proof-of-concept, which will be on display at MWC 2025 in Barcelona, uses high-fidelity ray tracing and digital twin technologies to test neural receivers for 5G-Advanced and 6G in a more realistic manner.
With its most recent breakthrough in neural receiver design and testing, Rohde & Schwarz is pushing the limits of AI-driven wireless communication research.
The most recent proof-of-concept, created in partnership with NVIDIA and set to be demonstrated at MWC 2025 in Barcelona, combines high-fidelity ray tracing and digital twin technology to provide a reliable framework for testing 5G-Advanced and 6G neural receivers under realistic propagation scenarios.
In order to enable more effective and precise testing of next-generation receiver architectures, the goal is to close the gap between AI-driven wireless simulations and actual deployment.
As demonstrated at previous Mobile World Congress events, this represents the fourth major milestone in Rohde & Schwarz’s long-term partnership with NVIDIA. From training neural receivers to handle analog impairments to designing unique constellations for pilotless communications, the joint demonstrations have led the way in advances in AI/ML for wireless communications in recent years.
The demonstration’s main component is NVIDIA Sionna, an open-source, GPU-accelerated library for link-level simulations that creates realistic RF propagation circumstances using ray-traced wireless channel models.
The R&S SMW200A vector signal generator from Rohde & Schwarz, which simulates intricate real-world radio channels without the need for pricey external RF fading equipment, may then easily receive the simulation results. This innovative testbed facilitates data-driven neural component fine-tuning using realistic training data and allows testing and verification of AI/ML-based receiver algorithms.
Data from a specific channel-sounding measuring campaign conducted in an urban street-canyon scenario is used to calibrate the simulation and guarantee that the digital twin and ray-tracing models faithfully represent real-world conditions.
These exact data are combined with NVIDIA Sionna to further improve the ray tracer’s modeling capabilities for electromagnetic propagation and material interactions. As a result, the digital duplicate of the real RF environment is calibrated.
With the use of this mix of technologies, next-generation machine learning-based communication methods, including neural receivers and ML-based CSI feedback upgrades, may be tested and validated more precisely at specific sites.
Rohde & Schwarz is a key contributor to global 6G research, collaborating with industry partners, research institutions, and standardization bodies to develop the next generation of wireless technologies, expected to be commercially deployed by 2030.
Visitors to MWC 2025 can experience this milestone demonstration live and speak with experts from Rohde & Schwarz and NVIDIA at the Rohde & Schwarz booth 5A80 in hall 5 of the Fira Gran Via in Barcelona from March 3 to 6, 2025.
Leadership Comments
Gerald Tietscher, Vice President Signal Generators, Power Supplies and Meters at Rohde & Schwarz, said: “The collaboration with NVIDIA marks a significant milestone in advancing AI/ML applications in wireless communications. Our work has already demonstrated the potential of AI in wireless system design, from custom constellations to neural receivers handling real-world impairments. Now, with the integration of digital twins and ray tracing, we are further expanding the possibilities of AI-driven signal processing.”
Soma Velayutham, Vice President of Telecommunications at NVIDIA, said: “Digital twin technology has transformative potential in wireless system design. By integrating advanced NVIDIA ray tracing and machine learning into receiver development, Rohde & Schwarz is paving the way for AI-native 6G networks poised to offer outstanding efficiency and innovation compared with conventional implementations.”
Further Info on AI/ML for 6G Networks:CLICK HERE
