Search papers, labs, and topics across Lattice.
The paper investigates the accuracy of channel-centric models in predicting end-to-end throughput in a private 5G industrial environment using ray-tracing simulations and Gaussian process regression. Through a measurement campaign with a mobile robot in a radio-shielded facility, the study reveals that ray-tracing simulators systematically over-predict throughput due to overestimation of sustainable MIMO spatial layers. A Gaussian process model, trained directly on end-to-end throughput measurements, significantly reduces prediction error, highlighting the limitations of relying solely on channel-level metrics for communication-aware robot planning.
Ray-tracing simulators can overestimate 5G throughput even with accurate channel predictions, because they fail to capture the real-world adaptation of MIMO spatial layers.
Communication-aware robot planning requires accurate predictions of wireless network performance. Current approaches rely on channel-level metrics such as received signal strength and signal-to-noise ratio, assuming these translate reliably into end-to-end throughput. We challenge this assumption through a measurement campaign in a private 5G industrial environment. We evaluate throughput predictions from a commercial ray-tracing simulator as well as data-driven Gaussian process regression models against measurements collected using a mobile robot. The study uses off-the-shelf user equipment in an underground, radio-shielded facility with detailed 3D modeling, representing a best-case scenario for prediction accuracy. The ray-tracing simulator captures the spatial structure of indoor propagation and predicts channel-level metrics with reasonable fidelity. However, it systematically over-predicts throughput, even in line-of-sight regions. The dominant error source is shown to be over-estimation of sustainable MIMO spatial layers: the simulator assumes near-uniform four-layer transmission while measurements reveal substantial adaptation between one and three layers. This mismatch inflates predicted throughput even when channel metrics appear accurate. In contrast, a Gaussian process model with a rational quadratic kernel achieves approximately two-thirds reduction in prediction error with near-zero bias by learning end-to-end throughput directly from measurements. These findings demonstrate that favorable channel conditions do not guarantee high throughput; communication-aware planners relying solely on channel-centric predictions risk overly optimistic trajectories that violate reliability requirements. Accurate throughput prediction for 5G systems requires either extensive calibration of link-layer models or data-driven approaches that capture real system behavior.
