Low-Altitude Channel Multipath Prediction via Panoramic Perception and Vision-Language Model

Unmanned aerial vehicle (UAV) communication is expected to support a wide range of low-altitude applications in 6G mobile networks. However, traditional statistical channel models provide limited accuracy in specific environments, while deterministic methods such as ray tracing usually rely on accurate three-dimensional environment models and involve high computational complexity. Existing multimodal channel prediction approaches mainly focus on large-scale metrics such as path loss, and remain insufficient for modeling small-scale parameters. To address these limitations, this paper proposes PanoLAMP, a Panoramic perception and vision-language model-based Low-Altitude Multipath Prediction framework. It adopts a pretrained vision-language model as the backbone and captures the propagation environment features through panoramic RGB-D observations collected at both the transmitter and receiver to predict the delay, power, azimuth angle, and zenith angle offset relative to the line-of-sight path. Experiments are conducted on a synthetic dataset containing 18,949 UAV-vehicle links across seven UAV altitudes. Experimental results show that the proposed method consistently outperforms representative baselines in both multipath parameters and statistical metrics, and demonstrates stronger generalization across different flight heights.

Directional Measurements and Analysis for FR3 Low-Altitude Channels in a Campus Environment

In this paper, we present detailed low-altitude channel measurements at the FR3 band in an outdoor campus environment. Using a time-domain channel sounder system, we conduct two types of measurements: path loss measurements by moving the transmitter (Tx) at one-meter intervals along a 26-point rooftop path, and directional power angular spectrum measurements through antenna scanning at half-power beam width intervals. The path loss analysis across different Rx shows that the close-in model outperforms conventional 3GPP models and height-corrected variants, with path loss exponents close to free space values indicating line-of-sight dominance. The power angular spectrum measurements show that propagation behavior varies significantly with environmental conditions. Closer Rx exhibit stronger sensitivity to ground reflections during downward Tx tilting, while obstructed links display uniform angular characteristics due to dominant scattering effects, and corridor environments produce asymmetric power distributions. These results indicate that low-altitude propagation is characterized by complex interactions between Tx height and ground scattering mechanisms, providing fundamental insights for channel modeling in emerging mid-band communication systems.