PILOT: One Physics-Integrated Generation Framework to Unify 2D and 3D Radio Map Construction

TL;DR

PILOT introduces a physics-integrated autoregressive framework for unified 2D and 3D radio map construction, improving accuracy and speed over existing methods by leveraging environment-aware sequential generation.

Contribution

It proposes a novel wavefront sequence generation method guided by environment instructions, extending to 3D with height-slice stacking and a gradient loss for vertical continuity.

Findings

Achieves lowest NMSE on 2D benchmarks.

Reduces NMSE by 78% compared to diffusion baseline in 3D.

Outperforms sparse measurement and zero-shot cross-domain methods.

Abstract

Unified 2D and 3D radio map construction supports network planning, wireless digital twins, and unmanned aerial vehicle (UAV) applications. In urban environments, blockage, reflection, and diffraction make accurate construction expensive for physics-based solvers. Autoregressive next-token prediction offers a single sequential formulation that can cover both 2D and 3D generation, but standard raster ordering ignores the spatial structure of radio propagation. When generation follows propagation, each token is predicted from propagation-relevant history rather than spatially arbitrary context, which provides more causally informative conditioning and lowers conditional uncertainty. We propose PILOT, a pretrained autoregressive framework that replaces raster scan with a wavefront sequence expanding outward from the transmitter. Each prediction step is guided by an environment-aware instruction that spatially aligns environment features with the queried radio map region. The same framework extends to 3D radio maps through height-slice stacking while a gradient loss enforces vertical continuity. On standard 2D benchmarks, PILOT achieves the lowest NMSE among all baselines. For volumetric generation, it reduces NMSE by 78% relative to the diffusion baseline at roughly $2500\times$ faster inference. It also outperforms methods that rely on 10% sparse measurements and achieves the best zero-shot results in the cross-domain evaluation.