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

2026-04-26

AI Summary

This work addresses the high simulation cost of existing radio channel map construction methods in urban environments, which stems from complex electromagnetic effects, and the neglect of spatial causality in propagation by current generative models. To overcome these limitations, the authors propose PILOT, a novel framework that, for the first time, integrates the physical laws of radio wavefront propagation into an autoregressive generation sequence. By modeling channel maps in wavefront order centered on the transmitter and incorporating environment-aware conditioning, height-slice stacking, and a gradient continuity loss, PILOT enables efficient and continuous modeling of both 2D and 3D channel maps. The method achieves the lowest normalized mean squared error (NMSE) on 2D benchmarks and, in 3D scenarios, reduces NMSE by 78% compared to diffusion models while accelerating inference by approximately 2,500×. It also demonstrates superior performance under sparse measurements (10% data) and zero-shot cross-domain settings.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: Generation
• Intelligent Robots: Localization, Mapping, and Navigation

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

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.

Problem

• radio map construction
• 2D and 3D unification
• urban propagation modeling
• autoregressive generation
• spatial structure

Innovation

• wavefront sequencing
• physics-integrated generation
• autoregressive radio map
• environment-aware instruction
• 3D radio map