# UAV-aided Radio Map Construction Exploiting Environment Semantics

arXiv: https://arxiv.org/abs/2107.10574 · HTML: https://mlsanity.com/paper/2107.10574/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jul 2021.

## Built on by (most cited first, 11 of 11)

- [Fast and Accurate Cooperative Radio Map Estimation Enabled by GAN](https://mlsanity.com/paper/2402.02729/) (2024)
- [Diffraction and Scattering Aware Radio Map and Environment Reconstruction using Geometry Model-Assisted Deep Learning](https://mlsanity.com/paper/2403.00229/) (2024)
- [Empowering Intelligent Low-altitude Economy with Large AI Model Deployment](https://mlsanity.com/paper/2505.22343/) (2025)
- [Blind Construction of Angular Power Maps in Massive MIMO Networks](https://mlsanity.com/paper/2510.07071/) (2025)
- [Two-Stage Radio Map Construction with Real Environments and Sparse Measurements](https://mlsanity.com/paper/2410.18092/) (2024)
- [Strategic Application of AIGC for UAV Trajectory Design: A Channel Knowledge Map Approach](https://mlsanity.com/paper/2412.00386/) (2024)
- [Unsupervised Radio Map Construction in Mixed LoS/NLoS Indoor Environments](https://mlsanity.com/paper/2510.08015/) (2025)
- [Physics-Informed Neural Networks for MIMO Beam Map and Environment Reconstruction](https://mlsanity.com/paper/2510.21238/) (2025)
- [RadioGen3D: 3D Radio Map Generation via Adversarial Learning on Large-Scale Synthetic Data](https://mlsanity.com/paper/2602.18744/) (2026)
- [CSI-tuples-based 3D Channel Fingerprints Construction Assisted by MultiModal Learning](https://mlsanity.com/paper/2603.25288/) (2026)
- [BeamRMX: Radiation-Pattern-Driven Learning for Generalizable Beam Radio Map Prediction and Beam Management](https://mlsanity.com/paper/2609.00615/) (2026)

## Abstract (arXiv)

This paper constructs a full dimensional (6D) radio map to predict the channel gain between any transmitter location and any receiver location based on received signal strength (RSS) measurements between low-altitude aerial nodes and ground nodes. The main challenge is how to describe the signal strength attenuation due to the blockage from the environment. Conventional interpolation-type approaches fail to exploit the close relation between the radio map and the geometry of the environment. This paper proposes to construct radio maps by first estimating and constructing a multi-class 3D virtual obstacle map that describes the geometry of the environment with radio semantics. Mathematically, a least-squares problem is formulated to jointly estimate the virtual obstacle map and the propagation parameters. This problem is found to have a partial quasiconvexity that leads to the development of an efficient parameter estimation and radio map construction algorithm. Numerical experiments confirm that the proposed method substantially reduces the amount of measurement required for achieving the same radio map accuracy. It is also demonstrated that in a unmanned aerial vehicle (UAV)-aided relay communication scenario, a radio map assisted approach for UAV placement can achieve more than 50% capacity gain.