Learning the Channel Gain from Anywhere to Anywhere via Cross-environment Transformer Estimators

2026-05-06

AI Summary

Estimating high-dimensional channel gain maps is highly challenging due to the complexity of the six-dimensional input space and the lack of effective spatial structure modeling. This work proposes a meta-learning-based, cross-environment Transformer estimator that, for the first time, integrates physical laws and environmental characteristics into the modeling process. By employing a physics-informed feature mapping and enforcing invariance constraints such as reciprocity, the method implicitly learns spatial channel gain patterns common across multiple environments. Consequently, it achieves high-fidelity map reconstruction with only a few measurements from a new environment. Experimental results demonstrate that the proposed approach reduces the required number of measurements to one-fifth of those needed by existing methods while significantly improving estimation accuracy.

Abstract

Channel-gain maps provide the channel gain between any two locations in a geographical region. They find numerous applications, from resource allocation and interference control to path planning for autonomous vehicles. Channel-gain map estimation (CGME) is considerably more challenging than conventional radio map estimation (RME) because channel-gain maps are functions over a 6-dimensional input space. This calls for specialized methods, which currently rely on the (inaccurate) radio tomographic model or require a prohibitively large number of measurements since they do not exploit any spatial structure. This paper overcomes this issue by leveraging spatial patterns that channel-gain maps exhibit across environments, as dictated by the laws of physics and typical environmental characteristics (e.g. building materials and layouts). Adopting a metalearning perspective, a transformer-based estimator is proposed to implicitly learn this common structure from measurements collected in multiple environments. This enables CGME in new environments from significantly fewer measurements (five times less in our experiments). To maximize learning efficiency, the transformer is composed with a feature map that enforces the invariances of CGME, such as those following from reciprocity. Numerical experiments corroborate the merits of the proposed estimator relative to existing methods.

Problem

• channel-gain map estimation
• radio map estimation
• spatial structure
• metalearning
• transformer

Innovation

• channel-gain map estimation
• transformer-based estimator
• metalearning
• spatial invariance
• cross-environment learning