# Bridging the Data Gap: Digital Twin as a New Paradigm for AI-based Radio Sensing

arXiv: https://arxiv.org/abs/2609.26214 · HTML: https://mlsanity.com/paper/2609.26214/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 15 references that are in the map.
- First posted on arXiv 11 Aug 2026.

## Builds on (most cited first, 10 of 10)

- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Sionna RT: Differentiable Ray Tracing for Radio Propagation Modeling](https://mlsanity.com/paper/2303.11103/) (2023)
- [CSI-based Fingerprinting for Indoor Localization: A Deep Learning Approach](https://mlsanity.com/paper/1603.07080/) (2016)
- [Deep Learning for Radio-based Human Sensing: Recent Advances and Future Directions](https://mlsanity.com/paper/2010.12717/) (2020)
- [Digital Twin Channel for 6G: Concepts, Architectures and Potential Applications](https://mlsanity.com/paper/2403.12467/) (2024)
- [Integrated Sensing and Communications Over the Years: An Evolution Perspective](https://mlsanity.com/paper/2504.06830/) (2025)
- [InverTwin: Solving Inverse Problems via Differentiable Radio Frequency Digital Twin](https://mlsanity.com/paper/2508.14204/) (2025)
- [RayLoc: Wireless Indoor Localization via Fully Differentiable Ray-tracing](https://mlsanity.com/paper/2501.17881/) (2025)
- [Distributed Intelligent Integrated Sensing and Communications: The 6G-DISAC Approach](https://mlsanity.com/paper/2402.18271/) (2024)
- [Integrated Sensing and Communications for 3D Object Imaging via Bilinear Inference](https://mlsanity.com/paper/2308.10423/) (2023)

## Abstract (arXiv)

We present a methodology that places a 3D digital twin (DT) of the environment as the main enabler behind the development of radio sensing at scale. The DT acts as a world model, providing geometry, materials, and transmitter/receiver placements to a ray-tracing engine that generates time-indexed channel impulse responses (CIRs) for large numbers of plausible scenes (moving people and objects, layout variants, seasonal/weather conditions, etc). From these synthetic sequences, we train a sequential neural network that maps CIR time series to spatial occupancy estimates, enabling device-free localization (DFL) without instrumented targets. We posit that sensing is best approached as an environment-conditioned learning problem: rather than seeking a single global model, we advocate training or fine-tuning local models specialized to a site-specific DT. As a first experiment, we introduce a novel State Space Model architecture, trained and evaluated across multiple room geometries. The localization performances obtained demonstrate the potential of the approach.