# TRACE: Learning to Self-Calibrate Wireless Digital Twins from ISAC Measurements

arXiv: https://arxiv.org/abs/2609.32923 · HTML: https://mlsanity.com/paper/2609.32923/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 24 references that are in the map.
- First posted on arXiv 26 Sep 2026.

## Builds on (most cited first, 16 of 16)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [RadioUNet: Fast Radio Map Estimation with Convolutional Neural Networks](https://mlsanity.com/paper/1911.09002/) (2019)
- [DeepMIMO: A Generic Deep Learning Dataset for Millimeter Wave and Massive MIMO Applications](https://mlsanity.com/paper/1902.06435/) (2019)
- [Integrated Sensing and Communications: Towards Dual-functional Wireless Networks for 6G and Beyond](https://mlsanity.com/paper/2108.07165/) (2021)
- [NeRF2: Neural Radio-Frequency Radiance Fields](https://mlsanity.com/paper/2305.06118/) (2023)
- [Calibrating Wireless Ray Tracing for Digital Twinning using Local Phase Error Estimates](https://mlsanity.com/paper/2312.12625/) (2023)
- [Learnable Wireless Digital Twins: Reconstructing Electromagnetic Field with Neural Representations](https://mlsanity.com/paper/2409.02564/) (2024)
- [Differentiable and Learnable Wireless Simulation with Geometric Transformers](https://mlsanity.com/paper/2406.14995/) (2024)
- [ISAC Imaging by Channel State Information using Ray Tracing for Next Generation 6G](https://mlsanity.com/paper/2509.06672/) (2025)
- [Radio Map Prediction from Noisy Environment Information and Sparse Observations](https://mlsanity.com/paper/2602.11950/) (2026)
- [OpenGERT: Open Source Automated Geometry Extraction with Geometric and Electromagnetic Sensitivity Analyses for Ray-Tracing Propagation Models](https://mlsanity.com/paper/2501.06945/) (2025)
- [A Robust CSI-Based Scatterer Geometric Reconstruction Method for 6G ISAC System](https://mlsanity.com/paper/2510.16389/) (2025)
- [Vision-Language-Model-Guided Differentiable Ray Tracing for Fast and Accurate Multi-Material RF Parameter Estimation](https://mlsanity.com/paper/2601.18242/) (2026)
- [Physically Accurate Differentiable Inverse Rendering for Radio Frequency Digital Twin](https://mlsanity.com/paper/2603.18026/) (2026)
- [RadTwin: Generalizable Wireless Digital Twin for Dynamic Environments](https://mlsanity.com/paper/2604.23310/) (2026)

## Abstract (arXiv)

Wireless digital twins (DTs) rely on 3D environment models to predict radio propagation and support wireless-network decisions, yet these models are often initialized from imperfect 3D maps. Errors in building position, height, footprint, and orientation can therefore cause a high-fidelity propagation engine to simulate the wrong physical environment. In this paper, we study how a deployed wireless network can repair an existing DT using its own radio frequency (RF) measurements. In particular, we introduce Twin Residual Alignment and Calibration Engine (TRACE), a physics-grounded learning-based self-calibration framework that treats twin maintenance as residual alignment between the physical world and the current DT. Using the same sensing configuration as the physical measurements, TRACE ray-traces the current DT, coherently backprojects the measured and simulated RF onto a common world grid, and extracts the same local region around each building's current DT position. A multi-view corrector then fuses evidence across sensing nodes and neighboring buildings to predict a gated six-parameter correction per building, without relying on absolute layout or sensor ordering, and supports iterative correction through re-rendering. On 5,400 held-out samples from unseen simulated scenes at 28 GHz, TRACE reduces 3D position RMSE from 2.202 m to 0.302 m and yaw RMSE from 4.978deg to 0.894deg, outperforming ViT and U-Net baselines under changes in layout, building count, sensing-node count, and SNR. On measured 28 GHz RF data from the NIST outdoor courtyard, a model trained only on synthetic RF reduces mean planar wall-position error from 1.00 m to 7.8 cm, without measured-data fine-tuning or geometric labels. These results show that the discrepancy between measured and twin-rendered RF can serve as a learning signal for repairing a wireless DT.