WiSegRT: Dataset for Site-Specific Indoor Radio Propagation Modeling with 3D Segmentation and Differentiable Ray-Tracing

TL;DR

WiSegRT tackles indoor radio propagation modeling, a problem made challenging by rich multipath and material-dependent interactions. It introduces a differentiable ray-tracing pipeline operating on segmented 3D indoor scenes to produce site-specific channel impulse responses for numerous Tx–Rx configurations, with CIRs defined by $h(\tau)=\sum_{i=1}^N \alpha_i \delta(\tau-\tau_i)$ and its baseband form $h_b(\tau)=\sum_{i=1}^N \alpha_i e^{-j 2\pi f \tau_i} \delta(\tau-\tau_i)$. Key contributions include ten high-fidelity scenes with per-path data and geometries in .obj format, a detailed comparison showing the impact of geometry and material fidelity on propagation statistics, and demonstrated applications in ML-based channel prediction, indoor localization, object detection, and wireless digital twins. The dataset enables vision-aided radio tracing and physics-informed indoor sensing, with future work on model-editing libraries for digital-twin style scenario customization.

Abstract

The accurate modeling of indoor radio propagation is crucial for localization, monitoring, and device coordination, yet remains a formidable challenge, due to the complex nature of indoor environments where radio can propagate along hundreds of paths. These paths are resulted from the room layout, furniture, appliances and even small objects like a glass cup. They are also influenced by the object material and surface roughness. Advanced machine learning (ML) techniques have the potential to take such non-linear and hard-to-model factors into consideration. However, extensive and fine-grained datasets are urgently required. This paper presents WiSegRT, an open-source dataset for indoor radio propagation modeling. Generated by a differentiable ray tracer within the segmented 3-dimensional (3D) indoor environments, WiSegRT provides site-specific channel impulse responses for each grid point relative to the given transmitter location. We expect WiSegRT to support a wide-range of applications, such as ML-based channel prediction, accurate indoor localization, radio-based object detection, wireless digital twin, and more.

Figures (4)

• Figure 1: WiSegRT dataset file structure
• Figure 2: Flow of WiSegRT dataset generation
• Figure 3: Comparison of total received power at different distances
• Figure 4: Radio tracing with vision data and ML