AoI-FusionNet: Age-Aware Tightly Coupled Fusion of UWB-IMU under Sparse Ranging Conditions

Abstract

Accurate motion tracking of snow particles in avalanche events requires robust localization in global navigation satellite system (GNSS)-denied outdoor environments. This paper introduces AoI-FusionNet, a tightly coupled deep learning-based fusion framework that directly combines raw ultra-wideband (UWB) time-of-flight (ToF) measurements with inertial measurement unit (IMU) data for 3D trajectory estimation. Unlike loose-coupled pipelines based on intermediate trilateration, the proposed approach operates directly on heterogeneous sensor inputs, enabling localization even under insufficient ranging availability. The framework integrates an Age-of-Information (AoI)-aware decay module to reduce the influence of stale UWB ranging measurements and a learned attention gating mechanism that adaptively balances the contribution of UWB and IMU modalities based on measurement availability and temporal freshness. To evaluate robustness under limited data and measurement variability, we apply a diffusion-based residual augmentation strategy during training, producing an augmented variant termed AoI-FusionNet-DGAN. We assess the performance of the proposed model using offline post-processing of real-world measurement data collected in an alpine environment and benchmark it against UWB multilateration and loose-coupled fusion baselines. The results demonstrate that AoI-FusionNet substantially reduces mean and tail localization errors under intermittent and degraded sensing conditions.

Figures (12)

• Figure 1: System model and data flow for UWB-IMU fusion. The mobile node is equipped with a UWB transceiver and a triaxial IMU and communicates with static anchors in a GNSS-denied outdoor environment. Raw UWB ranges with timestamps, and preprocessed inertial measurements are provided as inputs to multiple localization pipelines. Classical baselines include loose-coupled fusion using AKF and a Bi-LSTM model operating on trilaterated UWB positions. In contrast, the proposed AoI-FusionNet performs tightly coupled fusion directly on raw UWB and IMU measurements, incorporating AoI-aware decay, a learned fusion gate, and LSTM-based temporal modeling. The resulting 3D trajectory is evaluated against ground truth.
• Figure 2: Tracking experiment at Innsbruck Nordkettenbahn cable car to derive the trajectory along the avalanche path. An IMU and UWB sensor node together with a reference GNSS is traversing in high alpine terrain that is equipped with static UWB anchors.
• Figure 3: Relative error computed between UWB-only trilaterated positions and RTK GNSS ground truth along Z-axis.
• Figure 4: Calibrated accelerometer and gyroscope measurements along X-, Y-, and Z-axes.
• Figure 5: Comparison of UWB residual distribution for different GAN models.