Bayesian Learning-Enhanced Navigation with Deep Smoothing for Inertial-Aided Navigation
This work addresses accuracy limitations in navigation for applications like survey and mapping, offering a novel hybrid approach that is incremental in combining classical and learning-based methods.
The paper tackled the persistent accuracy gap in loosely coupled INS/GNSS navigation systems by proposing BLENDS, a data-driven post-processing framework that integrates Bayesian learning with deep smoothing, achieving up to 63% improvement in horizontal position accuracy over baseline methods on real-world datasets.
Accurate post-processing navigation is essential for applications such as survey and mapping, where the full measurement history can be exploited to refine past state estimates. Fixed-interval smoothing algorithms represent the theoretically optimal solution under Gaussian assumptions. However, loosely coupled INS/GNSS systems fundamentally inherit the systematic position bias of raw GNSS measurements, leaving a persistent accuracy gap that model-based smoothers cannot resolve. To address this limitation, we propose BLENDS, which integrates Bayesian learning with deep smoothing to enhance navigation performance. BLENDS is a a data-driven post-processing framework that augments the classical two-filter smoother with a transformer-based neural network. It learns to modify the filter covariance matrices and apply an additive correction to the smoothed error-state directly within the Bayesian framework. A novel Bayesian-consistent loss jointly supervises the smoothed mean and covariance, enforcing minimum-variance estimates while maintaining statistical consistency. BLENDS is evaluated on two real-world datasets spanning a mobile robot and a quadrotor. Across all unseen test trajectories, BLENDS achieves horizontal position improvements of up to 63% over the baseline forward EKF.