BLENDS: Bayesian Learning-Enhanced Deep Smoothing for GNSS-Denied Environments

• URL: http://arxiv.org/abs/2606.22456v1
• Date: Sun, 21 Jun 2026 12:00:10 GMT
• Title: BLENDS: Bayesian Learning-Enhanced Deep Smoothing for GNSS-Denied Environments
• Abstract summary: This paper presents a transformer-based framework that augments Bayesian smoothing with learned covariance adaptation and state correction.<n>The proposed method preserves the statistical foundations of Bayesian estimation while leveraging data-driven learning to improve navigation accuracy.<n> Evaluations on the quadrotor dataset with outages demonstrate that BLENDS consistently outperforms both model-based smoothers, achieving up to 25.6% improvement in the position root mean square error.
• Score: 8.510813384980262
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Maintaining accurate navigation during GNSS outages remains a significant challenge for autonomous systems relying on low-cost inertial sensors. While classical smoothing methods, such as the two-filter smoother and Rauch-Tung-Striebel smoother, exploit measurements collected before and after an outage, their performance remains limited by the accuracy of conventional GNSS measurements. This paper presents Bayesian learning-enhanced navigation with deep smoothing (BLENDS), a transformer-based framework that augments Bayesian smoothing with learned covariance adaptation and state correction. The proposed method preserves the statistical foundations of Bayesian estimation while leveraging data-driven learning to improve navigation accuracy. Evaluations on the quadrotor dataset with GNSS outages demonstrate that BLENDS consistently outperforms both model-based smoothers, achieving up to 25.6% improvement in the position root mean square error while also reducing estimation uncertainty. Furthermore, BLENDS learns to compensate for the systematic bias between conventional GNSS positioning and RTK ground truth, enabling accuracy beyond that achievable with conventional GNSS measurements alone. The results demonstrate the potential of learning-enhanced Bayesian smoothing for resilient and high-accuracy navigation in GNSS-challenged environments.

Related papers

• GNSS-free quantum gravity-aided navigation and fine-scale marine surveying with a strapdown quantum gravimeter [48.52363836235071]
  We perform gravity map matching and fine-resolution gravity survey with a mobile quantum gravimeter aboard a 29 m surface vessel.<n>A hybrid sensor corrected the inertial solution over an 83 km maritime trajectory by referencing locally measured gravity to a satellite-derived anomaly map.<n>Gravity-aiding constrains INS drift and delivers bounded positioning at nautical-mile-level accuracy.
  arXiv  Detail & Related papers  (2026-08-26T09:16:02Z)
• WinTA-GIL: Windowed Trajectory Alignment for GNSS-IMU-LiDAR Heading Refinement in Intermittent Signal Environments [5.192383265052114]
  This paper proposes WinTA-GIL, a novel heading refinement framework for navigation systems.<n>It integrates information from GNSS, IMU, and LiDAR through a temporal window-based optimization strategy.<n>Experiments on both open-source and self-collected datasets demonstrate that WinTA-GIL significantly outperforms state-of-the-art approaches in both estimation accuracy and robustness system.
  arXiv  Detail & Related papers  (2026-07-06T09:59:33Z)
• Information-Aided DVL Calibration [5.5217350574838875]
  The Doppler velocity log (DVL) velocity measurements are critical to the accuracy of autonomous underwater vehicle (AUV) navigation solutions.<n>To ensure accurate measurements, the DVL is commonly before mission start while the AUV sails on the water surface, receiving global navigation satellite system (GNSS) signals that provide accurate reference measurements.<n>In certain environments, errors signals may be unavailable, rendering conventional calibration impossible and forcing the use of uncalibrated DVL measurements.<n>This work proposes information-aided calibration (IAC) with two main contributions: first, improving the accuracy of conventional Kalman filter-based calibration in
  arXiv  Detail & Related papers  (2026-06-30T06:54:21Z)
• Loosely Coupled Factor Graph Optimization for Pseudolite-Augmented Navigation [3.5757009186345385]
  This paper presents a loosely coupled factor graph optimization framework that fuses the least-squares (LS) solutions with inertial measurement unit (IMU) data.<n>The evaluation considers low visibility scenarios with four high-elevation satellites and up to two PL transmitters over an 80s window.<n>Compared to a-IMU baseline, PL transmitters further improves positioning accuracy, with performance depending on geometry.
  arXiv  Detail & Related papers  (2026-05-24T10:18:46Z)
• Enhanced INS/GNSS State Estimation using GNSS-Based Acceleration Measurements [5.5217350574838875]
  We propose utilizing past measurements alongside a motion model to extract meaningful vehicle acceleration information.<n>This acceleration measurement is then integrated into the INS/GNSS filter to improve robustness and accuracy.<n>Results demonstrate consistent positioning accuracy improvements relative to the standard position-aided filter.
  arXiv  Detail & Related papers  (2026-05-23T23:04:30Z)
• Bayesian Learning-Enhanced Navigation with Deep Smoothing for Inertial-Aided Navigation [8.510813384980262]
  BLENDS is a data-driven post-processing framework that augments the classical two-filter smoother with a transformer-based neural network.<n> BLENDS achieves horizontal position improvements of up to 63% over the baseline forward EKF.
  arXiv  Detail & Related papers  (2026-03-26T12:11:59Z)
• Accurate Pedestrian Tracking in Urban Canyons: A Multi-Modal Fusion Approach [10.102277409472444]
  The contribution describes a pedestrian navigation approach designed to improve localization accuracy in urban environments where performance is degraded.<n>To address limitations and the impracticality of camera-based visual positioning, the work proposes a particle filter based fusion of inertial data.<n>The system was evaluated on six challenging walking routes in downtown San Francisco using three metrics related to sidewalk correctness and localization error.
  arXiv  Detail & Related papers  (2026-01-29T23:23:59Z)
• Adaptive Factor Graph-Based Tightly Coupled GNSS/IMU Fusion for Robust Positionin [0.0]
  Tightly coupled/IMU fusion improves robustness but remains vulnerable to non-Gaussian noise and outliers.<n>We present a robust and adaptive factor graph-based fusion framework that integrates pseudorange measurements with IMU preintegration factors.<n>The proposed solution reduces positioning errors by up to 41% relative to standard FGO, and achieves even larger improvements over extended Kalman filter (EKF) baselines in tunable urban environments.
  arXiv  Detail & Related papers  (2025-11-28T09:33:13Z)
• Addressing Label Shift in Distributed Learning via Entropy Regularization [45.25670338948615]
  We address the challenge of minimizing true risk in multi-node distributed learning.<n>We propose the Versatile Robust Label Shift (VRLS) method, which enhances the maximum likelihood estimation of the test-to-train label density ratio.
  arXiv  Detail & Related papers  (2025-02-04T18:14:27Z)
• Stable Neighbor Denoising for Source-free Domain Adaptive Segmentation [91.83820250747935]
  Pseudo-label noise is mainly contained in unstable samples in which predictions of most pixels undergo significant variations during self-training. We introduce the Stable Neighbor Denoising (SND) approach, which effectively discovers highly correlated stable and unstable samples. SND consistently outperforms state-of-the-art methods in various SFUDA semantic segmentation settings.
  arXiv  Detail & Related papers  (2024-06-10T21:44:52Z)
• Angle Robustness Unmanned Aerial Vehicle Navigation in GNSS-Denied Scenarios [66.05091704671503]
  We present a novel angle navigation paradigm to deal with flight deviation in point-to-point navigation tasks. We also propose a model that includes the Adaptive Feature Enhance Module, Cross-knowledge Attention-guided Module and Robust Task-oriented Head Module.
  arXiv  Detail & Related papers  (2024-02-04T08:41:20Z)
• Bias-Aware Minimisation: Understanding and Mitigating Estimator Bias in Private SGD [56.01810892677744]
  We show a connection between per-sample gradient norms and the estimation bias of the private gradient oracle used in DP-SGD. We propose Bias-Aware Minimisation (BAM) that allows for the provable reduction of private gradient estimator bias.
  arXiv  Detail & Related papers  (2023-08-23T09:20:41Z)
• Uncertainty-Aware Deep Calibrated Salient Object Detection [74.58153220370527]
  Existing deep neural network based salient object detection (SOD) methods mainly focus on pursuing high network accuracy. These methods overlook the gap between network accuracy and prediction confidence, known as the confidence uncalibration problem. We introduce an uncertaintyaware deep SOD network, and propose two strategies to prevent deep SOD networks from being overconfident.
  arXiv  Detail & Related papers  (2020-12-10T23:28:36Z)
• Stochastic-Sign SGD for Federated Learning with Theoretical Guarantees [49.91477656517431]
  Quantization-based solvers have been widely adopted in Federated Learning (FL) No existing methods enjoy all the aforementioned properties. We propose an intuitively-simple yet theoretically-simple method based on SIGNSGD to bridge the gap.
  arXiv  Detail & Related papers  (2020-02-25T15:12:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.