用学习方法提升GNSS定位误差评估精度，让导航更可靠。
Learning-based GNSS Uncertainty Quantification using Continuous-Time Factor Graph Optimization
- 用离线学习预测异常观测，在线学习逼近噪声分布
- 实测数据验证表明定位性能显著提升，能有效处理信号干扰
- 适合自动驾驶、高精度定位等复杂环境应用
本文提出两种基于学习的全球导航卫星系统（GNSS）测量不确定性量化方法。研究采用离线学习进行异常值预测，以及在线学习对噪声分布进行近似，专门应用于GNSS伪距观测。为开发和评估这些学习方法，提出一种新型多传感器状态估计算法，可从多源传感器输入中准确稳健地估计轨迹，从而生成用于训练不确定性模型的GNSS测量残差。使用在多样城市环境中采集的真实传感器数据验证了所提学习模型。实验结果表明，两种模型均能有效应对GNSS异常值，提升状态估计性能。此外，文章还提供了深入讨论，以推动未来在挑战性环境中构建联邦式鲁棒车辆定位框架的研究。
原文摘要 · Abstract (English)
This short paper presents research findings on two learning-based methods for quantifying measurement uncertainties in global navigation satellite systems (GNSS). We investigate two learning strategies: offline learning for outlier prediction and online learning for noise distribution approximation, specifically applied to GNSS pseudorange observations. To develop and evaluate these learning methods, we introduce a novel multisensor state estimator that accurately and robustly estimates trajectory from multiple sensor inputs, critical for deriving GNSS measurement residuals used to train the uncertainty models. We validate the proposed learning-based models using real-world sensor data collected in diverse urban environments. Experimental results demonstrate that both models effectively handle GNSS outliers and improve state estimation performance. Furthermore, we provide insightful discussions to motivate future research toward developing a federated framework for robust vehicle localization in challenging environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。