We present a neural network for mitigating pseudorange bias to improve
localization performance with data collected from Android smartphones. We
represent pseudorange bias using a pragmatic satellite-wise Multiple Layer
Perceptron (MLP), the inputs of which are six
satellite-receiver-context-related features derived from Android raw Global
Navigation Satellite System (GNSS) measurements. To supervise the training
process, we carefully calculate the target values of pseudorange bias using
location ground truth and smoothing techniques and optimize a loss function
containing the estimation residuals of smartphone clock bias. During the
inference process, we employ model-based localization engines to compute
locations with pseudoranges corrected by the neural network. Consequently, this
hybrid pipeline can attend to both pseudorange bias and noise. We evaluate the
framework on an open dataset and consider four application scenarios for
investigating fingerprinting and cross-trace localization in rural and urban
areas. Extensive experiments demonstrate that the proposed framework
outperforms model-based and state-of-the-art data-driven approaches.

本研究介绍了一种使用神经网络来改善 Android 智能手机数据收集中的伪距偏差以提高定位性能的方法。通过使用多层感知器来表示伪距偏差并进行监督训练，结合模型引擎计算修正后的伪距位置，该方法在实验中表现出超过基于模型和现有数据驱动方法的性能。