Multipath Parameters Estimation in Physically Based Synthetic Environment Using Robust Deep Neural Regression

Thomas Gonzalez (1, 2) , Antoine Blais (2) , Nicolas Couellan (3, 2) , Christian Ruiz (1)

1 OKTAL-SE
2 ENAC - Ecole Nationale de l'Aviation Civile
3 IMT - Institut de Mathématiques de Toulouse UMR5219

Mots clés: Convolutional Neural Networks; correlator output images; distributional loss; GNSS; Kullback-Leibler divergence; multipath; multi-channel regression; synthetic environment; truncated Gaussian; Von Mises distribution

Domaines: Machine Learning [stat.ML]

Thomas Gonzalez, Antoine Blais, Nicolas Couellan, Christian Ruiz. Multipath Parameters Estimation in Physically Based Synthetic Environment Using Robust Deep Neural Regression. 2023 International Technical Meeting of The Institute of Navigation, Jan 2023, Long Beach, United States. pp.808-822, ⟨10.33012/2023.18654⟩. ⟨hal-04099716⟩