In any case, the random multipath nature makes it difficult to anticipate and overcome. Therefore, for legacy GNSS signal performance assessment, modern GNSS signal design and future GNSS-based applications, robustness to multipath is a fundamental criterion. Different multipath metrics exist in the literature, such as the multipath error envelope, usually leading to analyses only valid for a dedicated receiver/signal combination and only providing information on the bias. This paper presents a general criterion to characterize the multipath robustness of a generic band-limited signal (e.g., GNSS or radar), considering the joint delay-Doppler and phase estimation. This criterion is based on the Cramr-Rao bound, which makes it universal, regardless the receiver architecture and the signal under analysis, and provides information on the actual achievable performance in terms of estimated time-delay (i.e., pseudo-range) and Doppler frequency variances.

The method extends from dataset generation to deep learning inference through Convolutional Neural Network (CNN). The process starts at the output of the correlation stage of the GNSS receiver. Correlations of the received signal with a local replica over a (Doppler shift, propagation delay)-grid are mapped into grey scale 2D images. They depict the received information possibly contaminated by multipath propagation. The images feed a CNN for automatic feature construction and multipath pattern detection. The issue of unavailability of a large amount of supervised data required for CNN training has been overcome by the development of a synthetic data generator. It implements a well-established and documented theoretical model. A comparison of synthetic data with real samples is proposed. The complete framework is tested for various signal characteristics and algorithm parameters. The prediction accuracy does not fall below 93% for C/N0 ratio as low as 36 dBHz, corresponding to poor receiving conditions. In addition, the model turns out to be robust to the reduction of image resolution. Its performance is also measured and compared with an alternative Support Vector Machines (SVM) technique. The results show the undeniable superiority of the proposed CNN algorithm over the SVM benchmark.

Networks are generally trained with pairs of signals and associated measurements. However, in various imaging problems, we usually only have access to compressed measurements of the underlying signals, hindering this learning-based approach. Learning from measurement data only is impossible in general, as the compressed observations do not contain information outside the range of the forward sensing operator. In this talk, I will present a new learning framework, called Equivariant Imaging, which overcomes this limitation by exploiting the invariance to transformations (translations, rotations, etc.) present in natural signals. I will also discuss necessary and sufficient conditions for learning without ground truth. Our proposed learning strategy performs as well as fully supervised methods and can handle noisy data. I will show results on various inverse problems, including sparse-view X-ray computed tomography, accelerated magnetic resonance imaging and image inpainting.