Publications

DoA estimation is a key array-processing task, with existing methods typically relying on accurate knowledge of the array response. Calibration mismatches can thus severely degrade DoA recovery, and existing calibration techniques struggle with rapid calibration drifts when only few snapshots are available and no labeled data is provided. We propose a rapid unsupervised online calibration framework that casts drifting array calibration as a state-estimation problem. The proposed method jointly tracks the source directions and calibration parameters over time, exploiting temporal structure rather than recalibrating each time block independently. We develop two state-space formulations: one using the empirical covariance matrix as the observation, and another based on subspace orthogonality, avoiding knowledge of the source and noise statistics. Both formulations are solved using few-step iterated extended Kalman filtering, yielding low-complexity recursive calibration from unlabeled measurements. Numerical results show that the proposed dynamic-system-based approach enables accurate DoA estimation under fast calibration variations and limited snapshots.

In this work, we consider end-to-end calibration of an integrated sensing and communication (ISAC) base station (BS) under gain-phase and antenna displacement impairments without collecting signals from predefined positions (labeled data). We consider a BS with two impaired uniform linear arrays used for simultaneous multi-target sensing and communication with a user equipment (UE) leveraging orthogonal frequency-division multiplexing signals. The main contribution is the design of a framework that can compensate for the impairments without labeled data and considering coherent receive signals. We harness a differentiable precoder based on the maximum array response in an angular direction at the transmitter and the orthogonal matching pursuit (OMP) algorithm at the sensing receiver. We propose an ISAC loss as a combination of sensing and communication losses that provides a trade-off between the two functionalities. We compare two sensing objective alternatives: (i) maximize the maximum response of the angle-delay map of the targets or (ii) minimize the norm of the residual signal at the output of the OMP algorithm after all estimated targets have been removed. The communication objective maximizes the energy of the received signal at the UE. Additionally, our framework leverages an approximation of the channel gradient that avoids the impractical knowledge of the gradient of the channel. Our results show that the proposed method performs closely to using labeled data and knowledge of the channel gradient in terms of sensing position estimation and communication symbol error rate. When comparing the two sensing losses, minimizing the norm of the OMP residual yields significantly better sensing position estimation with slightly increased complexity.

The increasing deployment of large antenna arrays at base stations has significantly improved the spatial resolution and localization accuracy of radio-localization methods. However, traditional signal processing techniques struggle in complex radio environments, particularly in scenarios dominated by non line of sight (NLoS) propagation paths, resulting in degraded localization accuracy. Recent developments in machine learning have facilitated the development of machine learning-assisted localization techniques, enhancing localization accuracy in complex radio environments. However, these methods often involve substantial computational complexity during both the training and inference phases. This work extends the well-established fingerprinting-based localization framework by simultaneously reducing its memory requirements and improving its accuracy. Specifically, a model-based neural network is used to learn the location-to-channel mapping, and then serves as a generative neural channel model. This generative model augments the fingerprinting comparison dictionary while reducing the memory requirements. The proposed method outperforms fingerprinting baselines by achieving sub-wavelength localization accuracy, even in NLoS environments. Remarkably, it offers an improvement by several orders of magnitude in localization accuracy, while simultaneously reducing memory requirements by an order of magnitude compared to classical fingerprinting methods.

Direction of arrival (DoA) estimation is a common sensing problem in radar, sonar, audio, and wireless communication systems. It has gained renewed importance with the advent of the integrated sensing and communication paradigm. To fully exploit the potential of such sensing systems, it is crucial to take into account potential hardware impairments that can negatively impact the obtained performance. This study introduces a joint DoA estimation and hardware impairment learning scheme following a model-based approach. Specifically, a differentiable version of the multiple signal classification (MUSIC) algorithm is derived, allowing efficient learning of the considered impairments. The proposed approach supports both supervised and unsupervised learning strategies, showcasing its practical potential. Simulation results indicate that the proposed method successfully learns significant inaccuracies in both antenna locations and complex gains. Additionally, the proposed method outperforms the classical MUSIC algorithm in the DoA estimation task.

Years of study of the propagation channel showed a close relation between a location and the associated communication channel response. The use of a neural network to learn the location-to-channel mapping can therefore be envisioned. The Implicit Neural Representation (INR) literature showed that classical neural architecture are biased towards learning low-frequency content, making the location-to-channel mapping learning a non-trivial problem. Indeed, it is well known that this mapping is a function rapidly varying with the location, on the order of the wavelength. This paper leverages the model-based machine learning paradigm to derive a problem-specific neural architecture from a propagation channel model. The resulting architecture efficiently overcomes the spectral-bias issue. It only learns low-frequency sparse correction terms activating a dictionary of high-frequency components. The proposed architecture is evaluated against classical INR architectures on realistic synthetic data, showing much better accuracy. Its mapping learning performance is explained based on the approximated channel model, highlighting the explainability of the model-based machine learning paradigm.

Reaping the benefits of multi-antenna communication systems in frequency division duplex (FDD) requires channel state information (CSI) reporting from mobile users to the base station (BS). Over the last decades, the amount of CSI to be collected has become very challenging owing to the dramatic increase of the number of antennas at BSs. To mitigate the overhead associated with CSI reporting, compressed CSI techniques have been proposed with the idea of recovering the original CSI at the BS from its compressed version sent by the mobile users. Channel charting is an unsupervised dimensionality reduction method that consists in building a radio-environment map from CSIs. Such a method can be considered in the context of the CSI compression problem, since a chart location is, by definition, a low-dimensional representation of the CSI. In this paper, the performance of channel charting for a task-based CSI compression application is studied. A comparison of the proposed method against baselines on realistic synthetic data is proposed, showing promising results.

Integrated sensing and communications (ISAC) is envisioned as one of the key enablers of next-generation wireless systems, offering improved hardware, spectral, and energy efficiencies. In this paper, we consider an ISAC transceiver with an impaired uniform linear array that performs single-target detection and position estimation, and multiple-input single-output communications. A differentiable model-based learning approach is considered, which optimizes both the transmitter and the sensing receiver in an end-to-end manner. An unsupervised loss function that enables impairment compensation without the need for labeled data is proposed. Semi-supervised learning strategies are also proposed, which use a combination of small amounts of labeled data and unlabeled data. Our results show that semi-supervised learning can achieve similar performance to supervised learning with 98.8% less required labeled data.

Modern communication systems rely on accurate channel estimation to achieve efficient and reliable transmission of information. As the communication channel response is highly related to the user’s location, one can use a neural network to map the user’s spatial coordinates to the channel coefficients. However, these latter are rapidly varying as a function of the location, on the order of the wavelength. Classical neural architectures being biased towards learning low frequency functions (spectral bias), such mapping is therefore notably difficult to learn. In order to overcome this limitation, this paper presents a frugal, model-based network that separates the low frequency from the high frequency components of the target mapping function. This yields an hypernetwork architecture where the neural network only learns low frequency sparse coefficients in a dictionary of high frequency components. Simulation results show that the proposed neural network outperforms standard approaches on realistic synthetic data.

Channel charting builds a map of the radio environment in an unsupervised way. The obtained chart locations can be seen as low-dimensional compressed versions of channel state information that can be used for a wide variety of applications, including beam prediction. In non-standalone or cell-free systems, chart locations computed at a given base station can be transmitted to several other base stations (possibly operating at different frequency bands) for them to predict which beams to use. This potentially yields a dramatic reduction of the overhead due to channel estimation or beam management, since only the base station performing charting requires channel state information, the others directly predicting the beam from the chart location. In this paper, advanced model-based neural network architectures are proposed for both channel charting and beam prediction. The proposed methods are assessed on realistic synthetic channels, yielding promising results.

Channel charting is an emerging technique whose aim is to learn a chart from estimated channels, on which spatially close users appear to be close as well. In contrast to conventional localization methods, channel charting is intended to be unsupervised. The proposed method is based on a distance measure adapted to channel vectors. The exploitation of this distance measure allows for the structuring of a neural network known as a model-based network. Initialized intelligently, this network is subsequently trained in triplet mode to improve its performance. Its performance is evaluated on a synthetic channel database generated using the Sionna library.

User equipment (UE) positioning accuracy is of paramount importance in current and future communications standard. However, traditional methods tend to perform poorly in non line of sight (NLoS) scenarios. As a result, deep learning is a candidate to enhance the UE positioning accuracy in NLoS environments. In this paper, we study the efficiency of deep learning on the 3GPP indoor factory (InF) statistical channel. More specifically, we analyse the impacts of several key elements on the positioning accuracy, the type of radio data used, the number of base stations (BS), the size of the training dataset, and the generalization ability of a trained model.

In modern communication systems, channel state information is of paramount importance to achieve capacity. It is then crucial to accurately estimate the channel. It is possible to perform SISO-OFDM channel estimation using sparse recovery techniques. However, this approach relies on the use of a physical wave propagation model to build a dictionary, which requires perfect knowledge of the system’s parameters. In this paper, an unfolded neural network is used to lighten this constraint. Its architecture, based on a sparse recovery algorithm, allows SISO-OFDM channel estimation even if the system’s parameters are not perfectly known. Indeed, its unsupervised online learning allows to learn the system’s imperfections in order to enhance the estimation performance. The practicality of the proposed method is improved with respect to the state of the art in two aspects, constrained dictionaries are introduced in order to reduce sample complexity and hierarchical search within dictionaries is proposed in order to reduce time complexity. Finally, the performance of the proposed unfolded network is evaluated and compared to several baselines using realistic channel data, showing the great potential of the approach.

In this paper, we investigate the effects of Phase Noise (PN) on the Array Factor (AF) and beamforming gain of massive MIMO mmWave systems. We present different PN models based on the Local Oscillators (LO) architecture. We then study the impact of those PN models on the Array Factor and beamforming gain. We introduce novel analytical bounds for the asymptotic AF Mean Squared Error (MSE) and asymptotic Gain Loss (GL) due to PN in a MIMO system. We then show the validity of our bounds through simulations. We also provide a statistical study on the underlying probability distributions for both the GL and the effective beam steering direction. The parametric study of the fitted distribution parameters with the number of antennas of the Base Station (BS) provides new overviews on how to model the massive MIMO array factor under PN effects.