A Neural Network-aided Low Complexity Chase Decoder for URLLC

Ultra-reliable low-latency communications (URLLC) demand decoding algorithms that simultaneously offer high reliability and low complexity under stringent latency constraints. While iterative decoding schemes for LDPC and Polar codes offer a good compromise between performance and complexity, they fall short in approaching the theoretical performance limits in the typical URLLC short block length regime. Conversely, quasi-ML decoding schemes for algebraic codes, like Chase-II decoding, exhibit a smaller gap to optimum decoding but are computationally prohibitive for practical deployment in URLLC systems. To bridge this gap, we propose an enhanced Chase-II decoding algorithm that leverages a neural network (NN) to predict promising perturbation patterns, drastically reducing the number of required decoding trials. The proposed approach combines the reliability of quasi-ML decoding with the efficiency of NN inference, making it well-suited for time-sensitive and resource-constrained applications.

Jamming Detection in MIMO-OFDM ISAC Systems Using Variational Autoencoders

This paper introduces a novel unsupervised jamming detection framework designed specifically for monostatic multiple-input multiple-output (MIMO)-orthogonal frequency-division multiplexing (OFDM) radar systems. The framework leverages echo signals captured at the base station (BS) and employs the latent data representation learning capability of variational autoencoders (VAEs). The VAE-based detector is trained on echo signals received from a real target in the absence of jamming, enabling it to learn an optimal latent representation of normal network operation. During testing, in the presence of a jammer, the detector identifies anomalous signals by their inability to conform to the learned latent space. We assess the performance of the proposed method in a typical integrated sensing and communication (ISAC)-enabled 5G wireless network, even comparing it with a conventional autoencoder.

Blind User Activity Detection for Grant-Free Random Access in Cell-Free mMIMO Networks

Cell-free massive MIMO (CF-mMIMO) networks have recently emerged as a promising solution to tackle the challenges arising from next-generation massive machine-type communications. In this paper, a fully grant-free deep learning (DL)-based method for user activity detection in CF-mMIMO networks is proposed. Initially, the known non-orthogonal pilot sequences are used to estimate the channel coefficients between each user and the access points. Then, a deep convolutional neural network is used to estimate the activity status of the users. The proposed method is "blind", i.e., it is fully data-driven and does not require prior large-scale fading coefficients estimation. Numerical results show how the proposed DL-based algorithm is able to merge the information gathered by the distributed antennas to estimate the user activity status, yet outperforming a state-of-the-art covariance-based method.

MADRL-based UAVs Trajectory Design with Anti-Collision Mechanism in Vehicular Networks

In upcoming 6G networks, unmanned aerial vehicles (UAVs) are expected to play a fundamental role by acting as mobile base stations, particularly for demanding vehicle-to-everything (V2X) applications. In this scenario, one of the most challenging problems is the design of trajectories for multiple UAVs, cooperatively serving the same area. Such joint trajectory design can be performed using multi-agent deep reinforcement learning (MADRL) algorithms, but ensuring collision-free paths among UAVs becomes a critical challenge. Traditional methods involve imposing high penalties during training to discourage unsafe conditions, but these can be proven to be ineffective, whereas binary masks can be used to restrict unsafe actions, but naively applying them to all agents can lead to suboptimal solutions and inefficiencies. To address these issues, we propose a rank-based binary masking approach. Higher-ranked UAVs move optimally, while lower-ranked UAVs use this information to define improved binary masks, reducing the number of unsafe actions. This approach allows to obtain a good trade-off between exploration and exploitation, resulting in enhanced training performance, while maintaining safety constraints.