OctCGS: Octree-Contextual Gaussian Splatting with Explicit Multi-Order Propagation Modeling for Channel Knowledge Map Construction

Channel knowledge maps (CKMs) learn the relation between transmitter (Tx) and receiver (Rx) positions and channel knowledge to support environment-aware wireless communications. Implicit neural methods can model continuous channel variation but often incur high training and inference cost, while existing Gaussian-splatting-based CKM methods improve efficiency yet still compress wireless multipath interactions into aggregated scattering representations. Consequently, explicit modeling of multi-bounce wireless propagation remains absent from CKM construction. We propose OctCGS, an octree-contextual Gaussian splatting framework that explicitly models the order of bounce jointly over Tx/Rx positions and carrier frequencies. OctCGS partitions the environment into a multi-resolution octree and anchors one Gaussian primitive to each leaf node. Rather than having each Gaussian independently encode all multi-path propagations, it models complex electromagnetic interactions among scatterers through tree attention over the octree hierarchy with controlled complexity. Experiments on simulated benchmarks show that OctCGS achieves a 2.99 dB channel-gain mean absolute error (MAE) and 0.065 channel gain normalized mean absolute error (NMAE), outperforming the strongest baseline by 0.88 dB MAE and 0.021 NMAE.

Joint Antenna Selection and Covariance Matrix Optimization for ISAC Systems

We consider an integrated sensing and communication (ISAC) system with a single communication user and multiple targets. For the communication functionality, the achievable rate is employed as the performance metric, while for sensing, we focus on minimizing the mean squared error (MSE) between the designed beampattern and a desired one for tracking the targets. Towards this, and by assuming that there are fewer radiofrequency (RF) chains than antenna elements at the transmitter (Tx), we focus on the joint antenna selection (AS) and covariance matrix (CM) optimization at the Tx. This is a mixed-integer optimization problem, yet we demonstrate that it can be efficiently solved, in polynomial time, by combining convex optimization tools with dynamic programming (DP). By introducing an adjustable trade-off parameter, we formulate a joint objective function that captures both the communication and sensing metric. In this way, different ISAC solutions can be obtained, considering the trade-off among the two functionalities. It is shown that selecting the active antennas with our proposed method is superior than assuming a uniform Tx array with fixed antenna positions. Notably, by individually considering the optimization of either the sensing or the communication system alone, our proposed algorithm outperforms the literature proposals, by incurring only a small increase in complexity.

Transfer Learning for CSI-based Positioning with Multi-environment Meta-learning

Utilizing deep learning (DL) techniques for radio-based positioning of user equipment (UE) through channel state information (CSI) fingerprints has demonstrated significant potential. DL models can extract complex characteristics from the CSI fingerprints of a particular environment and accurately predict the position of a UE. Nonetheless, the effectiveness of the DL model trained on CSI fingerprints is highly dependent on the particular training environment, limiting the trained model's applicability across different environments. This paper proposes a novel DL model structure consisting of two parts, where the first part aims at identifying features that are independent from any specific environment, while the second part combines those features in an environment specific way with the goal of positioning. To train such a two-part model, we propose the multi-environment meta-learning (MEML) approach for the first part to facilitate training across various environments, while the second part of the model is trained solely on data from a specific environment. Our findings indicate that employing the MEML approach for initializing the weights of the DL model for a new unseen environment significantly boosts the accuracy of UE positioning in the new target environment as well the reliability of its uncertainty estimation. This method outperforms traditional transfer learning methods, whether direct transfer learning (DTL) between environments or completely training from scratch with data from a new environment. The proposed approach is verified with real measurements for both line-of-sight (LOS) and non-LOS (NLOS) environments.

Deep Learning based Positioning with Multi-task Learning and Uncertainty-based Fusion

Deep learning (DL) methods have been shown to improve the performance of several use cases for the fifth-generation (5G) New radio (NR) air interface. In this paper we investigate user equipment (UE) positioning using the channel state information (CSI) fingerprints between a UE and multiple base stations (BSs). In such a setup, a single DL model can be trained for UE positioning using the CSI fingerprints of the multiple BSs as input. Alternatively, based on the CSI at each BS, a separate DL model can be trained at each BS and then the output of the different models are combined to determine the UE's position. In this work we compare these different fusion techniques and show that fusing the output of separate models achieves higher positioning accuracy, especially in a dynamic scenario. We also show that the fusion of multiple outputs further benefits from considering the uncertainty of the output of the DL model at each BS. For a more efficient training of the DL model across BSs, we additionally propose a multi-task learning (MTL) scheme by sharing some parameters across the models while jointly training all models. This method, not only improves the accuracy of the individual models, but also of the final combined estimate. Lastly, we evaluate the reliability of the uncertainty estimation to ascertain which of the fusion methods provides the highest quality of uncertainty estimates.

Non-uniform array design for robust LoS MIMO via convex optimization

The array design problem of multiple-input multiple-output (MIMO) systems in a line-of-sight (LoS) transmit environment is examined. As uniform array configurations at the transmitter (Tx) and receiver (Rx) are optimal at specific transmit distances only, they lead to reduced spectral efficiency over a range of transmit distances. To that end, the joint design of nonuniform Tx and Rx arrays towards maximizing the minimum capacity of a LoS MIMO system across a range of transmit distances is investigated in this paper. By introducing convex relaxation, the joint Tx and Rx array design is cast as a convex optimization problem, which is solved in a iterative manner. In addition, we also implement a local search to obtain a refined solution that achieves an improved performance. It is shown that the non-uniform configurations designed with our proposed approach outperform uniform and non-uniform array designs of the literature in terms of capacity and/or complexity.

Multi-Environment based Meta-Learning with CSI Fingerprints for Radio Based Positioning

Radio based positioning of a user equipment (UE) based on deep learning (DL) methods using channel state information (CSI) fingerprints have shown promising results. DL models are able to capture complex properties embedded in the CSI about a particular environment and map UE's CSI to the UE's position. However, the CSI fingerprints and the DL models trained on such fingerprints are highly dependent on a particular propagation environment, which generally limits the transfer of knowledge of the DL models from one environment to another. In this paper, we propose a DL model consisting of two parts: the first part aims to learn environment independent features while the second part combines those features depending on the particular environment. To improve transfer learning, we propose a meta learning scheme for training the first part over multiple environments. We show that for positioning in a new environment, initializing a DL model with the meta learned environment independent function achieves higher UE positioning accuracy compared to regular transfer learning from one environment to the new environment, or compared to training the DL model from scratch with only fingerprints from the new environment. Our proposed scheme is able to create an environment independent function which can embed knowledge from multiple environments and more effectively learn from a new environment.

Towards Integrated Sensing and Communications for 6G

For the next generation of mobile communications systems, the integration of sensing and communications promises benefits in terms of spectrum utilization, cost, latency, area and weight. In this paper, we categorize and summarize the key features and technical considerations for different integration approaches and discuss related waveform design issues for a future 6G system. We provide results on new candidate waveforms for monostatic sensing and finally highlight important open issues and directions that deserve future in-depth research.

Reliable Deep Learning based Localization with CSI Fingerprints and Multiple Base Stations

Deep learning (DL) methods have been recently proposed for user equipment (UE) localization in wireless communication networks, based on the channel state information (CSI) between a UE and each base station (BS) in the uplink. With the CSI from the available BSs, UE localization can be performed in different ways. One the one hand, a single neural network (NN) can be trained for the UE localization by considering the CSI from all the available BSs as one overall fingerprint of the user's location. On the other hand, the CSI at each BS can be used to obtain an estimate of the UE's position with a separate NN at each BS, and then the position estimates of all BSs are combined to obtain an overall estimate of the UE position. In this work, we show that UE localization with the latter approach can achieve a higher positioning accuracy. We propose to consider the uncertainty in the UE localization at each BS, such that overall UE's position is determined by combining the position estimates of the different BSs based on the uncertainty at each BS. With this approach, a more reliable position estimate can be obtained in case of variations in the channel.

CSI-Based Localization with CNNs Exploiting Phase Information

In this paper we study the use of the Channel State Information (CSI) as fingerprint inputs of a Convolutional Neural Network (CNN) for localization. We examine whether the CSI can be used as a distinct fingerprint corresponding to a single position by considering the inconsistencies with its raw phase that cause the CSI to be unreliable. We propose two methods to produce reliable fingerprints including the phase information. Furthermore, we examine the structure of the CNN and more specifically the impact of pooling on the positioning performance, and show that pooling over the subcarriers can be more beneficial than over the antennas.

Low Latency Scheduling Algorithms for Full-Duplex V2X Networks

Vehicular communication systems have been an active subject of research for many years and are important technologies in the 5G and the post-5G era. One important use case is platooning which is seemingly the first step towards fully autonomous driving systems. Furthermore, a key performance parameter in all vehicular communication systems is the end-to-end packet latency. Towards this goal, full-duplex (FD) transceivers can potentially be an efficient and practical solution towards reducing the delay in platooning networks. In this paper, we study the delay performance of dynamic and TDMAbased scheduling algorithms and assess the effect of FD-enabled vehicles with imperfect self-interference cancellation (SIC). By simulations, we demonstrate the performance-complexity tradeoff of these algorithms and show that a TDMA centralized scheme with low-complexity and overhead can achieve comparable performance with a fully-dynamic, centralized algorithm.