The key objective of this paper is to explore the recent state-of-the-art artificial intelligence (AI) applications on the broad field of beamforming. Hence, a multitude of AI-oriented beamforming studies are thoroughly investigated in order to correctly comprehend and profitably interpret the AI contribution in the beamforming performance. Starting from a brief overview of beamforming, including adaptive beamforming algorithms and direction of arrival (DOA) estimation methods, our analysis probes further into the main machine learning (ML) classes, the basic neural network (NN) topologies, and the most efficient deep learning (DL) schemes. Subsequently, and based on the prior aspects, the paper explores several concepts regarding the optimal use of ML and NNs either as standalone beamforming and DOA estimation techniques or in combination with other implementations, such as ultrasound imaging, massive multiple-input multiple-output structures, and intelligent reflecting surfaces. Finally, particular attention is drawn on the realization of beamforming or DOA estimation setups via DL topologies. The survey closes with various important conclusions along with an interesting discussion on potential future aspects and promising research challenges.

In this paper, we propose a new method for the localization of RFID tags, by deploying off-the-shelf RFID equipment on a robotic platform. The constructed robot is capable to perform Simultaneous Localization (of its own position) and Mapping (SLAM) of the environment and then locate the RFID tags around its path. The proposed method is based on properly treating the measured phase of the backscattered signal by each tag at the reader’s antenna, located on top of the robot. More specifically, the measured phase samples are reconstructed, such that the 2π discontinuities are eliminated (phase-unwrapping). This allows for the formation of an optimization problem, which can be solved rapidly by standard methods. The proposed method is experimentally compared against the SAR/imaging methods, which represent the accuracy benchmark in prior-art, deploying off-the-shelf equipment. It is shown that the proposed method solves exactly the same problem as holographic-imaging methods, overcoming the grid-density constraints of the latter. Furthermore, the problem, being calculations-grid-independent, is solved orders of magnitude faster, allowing for the applicability of the method in real-time inventorying and localization. It is also shown that the state-of-the-art SLAM method, which is used for the estimation of the trace of the robot, also suffers from errors, which directly affect the accuracy of the RFID localization method. Deployment of reference RFID tags at known positions, seems to significantly reduce such errors.

Millimeter-wave bands (around 28, 38, 60, and 73 GHz) are anticipated to play a decisive role in the hosting of future wireless systems. The necessity of smart antennas to adaptively meet the requirements of the wireless links calls for new pattern reconfiguration antennas with beam-steering and/or beam-shaping capabilities. This paper reviews the latest research contributions on pattern reconfigurable antennas at mm-Wave frequencies, proposing an original classification according to the reconfiguration technique and technology. The analyzed systems are divided into two main groups: Reconfigurable and non-reconfigurable feeding antennas. Phased-arrays antennas are the main component of the first category, whereas other reconfigurable means such as the use of metasurfaces or advance materials like liquid crystal or graphene form the second group, devoted to non-reconfigurable feeding antennas. Furthermore, some insights and theoretical background are provided to help the reader understand and appreciate the uniqueness of every solution. Similarly, the beam-scanning and beam-shaping performance of some of the discussed works is analyzed. Finally, some instructive remarks and open research challenges are discussed, with the aim of providing some guidelines for potential new works on the field.

A new iterative adaptive beamforming (ABF) algorithm based on conventional beamformers is proposed in order not only to steer the main lobe toward the desired signal and place radiation pattern nulls toward respective interference signals but also to achieve the desired sidelobe level (SLL). Thus, the algorithm becomes less susceptible to unpredicted interference signals than conventional beamformers. In each iteration, the algorithm finds the direction of the peak of the greatest sidelobe, which is considered as direction of arrival (DoA) of a hypothetical interference signal, and the conventional beamformer is then employed to find proper antenna array weights that produce an extra null toward this direction. The iterative procedure stops when the desired SLL is obtained. The algorithm is applied on three conventional beamformers and is tested for various signal DoA, while the direction deviation of the main lobe and the nulls is recorded, to evaluate the algorithm in terms of robustness. The proposed algorithm needs a few iterations to achieve the desired SLL and thus is much faster than any evolutionary iterative method employed for sidelobe suppression. Finally, unlike methods that employ neural networks (NNs), the proposed algorithm does not need any training to become functional.

An improved particle swarm optimization (PSO) method applied to the design of a new wideband log-periodic antenna (LPA) geometry is introduced. This new PSO variant, called PSO with velocity mutation (PSOvm), induces mutation on the velocities of those particles that cannot improve their position. The proposed LPA consists of wire dipoles with lengths and distances varied according to an exponential rule, which is defined by two specific parameters called length factor and spacing factor. The LPA is optimized for operation in 790-6000MHz frequency range, in order to cover the most usual wireless services in practice, and also to provide in this range the highest possible forward gain, gain flatness below 2dB, secondary lobe level below –20dB with respect to the main lobe peak, and standing wave ratio below 2. To demonstrate its superiority in terms of performance, PSOvm is compared to well-known optimization methods. The comparison is performed by applying all the methods on several test functions and also on the LPA optimization problem defined by the above-mentioned requirements. Furthermore, the radiation characteristics of the PSOvm-based LPA give prominence to the effectiveness of the proposed exponential geometry compared to the traditional Carrel’s geometry.

In this paper, we present a prototype method for 3D localization of UHF RFID tags by a moving robot. The proposed method represents an extension of Phase ReLock, in 3D space. Phase measurements are collected by at least two antennas, thus a multi-antenna synthetic aperture is created. We propose a new optimization problem, which involves measurements from all different antennas. Thanks to phase-unwrapping, the new multi-antenna optimization problem preserves its convex-like properties. Consequently, it is solved rapidly by standard optimization techniques. Furthermore, we introduce a confidence metric that can identify measured data, which deteriorate the accuracy of the estimations. These can be removed from the measurements' dataset. We have conducted extensive measurements, employing four antennas on top of a SLAM-enabled robot; i.e., the robot is able to create a map of the unknown environment and continuously estimate its pose inside the map. The proposed method outperforms prior art with respect to accuracy and computation time. It achieves mean 3D error less than 20cm with an estimation-time of only 0.17s per tag on an average laptop.