MARL to Choose Actions On-the-Fly in a Cognitive Radar System

A Unified Framework Combining Feature Extraction and Reward Estimation for Cognitive Radar Policy Prediction

Abstract Metasurfaces, as artificial structures, have shown their high capacity to arbitrarily tailor electromagnetic wavefronts. Here, a minimalist 1-bit phase coding metasurface with “0” and “1” states is proposed for high-efficiency complex beam generation. The elementary unit cell, insensitive to the polarization of the incident wave, is arrayed in a hexagonal lattice and can be further exploited in any metasurface for any functionality. This minimalist metasurface, with only 50% of its surface covered with metallic patterns, can achieve a more accurate response manipulation. Three complex beams, including zeroth-order Bessel beam, vortex beam, and Airy beam, are achieved for validation with a high efficiency of over 78.5%. Both simulations and measurements are performed in the frequency band ranging from 11 GHz to 13 GHz. This minimalist metasurface shows high efficiency for potential applications in wireless communications, cognitive radars, and adaptive beamforming.

Abstract Adaptive manipulation of electromagnetic scattering is useful to many applications, such as invisibility cloak, wireless communications, and optical imaging. In spite of great advancements brought by metamaterials and metasurfaces over the past decade, the existing works still face great challenges in broadband adaptability. Here, this study presents an intelligent metasurface with a novel structure driven by a conditional data integrated generative network, CVAE (conditional generative autoencoder), capable of autonomous optimization of electromagnetic scattering from 10 to 14 GHz. The proposed condition‐fused generative framework resolves multi‐solution ambiguities by synergistically evolving geometric configurations through sampling electromagnetic simulation‐guided latent space, achieving over 90% accuracy in scattering matrices while suppressing parasitic resonances. By co‐integrating tunable metasurfaces with real‐time intelligent control, this platform enables precise control of arbitrary scattering, from specular reflection to diffuse scattering, under varying illumination conditions. This work establishes a universal paradigm for adaptive electromagnetic engineering, with transformative implications for next‐generation cognitive radar, intelligent wireless management, and reconfigurable sensing.

Off-Grid Multisnapshot Spectrum Sensing for Cognitive Radar

Precise identification of active jamming in complex electromagnetic environments remains critically challenging for cognitive radar systems. Current methods often exhibit limitations in insufficient feature extraction and underutilization of jamming signals, leading to substantial performance degradation, particularly in low jamming-to-noise ratio (JNR) scenarios. To address these challenges, we propose a novel framework based on a multi-domain fusion network, MDFNet, to recognize 12 types of active jamming signals. MDFNet improves the recognition robustness under varying JNR conditions through a two-stage fusion of complementary features from pulse compression time–frequency (PC-TF) and range-Doppler (RD) domain images. Specifically, a novel dual-modal feature fusion (DMFF) module integrates PC-TF and RD features, while a decision fusion strategy leverages their distinctive characteristics. Experiments on typical jamming dataset demonstrate that MDFNet achieves an overall recognition accuracy of 96.05%. Notably, at a JNR of −20 dB, MDFNet outperforms the existing fusion methods by 12.86–18.19%. In summary, our proposed method significantly enhances the jamming recognition capability of cognitive radar systems in complex environments.

ABSTRACT Radar technology has developed revolutionary leaps from its early beginnings to the sophisticated systems that are pulse-based but now incorporate the latest signal processing and communication technologies. This article delves into the historical evolution, present advances, and future directions of radar systems, with a focus on their increasing use in civilian, military, and scientific applications. Static signal transmission and mechanical scanning of conventional radar systems are being replaced by dynamic models like Orthogonal Frequency Division Multiplexing (OFDM), Multiple-Input-Multiple-Output (MIMO) setups, and digital beamforming. These technologies improve resolution, minimize interference, and allow dual functionality with communication systems. At the same time, low-cost solutions like Arduino-based ultrasonic radar systems show how radar technology is being democratized for educational and small-scale applications. This research integrates theoretical foundations such as monostatic and bistatic radar equations with applied breakthroughs to overcome issues such as spectral efficiency, interference cancellation, and hardware miniaturization. Through the analysis of upcoming trends such as cognitive radar, SAR, and vehicular radar networks, this article highlights the leading role of radar in facilitating autonomous systems, environmental monitoring, and future defense systems. The combination of adaptive algorithms and machine learning puts the technology of radar at the peak of intelligent sensor solutions, where it is guaranteeing unparalleled adaptability and precision in a future that is going to be extremely connected. o KEYWORDS: Automobile, Electronic, Innovations, Technology, Amplitude, Clutter, Echo, Phase, Target, Arduino, Ultrasonic sensor, Servo motor, Simulation,

Optimization of slow-time transmit sequence endows cognitive radar with the ability to suppress strong clutter in the range-Doppler domain. However, in practice, inaccurate target velocity information or random phase error would induce uncertainty about the actual target steering vector, which would in turn severely deteriorate the the performance of the slowtime matched filter. In order to solve this problem, we propose a new optimization method for slow-time transmit sequence design. The proposed method transforms the original non-convex optimization with an uncertain target steering vector into a twostep worst-case optimization problem. For each sub-problem, we develop a corresponding trust-region Riemannian optimization algorithm. By iteratively solving the two sub-problems, a suboptimal solution can be reached without accurate information about the target steering vector. Furthermore, the convergence property of the proposed algorithms has been analyzed and detailed proof of the convergence is given. Unlike the traditional waveform optimization method, the proposed method is designed to work with an uncertain target steering vector and therefore, is more robust in practical radar systems. Numerical simulation results in different scenarios verify the effectiveness of the proposed method in suppressing the clutter and show its advantages in terms of the output signal-to-clutter plus noise ratio (SCNR) over traditional methods.

The operational environments of engineering systems are becoming increasingly complex and require automatic control systems to be more intelligent. Cognitive control extends the domain of intelligent control, whereby cognitive science theories are applied to guide the design of automatic control systems to make them conform to the human cognition paradigm and behave like a real person, hence improving physical systems performance. Cognitive control has been investigated in several fields, but a comprehensive review covering all these fields has yet to be provided in any paper. This paper first presents a review of cognitive control development and related works. Then, the relationship between cognitive control and cognitive science is analyzed, based on which the definition and framework of cognitive control are summarized from the perspective of automation and control. Cognitive control is then compared with similar concepts, such as cognitive radio and cognitive radar, and similar control methods, such as intelligent control, robust control, and adaptive control. Finally, the main issues, research directions, and development prospects are discussed. We expect that this paper will contribute to the development of cognitive control.

Bayesian Nonparametric Tracking of Target Impulse Response for Cognitive Radars

Nonlinear Waveform Sensing for Cognitive Radar Based on Reinforcement Learning

Bayesian Inverse Learning and Online Changepoint Detection of Cognitive Radar Strategies

Game Theory and Reinforcement Learning in Cognitive Radar Game Modeling and Algorithm Research: A Review

Latent-Maximum-Entropy-Based Cognitive Radar Reward Function Estimation With Nonideal Observations

Abstract When I fiddle with my hair, or adjust my posture, it is plausible that these activities fall well below my cognitive radar. Some have argued that these are examples of ‘sub‐intentional actions’, actions which are not intentional under any description at all. If true, they are direct counterexamples to the dominant view on which the difference between actions and other events is their intentionality. In this paper, I argue that the case for sub‐intentional actions fails. Firstly, I show that the main argument for the sub‐intentionality of these actions has a structural fault. Secondly, I argue that two apparently natural ways to remedy this fail. Thirdly, I argue that one of the main arguments for thinking of the phenomena as actions undermines thinking of them as sub‐intentional. Finally, I argue that a natural defensive move for the defender of sub‐intentional actions actually undermines the theoretical significance of the view. Ultimately, my aim is to show that although the case for sub‐intentional actions seemed both simple and compelling, it is in fact deeply troubled.

Today, the world's leading countries are intensively working on the development of new generation radars - microwave photonic radars. Microwave photonic radars make it possible to significantly reduce the mass and size characteristics of radar stations, to increase the information capability and range of target detection due to the reduction of losses in long communication lines when using optical fiber, to ensure high immunity due to the significantly lower sensitivity of optical-electronic equipment and fiber-optic lines of communication connection to external electromagnetic influences. Microwave photonics provides wide bandwidth, flat response, low loss transmission, multi-dimensional multiplexing, ultra-fast analog signal processing and immunity to electromagnetic interference. Radar implementation in the optical domain can provide better resolution, coverage, and speed performance, which would be difficult to implement with traditional electronics. The review article examines the state of development and system architectures of such photonic radars as optoelectronic hybrid radars, all-optical radars, multifunctional microwave photonic radar systems, distributed microwave photonic radars, software-defined radars, and cognitive radars. New technologies in this field and possible future directions of research are discussed. As an example, a broadband microwave photon radar reproduced on the basis of a microcircuit is considered. The broadband signal generator and receiver are built into the silicon crystal on the insulator. A high-precision distance measurement with a resolution of 2.7 cm and an error of less than 2.75 mm was obtained. Visualization of multiple targets with complex profiles has been implemented. But the performance of most integrated microwave photonic chips is not yet satisfactory for practical radar applications. Monolithic integration of key microwave photonic subsystems is also not mature enough for practical applications, so hybrid integration of devices fabricated on their optimal integration platforms is of practical interest. At present, indium phosphide, silicon nitride and silicon on insulator are the three leading platforms for photonic integration

Abstract Traditional radar systems use fixed patterns and constant electromagnetic wave transmission to illuminate targets, but they often do not effectively use prior information about targets and consume significant radar resources. Cognitive radar has emerged as a way to improve resource efficiency and address these shortcomings. A joint waveform design and resource allocation strategy for cognitive radar that incorporates target situational awareness is proposed. This method integrates the interacting multiple model algorithm and the Unscented Kalman Particle Filter to achieve target situation awareness as prior knowledge. By combining the target attitude and the frequency response function of the target radar cross section at different time points in the prior knowledge, a joint beam control and power allocation strategy is formulated and transformed into an optimization problem. In addition, a cognitive pulse‐to‐pulse frequency agile waveform design method is proposed to support multiple target tracking under complex motion models. Simulation experiments demonstrate the effectiveness of this approach in obtaining accurate target situation information, achieving beam control, and optimizing power allocation. The designed waveforms can enhance radar target detection performance and improve low probability of intercept characteristics by adjusting the pulse repetition interval. This method has significant technical value.

Inter-pulse carrier frequency agile design for cognitive radar

Transfer-Based DRL for Task Scheduling in Dynamic Environments for Cognitive Radar

The development of modern technologies has fundamentally transformed the field of radar signal and data processing. With the use of advanced algorithms and computational power, radars are now capable of extracting crucial information from received signals, facilitating improved target identification and tracking. This article presents some of the advanced technologies employed in radar signal and data processing and their impact on adaptability of radar systems. It traces the evolution of radar technology from old systems to the present, emphasizing the benefits of adaptive radar signal processing, which includes algorithms such as adaptive beamforming, Space-Time Adaptive Processing, and the integration of Machine Learning and Artificial Intelligence. In conclusion, challenges, and future prospects in the field of radar systems are discussed, with a focus on the potential integration of Artificial Intelligence methods, Cognitive radars, and Multiple Input Multiple Output technologies. Despite technical obstacles, opportunities emerge to enhance the performance of radar systems and achieve new levels of efficiency.