Reinforcement Learning For Waveform Design

Smith, Gerald Birney; Reininger, Taylor J.

doi:10.1109/radarconf2147009.2021.9455187

Cited by 7 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors compared the state-of-the art spectrum sharing methods for radar with RL ones, and concluded that the use of RL results in a decrease of MI. RL has shown good results on this application field [108,127]. However, since the nature of random waveforms provide robustness against interference, the application of AI-based methods to spectrum sharing in noise radar may not be a priority.…”

Section: Spectrum Sharingmentioning

confidence: 99%

“…In this specific problem approach there are many optimal and local minima in different regions of the fitness landscape, so the use of crossover leads to a random search procedure, and this can be discouraging for the use of genetic algorithms [60]. RL is also being researched to radar waveform design [108], however results are way more promising for other topics, such as discussed in Section 6.…”

Section: Waveform Designmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence applications in Noise Radar Technology

Sénica,

Marques,

Figueiredo

2024

IET Radar Sonar & Navi

View full text Add to dashboard Cite

Radar systems are a topic of great interest, especially due to their extensive range of applications and ability to operate in all weather conditions. Modern radars have high requirements such as its resolution, accuracy and robustness, depending on the application. Noise Radar Technology (NRT) has the upper hand when compared to conventional radar technology in several characteristics. Its robustness to jamming, low Mutual Interference and low probability of intercept are good examples of these advantages. However, its signal processing is more complex than that associated to a conventional radar. Artificial Intelligence (AI)‐based signal processing is getting increasing attention from the research community. However, there is yet not much research on these methods for noise radar signal processing. The aim of the authors is to provide general information regarding the research performed on radar systems using AI and draw conclusions about the future of AI in noise radar. The authors introduce the use of AI‐based algorithms for NRT and provide results for its use.

show abstract

Section: Spectrum Sharingmentioning

confidence: 99%

Section: Waveform Designmentioning

confidence: 99%

Artificial Intelligence applications in Noise Radar Technology

Sénica,

Marques,

Figueiredo

2024

IET Radar Sonar & Navi

View full text Add to dashboard Cite

show abstract

“…In Refs. [15][16][17], deep neural networks (DNN) are trained to design a phase-coded waveform with a power spectrum containing a low-power notch to support spectrum sharing.…”

Section: "Randomness" Of Nr Waveforms and Lpi Featuresmentioning

confidence: 99%

“…The above-referenced APCN waveforms design does not include the PAPR and PSL control; in order to achieve these important features, two approaches (FMeth and COSPAR generators) are presented and analysed in the following. Other methods, not described here, are shown in literature [15][16][17].…”

Section: Tailored Waveforms For Nrtmentioning

confidence: 99%

On the anti‐intercept features of noise radars

Galati,

Pavan

2024

IET Radar Sonar & Navi

View full text Add to dashboard Cite

Robustness against Electronic Warfare/Electronic Defence attacks represents an important advantage of Noise Radar Technology (NRT). An evaluation of the related Low Probability of Detection (LPD) and of Intercept (LPI) is presented for Continuous Emission Noise Radar (CE‐NR) waveforms with different operational parameters, that is, “tailored”, and with various “degrees of randomness”. In this frame, three different noise radar waveforms, a phase Noise (APCN) and two “tailored” noise waveforms (FMeth and COSPAR), are compared by time–frequency analysis. Using a correlator (i.e. a two antennas) receiver, assuming a complete knowledge of the band (B) and duration (T) of the coherent emission of these waveforms, it will be shown that the LPD features of a CE‐NR do not significantly differ from those of any CE radar transmitting deterministic waveforms. However, in real operations, B and T are unknown; hence, assuming an instantaneous bandwidth estimation will show that the duration T can be estimated only for some specific “tailored” waveforms (of course, not to be operationally used). The effect of “tailoring” is analysed with prospects for future work. Finally, some limitations in the classification of these radar signals are analysed.

show abstract

“…Waveform design can start by implementing known signal forms, such as chirp, and by utilizing reinforcement learning (RL) methods the waveforms can evolve to adapt to each environment [101], [102]. The key challenge in this research direction is that sensing should be performed simultaneously with communication, which facilitates the efficient utilization of so valuable system resources such as bandwidth and power.…”

Section: Waveform Designmentioning

confidence: 99%

XR-RF Imaging Enabled by Software-Defined Metasurfaces and Machine Learning: Foundational Vision, Technologies and Challenges

et al. 2022

View full text Add to dashboard Cite

We present a new approach to Extended Reality (XR), denoted as iCOPYWAVES, which seeks to offer naturally low-latency operation and cost effectiveness, overcoming the critical scalability issues faced by existing solutions. iCOPYWAVES is enabled by emerging PWEs, a recently proposed technology in wireless communications. Empowered by intelligent (meta)surfaces, PWEs transform the wave propagation phenomenon into a software-defined process. We leverage PWEs to: i) create, and then ii) selectively copy the scattered RF wavefront of an object from one location in space to another, where a machine learning module, accelerated by FPGAs, translates it to visual input for an XR headset using PWE-driven, RF imaging principles (XR-RF). This makes for an XR system whose operation is bounded in the physical-layer and, hence, has the prospects for minimal end-to-end latency. Over large distances, RF-to-fiber/fiber-to-RF is employed to provide intermediate connectivity. The paper provides a tutorial on the iCOPYWAVES system architecture and workflow. A proof-of-concept implementation via simulations is provided, demonstrating the reconstruction of challenging objects in iCOPYWAVES-produced computer graphics.

show abstract

Reinforcement Learning For Waveform Design

Cited by 7 publications

References 13 publications

Artificial Intelligence applications in Noise Radar Technology

Artificial Intelligence applications in Noise Radar Technology

On the anti‐intercept features of noise radars

XR-RF Imaging Enabled by Software-Defined Metasurfaces and Machine Learning: Foundational Vision, Technologies and Challenges

Contact Info

Product

Resources

About