US considers the Electromagnetic domain that is the electromagnetic spectrum portion of the information environment as a domain of Warfare. Assured access to the RF portion of the electromagnetic spectrum is critical to communications, radar sensing, command and control, time transfer, and geo-location and therefore for conducting military operations. The electromagnetic spectrum now includes complete range of frequencies of electromagnetic radiation from zero to infinity . Electromagnetic weapons have now become common in all three domains Air, Land and Water.
The US Electromagnetic Spectrum Strategy 2013, calls for ensuring the access to the congested and contested electromagnetic environment of the future, by adopting new agile and opportunistic spectrum operations, and through systems which are more efficient, flexible and adaptable and adopting new technologies capable of more efficient use of the spectrum and reduced risk of interference.
For many years machine learning approaches have been successfully applied to numerous detection and classification tasks from image processing to voice separation and text recognition. However, it is only recently that similar techniques have been applied to the processing of radio frequency (RF) signals and the electromagnetic environment (EME).
The EME is becoming more congested, contested and complex. This can be seen by:
- Machine learning enabled RF smart sensor systems being deployed in domains as diverse as medical diagnostics, driverless vehicles, satellites, defence and agriculture.
- An increase in the deployment of Internet of Things (IoT) devices.
- An increase in more complex communications in the form of MIMO rollout of 5G and development of WiFi6.
- The number of commercial and civilian satellite launches with synthetic aperture radar (SAR) capability set to pass 60 this year. (Rosen, J., 2021).
It is therefore becoming increasingly difficult for a human in the loop to handle the flood of information. This is resulting in the adoption of deep learning approaches for the detection, classification, identification and transmission of signals.
The development of new technologies for the automated, real-time processing and analysis of radio frequency data requires domain specific expertise that is spread across multiple organisations and disciplines. This special interest group aims to build a community of ML for RF researchers and to run a series of theme lead workshops covering the applications and challenges in this domain.
Applying ML technology to RF problems presents several unique challenges, including the high volume of input data, dynamics of the propagation environment, the complexity of controlling modern receivers and transmitters, and the computational constraints of embedded systems.
Addressing these challenges requires RF domain-specific insights, which may include novel ML architectures, curation of RF training data sets through preprocessing and synthetic data augmentation, hybrid processing pipelines integrating
traditional signal processing functions, network optimization for embedded processors, and advanced resource management techniques.
DARPA seeks information on organizations’ prior research addressing these and related technical challenges in the RF
domain. As applied research for specific defense applications may require access to classified data, responders should describe their organizational capability to conduct classified research.
In Oct 2021, The Defense Advanced Research Projects Agency began seeking information on companies, universities, nonprofit research institutions and other organizations with the capability to apply machine learning and artificial intelligence to radio frequency signals.
DARPA’s Microsystems Technology Office is asking interested stakeholders to state their prior experience in RF ML research and development initiatives, including a description of their research objectives and ML’s role in the RF processing chain, according to a request for information.
Organizations should provide a bibliography of key RF ML documents authored by the organization’s personnel and their organizations’ capabilities and infrastructure, including the availability of facilities to support future RF ML research efforts and accessibility of government computer networks that could be used to back research.