You are here

Novel Positioning, Navigation, and Timing (PNT) Signal Classification Techniques

Description:

OUSD (R&E) CRITICAL TECHNOLOGY AREA(S): Trusted Artificial Intelligence (AI) and Autonomy; Integrated Sensing and Cyber

 

OBJECTIVE: The purpose of this topic is to develop the capability to classify signals in real-time that impact navigation systems.  The intent is to better understand the type(s) of signal(s) experienced in relevant environments to appropriately apply mitigation techniques before harm can be done.  Currently, navigation systems depend on Radio Frequency (RF) signals that can be influenced by a variety of interference sources. It is a challenge to understand the signal characteristics quickly enough to react to/mitigate negative impacts.  Current antenna technologies treat all signals as the same and attempt to ignore them equally.  With more sophisticated interference sources, this is not always successful.  However, if the technique used to interfere with navigation is identified, more impactful mitigation methods can be implemented.

 

DESCRIPTION: This effort provides a risk reduction approach to improve on performance, provide for cost savings, and expand the application of the technology sensor solution set to include additional Army aviation assets. It seeks to demonstrate novel adaptive learning techniques to perform PNT signal classification of the battlefield environment. The proposed topic seeks to build upon AI/Machine Learning (ML) algorithm technologies that have been demonstrated as impactful for this solution. We have seen progress throughout the community demonstrating the ability to classify signals using AI/ML. This topic will build upon the progress and move towards real-time signal classification. ML approaches allow adaptability in the detection process that can be used to identify new unknown interference sources. These new signal types can be used to subsequently train an antenna system without requiring an upgrade. This will allow faster decisions, affording more protection to the navigation system.

 

PHASE I: This topic is accepting Direct to Phase II (DP2) proposals. Proposers interested in submitting a DP2 proposal must provide documentation to substantiate that the scientific and technical merit and feasibility equivalent to a Phase I project has been met. Documentation can include data, reports, specific measurements, success criteria of a prototype, etc.

 

PHASE II: It is expected that vendors should provide:

  • Two antenna systems capable of detecting and classifying interference signals in real-time and protecting the navigation solution from harm.
  • Data collection of relevant signals, training the AI/ML solution, and successfully demonstrating the ability to detect and identify the signal types in a relevant environment.

 

It is desired that the antenna design allows AI/ML training/techniques to be portable from one antenna system to another.  This will support upgrading antenna systems to handle new signals as well as providing support to other antenna systems in the same environment. The demonstration antenna system consists of antenna elements, antenna electronics, and associated AI/ML algorithms (hardware (HW) and software (SW) solution). The Army intends to assess these antenna systems in a relevant environment.

 

 

PHASE III DUAL USE APPLICATIONS:

  • Advanced PNT technologies have been used by the military and the private sector for decades. PNT firms can be divided into two categories: emerging and legacy.  Legacy PNT firms focus on Global Positioning Systems (GPS)-enabled tech and inertial guidance systems.  Emerging PNT organizations focus on major enhancements to existing systems or entirely new approaches.  ​
  • End-users for the PNT technology market span multiple sectors.​
    • The defense market can be divided into land, air, space, and naval with applications for autonomous vehicles, drones, and satellites.
    • Government and civil applications include traffic management, rail control, disaster management, and other critical government infrastructures.
    • Commercial applications include transport and logistics, aviation, marine, agriculture, mobile mapping, and surveying.

 

REFERENCES:

        1. O’Shea, T. Roy, T. C. Clancy, “Over-the-Air Deep Learning Based Radio Signal Classification,” IEEE J. of Selected Topics in Signal Processing, 12(1), Feb. 2018, pp. 168-179

https://arxiv.org/pdf/1712.04578

 

        1. R. Conlin, et al., “Keras2c: A Library for Converting Keras Neural Networks to Real-time Compatible C,” Engineering Appl. of Artificial Intelligence, v. 100, April 2021, 104182

https://www.sciencedirect.com/science/article/abs/pii/S0952197621000294

 

        1. R. Morales Ferre, et al., “Jammer Classification in GNSS Bands Via ML Algorithms,” Sensors, 2019, doi:10.3390/s19224841 https://www.researchgate.net/publication/337096847_Jammer_Classification_in_GNSS_Bands_Via_Machine_Learning_Algorithms

 

KEYWORDS: Positioning, Navigation, and Timing (PNT); Artificial Intelligence (AI); Machine Learning (ML); AI/ML algorithms; Signal Classification; Antenna; Antenna System; Radio Frequency (RF) signals; Global Positioning System (GPS); Global Navigation Satellite System (GNSS); Interference sources; Navigation systems

US Flag An Official Website of the United States Government