You are here

Automatic Track Generation Micro Preprocessor for Dismounted Electronic Warfare


TECHNOLOGY AREA(S): Sensors, Electronics, Battlespace 

OBJECTIVE: Develop an innovative and operationally suitable solution for Electronic Warfare Systems (EWS) Programs of Record (PORs) data pre-processing at the tactical edge that, enabled by artificial intelligence (AI) and machine learning (ML) algorithms, must be able to process vast amounts of raw data to detect, track and recommend actions on signals of interest in a complex electromagnetic environment. 

DESCRIPTION: Marine Corps Systems Command (MCSC) provides dismounted EWS for geo-locating, direction finding and countering threats on the ground and in the air. Currently these systems collect vast amounts of raw and unfiltered data that describe signals from electromagnetic sources in the form of individual pulse descriptor words (PDW) – potentially billions per minute. The raw data is then transmitted back to the tactical operations center (TOC) where it is downloaded, processed and analyzed to identify objects and track targets of interest. The sheer amount of raw data being transmitted over limited bandwidth and post-processed at the TOC is not conducive to real-time signal of interest tracking and hinders the Marines’ ability to react to potential threats. The advent of advanced AI and ML techniques, such as Long Short-Term Memory (LSTM) networks, and the availability of open-source software tools (e.g., TensorFlow) and off-the-shelf processing capabilities (e.g., NVIDIA) provides opportunity to more efficiently and effectively process electromagnetic signal data by enabling preprocessing and filtering at the antennae sensor. The ability to detect composite tracks in real time at the tactical edge will reduce the amount of data necessarily transmitted and post-processed at the TOC, resulting in more efficient signal analysis and ultimately improved effectiveness of EWS capabilities. MCSC is seeking a preprocessing solution for dismounted EWS systems. The solution will utilize innovative AI/ML algorithms to process large amounts of raw data (i.e., PDW) and recommend high priority tracks of interest indicative of patterns of life. The AI/ML algorithms will support signal classification to identify benign versus adversary signals based on a signals of interest list. In an operational scenario, a dismounted EWS could collect up to billions of PDW per minute, resulting in potentially millions of tracks. Processing the collected PDW from the electromagnetic environment is complicated by radio frequency (RF) reflections, clutter (e.g., foliage, structures, terrain, birds), and the sheer volume of PDW. The envisioned pre-processing capability should be able to process the PDW in such a way that objects, particularly slow moving or intermittent signals, can be automatically filtered from clutter and identified as a high priority for further analysis. Requirements for the preprocessing solution are as follows: Demonstrate a preprocessing capability to: (1) track very slow moving objects (0-40mph); (2) track objects among slow (0-40mph) moving point clutter (e.g., birds and insects); and (3) identify and rejoin intermittent or disjointed tracks in a highly complex electromagnetic environment. Each capability listed above should be demonstrated with a representative test case commensurate with the volume and complexity of data likely encountered in the battlespace. The solution must have sufficient time difference of arrival (TDOA) granularity to be able to draw out multiple tracks at once from billions of data points. The system shall have a Signal of Interest (SOI) false alarm rate no greater than 5% (Threshold) and no greater than 2% (Objective) within any 24-hour period of time. The hardware, software, or combined hardware/software solution must be easily integrated with a dismounted backpack-sized EWS, such as the current MODI II, and be antenna agnostic. A representative standard gain antenna should be used for demonstration purposes. The system shall be no larger than 12” by 6” by 4” (not including an antenna) and weighing no more than 5 lbs. not including the battery (Threshold) and no more than 5 lbs. including the battery (Objective). The preprocessor messaging shall be Joint Interface Control Document (JICD) 4.2 compliant. The solution should utilize commercial off-the-shelf hardware and software to the maximum extent possible. Proposals must describe the envisioned processing solution to include the software, hardware or combined approach. The proposer should also indicate expected size, weight, false alarm rate, classification performance, and memory requirements. Software or firmware shall meet cybersecurity requirements. The Phase I effort will not require access to classified information. If need be, data of the same level of complexity as secured data will be provided to support Phase I work. Work produced in Phase II may become classified. Note: The prospective contractor(s) must be U.S. Owned and Operated with no Foreign Influence as defined by DOD 5220.22-M, National Industrial Security Program Operating Manual, unless acceptable mitigating procedures can and have been implemented and approved by the Defense Security Service (DSS). The selected contractor and/or subcontractor must be able to acquire and maintain a secret level facility and Personnel Security Clearances, in order to perform on advanced phases of this contract as set forth by DSS and the Marine Corps in order to gain access to classified information pertaining to the national defense of the United States and its allies; this will be an inherent requirement. The selected company will be required to safeguard classified material IAW DoD 5220.22-M during the advance phases of this contract. 

PHASE I: Develop concepts for an automatic track generation that can be integrated with dismounted EWS, such as the MODI II [Ref 5], and that meets the requirements described above. Demonstrate the feasibility of the concepts in meeting Marine Corps needs through modeling and simulation. Establish that the concepts can be developed into a useful product for the Marine Corps. Provide a Phase II development plan with performance goals and key technical milestones, and that will address technical risk reduction. This Phase II plan will include specification for a prototype. 

PHASE II: Develop a scaled prototype integrated with a standard gain antenna for evaluating purposes and with data inputs representative of dismounted EWS PDW volume and complexity. Evaluate the prototype to determine its capability in meeting the performance goals defined in the Phase II development plan and the Marine Corps requirements for automatic track generation preprocessing. Demonstrate system performance through prototype evaluation and modeling or analytical methods that demonstrate the preprocessing capability with a test case for each of the three demonstration requirements listed in the Description. Use evaluation results to refine the prototype into an initial design that will meet Marine Corps requirements. Prepare a Phase III development plan to transition the technology to Marine Corps use. It is probable that the work under this effort will be classified under Phase II (see Description section for details). 

PHASE III: Support the Marine Corps in transitioning the technology for Marine Corps use, including testing and validation to certify and qualify the system. Develop a ruggedized automatic track generation pre-processor for integration and evaluation to determine its effectiveness in an operationally relevant environment. AI- and ML-enabled processing has potential use in a variety of commercial applications, including speech and handwriting recognition, communications, stock market predictions, robotics and autonomy. Other Government agencies with the need to identify and track objects or trends in complex environments, such as the Federal Aviation Administration, Federal Communications Commission, Customs and Border Protection, and the Federal Bureau of Investigation, could adapt this technology for insights and efficiencies to their particular missions. 


1. Gers, Felix, Schmidhuber, Jürgen & Cummins, Fred. “Learning to Forget: Continual Prediction with LSTM. Neural computation.” Neural Computation, October 2000, 12(10)2451-71. 10.1162/089976600300; 2. Greff, K., Srivastava, R., Koutnik, J., Steunebrink, B. and Schmidhuber, J. “LSTM: A Search Space Odyssey.” IEEE Transactions on Neural Networks and Learning Systems, 2016.; 3. 2018 U.S. Marine Corps Science & Technology Strategic Plan.; 4. Electronic Warfare. Marine Corps Reference Publication 3-32D.1, United States Marine Corps Publication Control Number144 000246 00. 02 May 2016.; 5. “Counter Radio-Controlled Improvised Explosive Device (RCIED) Electronic Warfare (CREW).” United States Marine Corps, 12 July 2018. The Official Website of the United States Marine Corps.

KEYWORDS: Electronic Warfare; Electromagnetic Spectrum; Signal Processing; Machine Learning; Artificial Intelligence; Neural Network; Recurrent Neural Network; Long Short-term Memory; Composite Tracker; Pulse Descriptor Word; NVIDIA; TensorFlow 

US Flag An Official Website of the United States Government