TECHNOLOGY AREA(S): Information Systems

ACQUISITION PROGRAM: PEO IWS 1.0, AEGIS Combat System Program Office

The technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the statement of work (SOW) tasks intended for accomplishment by the FN(s) in accordance with section 3.5 of the Announcement. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws.

OBJECTIVE: Develop a system architecture and algorithmic framework to identify air targets in real time quickly, accurately, and reliably for the AEGIS Combat System.

DESCRIPTION: Data stream analytics have been used in industry for a number of years to solve various logistical and other problems using on-the-fly monitoring, data-mining, and analysis of ongoing information streams. Recent advances in both Artificial Intelligence (AI) (e.g., Deep Learning techniques pioneered by Google) and high-speed parallel computing architectures (such as the Nvidia and AMD Graphical Processing Unit (GPU) subsystems) may now provide the ability to execute such data-stream analysis algorithms in real time.

Current Combat System Track Identification (ID) methodology utilizes transponder-based track ID data, Radio Frequency (RF) and voice interrogation of the potential air track under investigation, and estimated ID based on the operator�s best judgement when no other viable source of ID is available. In an environment where tactical communications are challenged or denied (e.g., where voice communications and/or transponder ID data may be unavailable), the operator is forced to rely only on his/her knowledge of the Area of Responsibility (AOR), the current Tactical Situation (TACSIT), and his/her own experience in determining if an air track is a potential threat. A system capable of providing the operator with additional ID options analytically derived from the observed air track behavior, with each potential ID suggestion ranked by probability, will greatly assist the operator in making a final track ID assignment to a questionable air track. An enhanced and semi-automated track ID capability will also contribute to the reduction of operator fatigue by reducing the operator�s need to ponder over each track ID to determine its veracity, thus allowing for a potential increase in the operator�s ability to handle extended duty time resulting in an associated reduction in manning by more than 20%, and improving affordability. One of the principal goals of this effort is to improve the operating efficiency of the combat systems air track identification capability, allowing a significant (>50%) improvement in the probability of successful identification for any specific track in the communications/sensor denied environment mentioned above. The current air traffic control aircraft ID uses mode-S transponder data stream provided by the aircraft. The issue is that mode-S is not a secure/verifiable source - transponders in aircraft can be switched/exchanged or modified. An alternate/verifiable form of aircraft identification needs to be developed that does not necessarily rely on the cooperation of the aircraft.

The Navy seeks a software system architecture and algorithmic model that implements real-time target track ID assignment within the AEGIS combat system. The system model architectural attributes will include scalability to process (in parallel) a large number (i.e., on the order of 10 times the current AEGIS capacity) of air tracks within the Common Operational Picture (COP). The system needs to be self-contained (i.e., require only software running within its current host combat systems suite to provide complete single-platform based capability) and have minimal impact on the performance of the current combat system. The system must also provide a well-defined and documented Applications Program Interface (API) allowing portability of the architecture and algorithms to other combat systems (e.g., Ship Self Defense System (SSDS) and the Future Surface Combatant (FSC) combat system).

The proposed system architecture and associated analytic algorithms must be capable of generating a real-time track ID for all air tracks within the COP based on an analytical combination of available parameters. These parameters may include a prospective air target transponder provided ID, observed real-time track behavioral characteristics (air speed, maneuver radius, projected destination, radar signature analysis, etc.) analyzed against a known track airframe dataset comprised of previously collected air track data and behavioral data retrieved from a shipboard airframe track database, and current principal ship TACSIT and geographic location with respect to known commercial air-traffic patterns in the AOR. The system must be capable of generating alterative track IDs developed in real time as a set of probability-ranked options. Each option will have associated track-ID reliability metrics that will indicate its relative merit with respect to the other options presented. The proposed system will allow an operator to specify an ID reliability threshold after which the real-time analysis will provide the alternate ID suggestions. The technology will also utilize multi-platform sourced data streams (when available) to provide a multi-platform distributed track ID capability and improve the reliability of its ID recommendations. The value of having a set of continuously updated probability ranked air track ID options available to the console operator will greatly reduce the probability of incorrect air track identification that could result in either erroneous engagement of non-threatening tracks, or non-engagement of lethal threats.

The proposed system must rapidly present the initial analytical results for real-time use in the operator�s decision-making process. However, the analytical process should not complete once the initial results are presented. The technology will continuously and dynamically update and present enhanced analytical results (i.e., updated target ID recommendations) in a real-time manner as the tactical air track data stream evolves. The method used to present the analytical results must be compatible with and implementable within the currently implemented AEGIS software and hardware display infrastructure. The technology will be well documented and conform to open systems architectural principals and standards.

The Phase II effort will likely require secure access, and NAVSEA will process the DD254 to support the contractor for personnel and facility certification for secure access. 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 will likely 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 be 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 NAVSEA 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 a concept for a software architecture and real-time data-stream analytics system as identified in the Description. Demonstrate that the model will show that it can feasibly meet the requirements in the Description. Establish feasibility through evaluation of the proposed model via a study and/or use of a simulation-based analysis. Develop a Phase II plan. The Phase I Option, if exercised, will include the initial design specifications and capabilities required to build a prototype in Phase II.

PHASE II: Develop and deliver a prototype software architecture and real-time data-stream analytics system that demonstrates the capability to perform all parameters described in the Description after implementation and integration into the combat system environment. Perform the demonstration at a Land Based Test Site (LBTS), provided by the Government, that represents an AEGIS BL9 or newer combat system environment and that should be capable of simultaneously simulating two AEGIS test platforms, to allow for the demonstration of track ID generation using sensor data provided by two cooperating platforms. Ensure that the prototype will demonstrate it has little to no impact on the performance of the combat system environment. The company will prepare a Phase III development plan to transition the technology for Navy combat systems and potential commercial use.

It is probable that the work under this effort will be classified under Phase II (see Description section for details).

PHASE III DUAL USE APPLICATIONS: Support the Navy in transitioning the technology to Navy use. Implement a fully functional software architecture and real-time data-stream analytics algorithms system into the AEGIS combat system baseline modernization process, consisting of integrating into the combat system baseline, validation testing, and combat system certification.

This architecture can benefit the commercial air traffic control systems, providing a potential capability to identify unknown air tracks utilizing commercial air space and/or approaching civilian airports. Such a capability may prove useful in civilian anti-terrorism scenarios.

REFERENCES:

1. Vasudevan, Vijay. �Tensorflow: A system for Large-Scale Machine Learning.� Usenix Association, USENIX OSDI 2016 Conference, 2 November 2016. https://www.usenix.org/system/files/conference/osdi16/osdi16-abadi.pdf

2. Vasudevan, Vijay. �TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems.� Usenix Association, 2016. http://download.tensorflow.org/paper/whitepaper2015.pdf

3. Schmidhuber, J�rgen. �Deep Learning in Neural Networks: An Overview.� Neural Networks, Volume 61, January 2015, pp. 85-117. http://www.sciencedirect.com/science/article/pii/S0893608014002135

4. Schmidt, Douglas. �A Naval Perspective on Open-Systems Architecture.� Carnegie Mellon University, Software Engineering Institute, SEI Blog, Posted 11 July 2016. https://insights.sei.cmu.edu/sei_blog/2016/07/a-naval-perspective-on-open-systems-architecture.html

KEYWORDS: Real-time Target Track ID; Deep Learning Techniques; Transponder Identification; ID Spoofing; Artificial Intelligence; Multi-platform Track ID; Track-ID Reliability Metric