N251-047 TITLE: Multi-sensor and Acoustic Contact Localization through Artificial Intelligence/Machine Learning

OUSD (R&E) CRITICAL TECHNOLOGY AREA(S): Trusted AI and Autonomy

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 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 technology that can localize maritime entities from passive sensor contact information using artificial intelligence or machine learning (AI/ML) algorithms.

DESCRIPTION: Modern submarines are fitted with numerous arrays with the intent of minimizing blind spots. However, the parameters associated with these disparate arrays makes it difficult to create a unified picture, particularly where entities are detected by multiple sensor arrays. Submarines and other undersea warfare systems use passive sensor information to develop track information (bearing, range, course and speed vs. time) of maritime entities. It does so by leveraging multiple separate algorithms and observations of changes in the dynamics of acoustic sensor data such as signal arrival angle at the sensor array, Doppler shift, and data from spatially separated arrays. Often the submarine will maneuver to drive changes in how the entity appears to the sensor to enable Target Motion Analysis (TMA). The sensor data feeds various algorithms that suggest the proper 4-state solution (bearing, range, course, and speed) for entity location and velocity. The quality of the solution depends on the completeness and accuracy of the data fed into the algorithms and how the submarine maneuvers.

Several of the acoustic arrays that submarines rely on are towed, with estimated shape and position used when computing entity positions.

The operator typically cycles between multiple separate solution development and evaluation tools to arrive at candidate contact track solutions. This process becomes increasingly inaccurate as the incoming information becomes more complex, as might occur with noisy, sparse, or weak contact signals or when a large number of contacts must be managed. Advances in solution accuracy have been achieved through refining the operator machine interface to support efficient operator workflow based on the current paradigm of cycling through multiple algorithm-generated displays to assess validity of multiple hypothetical track solutions.

The Navy seeks to shift to an integrated technology for simultaneously evaluating all available information for localizing maritime entities. A solution for obtaining this shift is not commercially available.

AI/ML algorithms for U.S. Navy Undersea Warfare sensors have been used to assist in detection and classification of signals within the current cyclic process. This SBIR topic seeks to migrate to AI/ML technology where detection information such as operator-promoted contact followers are used to achieve rapid and accurate localization of individual maritime entities in support of a holistic tactical contact picture. The tool developed will need to demonstrate an ability to develop contact track solutions using all promoted sensor data and associated environmental propagation information as measured by estimated 4-state solution (bearing, range, course, and speed) when compared to the true track.

In addition to producing rapid estimates of contact position and speed, the desired AI/ML technology should also be able to provide refined array shape and position estimates in real time, rather than relying on predicted shape and position using high-level parameters such as platform speed and tow cable scope.

The technology architecture must be extensible to multiple arrays and array types as well as contact follower data from multiple vehicles. It must use data that is diverse and representative of real world acoustic data. The data should be representative of both hull mounted and line array configurations. It is desirable for the technology to provide a confidence value in addition to track solution estimates. The solution will provide novel visualization tools or processes that suggest track solutions, the quality of constituent data sources, and instances where operator-specified information (e.g., propagation paths) do not make sense in light of the larger sets of data considered by the AI/ML technology.

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 32 U.S.C. § 2004.20 et seq., National Industrial Security Program Executive Agent and Operating Manual, unless acceptable mitigating procedures can and have been implemented and approved by the Defense Counterintelligence and Security Agency (DCSA) formerly Defense Security Service (DSS). The selected contractor must be able to acquire and maintain a secret level facility and Personnel Security Clearances. This will allow contractor personnel to perform on advanced phases of this project as set forth by DCSA 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 during the advanced phases of this contract IAW the National Industrial Security Program Operating Manual (NISPOM), which can be found at Title 32, Part 2004.20 of the Code of Federal Regulations.

PHASE I: Develop a concept for an AI/ML TMA tool that meets the parameters of the Description and demonstrates the feasibility of the concept using unclassified data obtained or created by the awardee and that is clearly extensible to the acoustic data use case. Show feasibility through analysis, modelling, simulation, and testing. The Phase I Option, if exercised, will include the initial design specifications and capabilities description to build a prototype solution in Phase II.

PHASE II: Develop and deliver a prototype AI/ML TMA tool with architecture and methodology for incorporating the capability into submarine sonar contact management. Demonstrate that the prototype meets the required range of desired performance attributes given in the Description. System performance will be demonstrated through installation and prototype testing on a testbed with the lead system integrator provided by the government.

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 in Anti-Submarine Warfare (ASW). Demonstrate and report on performance during laboratory testing. The prototype will be integrated into ASW combat systems for which IWS 5.0 develops updates, which include the AN/SQQ-89, AN/BQQ-10, and AN/BYG-1 systems.

The technology can be extended to any passive sensor, including non-acoustic sensors. This technology can be used in a wide range of complex systems of systems where AI/ML is used to characterize operator proficiency and just-in-time performance assistance is crucial to mission performance. The technology would be of greatest use in complex safety-critical systems where mistakes carry disproportionate risk of mission failure.

REFERENCES:

1. Shahbazian, Reze et al. "Machine Learning Assist IoT Localization: A Review of Current Challenges and Future Trends." Sensors 2023, 23(7), 3551. https://www.mdpi.com/1424-8220/23/7/3551

2. "AN/BQQ-10 Acoustic Rapid Commercial Off-the-Shelf Insertion (A-RCI) Sonar." FY16 Navy Programs. https://www.dote.osd.mil/Portals/97/pub/reports/FY2016/navy/2016arci.pdf?ver=2019-08-22-105302-370

3. "AN/SQQ-89(V) Undersea Warfare / Anti-Submarine Warfare Combat System." Navy Fact File, last updated 20 Sep 2021. https://www.navy.mil/Resources/Fact-Files/Display-FactFiles/Article/2166784/ansqq-89v-undersea-warfare-anti-submarine-warfare-combat-system/

4. "National Industrial Security Program Executive Agent and Operating Manual (NISP), 32 U.S.C. § 2004.20 et seq. (1993)." https://www.ecfr.gov/current/title-32/subtitle-B/chapter-XX/part-2004

KEYWORDS: Artificial intelligence or machine learning (AI/ML); acoustic sensor data; undersea warfare systems; data that is diverse and representative; Target Motion Analysis (TMA); Holistic Tactical Contact Picture

---