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 adaptive Artificial Intelligence / Machine Learning (AI/ML) automatic target recognition (ATR) algorithms to support Autonomous Undersea Vehicle (AUV) operations in complex environments. DESCRIPTION: ATR algorithm performance is degraded in littoral waters because of the clutter created by the abundance of marine life in a complex underwater environment. Complex underwater environments are underwater areas with varied seabed composition, bottom clutter, and a significant amount of marine life. Current ATR capabilities are created for non-complex environments with homogenous seabed and limited marine life. As a result, current ATR capabilities lack the ability to discriminate between targets and clutter caused by marine life, reducing the ability to perform detection, classification, and localization of targets. The Navy is seeking AI/ML ATR processing algorithms, or techniques to facilitate target identification in complex environments using acoustic, optical, and magnetic sensors. The resulting technology should provide a significant improvement in the performance and detection capability of ATR algorithms by reducing the Probability of False Alarm (Pfa) and improve operator work load. Improvements are considered significant when performance in complex environments approaches the current baseline requirements for performance in non-complex environments. The technology will be integrated into the Generalized ATR (GATR) system to improve performance and detection capability AI/ML capability should incorporate information from new data sets into the ATR system as they are acquired, and re-optimize the ATR algorithms quickly across all known environments, including those of newly acquired data. Online Machine Learning (OML) algorithms can potentially be used to “learn” in the field based on operator-provided results without affecting prior performance. The information collected online can be used to refine the prediction hypothesis (classifier) used in the ATR algorithms. In addition, the information may provide input for automated methods of optimizing ATR performance across all known data sets. The proposed effort will develop innovative OML algorithms for ATR that can incorporate human operator decisions to optimize probability of detection and probability of false alarm performance in new environments and for new target types. These algorithms will be integrated into mission and post-mission analysis systems in which operators review acquired data. Algorithms must be built for operation on the Nvidia Graphics Processing Unit (GPU) using the Compute Unified Device Architecture (CUDA). The OML algorithms and optimization tools developed in this effort will reduce program costs by minimizing the time required for optimizing ATR algorithms to perform well in complex operational environments where there is little or no data available. 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 Counterintelligence Security Agency (DCSA), formerly the Defense Security Service (DSS). The selected contractor 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 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 IAW DoD 5220.22-M during the advance phases of this contract. All DoD Information Systems (IS) and Platform Information Technology (PIT) systems will be categorized in accordance with Committee on National Security Systems Instruction (CNSSI) 1253, implemented using a corresponding set of security controls from National Institute of Standards and Technology (NIST) Special Publication (SP) 800-53, and evaluated using assessment procedures from NIST SP 800-53A and DoD-specific (KS) (Information Assurance Technical Authority (IATA) Standards and Tools). The Contractor shall support the Assessment and Authorization (A&A) of the system. The Contractor shall support the government’s efforts to obtain an Authorization to Operate (ATO) in accordance with DoDI 8500.01 Cybersecurity, DoDI 8510.01 Risk Management Framework (RMF) for DoD Information Technology (IT), NIST SP 800-53, NAVSEA 9400.2-M (October 2016), and business rules set by the NAVSEA Echelon II and the Functional Authorizing Official (FAO). The Contractor shall design the tool to their proposed RMF Security Controls necessary to obtain A&A. The Contractor shall provide technical support and design material for RMF assessment and authorization in accordance with NAVSEA Instruction 9400.2-M by delivering OQE and documentation to support assessment and authorization package development. Contractor Information Systems Security Requirements. The Contractor shall implement the security requirements set forth in the clause entitled DFARS 252.204-7012, “Safeguarding Covered Defense Information and Cyber Incident Reporting,” and National Institute of Standards and Technology (NIST) Special Publication 800-171. PHASE I: Develop a concept to facilitate target identification in complex underwater environments using acoustic, optical, and magnetic sensors that meets the requirements described above. Demonstrate the feasibility of the concept in meeting Navy needs and establish that the concept can be feasibly developed into a useful product for the Navy. Feasibility will be established by testing and analytical modeling. 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: Based on the results of Phase I and the Phase II Statement of Work (SOW), develop and deliver a prototype for evaluation as appropriate. The prototype will be evaluated to determine its capability in meeting the performance goals defined in the Phase II SOW and the Navy requirements for the algorithms. Demonstrate performance across a broad set of Government Furnished Information (GFI) data. Performance will be validated against Government-provided target truth. Prepare a Phase III development plan to transition the technology to Navy use. The company will prepare a Phase III development plan to transition the technology to Navy use. It is possible that the work under this effort will be classified under Phase II (see Description section for details). PHASE III DUAL USE APPLICATIONS: Produce and support a final prototype that will be integrated into developmental and operational frameworks used by the MK18 Family of Systems (FoS). Additionally, AI/ML algorithms developed may be inserted onboard AUV’s embedded processors. Technology developed under this effort is applicable to any domain that requires subsea platform autonomy such as subsea oil and gas pipeline inspection. REFERENCES: 1. Secretary of the Navy Innovation Awards; "The Expeditionary MCM (ExMCM) Company: The Newest Capability in U.S. Navy Explosive Ordnance Disposal (EOD) Community." July 2017. https://www.secnav.navy.mil/innovation/Documents/2017/07/ExMCM.pdf 2. Neupane, D., Seok, J., “A Review on Deep Learning-Based Approaches for Automatic Sonar Target Recognition”, Electronics 2020, 9(11), 1972; https://doi.org/10.3390/electronics9111972 3. Doshi, K., Yilmaz, Y., “Continual Learning for Anomaly Detection in Surveillance Videos”, Computer Vision Foundation, 2020. [2004.07941] Continual Learning for Anomaly Detection in Surveillance Videos (arxiv.org) https://arxiv.org/abs/2004.07941 KEYWORDS: Artificial Intelligence / Machine Learning; AUV / UUV; Automatic Target Detection; General ATR; Probability of false alarm; ATR capabilities; Complex water environments.