DON26BZ03-NV061 TITLE: Predictive Movement for Object Oriented Tracking
OUSW (R&E) CRITICAL TECHNOLOGY AREA(S): Applied Artificial Intelligence (AAI)
COMPONENT TECHNOLOGY PRIORITY AREA(S): Trusted AI and Autonomy
PROJECTED CMMC LEVEL REQUIREMENT: Level 2 (Self)
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 capability using Artificial Intelligence (AI) that investigates, tracks, and assigns priority for future state forecasting such as Geospatial-temporal Pattern of Life Analysis and change detection for the Maritime Targeting Cell (MTC).
DESCRIPTION: Maritime Targeting Cell is a high-tech "fusion" node, which receives massive amounts of data from diverse sources (e.g., satellites, sensors), making it difficult to process and interpret effectively. Current tracking relies heavily on manual methods, which can overwhelm staff and lead to inefficient resource allocation. They are essentially trying to find the proverbial needle in a haystack. Without an automated system, it is difficult to prioritize which objects require immediate attention, which can lead to critical threats being overlooked.
The Maritime Targeting Cell has a need to increase readiness for potential conflicts with adversaries. There are currently a large number of objects that need to be tracked, both above and below the surface of the ocean, across the globe. These objects include U.S. Navy Ships, other U.S. Government vessels, allied and partner Naval vessels, commercial vessels, adversary vessels, U.S. and other nations’ submarines, underwater drones and sensors, and aircraft. The Navy needs to utilize efficient tracking methods for large numbers of objects so future state forecasting, pattern of life, and change detection can enable analysts to investigate targets, maintain track custody, and assign priority to objects detected.
As more sensors come online, the data volume will only increase, exacerbating existing problems. The current manual processes simply cannot scale and as the Navy’s specific requirements are unique and complex, off-the-shelf tracking software is insufficient. Currently no existing commercial technology can meet this need.
The Navy envisions an AI-driven solution that aims to address these challenges by automating key aspects of the tracking process.
The solution must meet the following parameters:
1. It must use AI-powered tracking algorithms to process sensor data, identify and track objects, and predict their future movements.
2. It must use Automated Prioritization in which AI is used for activity prediction and Pattern of Life (POL) analysis to assign a priority level to each tracked object, allowing analysts to focus on the most important targets first.
3. It must use Predictive Forecasting and Change Detection to analyze historical data and current behavior and predict future object states and quickly identify deviations from expected patterns, enhancing situational awareness.
4. It must contain Hierarchical Target Management to allow the system to maintain track custody of all objects, but present them to analysts in a prioritized hierarchy, allowing for efficient resource allocation.
5. It will need to have Enhanced Scalability so as new sensors are added, the AI can seamlessly integrate the additional data without requiring a proportional increase in manpower.
6. It will need to have Improved Response Time through automating analysis and prioritization to accelerate the decision-making process, enabling faster responses to developing situations.
In essence, the proposed AI solution aims to transform the Navy from a reactive overwhelmed center to a proactive highly efficient hub for maritime domain awareness, which will empower the Navy to better manage the vast amount of data it collects and make more informed decisions, ultimately enhancing national security.
Evaluation metrics will be used to quantify the system’s performance, including accuracy, precision, recall, F1-score (a balanced measure of precision and recall), processing time, false positive rate, and false negative rate. These metrics will measure how often the system correctly identifies and tracks objects, the proportion of correctly identified objects out of all identified and all actual objects, a balance of precision and recall, the data processing time, and the rates of incorrect object identification and missed object identification.
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-driven maritime tracking system that automates data processing, object identification and tracking, and threat prioritization. Demonstrate the feasibility of this concept through modeling and simulation, showing how the proposed algorithms can achieve the required levels of accuracy in object identification, tracking, and prioritization using simulated sensor data representing realistic maritime scenarios. Ensure that this simulation demonstrates (1) the concept's ability to handle increasing data loads that reflect the Navy's future needs, (2) improved response times compared to current manual methods, and (3) the feasibility of hierarchical target management to prioritize objects based on predicted threat level. (Note: While full prototypes are not expected in Phase I, performers might need to develop subscale prototypes or surrogates of specific AI modules, such as predictive forecasting or POL analysis components.)
The Phase I Option, if exercised, will include the initial design specifications and capabilities to build a prototype solution in Phase II.
PHASE II: Develop a prototype AI-driven maritime tracking tool based on the results of Phase I. Demonstrate the core functionalities of the prototype, including AI-driven tracking, prioritization, predictive forecasting and change detection, hierarchical target management, enhanced scalability, and improved response time. Support rigorous prototype testing using simulated and/or real-world maritime sensor data and evaluation on the performance against metrics defined in the Description, including accuracy, prioritization effectiveness, and response time improvement. (Note: If a full prototype is cost-prohibitive, advanced modeling and simulation using representative data can be used to demonstrate the technology's potential.) Ensure that the prototype meets key requirements including specified accuracy levels, prioritization thresholds, and demonstrable improvements in response time and scalability.
It is probable that the work under this effort will be classified under Phase II (see the Description for details).
PHASE III DUAL USE APPLICATIONS: Support the Navy in transitioning the technology to Navy use. Support testing to ensure that the system meets the demanding requirements of modern naval operations via operational testing in simulated scenarios and field testing to assess its performance in actual conditions.
Once operators of the system have provided feedback on its usability, effectiveness, and suitability for operational needs, the system will be used to inform future development and deployment decisions, ultimately contributing to an enhanced scalability and improved response time.
Outside of the military, this technology has the potential to revolutionize various sectors, such as law enforcement, marine wildlife protection, climate change research, vessel collision avoidance, supply chain management, coordination of rescue/relief efforts, and meteorology. The system could be deployed across multiple domains, improving safety, efficiency, and environmental protection in diverse environments.
REFERENCES:
KEYWORDS: Pattern of Life; Hierarchical Target Management node; predictive forecasting; object oriented tracking; Change Detection; Automated Prioritization
| 7/8/26 | Q. | Is there a preference or requirement for how false positives on predicted threats should be handled operationally? For example, does a "predicted" flag require a lower confidence threshold than a confirmed detection? |
| A. | Proposed solutions should utilize a tiered confidence threshold. Predictive alerts inherently have lower initial confidence than confirmed real-time detections, and this must be reflected in your interface. | |
| 7/1/26 | Q. | Does the government have existing pattern-of-life or behavioral baseline data for maritime objects, or will Phase I need to establish those baselines from synthetic/simulated data alone? |
| A. | Phase I must establish these baselines from synthetic/simulated data and open-source data alone to construct a baseline statistical model of "normal" transit patterns, and use your simulation environment to inject anomalous deviations for testing. | |
| 7/8/26 | Q. | What does the government consider a meaningful prediction/warning-time improvement, and over what forecast horizon (minutes, hours) is "predictive" expected to operate? |
| A. | Forecasting Horizons: "Predictive" tracking is expected to operate across two primary operationally relevant scales:
* Short-Term (Tactical): Minutes to hours (e.g., kinematic projections for collision avoidance, immediate intercept routing, or sensor handoff). * Medium-Term (Operational): 12, 24, and 48 hours (e.g., predicting projected port destination, ETA, or potential mid-ocean rendezvous points). |
|
| 7/8/26 | Q. | Beyond the generic DoW Appendix A template, are there Component (Navy)-specific page limits or formatting instructions for this topic, and is a Phase I Option period included or anticipated? |
| A. | Please refer to the DON proposal submission instructions found here: https://www.dodsbirsttr.mil/submissions/api/public/download/solicitationDocuments?solicitation=DOD_SBIR_2026_P1_CBZ&documentType=INSTRUCTIONS&component=NAVY&release=3 |
|
| 7/8/26 | Q. | What baseline should we use to measure "improved response time," and will the government provide any representative or historical track data for Phase I modeling, or is fully synthetic data acceptable? |
| A. | No government-furnished data will be provided for Phase I. Fully synthetic data is completely acceptable and expected for the Phase I modeling and simulation demonstration, provided it incorporates realistic sensor noise, dropouts, and high background clutter. | |
| 7/8/26 | Q. | Can you confirm whether there are any restrictions on a single small business submitting both a Phase I proposal and a Direct to Phase II proposal within the same solicitation cycle? The direct to phase 2 submission is for a different topic for a distinct, already-fielded product. |
| A. | Yes, a small business can submit a proposal to both a Phase I topic and a Direct to Phase II topic in the same Release. | |
| 7/7/26 | Q. | The Description requires predictive forecasting and the ability to 'quickly identify deviations from expected patterns,' with performance evaluated on false positive and false negative rates. In real-world maritime traffic, many deviations from historical patterns are driven by benign environmental factors - weather avoidance, sea state, or seasonal shifts in fishing and shipping activity - rather than by threatening behavior. Does the Government consider the fusion of environmental and metocean forecast data into the Pattern of Life and predictive forecasting components to be within the intended scope of this topic, and would demonstrated reductions in false positive rate achieved through such environmental context be viewed as responsive to the evaluation metrics in the Description? |
| A. | Yes, consideration of meteorological and oceanographic (METOC) data (e.g., sea state, wind speed, currents, and visibility) would be in scope and should be considered for in methods to reduce false positives. | |
| 7/6/26 | Q. | 1. Given the requirement to track a diverse range of objects across multiple domains- surface, subsurface, and air- using varied sources, what specific data modalities (e.g., AIS, Synthetic Aperture Radar, EO/IR imagery, acoustic signatures) should we expect the system to ingest? Additionally, will the Navy provide a standardized data dictionary or specific API parameters that our AI system must be compatible with during Phase I?
2. Will the Navy provide government-furnished simulated datasets during Phase I to ensure our modeling accurately reflects the realistic maritime scenarios required for evaluation? If not, are there specific unclassified proxy datasets or open-source environments the Navy recommends performers use to train the predictive forecasting and Pattern of Life (POL) algorithms before accessing classified real-world data in Phase II? |
| A. | 1. For the Phase I demonstration, proposed solutions should assume ingestion of structured track state data (time, coordinates, course, speed, classification) derived from these data and sensor sources. Processing of raw, unstructured data is considered out of scope for Phase I. The Navy will not be providing standardized a data dictionary or specific APIs during Phase I.
2. The Government will not be providing simulated data sets during Phase I. Performers are encouraged to publicly available, unclassified maritime datasets. Proposed solution should consider open-source maritime simulation frameworks or custom-built synthetic trajectory generators to model non-cooperative target behaviors (e.g., transponder gaps, spoofing, and evasive maneuvers) that are not typically present in standard commercial data sets. |
|
| 7/4/26 | Q. | 1. The topic lists a projected CMMC Level 2 (Self) requirement. Given the CMMC Phase 2 implementation date of November 10, 2026, can the Government confirm that a current NIST SP 800-171 self-assessment score posted in SPRS with affirmation will satisfy the requirement at time of Phase I award, and that a C3PAO certification will not be required for Phase I or the Phase I Option?
2. The topic states the selected contractor must be able to acquire and maintain a Secret facility clearance for advanced phases. Can the Government confirm that a current FCL is not required at time of Phase I proposal or award, and that DCSA sponsorship for the FCL would be initiated by the Government in conjunction with Phase II selection? |
| A. | 1. Per the DON instruction on this topic, only CMMC Level 2 (Self) will be required by the time of award.
2. A current FCL is not required at the of Phase 1 proposal or award. Recommend addressing contractor’s ability and willingness to acquire and maintain a FCL. For selected Phase II performers who do not currently possess an active FCL, the Navy will initiate Defense Counterintelligence and Security Agency (DCSA) sponsorship for the required FCL in conjunction with the Phase II selection and contracting process. |
|
| 6/24/26 | Q. | 1. Is the interest in tracking specific vessels, or locating and tracking vessels with anomalous behavior when compared to historical Patterns of Life?
2. Is the SBC to rely on historical data to develop an initial Pattern of Life, or build the pattern based on incoming data? 3. If we detect, classify, and track vessels and aircraft in a specific ROI, how are the targets/threats to be prioritized? What is of most interest/need to the Navy? 4. Is the main sensing modality commercial satellite imagery? 5. Should government repositories of commercial satellite imagery such as GEGD and/or iSPY be included in the proposed system? 6. For Phase I, will government-furnished data be available? i.e., AIS over regions/times of interest with corresponding satellite imagery or SAR data? 7. Will the proposed tracking system have access to data from space-based government assets, airborne government assets, AIS data, passive RF information, commercial EO and SAR satellite-based imagery? 8. What resources are expected to be applied by the Navy once the tracking system reports a track of interest? Is this decided by an operator based on the set of prioritized targets? Is the decision-making process done by a human? (e.g., target a vessel with a weapon?, send a vessel to intercept it?, request future sensor tasking to maintain custody?) |
| A. | 1. The primary interest is identifying and tracking vessels exhibiting anomalous behaviors that deviate from established historical Pattern of Life (POL) baselines.
2. Companies should design their systems to do both. You must rely on historical data (weeks/months of past tracks) to develop the initial "normal" baseline, while continuously utilizing incoming real-time data to update those baselines, detect sudden deviations, and adjust track priorities. 3. Prioritization should be calculated as a dynamic, multi-variable index. Interest includes vessels showing high-significance deviations from POL, tracks converging on points of interest, etc. 4. The primary inputs for this tracking system are structured track tables containing positional and kinematics data derived from multi-sensor sources, including commercial and government sensor or systems. 5. During Phase I, architect your system to ingest standard structured geospatial and kinematics feeds. 6. No sample data sets will be provided during Phase I. Companies should construct their own simulated environments or use public/open-source feeds. Synthetic data must be used to simulate sensor noise, dropouts, and multi-sensor target behaviors. 7. In Phase II, the Navy intends to explore integrating the proposed solution(s) within other systems to provide access to a broader suite of military, national, and commercial sensor and track data. 8. Proposed solutions should reduce cognitive load and support decision making processes for an operator. The operator will use the prioritized list to determine the subsequent actions. |
|
| 6/23/26 | Q. | 1. Will the Navy provide sample datasets, specific data schemas, or access to a standardized simulation environment during Phase I to ensure the models accurately reflect the diverse sensor inputs and massive data volume the MTC currently handles?
2. Does the Navy have established quantitative baselines or specific performance threshold targets based on current manual operations that the proposed AI-driven prototype must exceed during Phase II testing? |
| A. | 1. No sample data sets will be provided during Phase I. Companies should construct their own simulated environments or use public/open-source feeds. Synthetic data must be used to simulate sensor noise, dropouts, and multi-sensor target behaviors.
2. The Navy has not established specific quantitative baselines or performance threshold targets that the proposed AL-driven prototype must exceed during Phase II testing. |
** TOPIC NOTICE ** |
The Navy Topic above is an "unofficial" copy from the Navy Topics in the DoW FY-26 Release 3 SBIR BAA. Please see the official DoW Topic website at www.dodsbirsttr.mil/submissions/solicitation-documents/active-solicitations for any updates. The DoW issued its Navy FY-26 Release 3 SBIR Topics pre-release on June 3, 2026 which opens to receive proposals on June 24, 2026, and closes July 22, 2026 (12:00pm ET). Direct Contact with Topic Authors: During the pre-release period (June 3, through June 23, 2026) proposing firms have an opportunity to directly contact the Technical Point of Contact (TPOC) to ask technical questions about the specific BAA topic. The TPOC contact information is listed in each topic description. Once DoW begins accepting proposals on June 24, 2026 no further direct contact between proposers and topic authors is allowed unless the Topic Author is responding to a question submitted during the Pre-release period. DoD On-line Q&A System: After the pre-release period, until July 8, 2026, at 12:00 PM ET, proposers may submit written questions through the DoW On-line Topic Q&A at https://www.dodsbirsttr.mil/submissions/login/ by logging in and following instructions. In the Topic Q&A system, the questioner and respondent remain anonymous but all questions and answers are posted for general viewing.
DoW Topics Search Tool: Visit the DoW Topic Search Tool at www.dodsbirsttr.mil/topics-app/ to find topics by keyword across all DoW Components participating in this BAA.
|