DON27BZ02-NV021 TITLE: SI-Enabled "Just-in-time" Knowledge Delivery for Naval Maintainers

OUSW (R&E) CRITICAL TECHNOLOGY AREA(S): Applied Artificial Intelligence (AAI)

COMPONENT TECHNOLOGY PRIORITY AREA(S): Human-Machine Interfaces;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 an SI-enabled maintenance associate that delivers interactive, expert-level guidance for complex diagnostic and repair tasks at point of need, provides technicians historical context on specific vehicles or components being repaired, and curates maintenance histories into easily mineable repository for future use.

DESCRIPTION: This effort is aimed at addressing the critical operational challenge of maintaining increasingly diverse and technologically complex arrays of systems with generalist knowledge. The solution requested in this SBIR topic is a just-in-time knowledge delivery system for Fleet maintainers that tells them what they need to know, when they need to know it. It would provide detailed procedures and technical knowledge for diagnostics, repair and maintenance procedures on demand, both ashore and at sea, where there will be limited access to remote data stores. The system will employ generative SI to analyze authoritative technical documentation and historical maintenance records, at both the Fleet and individual asset levels, and generate summarized technical guidance initiated by free-text queries or guided diagnostic dialogues. Post-task, the system will prompt the technician for repair feedback, synthesizing their insights to update the database with both general maintenance guidance and individual asset histories. Problems with current knowledge delivery are particularly acute when new systems and technology are introduced to the Fleet, such as with the introduction of unmanned systems (UxS), and when locally developed knowledge needs to be propagated across the larger maintenance community.

Operational readiness is currently bottlenecked by an inefficient maintenance paradigm: generalist maintenance technicians constantly face unfamiliar equipment without access to historical repair data, while frequent duty rotations continually erase localized (tribal) knowledge. This over-reliance on a transient pool of specialists causes extended system downtime and degrades operational readiness. These problems are particularly acute when new systems and technology are introduced to the Fleet.

While new advances in Large Language Models (LLMs) and generative SI present an opportunity to create sophisticated human-machine teaming tools for providing real-time interactive support, state-of-the-art predictive maintenance systems are not attuned to the unique challenges of the Navy’s maintenance environment. Effective solutions will need to integrate diverse approaches and overcome existing hard science problems to arrive at the desired solution. Current approaches in this domain excel at forecasting component failures and recommending procedures; however, they lack the interactive step-by-step guidance required to conduct the procedures or for dynamic on-the-job technical support to the maintainers. Existing maintenance knowledge tools operate as one-way information pipelines that fail to capture critical institutional knowledge and platform-specific maintenance histories, which prevents the continuous, enterprise-wide learning loop necessary for resilient maintenance operations.

Solutions must be able to ingest, synthesize, and appropriately structure a wide variety of data formats (e.g., technical manuals, structured databases, handwritten logs) while also integrating newly produced recurrent maintenance reports. This data should serve as a dynamically updated foundational knowledge base that is contextualized by the physical and operational situation unique to each repair, providing customized guidance to the technician. The solution should adapt its guidance to the user's specific skill level and experience to ensure interpretability across levels of expertise. Lastly, the desired Maintenance Associate solution must be capable of operating on local hardware in low-bandwidth and disconnected environments, operating on local storage and syncing fleetwide as connectivity allows.

This SBIR topic is seeking proposals that would contribute to the development of an SI-Enabled Maintenance Associate. It is expected that the initial capability would be focused on a specific technical domain and a representative set of equipment that would serve as a prototype that can be scaled up to apply to multiple domains and an array of deployed systems. One target domain of immediate interest is the maintenance and repair of unmanned systems. However, any equipment and application domain that is found within Naval systems is of interest.

The envisioned system workflow will ingest and distill technical documentation into interactive, multi-media or hard-copy repair procedures—complete with parts lists, safety warnings, and annotated tribal knowledge—delivered through a user-friendly Human-Machine Interface (HMI). The system will capture post-repair outcomes to continuously update the foundational knowledge base. Proposed solutions may address individual components of the Maintenance Associate system or work to develop a complete system.

Components of the Maintenance Associate System that may be addressed for this SBIR topic should include:

• A database management system for repair service/technical manuals and logs for distillation into maintenance procedures.
• An HMI for technician requesting support that delivers summary procedure, to include tools, parts lists, cautions, and warnings; and provides results that are appropriately annotated localized (tribal) knowledge (best practices, tips, and comments from other users).
• System products to end-users delivered as: multi-media content and/or hard copy outputs for technicians to access when performing procedures.
• An incorporated mechanism to capture results/maintenance outcomes with a data integration mechanism that feeds into the knowledge base for future reference.

Ideally, this transition effort will specifically focus on supporting the complex maintenance, diagnostics, and repair requirements of UxS hardware and platforms (e.g., Unmanned Surface Vessels, Unmanned Underwater Vehicles, Unmanned Ground Systems, and Unmanned Aerial Systems), although use cases for other Naval Applications and alternative transition customers would be acceptable. Unmanned systems and commands are nascent, and subject to wholesale platform change in short order. Operators and maintainers rely on vendor provided maintenance doctrine as they are developing historical context. Grounding for the Associate must include these documents which may be CUI or SECRET, performers must be able to operate at required classification levels. Reported technical evaluations, capability demonstrations, and success metrics will focus on the accuracy/interpretability of maintenance guidance and quality of the human-machine interaction as assessed by real-world end users and the generalizability of the technical approach across platforms and domains.

Offerors are reminded that SBIRs are expected to sufficiently develop one or more capabilities that will receive endorsement from an acquisition/development organization and who will provide matching funds for transition/acquisition during Phase II of the SBIR. Prospective agencies for potential matching funds should be identified in the Phase I proposal along with the description of the baseline capability to be delivered that the proposer believes that acquisition agency would be interested in funding during Phase II.

The proposer will need to:

1. Develop an SI-driven, maintenance task context-aware guidance prototype that functions as an on-demand technical expert and centralized intelligence hub for maintenance technicians, providing interactive support for complex diagnostic and repair tasks.
2. Incorporate a mechanism to ingest, process, and index a wide array of reference materials, including technical manuals, vendor publications, Maintenance Required Cards (MRCs), after-action reports, and historical service logs from various databases.
3. Demonstrate a workflow for capturing new experiential knowledge, observations, and "lessons learned" from maintainers post-task to ensure the system continuously learns and shares updated information across the fleet.
4. Be designed to operate effectively on simple hardware (e.g., tablets, laptops) in environments with limited or no connectivity by using a local knowledge store, with the capability to synchronize with a central cloud database when a connection is available.
5. Provide an adaptive human-machine interface that guides a user through troubleshooting and repair via natural language, tailors instructions to the technician’s skill level, and recognizes the specific system variant in use.

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 and/or subcontractor 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 ONR 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: Determine the technical feasibility of deploying a generative SI and LLM framework to support complex maintenance and diagnostic tasks in disconnected environments. Initial Phase I scoping should clearly define the domain, data sources, and commercial vendors that will inform a primary knowledge base for maintenance guidance and repair recommendations. (Note: Agent architecture and data ingest should be extensible to new domains and data types for the longer-term technical objective of applying Maintenance Associates to support both legacy platforms and novel technologies.) The system workflow will specify how newly submitted maintenance reports are ingested into the database to optimize future diagnostic guidance and dynamically tailor user assistance according to technician proficiency. Phase I success depends on selecting a use case to validate the Maintenance Associate's core methodology: generating initial repair guidance, iterating based on new inputs and evolving the knowledge base based on maintenance outcomes through an appropriate interface.

The Phase I proposal must address the following objectives:

• Identify and design a concept for the Maintenance Associate system architecture, processes through which the SI will securely ingest, process, index, and reason over heterogeneous maintenance data (e.g., technical manuals, structured databases, and unstructured historical logs).
• Analyze and classify open-source LLMs for their ability to perform consistent and accurate ingest and classification of new data sources and their capacity to generate reliable, accurate, and tailored maintenance guidance.
• Perform modeling and simulation to validate the local-to-cloud data synchronization process and the management of post-task "lessons learned" workflow, ensuring the system can continuously capture field knowledge and update the enterprise database with intermittent and/or low bandwidth connectivity.
• Define and develop a concept for operating the SI knowledge associate efficiently on tactical edge hardware (e.g., standard tablets or laptops) without relying on continuous cloud connectivity.
• Develop approaches for working prototypes for creating an adaptive human-machine interface that can dynamically tailor real-time troubleshooting guidance to the technician's specific information needs as well as address the exact equipment variant to be serviced.

Required Phase I deliverables will include:

1. A technical feasibility report describing the required SI model's performance and its adequacy for employment on edge hardware with limited cloud reach back.
2. A system architecture document outlining software requirements for data ingestion, local data caching, and synchronization protocols for cloud data storage and data management.
3. A preliminary human-machine interface mock-up or design concept for: a) data ingestion, b) user prompting of the system to obtain maintenance procedures, c) delivering prototype output from the recommender system, and d) ingestion of results from maintenance to update the knowledge base with lessons learned and details for repairs to specific equipment.
4. A detailed Phase II research and development plan that includes proposed performance metrics and a commercialization roadmap, and identifies a prospective transition target and describe customer expectations for providing matching funds as required during the Phase II development effort.

PHASE II: Develop, demonstrate, and validate a fully functional, edge-capable software prototype integrated onto representative ruggedized tactical hardware.

To the degree possible, describe the maturity of the capabilities and relevant performance metrics expected to be met in Phase II. Describe the proposed maintenance use-case(s) expected to be targeted for development and demonstration. Describe the process by which technical information will be ingested to be used by the Maintenance Associate system, and the requirements for scaling it to other application domains. Validate the system's ability to ingest a complex corpus of real-world technical manuals, proprietary vendor publications, and historical logs specific to that platform, its components, and its modular payloads. Demonstrate the bidirectional synchronization workflow, proving the prototype can capture user-generated "lessons learned" and post-task observations regarding unmanned platform anomalies at the edge, and successfully update the centralized enterprise database once connectivity is restored. Validate the human-machine interface and adaptive learning features with UxS maintenance personnel to ensure the system effectively tailors troubleshooting guidance to varying skill levels and accurately recognizes rapidly evolving unmanned equipment variants. Produce and validate a prototype of the Maintenance Associate application that successfully operates entirely disconnected from enterprise networks, simulating forward-deployed UxS maintenance hubs. Produce prototype hardware and software integrated systems (e.g., deploying the optimized LLM onto ruggedized shipboard tablets or maintenance laptops) ready for user-in-the-loop testing.

Deliver a functional, hardware-integrated prototype that demonstrates key functionality of a Maintenance Associate that can be scaled to multiple application domains. (Note: The preferred (but not required) application domain would be tailored for a maintainer of unmanned systems.); a comprehensive Test and Evaluation (T&E) report detailing the prototype's performance, utility, adequacy, and latency in delivering maintainer content using stand-alone (e.g., laptop) information technology with limited network connectivity; and a Maintenance Associate System software architecture documentation including document ingestion and end-user documentation that describes document ingestion (when required), user interaction to generate a maintenance procedure and get supporting documentation out of the system, and the mechanism by which the end user would describe the outcome of the maintenance procedure for updating the maintenance associate knowledge base.

Prepare a Phase III transition and commercialization plan detailing the path for transition to an acquisition entity or integration into a Naval Program of Record.

Work in Phase II may become classified. Please see note in the Description.

PHASE III DUAL USE APPLICATIONS: This topic was conceived with a primary Naval transition target of Unmanned Surface Vessel Squadrons (USVRONs) and their associated maintenance hubs for UxVs. The desired system should be appropriate for use by USVRON maintenance personnel on ruggedized tactical hardware (e.g., standard issue tablets or laptops) to diagnose and repair the complex, modular systems of Unmanned Surface Vessels (USVs) and other unmanned platforms. There is a wide range of application domains, both in the commercial and military sectors that would benefit from the maintenance associate. The general purpose of this technology is intended to be a secure, deployable and scalable generative SI enabled system capable of ingesting disparate technical data, operating entirely disconnected from enterprise networks, and providing interactive maintenance and troubleshooting guidance. The desired system would integrate experiential knowledge from users to iteratively append the knowledge base with lessons learned, best practices, tips and tricks as appropriate for use by future maintainers working on the same or similar system.

Phase III work may also orient towards commercializing the core SI maintenance technology for industries that manage complex, distributed assets in commercial domains that require disconnected or remote environments (e.g., commercial maritime, aviation, or energy/infrastructure operations).

REFERENCES:

1. "CNO Fighting Instructions, 2026." https://media.defense.gov/2026/Feb/06/2003871752/-1/-1/1/CNO%20FIGHTING%20INSTRUCTIONS.PDF/CNO%20FIGHTING%20INSTRUCTIONS.PDF
2. "Department of the Navy Unmanned Campaign Framework, 2021." https://www.navy.mil/Portals/1/Strategic/20210315%20Unmanned%20Campaign_Final_LowRes.pdf
3. Dimidov, V., Hawlader, F., Jafarnejad S. and Frank, R. "Cleaning maintenance logs with LLM agents for improved predictive maintenance." arXiv 2025. https://doi.org/10.48550/arXiv.2511.05311
4. Harbola, C. and Purwar, A. "Prescriptive agents based on RAG for automated maintenance (PARAM)." Proceedings of the International Conference on AI-ML-Systems 2025. arXiv. https://doi.org/10.48550/arXiv.2508.04714
5. Kirtania, S. et al. "STACKFEED: Structured textual actor-critic knowledge base editing with feedback." Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track. https://arxiv.org/abs/2410.10584
6. Koornneef, H., Verhagen, W. and Curran, R. "A web-based decision support system for aircraft dispatch and maintenance." Aerospace, 8(6), 164, 2021. https://doi.org/10.3390/aerospace8060164
7. Malyi, M., Shek, J., McDonald, A. and Biscaya, A. "A comparative benchmark of large language models for labelling wind turbine maintenance logs." arXiv 2025. https://doi.org/10.48550/arXiv.2509.06813
8. 8. "OPNAVINST 4700.7N Maintenance Policy for Navy Ships 2024. https://www.secnav.navy.mil/doni/Directives/04000%20Logistical%20Support%20and%20Services/04-700%20General%20Maintenance%20and%20Construction%20Support/4700.7N.pdf
9. 9. Wulf, J., Meierhofer, J. and Hannich, F. "Architecting human-AI cocreation for technical services: Interaction modes and contingency factors." arXiv 2025. https://doi.org/10.48550/arXiv.2503.00356
10. 10. Zhang, R. et al. "Toward edge general intelligence with agentic AI and agentification: Concepts, technologies, and future directions." IEEE Communications Surveys and Tutorials, 2025. https://arvix.org/abs/25084.18725
11. 11. "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: Agentic; maintenance; edge; associate; stepwise; adaptive; guidance; troubleshooting; repair

TPOC 1: Thomas McKenna
thomas.m.mckenna4.civ@us.navy.mil

TPOC 2: Dina Acklin
dina.m.acklin.civ@us.navy.mil