CRANFOA-22-0001 | N00164 22 1 1001

Opportunity Information: Apply for N00164 22 1 1001

CRANFOA-22-0001 (Funding Opportunity Number N00164 22 1 1001) is a Department of Defense basic research grant opportunity issued by the Naval Surface Warfare Center (NSWC), Crane Division, under CFDA 12.300. It is categorized as discretionary funding and uses a grant as the primary award instrument. The opportunity was created on February 24, 2022, with an original closing date of March 24, 2022. The stated maximum award size (award ceiling) is $400,000, and NSWC Crane anticipated making about two awards. Eligibility is listed as unrestricted, meaning proposals could come from essentially any type of qualified organization, subject to any additional eligibility notes in the full announcement.

The solicitation focuses on two basic research areas and looks for proposals that clearly advance the state of the art. The common thread across both areas is improving the realism, trustworthiness, and operational relevance of test and evaluation environments, especially where real-time constraints and hardware-in-the-loop (HWIL) testing matter. NSWC Crane is specifically interested in novel methods that can be used in practical evaluation pipelines, not just theoretical concepts, and that can demonstrate measurable improvement over existing approaches.

The first research area is High Fidelity Radio Frequency Scene Generation for Real-Time Processing. NSWC Crane is seeking new ways to generate complex synthetic radio frequency (RF) scenes that can be used in real-time HWIL simulations. The emphasis is on scenes that support navigation and identification functions, including terrain feature mapping radars, Doppler mapping radars, pulse-Doppler radar object identification within radar scenes, and synthetic aperture radar (SAR) scene generation. The topic also explicitly includes interest in related sensing modalities such as LIDAR-generated scenes. In this context, an RF scene is described as a digital, synthetic representation of the environment built from terrain databases (for example, Digital Terrain Elevation Data or DTED), enhanced with three-dimensional objects or scatterers, and tied to an aerospace vehicle state description that includes 3D position, orientation, and 3D velocity. That scene is then intended to be converted into RF signals that the system under test can process in real time, which places strict limits on latency and computational load.

A key technical challenge highlighted in the announcement is the trade space between scene resolution and fidelity versus computation time and effort given finite computing capability. NSWC Crane is open to approaches that manage this trade deliberately, including methods that reduce runtime computation without sacrificing the ability to present realistic scenes to the hardware. One specific direction encouraged is precomputation: if an aerospace vehicle trajectory or state evolution is known ahead of time over a window, parts of the RF scene could be precomputed to reduce real-time workload. However, the announcement is clear that precomputation must be practical: the approach should minimize both computation and storage requirements while still allowing those scenes to be delivered in real time during HWIL tests. The expected operating envelope includes aerospace vehicle speeds from subsonic up to hypersonic, which implies that scene update rates, Doppler effects, and time-varying geometry could be especially demanding. Proposals in this area are expected to target at least one of these problems and show a credible path to better-than-current capability in real-time, high-fidelity RF scene synthesis for HWIL.

The second research area is Validation and Verification for Trusted Autonomous Vehicles. Here, NSWC Crane is looking for research into validation and verification (V&V) methods for autonomous vehicles that use artificial intelligence algorithms. The central theme is how to evaluate and build operational "trust" in AI-driven autonomy, especially when the AI may learn, adapt, or behave differently across scenarios. The solicitation emphasizes V&V approaches that support pre-mission evaluation of learning integrity, meaning methods that help determine whether the system has learned the right things, will generalize safely, and will behave reliably when deployed. Live-Virtual-Constructive (LVC) methods and HWIL testing are called out as particularly relevant, suggesting NSWC Crane wants approaches that blend real assets, simulated environments, and constructive (computer-generated) entities into rigorous test campaigns that can scale while remaining operationally meaningful.

Within this autonomy V&V topic, NSWC Crane expresses special interest in approaches that use Unmanned Surface Vessel (USV) platforms as a focus area for implementing and assessing AI capabilities. That implies a maritime autonomy angle where sensing, navigation, perception, and decision-making may be tested against real-world constraints. Another highlighted interest is federated learning across multiple laboratory facilities, which points to distributed development and evaluation setups where data, models, or learning processes are shared across sites. Research in this sub-area would likely need to address how to validate systems trained or updated in a federated manner, how to ensure consistent performance and safety across distributed training and test pipelines, and how to establish evidence that supports trustworthy fielding decisions.

Overall, CRANFOA-22-0001 aims to fund early-stage, basic research that strengthens two critical DoD capability areas: (1) producing realistic, computationally feasible RF and related sensor scenes for real-time HWIL testing of radar and navigation/identification systems, and (2) developing credible V&V methods that help establish justified trust in AI-enabled autonomous vehicles, with an emphasis on LVC/HWIL evaluation, USV-relevant implementations, and federated learning considerations.

• The Department of Defense, NSWC - CRANE in the science and technology and other research and development sector is offering a public funding opportunity titled "CRANFOA-22-0001" and is now available to receive applicants.
• Interested and eligible applicants and submit their applications by referencing the CFDA number(s): 12.300.
• This funding opportunity was created on Feb 24, 2022.
• Applicants must submit their applications by Mar 24, 2022. (Agency may still review applications by suitable applicants for the remaining/unused allocated funding in 2026.)
• Each selected applicant is eligible to receive up to $400,000.00 in funding.
• The number of recipients for this funding is limited to 2 candidate(s).
• Eligible applicants include: Unrestricted (i.e., open to any type of entity above), subject to any clarification in text field entitled Additional Information on Eligibility.

Apply for N00164 22 1 1001

[Watch] Creating a grant proposal using the step-by-step wizard inside the applicant portal: