TECHNICAL POINT OF CONTACT (TPOC)
SCO SBIR
PROJECTED CMMC LEVEL REQUIREMENT
Level 2 (Self)
TECHNOLOGY AREAS
Information Systems
MODERNIZATION PRIORITIES
Advanced Computing and Software
|
Integrated Sensing and Cyber
KEYWORDS
Machine Learning; SIGINT; Autonomous Systems; Intelligence, Surveillance, and Reconnaissance (ISR); Threat Detection; predictive analytics
OBJECTIVE
To develop and demonstrate a flexible, scalable, and robust Machine Learning (ML)-based software processers capable of running on COTS platforms to identify and classify known and unknown Radio Frequency (RF) signals in complex, contested spectral environments. The objective is to develop the capability that consistently outperforms expert Signals Intelligence (SIGINT) Analysts, provide decision-makers with a significant strategic advantage in spectrum analysis, and integrate with multi-function C5ISR systems.
DESCRIPTION
Modern military operations are conducted in contested RF spectrum environments, where adversaries' actions produce a growing number of complex spectral signatures. The operational need for automation of RF signal classification and anomaly detection using ML techniques addresses threat detection, pattern recognition, and predictive analysis within C5ISR systems which currently require a manual, human-in-the-loop process. With an exponential increased demand for automated signal processing and the limited manpower available with this expertise, this capability will dramatically increase the capacity of SIGINT analysis and processing functions which are critical features for C5ISR systems. Standard machine learning approaches are often insufficient as they require massive, labeled datasets that do not exist for future conflicts and frequently produce "black box" solutions that are difficult for commanders to trust, interpret, or certify.
This topic seeks an alternative approach for an ML-based solution that can classify RF signals based on similar patterns of emission and provide the flexibility of integration on COTS platforms to facilitate integration with existing C5ISR systems. The desired ML capability will be modular and scalable to fine-tune classification inference results for varying base modulations and frequency ranges.
The proposed solution and approach must demonstrate the following critical attributes:
Dominant Performance: The system must generate run-time identification and classification inferences that are demonstrably faster as compared to expert SIGINT analysts in complex RF environments scenarios.
Human-Interoperable: Generated results must be transparent and understandable, composed of modular components (i.e., not a monolithic neural network). Commanders must be able to understand the "why" behind the recommendations.
Scalable: The approach must be capable of scaling from tactical engagements (e.g., individual flight combat) to operational-level scenarios involving thousands of assets across multiple domains (air, sea, land) and extended time horizons.
Computational Efficiency: The solution must operate effectively on modest computational footprints (e.g., single or small-cluster CPU-based workstations), avoiding reliance on cost-prohibitive, large-scale GPU clusters for its core training and inference loops.
Improved Accuracy: The approach must describe the methodology and metrics for improved accuracy over time as additional data sets, results, and resources are employed.
Delivery & Integration: The approach must describe the Continuous Integration / Continuous Deployment methodology to include automation for rapid development changes, testing, and containerized deployment.
This solicitation is for a Direct to Phase II (D2P2) award. Offerors are expected to have already achieved significant technical maturity and be prepared to demonstrate existing capabilities upon request.
PHASE I
Offerors must provide comprehensive documentation as part of their D2P2 application that proves the technical merit and feasibility of their approach. This documentation must include, at a minimum:
A detailed white paper describing the underlying architecture, ML model definitions, system components, services, data flow, training, and inference approach. Technical specifications detailing the computational resources required for both training and inference.
Demonstrated results (e.g., data, reports, or videos) of the current model performance using open source and synthetic data sets against state-of-the-art ML benchmarks. Performance must be quantified using clear metrics or scoring function.
Evidence of the model's capability to generate novel, effective, and human-interpretable results relevant for integration with a C5ISR system of record.
Identify candidate integration pathways, potential end-user systems, risks and security considerations for deployment in classified or tactical environments.
Proposals lacking sufficient evidence of an existing prototype and demonstrated performance will be deemed non-responsive.
PHASE II:
Building on the proven feasibility from Phase I, the offeror will mature, harden, and scale their prototype ML engine for defense-specific applications. The scope of work will include:
Conduct additional model training and fine-tuning using government-designated RF signal datasets.
Improve model performance through time-boxed training cycles, incorporating refinements to model architecture, feature extraction, and dataset diversity. Each iteration supports increasingly accurate signal classification and aggregation under realistic RF conditions.
Prepare the ML processor for integration with a government-designated C5ISR system of record. Conducting a series of validation and verification (V&V) events in government-provided scenarios of increasing complexity, including multi-domain data sets and joint all-domain operations.
Demonstrate the robustness of the ML system by assessing its performance to detect known and unknown signals under conditions of degraded communications, sensor uncertainty, incomplete information, and novel adversary tactics not present in the training set.
Deliver a robust, containerized software prototype of the ML processor and a technical data package (TDP) sufficient for government use in a pre-production environment.
PHASE III - DUAL-USE APPLICATIONS:
Government/Military: The primary application is to integrate with a C5ISR system of record to enhance threat detection, pattern recognition, and predictive analysis. Other Government and Military applications of this technology include integration with smaller [tactical] remote C2 systems, integration with DoW-approved Software Defined Radios (SDRs), and GPS/PNT applications to detect jamming and spoofing.
Commercial: The underlying system can be adapted for a wide range of commercial markets including licensing to COTS SDR manufacturers, urban and civilian RF spectrum monitoring, adaptation to acoustic signal classification with applications such as ultrasonic and vibration analysis. The offeror is expected to pursue these commercial applications to ensure long-term viability and innovation.
PHASE II
Offerors must provide comprehensive documentation as part of their D2P2 application that proves the technical merit and feasibility of their approach. This documentation must include, at a minimum:
A detailed white paper describing the underlying architecture, ML model definitions, system components, services, data flow, training, and inference approach. Technical specifications detailing the computational resources required for both training and inference.
Demonstrated results (e.g., data, reports, or videos) of the current model performance using open source and synthetic data sets against state-of-the-art ML benchmarks. Performance must be quantified using clear metrics or scoring function.
Evidence of the model's capability to generate novel, effective, and human-interpretable results relevant for integration with a C5ISR system of record.
Identify candidate integration pathways, potential end-user systems, risks and security considerations for deployment in classified or tactical environments.
Proposals lacking sufficient evidence of an existing prototype and demonstrated performance will be deemed non-responsive.
PHASE II:
Building on the proven feasibility from Phase I, the offeror will mature, harden, and scale their prototype ML engine for defense-specific applications. The scope of work will include:
Conduct additional model training and fine-tuning using government-designated RF signal datasets.
Improve model performance through time-boxed training cycles, incorporating refinements to model architecture, feature extraction, and dataset diversity. Each iteration supports increasingly accurate signal classification and aggregation under realistic RF conditions.
Prepare the ML processor for integration with a government-designated C5ISR system of record. Conducting a series of validation and verification (V&V) events in government-provided scenarios of increasing complexity, including multi-domain data sets and joint all-domain operations.
Demonstrate the robustness of the ML system by assessing its performance to detect known and unknown signals under conditions of degraded communications, sensor uncertainty, incomplete information, and novel adversary tactics not present in the training set.
Deliver a robust, containerized software prototype of the ML processor and a technical data package (TDP) sufficient for government use in a pre-production environment.
PHASE III DUAL USE APPLICATIONS
Government/Military: The primary application is to integrate with a C5ISR system of record to enhance threat detection, pattern recognition, and predictive analysis. Other Government and Military applications of this technology include integration with smaller [tactical] remote C2 systems, integration with DoW-approved Software Defined Radios (SDRs), and GPS/PNT applications to detect jamming and spoofing.
Commercial: The underlying system can be adapted for a wide range of commercial markets including licensing to COTS SDR manufacturers, urban and civilian RF spectrum monitoring, adaptation to acoustic signal classification with applications such as ultrasonic and vibration analysis. The offeror is expected to pursue these commercial applications to ensure long-term viability and innovation.
REFERENCES
"National Security Strategy of the United States of America." The White House, November 2025.
"2026 National Defense Strategy." Department of War, January 2026.
"Artificial Intelligence Strategy for the Department of War." Secretary of War, January 2026.
Boegner, L., Vanhoy, G., Vallance, P., Gulati, M., Feitzinger, D., Comar, B., Miller, R. D. (2022). Large Scale Radio Frequency Wideband Signal Detection & Recognition. Peraton Labs Laboratory for Telecommunication Science Applied Insight. https://arxiv.org/pdf/2211.10335
QUESTIONS & ANSWERS
NOTE:
To ask a question, you must
log in or create an account
for the DSIP.
