Part of the DoW SBIR/STTR FY27 Release 2 topic list. Browse all 83 topics by industry or service.
Topic DON27BZ02-DV026 from the DoW SBIR 2027 BAA, Release 2. Pre-release now; proposals due January 6, 2027, 12:00 PM ET.
Quick answer
DON27BZ02-DV026 is a Department of the Navy Direct-to-Phase II SBIR topic seeking an AI-driven signal processing framework that detects, classifies, and characterizes covert, agile LPI/LPD waveforms, including emissions below the thermal noise floor. Applicants must submit feasibility documentation instead of receiving a Phase I award. Proposals are due January 6, 2027, 12:00 PM ET.
Solicitation at a glance
- Topic number: DON27BZ02-DV026
- Official title: DIRECT TO PHASE II: Frequency-Based Persistent Super Intelligence Tracking and Surveillance Capability
- Agency: Department of the Navy
- Program: SBIR (DoW SBIR 2027 BAA, Release 2)
- Award type: Direct to Phase II (no Phase I awards)
- Award amount: Base up to $750,000 (18 months) plus an option up to $1,000,000 (24 months); the option requires 1:1 matching non-SBIR funds. Source: Navy Release 2 instructions in DSIP.
- CMMC level: Level 2 (Self)
- ITAR: No
- Technology areas: None
- Pre-release (direct TPOC contact allowed): November 4 to December 2, 2026, 8:00 AM ET
- Opens in DSIP: December 2, 2026, 8:00 AM ET
- Proposals due: January 6, 2027, 12:00 PM ET
- Official source: DSIP Topics app (search DON27BZ02-DV026)
BW&CO's take
What the Department of the Navy wants
Adversary radars and datalinks increasingly use LPI/LPD techniques such as DSSS, ultra-fast frequency hopping, wideband LFM, Costas coding, and polyphase codes to push emissions below the noise floor, and conventional ESM and energy-detection receivers miss them. The Navy wants a working prototype that uses AI-driven processing for blind detection, characterization, parameter estimation, de-interleaving, and classification of these waveforms in contested and congested spectrum. Candidate techniques include cyclostationary analysis, time-frequency deep learning, adaptive de-interleaving, calibrated uncertainty for operators, and edge optimization for SWaP-constrained hardware. Phase II validates performance in a representative lab or simulated environment and delivers a final report with Pd, false alarm, accuracy, and latency data.
Who is a good fit
- Existing blind detection or classification results on LPI/LPD waveforms in sub-noise-floor conditions, simulated or captured
- Cyclostationary, time-frequency deep learning, or RL-guided de-interleaving methods with measured Pd/Pfa and latency
- Experience deploying quantized or pruned neural networks on SWaP-constrained edge hardware or SDR front-ends
- Access to EW/ES testbeds, SDR hardware, or open-architecture signal processing frameworks for prototype demonstration
Watch-outs
- This is Direct-to-Phase II: feasibility documentation must show Phase I-type work not solely based on prior or ongoing federally funded SBIR work, with stated minimum values for SNR, Pd/Pfa, accuracy, bandwidth, latency, and other metrics tied to defined test conditions.
- Phase II work may become classified. The prospective contractor(s) must be U.S. owned and operated with no foreign influence (unless DCSA-approved mitigation is in place) and the selected contractor and/or subcontractor must be able to acquire and maintain a secret level facility and personnel security clearances.
- The topic is not marked ITAR-restricted in the metadata, but the classification and foreign-influence requirements above still apply.
- The topic metadata lists CMMC Level 2 (Self).
Think your company fits DON27BZ02-DV026? Talk with BW&CO before the January 6 deadline.
Plan Your DON27BZ02-DV026 Submission
Official topic text (verbatim from DSIP)
The text in this section is copied word for word from the official DSIP topic as published on November 4, 2026. DSIP is the official source and topics can be amended. Always confirm the current version at dodsbirsttr.mil before you submit. Our commentary above is BW&CO's interpretation, not Government guidance.
Title
DIRECT TO PHASE II: Frequency-Based Persistent Super Intelligence Tracking and Surveillance Capability
Objective
Develop and demonstrate an super intelligence (SI)-driven signal processing framework that leverages high-dimensional spectral feature extraction, adaptive neural control loops, and secure human-machine teaming to detect, classify, and characterize covert and agile waveforms in complex electromagnetic environment.
Description
The Navy faces acute operational challenges in intercepting and characterizing covert, highly agile adversarial emissions across dense electromagnetic operational environments. Modern threat systems increasingly utilize Low Probability of Intercept and Low Probability of Detection (LPI/LPD) techniques—such as Direct-Sequence Spread Spectrum (DSSS), ultra-fast frequency hopping (UFLH), wideband Linear Frequency Modulation (LFM), Costas frequency coding, and polyphase pulse compression (e.g., Frank, P1–P4 codes)—deliberately depressing emission power densities below the thermal noise floor [Refs 1, 2]. Consequently, conventional Electronic Support Measures (ESM) and wideband radiometer/energy-detection receivers exhibit severe performance degradation, failing to detect stealth radar transmissions, covert datalinks, and distributed sensor relays. This visibility shortfall undermines the tactical sensor-to-shooter timelines foundational to Combined Joint All-Domain Command and Control (CJADC2) and Distributed Maritime Operations (DMO).
To counter advanced stealth emitters, an AI-driven signal processing framework can draw upon several modular algorithmic pathways and candidate techniques, such as:
Sub-Noise-Floor Cyclostationary Analysis: For instance, computing the spectral correlation density (SCD) or cyclic autocorrelation can expose covert signal periodicities (e.g., symbol rates, chipping sequences, and carrier modulation artifacts), isolating structured LPI/LPD waveforms from stationary thermal background noise and Gaussian interference [Refs 3, 4].
Time-Frequency Deep Learning Architectures: As an example for intra-pulse modulation recognition, raw wideband In-phase/Quadrature (I/Q) samples can be transformed into high-resolution time-frequency representations—such as Wigner-Ville Distributions (WVD) or Continuous Wavelet Transforms (CWT)—and processed by deep convolutional or recurrent neural networks (CNN/RNN) to classify polyphase or frequency-coded pulses without requiring prior waveform templates [Refs 5, 6].
Adaptive Multi-Channel De-interleaving: For high-density pulse environments, candidate approaches include reinforcement-learning-guided spectral search or adaptive filter banks to isolate agile hopping channels and separate co-channel, overlapping LPI signals across wide instantaneous bandwidths [Ref 7].
Calibrated Operator Decision Metrics: To support tactical watchstanders, Bayesian neural networks or conformal prediction methods can be applied to generate uncertainty bounds alongside extracted parameters (e.g., pulse repetition intervals, modulation bandwidths, chirp rates), providing validated, interpretable indicators of stealth emitter activity.
SWaP-Constrained Edge Optimization: Potential implementation paths for tactical platforms include neural network quantization, weight pruning, and tensor acceleration to facilitate low-latency inference on Size, Weight, and Power (SWaP)-constrained naval edge computing hardware.
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 NAVWAR 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
For a Direct to Phase II topic, the Government expects that the small business will have accomplished the following in a Phase I-type effort and developed a concept for a workable prototype or design to address, at a minimum, the basic requirements of the stated objective above. The following actions would be required to satisfy the requirements of Phase I:
DIRECT TO PHASE II: Demonstrated the feasibility and foundational algorithm performance of an AI-driven signal processing approach for the blind detection, classification, or characterization of Low Probability of Intercept/Low Probability of Detection (LPI/LPD) waveforms in simulated or captured sub-noise-floor electromagnetic spectrum environments, establishing clear metrics for signal-to-noise ratio (SNR) thresholds, probability of detection and probability of false alarm (Pd/Pfa), classification/characterization accuracy, signal density and agility, instantaneous bandwidth, processing latency, and computational viability for tactical hardware deployment. It is advantageous—and expected in the feasibility documentation and prototype concept—to state the minimum values of these metrics that apply to the prototype demonstration. These parameters are coupled: instantaneous bandwidth, signal density/agility, and processing latency determine compute and data-rate load; SNR and Pd/Pfa determine integration time and detector thresholds; and classification/characterization accuracy depends on the detections and features obtained under that load. A single, internally consistent demonstration envelope, tied to defined test conditions (waveform family, observation interval, simulated versus captured data, and platform), provides an objective success criterion for the prototype without treating the demonstration minima as full operational requirements. Values should be supported by Phase I-type results and set at or modestly beyond what that work already achieved.
FEASIBILITY DOCUMENTATION: Offerors interested in participating in Direct to Phase II must include in their response to this topic Phase I feasibility documentation that substantiates the scientific and technical merit and Phase I feasibility described in Phase I above has been met (i.e., the small business must have performed Phase I-type research and development related to the topic NOT solely based on work performed under prior or ongoing federally funded SBIR work) and describe the potential commercialization applications. The documentation provided must validate that the proposer has completed development of technology as stated in Phase I above.
Phase II
Develop, mature, integrate, and demonstrate a working prototype that utilizes AI-driven signal processing algorithms to provide measurable improvements in the blind detection, characterization, parameter estimation, de-interleaving, and classification of adversarial LPI/LPD waveforms under contested and congested electromagnetic spectrum conditions. Validate the proposed capability within a representative laboratory or simulated operational environment, demonstrating performance against sub-noise-floor and highly agile emitters.
(Note: Prototype demonstrations may include integration with representative software-defined radio (SDR) front-ends, open architecture signal processing frameworks, electronic warfare/electronic support (EW/ES) testbeds, or relevant tactical edge computing hardware.)
Prepare a final report that includes comprehensive performance characterization data (e.g., probability of detection, false alarm rates, parameter estimation accuracy, and latency), a platform transition strategy, deployment and SWaP-C considerations, a sustainment approach, and a commercialization plan.
Work in Phase II may become classified. Please see note in the Description.
Phase III Dual Use Applications
Support transition of the developed AI-driven LPI/LPD signal detection and characterization capability to Fleet operators and associated Electronic Warfare (EW), Information Warfare (IW), and maritime surveillance Programs of Record.
Commercial organizations increasingly require the ability to detect, de-interleave, identify, and monitor low-power, transient, and covert signals across congested and noisy radio frequency (RF) environments. Technologies developed under this topic may have broad applicability in 5G/6G dynamic spectrum sharing and network optimization, commercial satellite communications interference mitigation, autonomous transportation and maritime shipping collision avoidance, commercial aviation RF monitoring, passive counter-unmanned aerial system (C-UAS) sensing, critical infrastructure perimeter surveillance, and federal/industrial spectrum management.
References
Pace, P. E. “Detecting and Classifying Low Probability of Intercept Radar (2nd ed.).” Artech House Radar Library, 2009. https://www.amazon.com/dp/1580533221?lv=shuf&channelId=500&plpRedirect=mhFallback
Adamy, D. L. “EW 104: Electronic Warfare Against a New Generation of Threats.” Artech House, 2015. https://us.artechhouse.com/EW-104-Electronic-Warfare-Against-a-New-Generation-of-Threats-P1707.aspx
Gardner, W. A., Napolitano, A. and Spooner, L. “Cyclostationarity: Half a century of research.” Signal Processing, 86(4), 2006, pp. 639-697. https://www.sciencedirect.com/science/article/abs/pii/S0165168405002409
K. Kim, I. A. Akbar, K. K. Bae, J. Um, C. M. Spooner, and J. H. Reed, “Cyclostationary Approaches to Signal Detection and Classification in Cognitive Radio,” in Proc. 2nd IEEE Int. Symp. New Frontiers in Dynamic Spectrum Access Networks (DySPAN), 2007, pp. 212–215. https://ieeexplore.ieee.org/document/4221497
O’Shea, T. J., Roy, T. and Clancy, T. C. “Over-the-air deep learning based radio signal classification.” IEEE Journal of Selected Topics in Signal Processing, 12(1), 2018, pp. 168-179. https://arxiv.org/pdf/1712.04578
T. An and B. M. Lee, “Robust Automatic Modulation Classification in Low Signal to Noise Ratio,” IEEE Access, vol. 11, pp. 7860–7872, 2023. https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10024264.
Haykin, S. “Cognitive radio: Brain-empowered wireless communications.” IEEE Journal on Selected Areas in Communications, 23(2), 2005, pp. 201-220. https://ieeexplore.ieee.org/document/1391031
“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
AI: Quantum-Resiliency: Frequency-Based Cryptography: Adaptive-Security: Reliability: Human-Machine Teaming
Frequently asked questions
What is DON27BZ02-DV026?
It is a Department of the Navy SBIR topic to develop and demonstrate an AI-driven signal processing framework that detects, classifies, and characterizes covert and agile LPI/LPD waveforms in complex electromagnetic environments.
When is DON27BZ02-DV026 due?
Proposals are due January 6, 2027, 12:00 PM ET. DSIP pre-release began November 4, 2026, and direct contact with the topic authors is allowed only until the topic opens on December 2, 2026, 8:00 AM ET.
Is this a Phase I or Direct-to-Phase II topic?
It is Direct-to-Phase II. Offerors must include feasibility documentation proving Phase I-type research and development was already completed, not solely based on prior or ongoing federally funded SBIR work.
What metrics should the feasibility documentation state?
The topic asks for minimum values for SNR thresholds, Pd/Pfa, classification or characterization accuracy, signal density and agility, instantaneous bandwidth, processing latency, and computational viability. These should form one internally consistent demonstration envelope tied to defined test conditions and set at or modestly beyond what prior work achieved.