Company
Portfolio Data
Back to Company SearchOZNI AI LLC
UEI: UQZKQX7L6MQ4
Number of Employees: 1
HUBZone Owned: No
Woman Owned: No
Socially and Economically Disadvantaged: No
SBIR/STTR Involvement
Year of first award: 2024
1
Phase I Awards
2
Phase II Awards
200%
Conversion Rate
$179,550
Phase I Dollars
$3,796,305
Phase II Dollars
$3,975,855
Total Awarded
Awards
REGAL
Amount: $1,799,940 Topic: AF241-0004
Rapid Emitter Geolocation with Adaptive Learning (REGAL) introduces a transformative approach to radio frequency (RF) signal identification and emitter geolocation in urban settings, utilizing local 3D models of buildings and terrain to train context-specific neural networks that calculate emitter position based on multi-path effects of the received signal. These neural networks are designed for low-latency and rapid deployment on Group 1 and Group 2 unmanned aircraft system (UAS), and are trained through extensive RF simulations that leverage NVIDIA ray-tracing techniques for highly detailed signal trajectories and multi-bounce effects within the physical environment. As the cornerstone of a comprehensive Electronic Surveillance Monitoring (ESM) suite, REGAL's capabilities extend to searching, intercepting, collecting, classifying, monitoring, copying, and exploiting RF signals. Optimized for dense urban landscapes, REGAL stands to significantly enhance operations in surveillance, emergency response, law enforcement, and urban infrastructure management. During this Phase II activity we will: (1) develop a containerized software application for gathering offline 3D models, performing RF simulation, and training the geolocation neural network, (2) develop a run-time optimized RF processor for use on low size, weight, and power (SWaP) platforms, and (3) physically construct a REGAL payload and evaluate it via flight testing on a Group II UAS platform.
Tagged as:
SBIR
Phase II
2025
DOD
USAF
NEMESIS
Amount: $1,996,365 Topic: A244-P037
The Army’s strategic environment demands persistent deep sensing in contested and dynamic settings. While the military Internet-of-Things (MIoT) offers a framework for intelligence gathering, its reliance on centralized processing and high-bandwidth communication poses significant challenges in austere environments where connectivity may be limited or denied. Ozni AI proposes NEMESIS (Networked Edge-based Multi-INT Exploitation for Situational Intelligence and Security), a novel AI system that addresses these challenges by federating sense-making capabilities directly onto sensor platforms. NEMESIS leverages new AI techniques, including foundational Large Language Models (LLMs) and multi-INT embeddings (EO/IR, RF, audio), to enable sensors to interpret and understand the context of their local environment in order to estimate the pattern of life and detect anomalies. This processes enables the generation of trusted, traceable intelligence in real-time at the tactical edge, and provides actionable insights to warfighters and commanders.
Tagged as:
SBIR
Phase II
2025
DOD
ARMY
Rapid Emitter Geolocation with Adaptive Learning
Amount: $179,550 Topic: AF241-0004
Wide-band RF spectrum monitoring and geolocation is a challenging task that is exacerbated by complex collection geometry and the intricate interplay of signals in complex 3D urban environments. This interaction often leads to complex signal behaviors like multipath propagation, reflection, and absorption, significantly reducing the efficacy of traditional geolocation methods. Geolocation, typically treated as a distinct step in signal processing chains, has not yet fully benefited from the AI advancements that have revolutionized other areas like signal detection/identification, as it relies heavily on physical models for signal propagation that are grounded by well-established equations describing physical phenomena. In urban environments, where multi-path and co-channel interference effects are prevalent, these traditional methods falter.Ā Rapid Emitter Geolocation with Adaptive Learning (REGAL)Āpresents the opportunity to revolutionize RF signal processing in urban areas by developing a system that exploits local 3D models of an area to train a SWaP-efficient neural network that is specialized to the local context of the deployment area of interest. The ability to precompute and train a neural network, such as a Convolutional Neural Network (CNN), for rapid edge computation not only aligns with the demands for speed and efficiency in real-world applications, but it also creates numerous opportunities for advanced RF processing at the edge across the DoD, IC, and commercial domain. REGAL is structured to deliver its innovative solutions within a strategically planned timeline and budget. In Phase I, we focus on feasibility studies, system design, and software prototyping for $180,000 over a period of six months. This phase is crucial for establishing the foundation of a novel AI-based geolocation system. Subsequent phases build upon these initial developments, scaling up the technology with payload development and integration into operational scenarios.
Tagged as:
SBIR
Phase I
2024
DOD
USAF