Award Data

Current artificial intelligence (AI) algorithms are built to align with ground truth or consensus of trusted human decision-makers. This is not effective for difficult decision domains, such as patient triage, where even experts disagree on the best course of action. A key reason human experts disagree is that their individual attributes influence their decision-making. To develop human-off-the-lo ...

Extending research on scalable Transformer models performed on previous SBIR-funded work for DARPA, Soar-Tech proposes an investigation into Scalable Language Association Models for Domain-specific Utterances in Novel Contexts (SLAMDUNK), a Phase II SBIR research effort focused on developing novel synthetic data generating pipelines and extending these pipelines with novel index-learning, token gr ...

This proposal responds to the direct to the Snap-On Phase 2 SBIR by extending our novel non-parametric Bayesian framework---OTACON: (O)pen world intelligence (T)hrough (A)ugmentation and (Co)mposition of (N)on-parametrics---for novelty detection in open worlds.  We build on our advances in composition and inference of non-parametric Bayesian models, and insights from the mathematics of Optimal Tr ...

If civilian and military equipment and personnel are to be effectively shielded in a high radiation environment- such as that found in space, or in a nuclear-powered naval vehicle, or in a nuclear-active battlefield environment- then protection against high-energy photons must be enhanced well beyond that currently delivered by existing materials. Materials that are highly effective in stopping th ...

This SBIR project will exploit the nanoscale physics delivered by percolating networks of PbTe nanoparticles to develop an efficient, low-cost imager of hard x-rays (5 – 300 keV) that has high spatial (< 55 mm) and energy resolutions (< 2 %). We developed methods to assemble PbTe into scalable solids using either templated growth or self-assembly. PbTe gels self-assembled from colloidal nanopart ...

In recent years, the nuclear power industry has been exploring the use of conventional powder metallurgy and hot-isostatic press technologies to fabricate large, near net shape components for high pressure components and other applications pertaining to the generation of electric power. Powder metallurgy has many manufacturing consistency and reliability advantages over other large-scale manufactu ...

This SBIR Phase I project will demonstrate that high sensitivity, radiation-resistance, and resolution can be elicited from nanostructured media composed of semiconducting nanoparticles derived from size-governed PbTe. In order to transform x-ray imaging instruments, nanocrystalline semiconductors provide an attractive material basis because they present a means of: 1) decreasing the underlying ma ...

The fifth generation (5G) of mobile technologies will provide unprecedented improvements in connectivity, data speeds, latency, and bandwidth compared to existing 4G networks, enabling new military and commercial applications. In the military space, 5G will augment capabilities in intelligence, surveillance, and reconnaissance systems by addressing their growing demand for increased bandwidth and ...

Natural rubber is an essential manufacturing material that possesses performance properties that are superior to synthetic rubber for many product applications, including increased tear and tensile strength, as well as superior mechanical performance properties. Aircraft tires, for example, are made of natural rubber; whereas, synthetic rubber (which is less expensive to procure) is used for less ...

Methods for interconversion between cell types (cellular reprogramming) are currently discovered through resource intensive trial and error. Experiments may test a multitude of transcription factors to identify correct combinations that influence cell fate. In addition, reprogramming approaches commonly use stem cell intermediates such as induced pluripotent stem cells (iPSCs), which are generated ...