Award Data

Hemp-based clothing are excellent for outdoor active wear, due to high strength, UV-protective qualities, mold resistance, and excellent moisture absorption and desorption. While academic research on hemp-based textiles in the US is increasing, it has naturally also become an area of interest to competing countries. Specifically, China is outperforming the US in hemp fiber technological advancemen ...

In this Phase I effort, Tiami, LLC, aims to develop and demonstrate a hardware proof of concept for a collaborative multi-robot system (MRS) that leverages imitative augmented deep reinforcement learning (IADRL) amongst heterogeneous uncrewed systems (robots) to achieve a common task. Collaboration is based on low-latency machine-to-machine wireless links between robots that use both RF and optica ...

Ad Hoc Swarm Modulation and Adaptation focuses on the ability to enable secure cyber communications, data, and distributed AI processing for any robotic swarm in any condition.  The system incorporates a range of multi-robotic system functionality to allow for coordination, cooperation, and reconfigurable methods of robotic teams, flocks, and swarms.  The system further includes methods for swar ...

krtkl (“critical”) will conduct a Phase I Feasibility Study to identify the best approach for reducing aviator cognitive load by optimizing information delivery and decision-making based on a thorough analysis of existing platforms, sensors, data sources, and onboard compute resources. This information will be used to identify Artificial Intelligence and Machine Learning based algorithms for p ...

In Phase I, our team of Kitware and UC-Berkeley developed Scale-MAE by adding ground sample distance (GSD) to positional encodings, and produced a multiscale representation that achieves state-of-the art results across image classification, semantic segmentation, and object detection tasks. In Phase II, we will create a remote sensing pretraining toolkit to enable fast and easy experimentation wit ...

Artificial intelligence-assisted detection and imaging technology can gather data on underwater, surface, and aerial threats to gain situational awareness over opposing forces, and aids in navigating dangerous marine and terrestrial environments. Successful and efficient use of intel is crucial for strategic information warfare, but many current technologies require active monitoring to identify t ...

To compete on the world stage of undersea warfare (USW), the US Navy’s USW systems are frequently updated with advanced capabilities. As a result, modernization trainers need to perform the challenging tasks of updating training material to reflect the new (and obsolete) capabilities. This process requires comparing legacy to updated documentation, identifying changes to system capabilities, and ...

We propose to develop and transition CodeSurgeon: an adaptable, AI-guided, full-stack debloating system. CodeSurgeon is innovative and unique in the field because it produces high-quality debloated programs with improved security posture that are safe, reliable, and sound. Following the lessons learned from a broad comparative evaluation of debloating tools conducted by the PI , CodeSurgeon will i ...

Areté and its teaming partner the University of Arizona (UofA) will develop a software tool that transforms sensor and metadata from a given sensor system into realistic synthetic data as if it were collected by a different sensor system. The exponential rise in available data from a multitude of sensor systems has driven commercial and academic entities to achieve significant innovations in arti ...

High temperature jet plumes emanating from aircraft engines and missiles produce effects that are of interest for threat detection, environmental noise, and engine development purposes. Optical and infrared emissions from plumes are sources of light and heat signatures, respectively, that can potentially be used for tracking or targeting vehicles in flight.  Acoustic noise from jet plumes can pot ...