Award Data

Deep Neural Networks have become ubiquitous in the modern analysis of voluminous datasets with geometric symmetries. In the field of Particle Physics, experiments such as DUNE require the detection of particle signatures interacting within the detector, with analyses of over a billion 3D event images per channel each year; with typical setups containing over 150,000 different channels.  In an ...

Software and hardware flaws can be exploited to make programs perform unintended computations or leak sensitive data. We propose to counter these threats by isolating libraries and other program units inside a single process. The developer will insert source-level annotations that i) map code and data units to compartments and ii) capture how each compartment is intended to interact with others, i ...

DoD has a critical need for protecting sensitive data to make sure that only the intended, trusted programs or parts of programs can access the data. This protection must be also effective when data is loaded into memory while being processed by software. Lately, the side-channel attacks which are based on information gained from the implementation of a computer system rather than exploiting algor ...

Rapidly expanding Low Earth Orbit (LEO) satellite constellations force traditional ground-based tracking methods to adapt as the current ground sensor networks can no longer provide a data rich tracking environment. Accurate tracking information is continually consumed by the Government and private sector to varying degrees of accuracy throughout satellites’ mission lifecycles to provide and uti ...

Opterus Research and Development, Inc. (Opterus) and Colorado State University (CSU) have combined the best features of high strain composites (HSC), continuum robots, and tendon actuated robots to develop a new concept called Continuum Actuated Redundant Tendon (CART) Robot to enable self-reconfigurable modular robots that can perform various tasks (e.g., walking, crawling, wheeling, and grasping ...

The Defense Advanced Research Projects Agency (DARPA) is seeking to utilize small reconfigurable robotic system to operate independently in unknown highly complex environments. We propose a modular reconfigurable robot, which presents several locomotion modality to handle different type of off-road environments. We proposed several configurations for the robot, which are well-suited to the type of ...

Air and missile threats can fly highly maneuvering, complex trajectories. This poses a challenge to tracking algorithms during data association because of confusing targets, proximal detections and fast motion. In the proposed effort we propose to develop deep learning based technologies for data association to improve the accuracy of data association. Deep learning has shown significant gains in ...

The objective of this project is to develop a capability to model fracture of materials used in hypersonic vehicles that results from hypervelocity impact while exposed to extreme temperatures. Symplectic Engineering’s approach addresses this challenge at two levels. At the computational level, a Relaxed Extended Finite Element approach is pursued to represent (possibly intersecting) fractures l ...

This STTR research study aims to enhance and apply thermo-mechanically coupled computational models for high-temperature fracture. This topic is particularly challenging in that hypersonic flight in the atmosphere generates extreme conditions over a vehicle that can affect the strength and performance the vehicle materials, both in-flight conditions as well as for cases where the vehicle encounter ...

Seed Innovations (Seed) and the University of Colorado in Denver (UCD) apply our experience in natural language processing (NLP), artificial intelligence, big data, data analytics, automatic code generation, framework development, and software architecture to accomplish the research required. Through the research on this project, Seed and UCD design and develop a proof-of-concept system, Intellige ...