Award Data

R-DEX Systems proposes to adapt its commercial discrimination technology used in industrial automation to develop Deep Automatic Target Recognition (DATR) Technology. DATR utilizes revolutionary deep learning processing (deep belief networks or DBNs, restricted Boltzmann machines RBMs, and convolutional neural networks or CNNs) to automatically identify hidden, nonlinear features that are not iden ...

One key concern of the Strategic Capabilities Office (SCO) is the security component of the “Asia-Pacific Rebalance” where the Chinese anti-access/area denial (A2/AD) policy threatens regional security. In response to A2/AD our forces in the Pacific require more affordable and rapidly deployable alternatives to costly missile defense such as large caliber projectiles for Navy electroma ...

Few-shot Object detection via Reinforcement Control of Image Simulation (FORCIS) will combine deep reinforcement learning with additional training data augmentations and strategies to develop robust few shot detectors leveraging available simulations.

To fully understand the combustion dynamics when chemical warfare agents are detonated, fast time-scale diagnostics are needed. While computational modeling may provide insight into the different processes, experimental measurements are needed to verify and validate these models. Since the detonation or combustion of chemical agents can result in optically thick fireballs, innovative techniques mu ...

OSD solicits vendors for a ‘High Acceleration and Hypervelocity Inertial Measurement Unit System’ for use in 155mm projectiles. Development of a gun-hardened and highly miniaturized IMU would revolutionize the way in which 155mm gun systems are employed. A 155mm projectile with guidance, navigation and control would enable the development of new systems such as precision gun launched missile d ...

Reliable automated pattern recognition in the current system is limited by excessive noise and clutter combined with insufficient and/or ambiguous features. Our team consisting of AcornSI and Leidos thus propose a multi-step approach based on the combined effects of improved detection, feature extraction, phase identification, and global association. A key innovation here is creating a new classif ...

N/A

The final prototype of the Microcircuit Board Repair apparatus will be capable of laying down or lifting metal strips with micrometer dimensions. Under real time computer control, the translation stages will be fully automated or manually controlled. The end user will monitor the process in real time using a camera attached with the source. Laying down the metal lines will be done using Laser C ...

Survival of present day microelectronic circuits depends on their protection from self generated and external electromagnetic interference. This proposal is oriented toward the class of interference generally referred to as overvoltage transients. Means for mitigating these transients include gas discharge tubes, and various solid state devices. Each of these has their own advantages in particu ...

1. A conceptual baseline design of a hydrogen supply system with a on/off capability will be prepared for delivering hydrogen in increments of up to 10g/hour with a total capacity of 120g hydrogen. This baseline design will be based upon a solid state hydrogen reactant mixture with a yield of 8% by reactant weight which has been previously qualified for military use. ...