Award Data

LongShortWay Inc. and Northeastern University propose a family of feature reduction and ensemble classifier methods based on Principal Component and Dynamic Logic feature clustering algorithms. New methods combine feature clustering with non-linear feature reduction via manifold learning, and bagging, boosting, and stacking ensemble algorithms.

As systems become more heterogeneous and distributed, determining optimal actions for each “teammate” within the system becomes increasingly complex. A particular difficulty in guiding the actions of these teammates is the fact that they are not guaranteed to follow suggestions provided by a supervisor, especially when those suggestions are inconsistent with the teammate’s tendencies, prefer ...

SI2 Technologies, Inc. (SI2) proposes to accelerate development of printed, high-efficiency phased arrays operating at Navy-relevant frequencies. The proposed development effort will include optimization of the array printing techniques from Phase I to meet the Navys phased array performance goals. The printed arrays will incorporate both printed radiating elements and an innovative printed packag ...

Triton Systems, Inc. proposes to develop an affordable, lightweight and durable hybrid composite system for next generation structural frame composites that will survive both short- and long-term thermal and chemical exposure and abrasive conditions. The team will develop a hybrid materials system that is an improvement on traditional carbon fiber reinforced polymer (CFRP) systems in performance a ...

The Internet of Things (IoT) connects people, data, and "things" (e.g., software, sensors, platforms), facilitating the translation of information into actions. Although naval platforms’ networks and communication suites have evolved significantly in the past few years to support such required connectivity, one of the greatest technical challenges still facing the military community is the proce ...

In Dense Urban Environments (DUEs), a new and evolving battlefield, the ability to detect and respond quickly to multiple threats in complex environments (e.g., snipers on rooftops or in windows) is critical and is extremely important to both civilian and military tactical needs. Response latency in the critical moments after the beginning of an attack can significantly increase casualties. SWIFT ...

Boston Engineerings Advanced Systems Group is collaborating with Prof. Holly Yanco at the University of Massachusetts at Lowell to develop a design science for robot-operator interfaces under a DARPA Phase I STTR program. Our program, called Robot Linked User Control and Interface Design (R-LUCID), is aimed at distilling and understanding the components of interaction including robot capability, ...

Optically pumped magnetometers provide very high performance but they cost tens of thousands of dollars, and they are large and power hungry. Recently we successfully developed and commercialized laser pumped magnetometers with size, weight and power consumption that is an order of magnitude below current state-of-the-art without sacrificing performance. In this project, the focus will be on produ ...

Existing machine perception systems are too inflexible, and are not robust enough to environmental uncertainty. In existing systems, perception components are statically (and manually) configured to process sensor data. The parameters of components in such a system are also statically tuned to operate optimally under very specific conditions. Information flow in such systems is bottom up, and gene ...

The US Navy is moving towards a Single Sortie Detect to Engage (SSDTE) paradigm to implement in-stride minehunting and mine prosecution. Integrating in-stride Mine Search and Mine Prosecution functions is a key requirement to achieve the SSDTE paradigm. Mine Target Reacquisition between the mine search operations and mine prosecution phases poses a particular challenge, as planned mine prosecution ...