Award Data

Agents, Agent Architectures and Agent-based applications have become a phenomena in recent years with seemingly everyone jumping on the bandwagon. However, as with any truly revolutionary breakthrough technology, Agents have lacked standards and rulingbodies to govern the direction of the bandwagon in its infancy. While inside this wagon train apparent chaos ruled, but with that chaos came many ...

The Phraselator, a handheld automatic translation device, currently uses a cardioic microphone as an input for automatic speech recognition (ASR). This microphone is highly vulnerable to performance degradation in typical noisy military environments and,thus, there is a need for an improved transducer for this application. We propose to develop a new directional microphone that is immune to extr ...

Radios are required for every spacecraft mission, yet spacecraft radios truly suited for nanosatellites currently do no exist. AeroAstro's proposed Modular S-Band Radio Suite (MSBRS) will solve this problem and make inexpensive spacecraft in the 1 to 30kgclass feasible. In this SBIR program AeroAstro will develop a set of miniature radio modules specifically intended to allow the spacecraft deve ...

We propose a new automatic target recognition (ATR) system that operates on video data, exploiting the inherent redundancy and spatio-temporal coherence of motion imagery to create three-dimensional target signatures. Unlike previous approaches that useshape alone, our method will additionally model and predict object surface appearance properties, in the form of bi-directional reflectance distrib ...

Detecting and disrupting a terrorist network requires the ability to: link disparate (noisy, deceptive) data and recognize patterns in the underlying networks, estimate where further intelligence would be useful, and predict the network's response topossible attacks.We propose to combine state-of-the-art social network analysis (meta-networks) and statistical inferencing (probabilistic relational ...

Organic Air Vehicles have the potential to dramatically improve knowledge of the battlespace by providing persistent networked coverage which can dynamically adjust to changing conditions. These systems require novel algorithms which can address theproblems of positioning, sensor resource allocation, and tracking. Here we propose to define an architecture and create core algorithms which address ...

To predict likely terrorist actions and terrorist targets in the U.S. we need (1) models of how terrorist organizations evolve and learn (2) identification of cultural variables likely to shape the evolution of terrorist organizations within the U.S. and(3) methods for including these cultural context variables in organizational learning models. Our team includes three essential types of expertise ...

Bluefin Robotics proposes (in Phase I) to create a methodology for developing the Bluefin Agent Behavior Language (BABL) and associated tools. BABL will enable the rapid design and development of behaviors for autonomous vehicles. Key features of BABL arethat it:1) Makes a minimal set of assumptions about the capabilities and assumptions of the target UVs.2) Maintains generality without losing the ...

The goal of our proposed research is autonomous real-time detection, classification, and location of targets from a video image. DTS Inc (www.dtsits.com) proposes to combine its robust software in real-time video tracking and classification of vehicles forthe transportation industry with a new classifier (From our subcontractor, Quasar International, www.quasarintl.com) to develop a true ATR video ...

This Phase II SBIR effort will develop a compact high pulse energy eyesafe laser transmitter with a pulse width of 1ns and a repetition rate of 30Hz. This source will be compatible with multi-function operation (imaging, rangefinding and designation) anddesigned for compact packaging. The end product will be a fieldable brassboard laser.