You are here

Virtual Reality for Multi-INT Deep Learning (VR-MDL)

Award Information
Agency: Department of Defense
Branch: Air Force
Contract: FA8750-19-C-0223
Agency Tracking Number: F19A-010-0135
Amount: $148,420.00
Phase: Phase I
Program: STTR
Solicitation Topic Code: AF19A-T010
Solicitation Number: 19.A
Timeline
Solicitation Year: 2019
Award Year: 2019
Award Start Date (Proposal Award Date): 2019-08-20
Award End Date (Contract End Date): 2020-08-20
Small Business Information
12900 Brookprinter Place, Suite 800
Poway, CA 92064
United States
DUNS: 107928806
HUBZone Owned: No
Woman Owned: No
Socially and Economically Disadvantaged: No
Principal Investigator
 Joesph Guerci
 Principal Investigator/Project Manager
 (858) 373-2702
 jguerci@islinc.com
Business Contact
 Margaret Latchman-Geller
Phone: (858) 373-2717
Email: mgeller@islinc.com
Research Institution
 Ohio University
 Nate Wallace Nate Wallace
 
340 West State Street
Athens, OH 45701
United States

 (740) 593-9986
 Nonprofit college or university
Abstract

Recent advances and successes of deep learning neural networks (DLNN) techniques and architectures have been well publicized over the last several years. Voluminous, high-quality and annotated training data, or trial and error in a realistic environment, is required to achieve the promised performance potential of DLNNs. Unfortunately for DoD and/or Intelligence Community (IC) applications of multi-INT fusion, there is a dearth of high-quality, annotated training data covering all contingencies in highly-contested adversarial environments. And there is really no conceivable practical way in the future to obtain such data. Although we routinely collect a “fire house” of multi-INT data, it is not suitable for DLNN training since it is not processed, vetted, and annotated. Not to mention that true targets of interest are embedded in enormous amounts of clutter, noise and other extraneous signals. In this project, ISL and Ohio University propose a novel approach for creating the requisite training data and environment by combining state-of-the-art DLNN methods with a high-fidelity, multi-physics-based modeling and simulation framework for multi-INT sensor systems.

* Information listed above is at the time of submission. *

US Flag An Official Website of the United States Government