SBIR-STTR Award

Tactical Funding Increase (TACFI) for NASIC/GXK
Award last edited on: 5/30/2023

Sponsored Program
SBIR
Awarding Agency
DOD : AF
Total Award Amount
$2,497,068
Award Phase
2
Solicitation Topic Code
AF203-DCSO1
Principal Investigator
Brett Granberg

Company Information

Vannevar Labs Inc

160 Forest Avenue
Palo Alto, CA 94301
   (650) 278-2302
   N/A
   www.vannevarlabs.com
Location: Single
Congr. District: 16
County: Santa Clara

Phase I

Contract Number: FA8649-20-P-0479
Start Date: 3/9/2020    Completed: 6/9/2020
Phase I year
2020
Phase I Amount
$49,434
Our solution is a tactical targeting platform for intelligence operations teams looking for start points, targets, and trends in volumes of text data. We use machine learning to structure this data, translate it into English, and automatically extract the entities of interest within a user interface designed for an intelligence operations airman who needs to quickly identify actionable intelligence in large caches of foreign language text, such as publicly available information or captured enemy material.

Phase II

Contract Number: FA8649-21-P-0894
Start Date: 3/16/2021    Completed: 3/16/2022
Phase II year
2021
(last award dollars: 2022)
Phase II Amount
$2,447,634

Vannevar Labs -- Decrypt platform with Optical Character Recognition (OCR) technology enables users to extract foreign language information from documents and images and exploit the data in English. Decrypt helps mission teams find and target data in non-permissive environments through taskable, persistent foreign text collected in Russian and Mandarin and provides high performance machine translation to decipher this data for users in English through data feeds that teams can tune for their operations. Developing OCR technology will allow Decrypt users to instantly exploit images, graphs, tables, and figures in foreign adversary technical documents for predictive analysis on foreign threats to US air and space operations. This is critical because 90%of these technical documents contain non-readable images but are often essential to understanding the threat picture. The system uses CNN and LSTM neural networks and is trained and deployed on commercially developed GPU processors, providing for fast and accurate transcription and translation. This technology will enable NASIC to track our adversariesâ?? development of critical weapons systems faster and at a more fine-grained level through directly exposing technical information to analysts that currently requires human linguist review or goes unexploited. Â Vannevar Labs collaborated with NASIC after Phase I to test and evaluate our technologyâ??s performance against relevant data for this mission set. Together, we identified the specific enhancements necessary through this R&D Phase II project to enable NASIC and its partner organizations to integrate our technology into their classified analytics pipeline. Decrypt has already delivered access to thousands of foreign language end points for NASIC users to exploit through Phase II. In immediate response to user needs, the platform was updated to allow the user to add new sources and download pdf documents of translated Russian technical information. NASIC intends to use additional funds from TACFI to prepare Decrypt for use on the low-side integration environment. At an enterprise level, NASIC is interested in funding a Phase III contract after development is complete to pursue authority to operate (ATO) on their production software systems and integrate our software into their pipeline through Application Programming Interfaces (APIs). They intend this eventual Phase III to be an IDIQ contract type to enable other Air Force partners, including 16th Air Force, that face similar foreign data exploitation challenges to choose the level of service they need from the technology.