Search Contract Opportunities

Explainable AI (XAI) for RF Applications of Deep Learning

ID: AF221-0022 • Type: SBIR / STTR Topic
Question & Answer Assistant

Hello! Please let me know your questions about this opportunity. I will answer based on the available opportunity documents.

Please sign-in to link federal registration and award history to assistant. Sign in to upload a capability statement or catalogue for your company

Some suggestions:
Please summarize the work to be completed under this opportunity
Do the documents mention an incumbent contractor?
Does this contract have any security clearance requirements?
I'd like to anonymously submit a question to the procurement officer(s)
Loading

Description

TECH FOCUS AREAS: Artificial Intelligence/Machine Learning TECHNOLOGY AREAS: Sensors; Information Systems OBJECTIVE: This topic seeks to develop new approaches to explainable AI (XAI) applicable to advanced radio frequency (RF) applications such as radar, electronic warfare (EW), ELINT and SIGINT. This would allow for adequate testing and evaluation (T&E) of deep learning networks (DLNs). DESCRIPTION: The recent successes of deep learning applied to a variety of complex RF applications such as cognitive radar (CR) has prompted the need for new T&E methods to validate both performance and reliability, particularly for DoD applications. Explainable AI (XAI) is a branch of research focused on understanding "how and why" a DLN arrived at the response it did. However, for DoD applications, a very rigorous level of validation and reliability must be achieved in order to declare a system "operational". Thus, new XAI methods for DoD-specific applications are required that statistically: (1) quantify performance in an operationally relevant environment: and (2) quantify reliability (and thus availability). Methods are sought that do not require extensive (and expensive) field testing to obtain the relevant statistics. PHASE I: Phase I efforts will pursue new XAI methods specifically addressing the DoD's needs for rigorous T&E to declare a warfighting system operational. In particular, rigorous XAI approaches are sought that can result in accurate statistical characterizations of both performance and reliability. These approaches should also minimize reliance on costly field experiments or testing. The feasibility of the proposed methods should be established in Phase I via a combination of analysis and computer simulation. Phase I should end with a clear technology development and transition roadmap for Phase II and beyond. PHASE II: In Phase II, the methods developed in Phase I should be further developed and matured. One or more real-world focus applications will be selected to serve as the pathfinder for the new XAI approaches. Details of the new XAI procedures shall be delineated in a manner sufficient to transition to established DoD T&E organizations. The output of Phase II should be mature enough to enter low-rate initial production (LRIP) in Phase III. PHASE III DUAL USE APPLICATIONS: Phase III efforts will identify potential commercial and dual use applications. It is expected the inherent utility of the new XAI methods will be of immediate value to all commercial enterprises, incorporating advanced DL methods. NOTES: The technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the proposed tasks intended for accomplishment by the FN(s) in accordance with section 5.4.c.(8) of the Announcement and within the AF Component-specific instructions. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws. Please direct questions to the Air Force SBIR/STTR Help Desk: usaf.team@afsbirsttr.us REFERENCES: [1] J.R. Guerci, Cognitive Radar: The Knowledge-Aided Fully Adaptive Approach, 2nd Ed. Norwood, MA USA: Artech House, 2020 [2] C. Warner, "Institutionalizing a Culture of Statistical Thinking in DoD Testing," Operational Test & Evaluation, Department of Defense, 2017. [Online]. Available: https://www.dote.osd.mil/Portals/97/pub/presentations/2017/20170925StatisticalEngineeringWebinarcwarner.pdf?ver=2019-09-03-104246-703; [3] M. Jasper, "JAIC Seeks Test and Evaluation Services for Artificial Intelligence," Nextgov, Artificial Intelligence, 11 February 2021. https://www.nextgov.com/emerging-tech/2021/02/jaic-seeks-test-and-evaluation-services-artificial-intelligence/172018/ [4] "Test & Evaluation Management Guide." https://www.dau.edu/guidebooks/Shared%20Documents/Test_and_Evaluation_Mgmt_Guidebook.pdf KEYWORDS: Artificial Intelligence; Explainable AI; Deep Learning; Cognitive Systems; RF modeling and simulation;

Overview

Response Deadline
Feb. 10, 2022 Past Due
Posted
Dec. 1, 2021
Open
Jan. 12, 2022
Set Aside
Small Business (SBA)
Place of Performance
Not Provided
Source
Alt Source

Program
SBIR Phase I / II
Structure
Contract
Phase Detail
Phase I: Establish the technical merit, feasibility, and commercial potential of the proposed R/R&D efforts and determine the quality of performance of the small business awardee organization.
Phase II: Continue the R/R&D efforts initiated in Phase I. Funding is based on the results achieved in Phase I and the scientific and technical merit and commercial potential of the project proposed in Phase II. Typically, only Phase I awardees are eligible for a Phase II award
Duration
6 Months - 1 Year
Size Limit
500 Employees
On 12/1/21 Department of the Air Force issued SBIR / STTR Topic AF221-0022 for Explainable AI (XAI) for RF Applications of Deep Learning due 2/10/22.

Documents

Posted documents for SBIR / STTR Topic AF221-0022

Question & Answer

Contract Awards

Prime contracts awarded through SBIR / STTR Topic AF221-0022

Incumbent or Similar Awards

Potential Bidders and Partners

Awardees that have won contracts similar to SBIR / STTR Topic AF221-0022

Similar Active Opportunities

Open contract opportunities similar to SBIR / STTR Topic AF221-0022