You are here

ARCTIC: Advanced Radar Classification of Targets In Cluster

Award Information
Agency: Department of Defense
Branch: Missile Defense Agency
Contract: HQ0860-22-C-7404
Agency Tracking Number: B2D-0043
Amount: $1,702,433.00
Phase: Phase II
Program: SBIR
Solicitation Topic Code: MDA21-D002
Solicitation Number: 21.3
Solicitation Year: 2021
Award Year: 2022
Award Start Date (Proposal Award Date): 2022-04-19
Award End Date (Contract End Date): 2024-04-18
Small Business Information
7047 Old Madison Pike, Suite 305
Huntsville, AL 35806-2197
United States
DUNS: 968887195
HUBZone Owned: No
Woman Owned: Yes
Socially and Economically Disadvantaged: No
Principal Investigator
 Joshua Wilson
 (262) 442-3007
Business Contact
 Heather Johns
Phone: (256) 327-5541
Research Institution

Current ship-based radars encounter complex target scenes involving various types of clutter (e.g. debris, chuff, chaff, PID), challenging the ability of these radars to identify lethal targets and complete their critical mission. nou Systems, Inc (nSI) proposes a suite of physics-based algorithms integrated into a machine learning (ML) framework to mitigate the impact of the clutter and enable the radar to discriminate lethal objects in challenging clutter scenes. nSI has developed the primary components of this technology through multiple DoD contracts (including but not limited to a Phase I SBIR) and through internal research and development efforts. Because each of the individual physics-based algorithms and features are selected to be robust in the presence of clutter, the proposed solution inherently provides improved capability in these complex target scenes. nSI will prove the applicability of the developed technology to the SPY-1 and SPY-6 radars by training and testing the algorithms with government-provided radar data augmented with data developed through nSI's comprehensive radar modeling and scene generation toolset. By partnering with Lockheed Martin, Raytheon, and SEG, we will ensure the algorithms are suitable for insertion into the tactical radars. Because the ML framework intelligently fuses data from diverse algorithms involving various RF features, the proposed solution will improve capability when using existing waveforms and resource allocation, as well as when using planned or upgraded waveforms. Approved for Public Release | 22-MDA-11102 (22 Mar 22)

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

US Flag An Official Website of the United States Government