SBIR-STTR Award

5-Context and AI-based Reasoning for Identification Onboard UxVs (5-CARIBOU)
Award last edited on: 2/10/2023

Sponsored Program
SBIR
Awarding Agency
DOD : Navy
Total Award Amount
$1,736,704
Award Phase
2
Solicitation Topic Code
N193-A02
Principal Investigator
Christopher (Alex) George

Company Information

Boston Fusion Corporation

70 Westview Street Suite 100
Lexington, MA 02421
   (617) 583-5730
   info@bostonfusion.com
   www.bostonfusion.com
Location: Single
Congr. District: 05
County: Middlesex

Phase I

Contract Number: N68335-20-F-0117
Start Date: 11/21/2019    Completed: 4/20/2020
Phase I year
2020
Phase I Amount
$149,953
Context- and AI-Based Reasoning for Identification onBOard UUVs (CARIBOU) is a comprehensive, AI-based automatic target recognition (ATR) agent paired with a fundamentally novel reasoning engine. CARIBOU is designed to provide accurate, robust target recognition capabilities that are not easily fooled by novel classes, dim signals, or attempts to deceive, without requiring a human-in-the-loop or burdensome size, weight, and power (SWaP) requirements. The CARIBOU team has already completed some studies under IRAD funding which provide a basis of confidence for the proposed work, demonstrating that off-the-shelf deep neural networks (DNNs) are able to recognize sonar signals at high accuracy. In Phase I, we will expand our work into a full proof-of-concept that demonstrates not only target recognition, but also an ability to reason over the results. This reasoning will improve classification accuracy and identify irregularities such as results with high-uncertainty or indicators of attempts to deceive. Phase I will focus on passive sonar; future phases will consider additional modalities and will include in-water testing using our facilities. CARIBOU is a joint effort between Boston Fusion Corp, which brings expertise in machine learning research for DoD applications, and Advanced Acoustic Concepts, which brings expertise in sonar processing, acoustic modeling, and UxV development.

Benefit:
CARIBOU will find immediate application as a tool for ATR on passive sonar, including (1) operationally, both directly and on US Navy platforms such as AN/SQQ-89; (2) commercially, on large cargo ships; and (3) in the context of sonar watch-stander training programs. Integrating CARIBOU onboard UxVs will likely generate high interest both from within the US Navy and from other NATO countries. Finally, the reasoning modules represent a significant advance in shortening the data-to-decision pipeline and improving ATR performance.

Keywords:
Sonar Processing, Sonar Processing, UUVs, Deep Learning, Signal processing, Artificial Intelligence, Machine Learning

Phase II

Contract Number: N68335-20-F-0556
Start Date: 4/24/2020    Completed: 10/23/2021
Phase II year
2020
Phase II Amount
$1,586,751
Context- and AI-Based Reasoning for Identification onBOard UxVs (CARIBOU) is a comprehensive, AI-based automatic target recognition (ATR) agent paired with a fundamentally novel reasoning engine and a state-of-the-art sonar simulator. CARIBOU provides accurate, robust target recognition capabilities that are not easily fooled by novel classes, dim signals, or attempts to deceive, without requiring a human-in-the-loop or burdensome size, weight, and power (SWaP) requirements. In Phase I, we prototyped CARIBOU’s “brain” and demonstrated that it could classify similar contacts with an overall accuracy greater than 97%. In Phase II, we will continue to upgrade Brain while also developing SKULL, which is a novel interface between Brain and the simulator and acoustic processors. Phase II will also consider additional passive sonar sensors and will develop a roadmap for adding other modalities to CARIBOU. Finally, Phase II will target an in-water demonstration using the UD-GARC USV in the Chesapeake Bay. CARIBOU is a joint effort between Boston Fusion Corp, which brings expertise in machine learning research for DoD applications, Advanced Acoustic Concepts, which brings expertise in sonar processing, acoustic modeling, and sonar hardware, and Maritime Applied Physics Corp., which brings expertise in building, modifying, and operating UxVs and other small watercraft.