STOTTLER HENKE ASSOCIATES, INC — Department of Defense SBIR Phase I: N201-059

Description

USV SIGCON (signature control) consists of enhancing, reducing, manipulating, and directionally controlling all signatures including electromagnetic (EM) and acoustic signatures. USVs will be tasked with a variety of missions from collections to mine clearance, and every situation within every mission demands autonomous, dynamic, real-time onboard SIGCON. This includes the ability to follow International Regulations for Preventing Collisions at Sea (COLREGs)/Rules of the Road and Emissions Control (EMCON) as appropriate. We propose SIGMA (SIGnature Management Agent) to autonomously control signatures on USVs. SIGMA takes in potentially days-old broad guidance from a distant controlling station (e.g., mission objectives, commander’s intent, ROE, etc.) as well as organic and inorganic data (e.g., radar, sonar, AIS, GPS, weather) to appropriately control sensors (e.g., turn off active radar, turn ship, broadcast AIS) and employ techniques (e.g., utilize deceptive lighting, spray mist or chaff). SIGMA utilizes several tried-and-tested artificial intelligence (AI) techniques including Knowledge Engineering (KE), Fuzzy Logic (FL), Behavior Transition Networks (BTNs), and Case-Based Reasoning (CBR). Knowledge Engineering refers to the process of extracting knowledge from subject matter experts, developing a Knowledge Representation (KR), and building a system based on formal and informal facts, rules, and frames. Robert Bergman and Jonathan Vandervelde, who have expert knowledge in Electromagnetic Spectrum Operations (EMSO) and Electronic Warfare (EW), will provide subject matter expertise that will be integrated into SIGMA. Fuzzy Logic captures rules that reference qualitative, inexact, or “fuzzy” values such High/Medium/Low. Behavior Transition Networks create intelligent behaviors by dividing behavior hierarchically into tasks connected by transitions. Finally, Case-Based Reasoning (CBR) attempts to solve the current problem by retrieving a previously encountered similar problem and adapting that problem’s solution to the current situation. In Phase I, we will develop a limited prototype SIGMA and test it using both the Navy-provided data and our in-house simulator. In Phase II, we will build at least two SIGMAs with improved capabilities that meet the Unmanned Maritime Autonomy Architecture (UMAA), and we will integrate them into actual USVs.