Automated Multi-System Course of Action Analysis Using Artificial Intelligence
Navy SBIR 2019.1 - Topic N191-034
NAVSEA - Mr. Dean Putnam - dean.r.putnam@navy.mil
Opens: January 8, 2019 - Closes: February 6, 2019 (8:00 PM ET)

N191-034

TITLE: Automated Multi-System Course of Action Analysis Using Artificial Intelligence

 

TECHNOLOGY AREA(S): Battlespace, Electronics, Sensors

ACQUISITION PROGRAM: PEO IWS 1.0, FNC - Operator Planning Tool

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 statement of work (SOW) tasks intended for accomplishment by the FN(s) in accordance with section 3.5 of the Announcement. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws.

OBJECTIVE: Create a mission planner decision aid that enables Automated Decision Support (ADS) utilizing Artificial Intelligence (AI) and is scalable and composable to provide timely and effective employment of maritime resources and off board sensors.

DESCRIPTION: AI ADS that is advanced, scalable, and composable is needed to address the planning and simulation of complex missions. Current commercial Course of Action (COA) decision aids and Maritime Mission Planning Systems (MMPS) do not adequately address this need. Commercial decision aids are slow and unsuitable for tactical application. Current Navy mission planning and tactical decision aids are cumbersome, disaggregated, and labor-intensive. Current tools inherently lack the scalability and solution speed necessary to support the volume and diversity of the data that is acquired in order to make the required tactical decisions in dynamic and uncertain environments. These systems typically require operators to manually translate and aggregate the data needed to input into the tactical decision process. These systems are not multi-mission and do not provide predictions (estimates), deception reasoning, tactical options, COA animation, visualization, optimality assessment and tactical alternatives, and recommendations. Consequently, there is an increasing demand for developing and combining both deliberate planners and Mission Planning (MP) Tactical Decision Aids (TDAs) within a common architecture framework that is scalable across multiple mission areas. To address these needs, advanced AI technologies are desired for the generation and simulation of mission plans of various concurrent, multi-agent systems such as naval combat operations, air defense operations, cyberwarfare, and land combat missions. Within the foreseeable future, the planning and control of these types of missions requires adaptation to the intermediate results and dynamic re-computation in real time (i.e., in seconds from the initiation of the planning request).

AI-based MP TDAs integrated with the AEGIS Weapons System and capable of output to external collaborative planners are needed that enable faster than real-time COA generation and performance analysis in simulation, and support real-time and post mission analysis. This will not require a new Graphical User Interface (GUI), but will expand the function of the current integrated AEGIS Weapons System planner. Furthermore, to be of high tactical relevance, the requested COA estimates produced should be differentiated by key assessment factors and (i.e., damage to US units; damage inflicted on enemy units; weapons usage; mission objectives attained; timeliness of response) available to the commander and staff within seconds from the initiation of a request on standard desktop computing hardware. This capability should provide quick (i.e., less than 30 seconds) Automatic Generation, Analysis, and Assessment of COAs of friendly and enemy forces, including generation and comparative analysis of assumption-based COA options (e.g., “what-ifs”). The developed AI planner tool will generate, analyze, and assess COA options based on threat (Threat based Course of Action Generation and Comparative Analysis), blue force capability, intelligence estimates and meteorological data; and support collaboration in the Navy’s Maritime Tactical Command and Control (MTC2) network. The developed AI planner tool will also support integration within the AEGIS Weapon System (AWS in Advanced Capability Build (ACB) 20 or higher) as a functional component of an Integrated AWS planner. It will concurrently support integration within the AEGIS Weapon System (AWS in Advanced Capability Build (ACB) 20 or higher) as a functional component of an Integrated AWS planner. COA generation should be based on a well-supported adversarial reasoning engine (Threat based Course of Action Generation and Comparative Analysis) that permits both autonomous operation and interactive human-in-the-loop participation. The output should be the expected outcomes of the prescribed mission (e.g., success, partial success, failure) accompanied by TDA Metrics comparisons of user selected performance criteria (e.g., enemy units destroyed, ordnance expended, fuel usage, casualties). By defining qualitative means of comparing COAs, the developed MP TDAs will support tactical employment optimization. These features are especially important in dynamic mission environments where the potential impact of actionable information may require immediate re-planning.

The Phase II effort will likely require secure access, and NAVSEA will process the DD254 to support the contractor for personnel and facility certification for secure access. The Phase I effort will not require access to classified information. If need be, data of the same level of complexity as secured data will be provided to support Phase I work.

Work produced in Phase II may become classified. Note: The prospective contractor(s) must be U.S. Owned and Operated with no Foreign Influence as defined by DoD 5220.22-M, National Industrial Security Program Operating Manual, unless acceptable mitigating procedures can and have been be implemented and approved by the Defense Security Service (DSS). The selected contractor and/or subcontractor must be able to acquire and maintain a secret level facility and Personnel Security Clearances, in order to perform on advanced phases of this contract as set forth by DSS and NAVSEA in order to gain access to classified information pertaining to the national defense of the United States and its allies; this will be an inherent requirement. The selected company will be required to safeguard classified material IAW DoD 5220.22-M during the advance phases of this contract.

PHASE I: Develop and deliver an initial concept design of a mission planning decision aid that shows the aid can feasibly meet the requirements described in the Description. Establish feasibility through analysis, modeling, and testing. Develop a Phase II plan. The Phase I Option, if exercised, will include the initial design specifications and capabilities description to build a prototype solution in Phase II.

PHASE II: Develop a prototype that meets the parameters in the Description. Evaluate the prototype to ensure it supports optimal mission planning, taking into account both the new Navy capabilities and the existing legacy manned platforms, and the Navy information assurance specifications for classification security. Demonstrate system performance through prototype installation and testing with the prime integrator for the AEGIS Weapon System. The Government will direct the prime integrator to work with the performer. The small business’s SBIR data rights will be protected while working with the prime integrator. The Government will provide the demonstration facility. Prepare a Phase III development plan to transition the technology for Navy use.

It is probable that the work under this effort will be classified under Phase II (see Description section for details).

PHASE III DUAL USE APPLICATIONS: Support the Navy in transitioning the technology to Navy use. Ensure that the developed AI planner tool is compliant with software interface requirements as a web application service in the Navy’s Maritime Tactical Command and Control (MTC2) network; and will concurrently support integration within the AEGIS Weapon System (AWS in Advanced Capability Build (ACB) 20 or higher) as a functional component of an Integrated AWS planner. Support the Government during testing and qualification before transitioning into Navy use.

With respect to commercial application, the developed services should be broadly applicable to live testing of manned and unmanned systems and simulations like in production control or human planning within a factory.

REFERENCES:

1. Chalmers, Bruce A. “Supporting Threat Response Management in a Tactical Naval Environment.” Penn State University, 2002. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.572.7353&rep=rep1&type=pdf

2. Stilman, B. “Mosaic Reasoning for Discoveries.” Journal of Artificial Intelligence and Soft Computing Research, Vol. 3, No. 3, pp. 147-173., 2013 (published in 2014). https://www.researchgate.net/publication/273303659_Mosaic_Reasoning_for_Discoveries

3. Stilman, B., Yakhnis, V., and Umanskiy, O. “Chapter 3.3. Strategies in Large Scale Problems.” Adversarial Reasoning: Computational Approaches to Reading the Opponent's Mind, Ed. by A. Kott (DARPA) and  W. McEneaney (UC-San Diego), Chapman & Hall/CRC, pp. 251-285, 2007. https://books.google.com/books?hl=en&lr=&id=V0HMBQAAQBAJ&oi=fnd&pg=PP1&dq=Kott+A,+McEneaney+W+(eds)+(2007)+Adversarial+reasoning:+computational+approaches+to+reading+the+opponent%E2%80%99s+mind.+Chapman+%26+Hall/CRC,+New+York,+p+355&ots=xei6NeUc-X&sig=4daFBHEEU2S-eTGxSsATbGicibU#v=onepage&q&f=false

4. Stilman, B. Linguistic Geometry: From Search to Construction. Kluwer (now Springer), 2000. https://www.springer.com/us/book/9780792377382

KEYWORDS: Mission Planning Tactical Decision Aids; Automated Decision Support; Artificial Intelligence Decision Support; Threat based Course of Action Generation and Comparative Analysis; Tactical Decision Aid Metrics; Tactical Employment Optimization

 

** TOPIC NOTICE **

These Navy Topics are part of the overall DoD 2019.1 SBIR BAA. The DoD issued its 2019.1 BAA SBIR pre-release on November 28, 2018, which opens to receive proposals on January 8, 2019, and closes February 6, 2019 at 8:00 PM ET.

Between November 28, 2018 and January 7, 2019 you may communicate directly with the Topic Authors (TPOC) to ask technical questions about the topics. During these dates, their contact information is listed above. For reasons of competitive fairness, direct communication between proposers and topic authors is not allowed starting January 8, 2019
when DoD begins accepting proposals for this BAA.
However, until January 23, 2019, proposers may still submit written questions about solicitation topics through the DoD's SBIR/STTR Interactive Topic Information System (SITIS), in which the questioner and respondent remain anonymous and all questions and answers are posted electronically for general viewing until the solicitation closes. All proposers are advised to monitor SITIS during the Open BAA period for questions and answers and other significant information relevant to their SBIR/STTR topics of interest.

Topics Search Engine: Visit the DoD Topic Search Tool at sbir.defensebusiness.org/topics/ to find topics by keyword across all DoD Components participating in this BAA.

Proposal Submission: All SBIR/STTR Proposals must be submitted electronically through the DoD SBIR/STTR Electronic Submission Website, as described in the Proposal Preparation and Submission of Proposal sections of the program Announcement.

Help: If you have general questions about DoD SBIR program, please contact the DoD SBIR Help Desk at 800-348-0787 or via email at sbirhelp@bytecubed.com