TECHNOLOGY AREA(S): Air Platform, Battlespace, Weapons

ACQUISITION PROGRAM: PMA 281 (UAS) Strike Planning & Execution Systems

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 5.4.c.(8) 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: Develop an approach to exploit artificial intelligence (AI) and machine learning (ML) techniques (e.g., deep learning [DL]) to improve mission planning capability, and to provide autonomous and dynamic mission and strike planning capabilities in support of manned and unmanned vehicles and weapon systems.

DESCRIPTION: AI, and various versions of ML, have been applied to many fields such as cancer research, complex games like Jeopardy, Poker, and GO, and more recently heart attack prediction with great success [Ref 8].  These techniques have begun to be investigated and researched related to the topic of mission planning, as discussed at a recent conference, Tactical Advancement for the Next Generation (TANG).  This SBIR topic seeks to demonstrate how AI and ML can be applied to multi-vehicle, multi-domain mission planning.  Mission and strike planning are complex processes, integrating specific performance characteristics for each platform into a comprehensive mission.  The Joint Mission Planning System (JMPS), a software application, consists of a basic framework and unique mission planning environment software packages for each platform.  To fully appreciate the overall complexity, a basic understanding of the planning (operational and tactical) process workflow as well as the actual human involvement in the mission planning process is necessary.  The result of this project will provide the foundation of how to train the computer and exploit AI capabilities to generate automatic mission and strike plans for multi-vehicle, multi domain scenarios involving manned and unmanned systems.  The developer should also consider how to deal with different levels of security classifications in ingestion of data for training and subsequently in generating mission and strike plans, to include shared plan representation, adaptive coordination and interoperability.

Note: To understand the JMPS functionality and appreciate the complexity of the JMPS software and to support the objective of the topic, Government will provide companies awarded a Phase I contract a current version of the software and source code with embedded help files and JMPS Concept of Operation (CONOPS) and Use Cases document.

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 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 NAVAIR 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: Define and develop a concept for how AI and DL/ML will be applied to the mission and strike planning process as well as dynamic re-planning.  Identify what type of processing power is needed for a representative computing environment. Determine, when employing AI and ML, the level of improvement in the mission and strike planning process and in mission planner performance, and how AI and ML would generate mission plans in a near-autonomous mode, given the current workflow.  The Phase I effort will include prototype plans to be developed under Phase II.

PHASE II: Develop a prototype approach based on the Phase I concept using available commercial off-the-shelf (COTS) computing environment.

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: Test the developed technology in simulated mission environment and determine if and how much of the prototype is ready for integration into JMPS.  Based upon that information, continue working on the prototype with the ultimate goal toward the nearly full autonomous mission and strike planning operation.

AI and ML are used by many companies in various applications ranging from big data analysis to economics to investment and cancer research, just to name a few.  The results of this project should benefit various companies that deal with parcel delivery such as Amazon, UPS, FedEx, and others by potentially generating autonomous mission plans—in this case optimized delivery plans for either multiple ground and air vehicles.  Another field that could benefit from this technology is traffic engineering, providing a more adaptive approach to traffic control based on various traffic conditions.

REFERENCES:

1. Chen, K. "Watson claims to predict cancer, but who trained it to 'think?'" Recode, August 16, 2016. http://www.recode.net/2016/8/16/12490110/watson-artificial-intelligence-machine-learning-cancer-prediction-human-input

2. Hof, R. D. "Deep Learning." MIT Technology Review. https://www.technologyreview.com/s/513696/deep-learning/

3. Parloff, R. "Why Deep Learning Is Suddenly Changing Your Life." Fortune, September 28, 2016. http://fortune.com/ai-artificial-intelligence-deep-machine-learning/

4. Noyes, K. "5 things you need to know about A.I.: Cognitive, neural and deep, oh my!" Computer World, March 3, 2016. http://www.computerworld.com/article/3040563/enterprise-applications/5-things-you-need-to-know-about-ai-cognitive-neural-and-deep-oh-my.html

5. "Summer Study on Autonomy." Defense Science Board, June 2016, http://www.acq.osd.mil/dsb/reports/2010s/DSBSS15.pdf?zoom_highlight=Autonomy

6. "The Role of Autonomy in DoD Systems." Defense Science Board Task Force Report, July 2012, http://fas.org/irp/agency/dod/dsb/autonomy.pdf

7. “Watson,” IBM website. http://www.ibm.com/watson/

8. Hutson, M. "Self-taught artificial intelligence beats doctors at predicting heart attacks." Science Magazine, 14 April 2017. http://www.sciencemag.org/news/2017/04/self-taught-artificial-intelligence-beats-doctors-predicting-heart-attacks

KEYWORDS: Artificial Intelligence; Machine Learning; Mission and Strike Planning; Multi-Vehicle; Multi-Domain; Autonomous