Data Science Techniques for Various Mission Planning Processes and Performance Validation
Navy STTR 2019.B - Topic N19B-T029
NAVAIR - Ms. Donna Attick - email@example.com
Opens: May 31, 2019 - Closes: July 1, 2019 (8:00 PM ET)
TECHNOLOGY AREA(S): Battlespace, Information Systems, Weapons ACQUISITION PROGRAM: PMA281 (UAS) Strike Planning & Execution Systems
OBJECTIVE: Develop an Artificial Intelligence (AI) and Machine Learning (ML) based Mission Planner and Management technology that is based on initial analysis of various mission plans to determine where and how AI techniques could significantly benefit the mission planning and management process, including how to validate and verify autonomous performance.
DESCRIPTION: The National Defense strategy states, “The Department will invest broadly in military application of autonomy, artificial intelligence, and machine learning, including rapid application of commercial breakthroughs, to gain competitive military advantages.” [Ref 4] This topic is clearly aligned with this statement as it seeks to exploit the promising advantages of AI and ML in mission planning. The current Joint Mission Planning System (JMPS) mission planning process may be best described as a hybrid planning activity (i.e., partially accomplished manually by mission planners/pilots and partially accomplished through an automated process). To gain familiarity Reference 1 describes a basic mission planning process. There are a variety of mission types (e.g., Strike, Intelligence Surveillance and Reconnaissance (ISR), manned and unmanned teaming (MUM-T), Multi-Domain Missions (MDM), Close Air Support (CAS), Naval Integrated Fire Control-Counter Air (NIFC-CA)). Each type has unique mission planning components but there are many facets of the planning process that are common to each mission type. These areas should be candidates for automation using AI and ML techniques. In the near future, mission planning will include multi domains that will include air, maritime, land, and space. Many current AI applications focus on human-centric processes. Thus, since part of mission planning is a human-centric activity,
increasing the potential for errors. AI technologies would provide tremendous benefit. This effort should determine a method to leverage advantages of AI and ML (to name two of the most often cited, speed and accuracy) and apply it within the mission planning process. Besides defining how to apply AI, the project will also address how to verify and validate the performance of the mission planning with AI, (i.e., what development/technique is necessary to provide planners assurance that the results of AI-generated plans are realistic and/or improved when compared to current planning processes).
In addition, aligned with the overall planning process there are two security concerns that will have to be addressed: one being multi-level security due to the fact that some planning data/information is classified at different classification levels; and the other focusing on the highly critical need to protect software and information, thus requiring the need to embed cyber security measures [Refs 9 & 10] Both security concerns should be able to be resolved with AI techniques and should seamlessly and transparently be integrated in the overall planning process.
The final step is to simulate mission plans (perhaps not as detailed as described in Reference 4, but somewhat similar) and potentially show how to improve the planning process through ML.
Note: It is anticipated that proposers to the topic have some understanding of the mission planning process (relevant mission planning documentation will be made available in Phase I that includes descriptions of different scenarios and software) and should be highly experienced with the development and transition of AI and ML technology, relating to the current state-of-the-art AI and ongoing research as it may be applicable to this topic.
PHASE I: Determine and identify where and how within the mission planning process AI can make the most significant impact to the process and develop a concept to simulate the overall mission plan with AI and ML. Define a conceptual AI-based planning process that includes multi-level security and cyber security. The Phase I effort will include prototype plans to be developed under Phase II.
PHASE II: Develop a prototype based on the results of Phase I and demonstrate the capability to verify and validate the mission plan performance with embedded AI. Generate simulated mission plans based on actual Air Tasking Orders. Additionally, show if AI can achieve / identify further improvements in the planning process via self- learning capability. Also address feasibility of dynamic real-time mission replanning during mission execution.
PHASE III DUAL USE APPLICATIONS: Finalize the complete AI/ML based mission planning capability and conduct operational testing. Transition technology to a next generation of JMPS and other services in support of mission planning processes. The development will benefit manned / unmanned mission planning that supports commercial delivery companies, especially addressing those that deliver via Unmanned Systems such as Amazon, United Parcel Service, and other organizations and companies that employ Unmanned Air Vehicles as part of their business (e.g., land management).
1. Menner, W.A. “The Navy’s Tactical Aircraft Strike Planning Process." Johns Hopkins APL Technical Digest, Vol. 18, No.1, 1997. www.jhuapl.edu/techdigest/TD/td1801/menner.pdf
2. Boukhtouta, A., Bedrouni, A., Berger, J., Bouak, F., and Guitouni, A. “A Survey of Military Planning Systems." Defence Research and Development Canada-Toronto: Toronto, Ontario Canada. www.dodccrp.org/events/9th_ICCRTS/CD/papers/096.pdf
3. Strong, B.D. "Simulate Tomorrow's Battle with AI." Proceedings Magazine, February 2018, Vol. 144/2/1,380. https://www.usni.org/magazines/proceedings/2018-02/simulate-tomorrow%E2%80%99s-battles-ai
4. "Summary of the 2018 National Defense Strategy of the United States of America." https://www.defense.gov/Portals/1/Documents/pubs/2018-National-Defense-Strategy-Summary.pdf
5. Broadway, C. “DoD Official Highlights Value of Artificial Intelligence to Future Warfare." DoD News, Defense Media Activity, April 9, 2018. https://www.defense.gov/News/Article/Article/1488660/dod-official-highlights- value-of-artificial-intelligence-to-future-warfare/
6. Cummings, M.L. “Artificial Intelligence and the Future of Warfare." Research Paper, International Security Department and US and the Americas Programme, January 2017.
Chatham House, The Royal Institute of International Affairs. https://www.chathamhouse.org/sites/files/chathamhouse/publications/research/2017-01-26-artificial-intelligence- future-warfare-cummings-final.pdf
7. Joint Mission Planning System _Air Force (JMPS-AF). Air Force Programs, pp. 235-236. http://www.dote.osd.mil/pub/reports/FY2011/pdf/af/2011jmps-af.pdf
8. Tian, Z., Wei, Z., Yaoping, L., and Xianjun, P. "Overview on Mission Planning System." International Journal of Knowledge Engineering, Vol. 2, No. 1, March 2016. http://www.ijke.org/vol2/52-CQ3048.pdf
9. Davis, S., “Navy Finalizes 8 Cyber Security Standards, Now Available to Industry,” Space and Naval Warfare Systems Command Public Affairs, 2/17/2016, https://www.navy.mil/submit/display.asp?story_id=93151
10. National Institute of Standards and Technology (NIST) Information Technology Cybersecurity, https://www.nist.gov/topics/cybersecurity
KEYWORDS: Artificial Intelligence; Machine Learning; Multi-Platform Planning; Manned-Unmanned Teaming; Joint Mission Planning System; Naval Open Mission System