Develop and Apply Artificial Intelligence and Machine Learning Techniques for Next-Generation Mission Planning
Navy SBIR FY2018.1


Sol No.: Navy SBIR FY2018.1
Topic No.: N181-018
Topic Title: Develop and Apply Artificial Intelligence and Machine Learning Techniques for Next-Generation Mission Planning
Proposal No.: N181-018-0906
Firm: GBL Systems Corporation
760 Paseo Camarillo
Suite 401
Camarillo, California 93010
Contact: Jason Laver
Phone: (805) 987-4345
Web Site: http://www.gblsys.com
Abstract: GBL proposes the Rapid Artificially Intelligent Strike Mission Planner (RASP) to develop a layered technology approach that allows for the application of Machine Learning to this complex mission/strike planning domain. The integration of RASP with JMPS will provide a foundation for implementing Artificially Intelligent Mission Planning techniques that learn from prior mission experience/data. GBL proposes to utilize its NO4-174 EA-18G Electronic Combat Automation SBIR technologies called Electronic Combat Decision Support System as a core technology that will be leveraged. RASP will provide a Distributed Intelligent Agent-based framework (DAI) to automate development of platform mission plans. The Agent-based framework implements a publish and subscribe message system to allow for collaborative and concurrent planning amongst multiple mission planning teams across security levels while minimizing the face-to-face communication that slows the mission planning process. The decentralized capability of RASP will reduce mission planning time by allowing multiple users to simultaneously plan their role in a mission vice the waterfall method of planning that is often practiced today. The intelligent agents will communicate planning information amongst necessary users to help improve the mission planning workflow and ultimately reduce the overall time and improve automation of mission planning for multi-vehicle strike mission platforms.
Benefits: Artificial Intelligent (AI) Multiple Agent Systems (MAS) have been studied and advocated by various DoD factions for all future weapon system development efforts. The current market for automated intelligent learning planning systems for complex environments is large and forecast to rapidly grow as the DoD recognizes new and legacy systems that can be upgraded to be active participants various planning environments. RASP has an additional market in the near future with non-DoD companies as the agent-based approach is more widely adopted by the DoD. The GBL Team will therefore focus early marketing on the Navy programs based on their expressed need for improved coordinated operations in an increasingly complex battlefield including cross service and cross-national forces. This same functionality will transfer directly to robot reconnaissance used in boarder control and �?~swarm�?T tactics in homeland security operations. Adaptation of the airborne RASP agents to commercial airlines for navigation and communication aircrew aids as well as self-protection against man held surface to air missiles involves only minor modifications and can lead directly to unaided air traffic control and coordinated multi-vehicle operations. By transporting the basic RASP elements into a space qualified platform additional markets including satellite and extraterrestrial explorer �?~swarm�?T tactics can be pursued. Additional markets that will be explored during the Phase 1 development are to sell / license our RASP to or through Value Added Reseller (VAR) agreements to MAS development companies. There is the additional revenue stream of re-configuring components of the RASP for various Army, Marine, Navy, and Air Force unique requirements.

Return