ODETTE - Automated Model Learning and Simulation of Carrier Deck Operations Navy SBIR FY2013.1 Sol No.: Navy SBIR FY2013.1 Topic No.: N131-075 Topic Title: ODETTE - Automated Model Learning and Simulation of Carrier Deck Operations Proposal No.: N131-075-0295 Firm: Aurora Flight Sciences Corporation 9950 Wakeman Drive Manassas, Virginia 20110 Contact: Raghvendra Cowlagi Phone: (617) 229-6810 Web Site: www.aurora.aero Abstract: Unmanned and partially autonomous aerial systems (UAS) and intelligent decision support systems have become integral components of emerging large-scale cyber-physical systems that will be involved in future military operations. Aircraft carrier decks will be central to many such operations involving multiple UAS, traditional piloted aircraft, sensory equipment, and human operators. Aurora Flight Sciences proposes to develop an algorithmic toolkit, called ODETTE (Observation-based Discrete Event Training and Test Environment), for automatically modeling carrier deck operations based on observed traffic flow data. The proposed research will enable analyses and simulations of future carrier deck operations involving new elements such as UAS and autonomous decision support systems. The proposed research is summarized as follows: We will develop a Markov Decision Process model of carrier deck operations, and survey various existing algorithms for learning of unknown state transition relations in MDPs. To address scalability, we will investigate modifications of these algorithms that are incremental and operate in a multi-resolution framework. Finally, we will develop a relatively high-fidelity software simulation of carrier deck operations, including the simulation of various sub-systems and human operators involved. This simulation environment will be used throughout the duration of the proposed research for validation and testing of the model generator. Benefits: The proposed automated carrier deck model generation tool, ODETTE, that will be developed in this program will find applications both in the design phase (for lifecycle simulations) as well the execution phase (for decision support systems) of flight operations similar to carrier decks, involving UAS. Consequently, there is immediate as well as sustained long-term market for this tool. Because such operations are not in common practice currently, and because fundamental questions about the design and development of such operations - such as the evaluation of an operation, which ODETTE will perform - are currently unanswered, the potential market for this tool is a large emerging market, which is a key opportunity that Aurora seeks to capitalize. Aurora foresees significant investments from major DoD agencies, including the Navy, the Army, and the Air Force in the design and deployment of future military operations based on carrier decks or other air bases. In civilian applications, Aurora foresees investments from agencies such as NASA, FAA, and NTSB for the design, deployment, and analysis of future air traffic management systems that will supervise airspace and airport ground operations being shared between piloted aircraft, UAS, and optionally piloted aircraft. Furthermore, several nuclear power plants hundreds of warehouse management systems worldwide will involve a small team of humans supervising large numbers of cooperative mobile robots that perform a majority of the physical tasks. The model generation and simulation tool developed in this program, and adaptations thereof, will be crucial components in all of these military and civilian applications. As previously stated, Aurora will synergistically develop several applications, including tools for safety metrics and prognostic indicators, and training and performance evaluation tools and these products will be commercialized in parallel. Return