Government and industry agree on the potential of learning algorithms in providing flight safety in the presence of adverse conditions (resulting from, e.g., degraded modes of operation, loss of…

This federal contract award, valued at $749,937.00, was issued by the National Aeronautics and Space Administration (NASA) to the University of Missouri System, doing business as the Missouri University of Science & Technology (Missouri S&T). The contract, a cooperative agreement, supports research to develop a theoretical framework and necessary conditions for guaranteed flight control safety and resilience in the presence of aircraft adverse conditions using learning algorithms. The goal is to enable learning algorithms to keep aircraft trajectories within a predefined safe flight envelope, even in the face of anomalies. The research will also explore how to leverage these algorithms in pilot decision support systems to indicate aircraft proximity to safe flight boundaries. This work is expected to benefit a range of aerospace applications involving safe and effective aircraft control, crew decision-making, and vehicle control. The contract does not have a set-aside designation.

Government and industry agree on the potential of learning algorithms in providing flight safety in the presence of adverse conditions (resulting from, e.g., degraded modes of operation, loss of control, and imperfect aircraft modeling) and reducing aircraft development costs. A major roadhlock to their widespread adoption is the lack of a-priori, user-deflned performance guarantees to preserve a given safe flight envelope in general and commercial aviation. Current practice relies heavily on excessive flight testing as a means of performing veriflcation and/or development of the tools to validate existing learning algorithms. Besides the cost, the major drawback of excessive flight testing is that IT only provides limited performance guarantees for what was tested; the flxed set of initial conditions, pilot commands, and failure profiles. The drawback of current tools to validate existing learning algorithms is that such tools can only provide guarantees if there exists a-priori and complete structural and behavioral knowledge regarding any and all anomalies that might occur. The proposed research will address this fundamental GAP in the utilization of learning algorithms for aerospace applications by (1) establishing a new theoretical framework along with necessary and sufflcient conditions for guaranteed flight control safety and resilience in the presence of aircraft adverse conditions. Learning algorithms developed using this framework will keep the aircraft trajectories within this a-priori determined envelope (set) in the presence of anomalies. Analytical expressions for robustness margins of the proposed algorithms will also be developed. (2) methods will be developed to use these algorithms effectively in the pilot decision support display of NASA ames that indicates the proximity of the aircraft to safe flight boundaries caused by adverse conditions. As a complementary effort to flight control, a set theoretic learning approach will be utilized in estimation theory to support of pilot decision-making via providing real-time aircraft flight health and prediction. (3) the proposed algorithms will be demonstrated in flight tests using CJ-144 fly-by-wire bonanza aircraft. This research direction WUL allow the investigators to revisit the proposed theoretical approaches and relax assumptions, if necessary. The novel feature of this research is that the proposed algorithms will have the capability to preserve a given, user-deflned safe flight envelope through formal analytical synthesis at the pre-design stage, instead of excessive flight testing during the post-design stage. The proposed research will (1) impact a broad range of applications utilizing learning algorithms that involve but are not limited to safe and effective aircraft control, crew decision-making in complex situations, and CEV/CLV vehicle control, (2) make the general and commercial aviation community aware of the safety beneflts of advanced adaptive flight control and estimation methods, (3)disseminate NASA and DOD research into the aviation community, (4) establish a new partnership between flight controls research at MST and WSU, (5) increase the ability of researchers and industries in the states of MO and KS to successfully compete for research funding, (6) give the MO and KS aviation industry a global leading role in using intelligent aviation technologies on civil aviation aircraft, and (7) contribute to the advanced workforce by educating students in advanced flight controls and pilot warning systems. The research outcomes, which include advancement ofthe theory on veriflable learning algorithms for flight control and pilot awareness systems, simulations at multiple levels of granularity, data collected from ground and flight testing, publications in highly regarded journals and conferences, online seminars, an invited session, and a workshop, will signiflcantly contribute to the current and future NASA research and technology priorities.