This paper details the application of an adaptive neural network based limit detection and avoidance algorithm for envelope protection on the autonomous Yamaha R-Max unmanned helicopter test bed. Software-in-the-loop and flight test results are presented. The envelope protection system is implemented as a mid-level controller component into the unmanned helicopter software infrastructure, called the Open Control Platform (OCP). The method utilizes an observer type adaptive neural network loop for the estimation of limit parameter dynamics. The constructed model is then used to predict dynamic trim response and corresponding command margins. Standard sensor measurements are used in the adaptation process and no off-line training of the networks is necessary. The command margin information is used to avoid prescribed limits.
This paper presents the development and flight test evaluation of a reactionary envelope protection method suitable for limit protection in uninhabited aerial vehicles (UAVs). The method is based on finite-time horizon predictions of limit parameter response for detecting any impending limit boundary violations. Limit violations are prevented by treating limit boundaries as obstacles and by correcting nominal control/command inputs to track safe-response profiles of limit parameters near the limit boundaries. The method is first evaluated in simulations using the Georgia Tech UAV simulation tool (GUST) for the load factor limit protection. The load factor limit protection system is then evaluated using flight tests on the Georgia Tech unmanned rotorcraft vehicle (GTMax UAV) at Georgia Tech. The flight test results show that the reactionary load factor limit protection system is successful at maintaining the vehicle load factor response within prescribed upper limit while executing an aggressive e-turn maneuver.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.