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.
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.