Envelope Protection in Autonomous Unmanned Aerial Vehicles

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.