FLIGHT PHASE CLASSIFICATION FOR SMALL UNMANNED AERIAL VEHICLES

This article describes research on the classification of flight phases using a fuzzy inference system and an artificial neural network. The aim was to identify small set input parameters that would ensure correct phase simple classifier, meaning network with low number neurons rule base. done created classifier could be implemented in control units limited computational power affordable UAVs. functionality designed validated by several experimental flights fixed-wing UAV. To evaluate validity proposed system, special maneuvers performed during test flights. It found even feedforward classify basic very high accuracy three parameters.