Optical flow-based angular rate sensor fault detection on UAVs

The paper first extends the previous work of the authors dealing with optical flow-based angular rate estimation. Extension means consideration of camera position and orientation relative to the UAV body system (non-aligned camera). After the extension the proposed method is evaluated with virtual reality (Unreal-Carla) image sequences considering simulated aircraft flight trajectories and different frames per second (fps) rates. Based-on the results showing high fps requirements for agile flight scenarios a reversed method is proposed for angular rate sensor fault detection considering the integration of system dynamics based-on angular rate and velocity measurements and comparing the predicted image feature positions with the measured ones. The feature position differences are the error measures completed with up-down counters. The results are promising however, only basic evaluation of the proposed methods is done paving the way for detailed evaluation and development outlined in the conclusion. Copyright (C) 2022 The Authors. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)