Cross Validation of Sensor Inputs as Part of Position Estimation for Urban Air Mobility

Large scale networks of redundant ground nodes with heterogeneous sensors need some form of cross validation to determine which measurements are most trustworthy. One way to do this is residual based, by evaluating the residual between real measurements and ‘estimated measurements’ based on the estimated position. These residuals are an indicator of the reliability of the individual ground nodes which varies in time. One of the possible methods is based on the hierarchical mixture of experts (HME) and is discussed in this paper. This info can later be used in the Kalman Filter to improve performance (this is future work and not part of this paper).