A FIR filter assisted with the predictive model and ELM integrated for UWB-based quadrotor aircraft localization

Abstract

To improve the accuracy of the Ultra-Wide Band (UWB) based quadrotor aircraft localization, a Finite Impulse Response (FIR) filter aided with an integration of the predictive model and Extreme Learning Machine (ELM) is proposed in this work. The FIR filter estimates the quad-rotor aircraft ’s position by fusing the positions measured with the UWB and Inertial Navigation System respectively. When the UWB dada are unavailable, both the ELM and the predictive model are used to provide the measurements, replacing those unavailable UWB data, for the FIR filter. The ELM estimates the measurement via the mapping between the one step prediction of state vector and the measurement built when the UWB data are available. For the predictive model, we mathematically describe the missing UWB data. Then, both the measurements estimated with the ELM and predictive model are employed to estimate the observations via Mahalanobis distance. The test results show that the FIR filter aided by the predictive model/ELM integrated can reduce the Cumulative Distribution Function and position Root Mean Square Error effectively when the UWB is unavailable. Compared with the ELM assisted FIR filter, the proposed FIR filter can reduce the localization error by about 48.59 %, meanwhile, the integrated method is close to the method with a better solution.Graphical