Nonparametric Method for Predicting the Trajectory of an Actively Maneuvering Vessel for Unmanned Aerial Vehicle Landing
The article is devoted to the development of algorithms for predicting the trajectory of maneuvering objects based on nonparametric systems theory. The analysis of uncertainties affecting the modeling of the movement maneuvering water objects is presented. An overview of parametric, nonparametric and combined methods for predicting maneuvering water objects trajectory is given. The problem of high-precision autonomous control of the landing unmanned aerial vehicles on the landing vessel in the conditions of its irregular movement caused by meteorological conditions and active maneuvering is being solved. The method for predicting the trajectory of a vessel’s movement based on solving direct problems of dynamics using nonparametric systems theory is proposed. The advantages of the proposed method are that it’s not affected by model errors, due to the fact that it is based only on a retrospective analysis of several consecutive values of the spatial vessel coordinates. The proposed method differs from similar nonparametric methods in that it does not require statistical calculations, own training, or time-consuming tuning. The method does not imply the solution of identification model parameters, state and control actions problems and can be applied with any unknown linearizable input control actions, including when the model of the vessel’s motion dynamics is not identifiable. The results of numerical modeling for solution the problem of predicting the trajectory of an actively maneuvering small-sized landing vessel using a full nonlinear dynamic model with six degrees of freedom are presented. The studies carried out confirm the efficiency, adequacy and very fast adjustment of the developed method under conditions of complete parametric and nonparametric uncertainty. The proposed method can be used to predict the trajectory of any vehicle under the condition of linearizability of its model and control signals over the observed time interval.