Online DGPS Correction Prediction using Recurrent Neural Networks with Unscented Kalman filter
نویسنده
چکیده
This paper focuses on applying a neural network model to predict pseudorange corrections (PRC) for differential Global Positioning System (DGPS). The class of nonlinear autoregressive recurrent neural networks is chosen as the basic architecture. The neural networks are trained by an unscented Kalman filter due to its powerful capabilities for online parameters estimation. The paper first briefly introduces GPS and DGPS navigation performance principles. Following the discussion of temporal characteristics of the DGPS pseudorange corrections, a technique for predicting the DGPS corrections based on recurrent multilayer perceptrons with an unscented Kalman filter is presented. With a given set of data, the unscented Kalman trained networks can online predict the PRC precisely when the PRC signal is lost for a short period of time.
منابع مشابه
Prediction of Dynamical Systems by Recurrent Neural Networks
Recurrent neural networks in general achieve better results in prediction of time series then feedforward networks. Echo state neural networks seem to be one alternative to them. I have shown on the task of text correction, that they achieve slightly better results compared to already known method based on Markov model. The major part of this work is focused on alternatives to recurrent neural ...
متن کاملDoppler and bearing tracking using fuzzy adaptive unscented Kalman filter
The topic of Doppler and Bearing Tracking (DBT) problem is to achieve a target trajectory using the Doppler and Bearing measurements. The difficulty of DBT problem comes from the nonlinearity terms exposed in the measurement equations. Several techniques were studied to deal with this topic, such as the unscented Kalman filter. Nevertheless, the performance of the filter depends directly on the...
متن کاملRecurrent Neural Network Training with the Extended Kalman Filter
Recurrent neural networks, in contrast to the classical feedforward neural networks, better handle inputs that have spacetime structure, e.g. symbolic time series. Since the classic gradient methods for recurrent neural network training on longer input sequences converge very poorly and slowly, the alternative approaches are needed. We describe the principles of the training method with the Ext...
متن کاملOnline Symbolic-Sequence Prediction with Discrete-Time Recurrent Neural Networks
This paper studies the use of discrete-time recurrent neural networks for predicting the next symbol in a sequence. The focus is on online prediction, a task much harder than the classical offline grammatical inference with neural networks. The results obtained show that the performance of recurrent networks working online is acceptable when sequences come from finite-state machines or even fro...
متن کاملOnline Symbolic-Sequence Prediction with Recurrent Neural Networks
This paper studies the use of recurrent neural networks for predicting the next symbol in a sequence. The focus is on online prediction, a task much harder than the classical offline grammatical inference with neural networks. Different kinds of sequence sources are considered: finitestate machines, chaotic sources, and texts in human language. Two algorithms are used for network training: real...
متن کامل