A Neural Network Aided Adaptive Kalman Filtering Approach for GPS Navigation

D-J. Jwo, H-C. Huang, J. Huang

Abstract:	The Kalman filter, when employed in the GPS receiver as the navigation state estimator, provides optimal solutions if the noise statistics for the measurement and system are completely known. In practice, the noises are varying with time, which results in performance degrading. Covariance matching is a conventional adaptive approach for estimation of noise covariance matrices. The technique attempts to make the filter residuals consistent with their theoretical covariance. However, this innovation-based adaptive estimation shows noisy result if the window size is small. To overcome the problem, a multilayered neural network is trained to identify the measurement noise covariance matrix, in which the back-propagation algorithm is employed to iteratively adjust the link weights using the steepest descent technique. Numerical simulations show that the performance based on the proposed approach is substantially improved.
Published in:	Proceedings of the 16th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GPS/GNSS 2003) September 9 - 12, 2003 Oregon Convention Center Portland, OR
Pages:	1240 - 1247
Cite this article:	Jwo, D-J., Huang, H-C., Huang, J., "A Neural Network Aided Adaptive Kalman Filtering Approach for GPS Navigation," Proceedings of the 16th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GPS/GNSS 2003), Portland, OR, September 2003, pp. 1240-1247.
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In