Neural-network-aided Federated Filtering Technique in Integrated Navigation SystemReport as inadecuate




Neural-network-aided Federated Filtering Technique in Integrated Navigation System - Download this document for free, or read online. Document in PDF available to download.

The classical Kalman filter assumes that the statistical properties of the noise in dynamic model and observation system are exactly known, yet the noise in integrated system is uncertain. This leads to a poor adaptive capability for the classical Kalman filter. A method of incorporating a RBF neural network into a adaptive federated Kalman filter is proposed for the INS-GPS-DVL integrated navigation system. This method combines the estimation capability of the adaptive Kalman filter and the learning capability of the RBF neural network, thus resulting in improved adaptive capability and estimation accuracy. Simulation results show improvement in the navigation accuracy for this integrated navigation system.

KEYWORDS

integrated navigation; RBF neural network; federated filtering; adaptivity; navigation accuracy

Cite this paper







Author: Changsong Yang, Wang Qi, Zijia Zhang, Yuanli Li

Source: http://www.scirp.org/



DOWNLOAD PDF




Related documents