An Adaptive Neuro-Fuzzy Model for Bridging GPS Outages in MEMS-IMU/GPS Land Vehicle Navigation

Naser El-Sheimy, Walid Abdel-Hamid and Gérard Lachapelle

Abstract:	Kalman filter (KF) represents one of the best estimation techniques for integrating signals from short-term high performance systems, like inertial navigation systems (INS), with reference systems exhibiting long-term stability, like the Global Positioning System (GPS). However, KF only works well under appropriately predefined linear dynamic error models and input data that fit this model. The latter condition is rather difficult to be fulfilled by a low-cost Inertial Measurement Unit (IMU) utilizing micro-electro-mechanical-system (MEMS) sensors due to the significance of their longterm and short-term errors that are mixed with the motion dynamics. As a result, if the reference GPS signals are absent or the Kalman filter is working for a long time in the prediction mode, the corresponding state estimate will quickly drift with time causing a dramatic degradation in the overall accuracy of the integrated system. A new design model for navigation applications using adaptive neuro-fuzzy inference systems (ANFIS) is proposed in this paper to bridge periods of GPS signal blockage. The proposed model uses Neuro-fuzzy networks and the input/output patterns to train the fuzzy network during the availability of GPS solutions (which are used as a reference trajectory). During GPS signal blockage, the trained fuzzy model is implemented to predict the error drift of the standalone MEMS-INS estimated position. Performance of the suggested model was compared to that of the traditional KF particularly during a number of simulated GPS outages. The test results indicate that the proposed neuro-fuzzy model can efficiently predict the INS errors during GPS outages.
Published in:	Proceedings of the 17th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS 2004) September 21 - 24, 2004 Long Beach Convention Center Long Beach, CA
Pages:	1088 - 1095
Cite this article:	El-Sheimy, Naser, Abdel-Hamid, Walid, Lachapelle, Gérard, "An Adaptive Neuro-Fuzzy Model for Bridging GPS Outages in MEMS-IMU/GPS Land Vehicle Navigation," Proceedings of the 17th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS 2004), Long Beach, CA, September 2004, pp. 1088-1095.
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In