An Augmented Wavelet - Neuro-Fuzzy Module for Enhancing MEMS based Navigation Systems

Low cost navigation systems relying on gyroscopes and accelerometers manufactured using micro electro-mechanical system (MEMS) technology have been recently utilized in land vehicles. These MEMS-based sensors are integrated with GPS to provide reliable positioning solutions in case of GPS outages that commonly occur in urban areas. The major inadequacies of MEMS-based navigation sensors are the high noise level and the large bias instabilities that are stochastic in nature. The effects of these inadequacies manifest themselves as large position errors during GPS outages. This research proposes the utilization of wavelet denoising to improve the signal-to-noise ratio of each of the MEMS-based sensors. In addition a neuro-fuzzy module is used to provide a reliable prediction of the vehicle position during GPS outages. The results from a road test experiment show the effectiveness of the proposed wavelet - neuro-fuzzy module.