Precise real-time positioning with a low cost GPS engine using neural networks

Position information obtained from standard GPS receivers hay time variant errors. To make effective use of GPS information in a navigation system, it is essential to model these errors. In this paper, a new approach is presented for improvement of positioning accuracy using MLP, RBF and RNN neural networks (NNs). The NNs estimate position errors that are used as Differential GPS (DGPS) corrections in real time positioning. Method validity is verified with experimental data from an actual data collection before and after Selective A validity (SA) error The result is a highly effective estimation technique for accurate positioning, so that positioning accuracy is drastically improved to less than 1.10 meters with SA on and 0.70 with SA off The experimental tests results with real data emphasize that total performance of RAIN is better than RBF and MLP considering trade off between accuracy and speed for DGPS corrections prediction.