An Adaptive Filter for Land Navigation Using Neural Computing

Mark Dumville and Maria Tsakiri

Abstract:	The Global Positioning System (GPS) is approaching its Full Operational Capabiiity (FOC) and is ideally suited to hecome the principal component in land navigation systems for both tbe personal in-car user and commercial fleet management. Navigation within the urban environment is, however, hampered by problems associated with signal obstruction. To provide a robust system it is necessary to integrate the GPS sensor with other positioning systems. This study has investigated tbe integration of GPS with Dead-Reckoning (DR) sensors. The classical approach of using Kahnan filtering to integrate different systems has been extensively used [1].[2]. In addition. the use of neural computing techniques bas been investigated as an alternative method of integrating both systems. The method relies on the use of an Artificial Neural Network (ANN) to model the dynamics of the vehicle. The ANN is trained through example which can then be used to predict the vehicle’s position when there is loss of tbe GPS signal. Following a theoretical description of hotb approaches of adaptive filtering tbe paper presents results from tests performed with observed data using tbe new approach.
Published in:	Proceedings of the 7th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GPS 1994) September 20 - 23, 1994 Salt Palace Convention Center Salt Lake City, UT
Pages:	1349 - 1356
Cite this article:	Dumville, Mark, Tsakiri, Maria, "An Adaptive Filter for Land Navigation Using Neural Computing," Proceedings of the 7th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GPS 1994), Salt Lake City, UT, September 1994, pp. 1349-1356.
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In