Performance Improvement of a Low-Cost Gyro-Free INS for Land Vehicle Navigation by Using Constrained Navigation Algorithm and Neural Network

J-H. Wang, Y. Gao

Abstract:	The development of low-cost solutions to fill the gaps during GPS outage for land vehicle navigation is increasingly demanded by the industry. A gyro-free inertial navigation system without accumulated attitude errors and complicated initializations could be an effective solution. This paper has investigated the error behaviors of the measurements used in the system and has proposed a method which applies a Constrained Navigation Algorithm (CNA) and the Artificial Neural Network (ANN) technique to improve the performance of a low-cost gyro-free navigation system. The CAN constrains the vehicle's velocity in the forward direction to be compensated by pre-trained neural network. The vehicle's heading is to be calibrated so that the magnetometer's bias and scale factor error could be removed. The test results show that the position accuracy of the low-cost gyro-free INS has been significantly improved and its navigation solution can be used to assist GPS for land vehicular navigation if the GPS outage is less than 30 seconds.
Published in:	Proceedings of the 16th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GPS/GNSS 2003) September 9 - 12, 2003 Oregon Convention Center Portland, OR
Pages:	762 - 768
Cite this article:	Wang, J-H., Gao, Y., "Performance Improvement of a Low-Cost Gyro-Free INS for Land Vehicle Navigation by Using Constrained Navigation Algorithm and Neural Network," Proceedings of the 16th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GPS/GNSS 2003), Portland, OR, September 2003, pp. 762-768.
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In