Inertial navigation positioning method and system based on attitude dynamics and neural network

Abstract

This application relates to the field of navigation and positioning technology, and in particular to an inertial navigation and positioning method and system based on attitude dynamics and neural networks. The method includes determining the initial coordinates of a target person; acquiring the target person's attitude data in real time to obtain corrected attitude data; inputting the corrected attitude data into a preset neural network model, which includes a noise suppression module and a predictive correction module. The noise suppression module outputs noise-suppressed attitude data; the predictive correction module obtains the final attitude data; and combining the initial coordinates of the target person, mapping the final attitude data obtained at each moment to a global coordinate system to generate continuous three-dimensional spatial position points and form the complete motion trajectory of the target person. This application can accurately and continuously generate the positioning trajectory of a target person in a ship scenario.

Images