Polarized light inertial rigorous integrated navigation method based on self-learning multi-rate residual correction

Abstract

The invention discloses a polarized light inertial rigorous combined navigation method based on self-learning multi-rate residual error correction. When the polarized light system is working normally, the heading angle output by the inertial navigation system is converted into the orientation of the body axis of the carrier relative to the sun meridian Angle is used as the state quantity, and the azimuth angle of the carrier body axis relative to the sun meridian calculated by the polarized light navigation system is used as the observation quantity, and the CKF-ERC is used to fuse the two data; the time information and z The axial angular rate is used as the input of the long-short-term memory neural network, and the data calculated by the polarized light navigation system is used as the network output, and it is trained to realize the self-learning function; when the polarized light system is not available, it enters the error compensation stage and is predicted by LSTM Polarized light data, and data fusion between the predicted value and the azimuth angle calculated by inertia, to improve the long-term navigation accuracy of the vehicle in complex environments. The invention can effectively improve the autonomy of navigation and orientation, and further improve the intelligence degree of the unmanned aerial vehicle.

Description

technical field [0001] The invention relates to the technical field of deep learning and navigation and positioning, in particular to a polarized light inertial rigorous combined navigation method based on self-learning multi-rate residual correction. Background technique [0002] Inertial Navigation System (INS) has been widely used in military and civilian industries such as aerospace, smart cars, and drones due to its advantages of anti-jamming, high autonomy, and high output efficiency. The existence of cumulative errors has brought about serious divergence of accuracy under long-duration conditions. The polarized light navigation system uses a stable atmospheric polarization mode to achieve carrier heading angle acquisition. It has the advantages of high precision, small size, and no cumulative errors. An emerging way of navigating. However, it is greatly affected by occlusion and rainy weather, so it is difficult to meet the accuracy requirements of the carrier for th...

AI Technical Summary

Problems solved by technology

[0003] Purpose of the invention: In order to solve the problem that the accuracy of the integrated navigation system diverges when the polarized light navigation system is not available and under long-duration working conditions, the present invention provides a polarization based on self-learning multi-rate residual correction Optical-inertial rigorous integrated navigation method

Images