Pose estimation system and method for visual carrier landing navigation on mobile platform

Abstract

The invention belongs to unmanned aerial vehicle autonomous carrier landing field, and in particular relates to a pose estimation system and method for visual carrier landing navigation on mobile platform. The system and method can resolve the pose information of a moving ship relative to a UAV on a real-time basis through treatment of a collaborative landmark, have the advantages of small amount of calculation in the algorithm, good real-time property, and simple implementation, and provides a premise for safe landing of the UAV. The method uses a camera as a main sensor to reduce development costs and shorten the development cycle.

Description

technical field [0001] The invention belongs to the field of unmanned aerial vehicle autonomous landing, and in particular relates to a pose estimation system and method for visual landing navigation on a mobile platform. Background technique [0002] The autonomous landing capability of UAV is the core part of autonomous flight capability. In the existing landing navigation method, inertial navigation needs to obtain the approximate position and speed information of the aircraft through integral calculation, so that the error will continue to increase over time; GPS (Global Positioning System) satellite navigation is susceptible to electronic interference; INS The / GPS (INS: Inertial Navigation System) integrated navigation system can only locate its own position and orientation information. If it lands at a specific location, even if the longitude and latitude of the landing point are known in advance, it is difficult to guarantee the accuracy of the landing. When it is n...

AI Technical Summary

Problems solved by technology

In the existing landing navigation method, inertial navigation needs to obtain the approximate position and speed information of the aircraft through integral calculation, so that the error will continue to increase over time; GPS (Global Positioning System) satellite navigation is susceptible to electronic interference; INS The / GPS (INS: Inertial Navigation System) integrated navigation system can only locate its own position and orientation information. If it lands at a specific location, it is difficult to guarantee the accuracy of the landing even if the longitude and latitude of the landing point are known in advance.

When it is necessary to implement autonomous landing on a mobile platform, unless the real-time attitude and position information of the platform can be obtained, the landing task cannot be completed

It can be seen that using the INS / GPS integrated navigation system alone cannot provide the navigation information required for the drone to land autonomously.

[0003] The existing computer vision-based landing navigation technology mainly solves the problem of UAV landing on a stationary platform, and rarely involves the landing problem on a mobile platform; and for the acquisition of all three-dimensional pose information, the existing technology generally uses Binocular stereo vision performs three-dimensional reconstruction of the scene to obtain the pose information of the target. The binocular stereo vision method can handle most of the scenes, but the depth information obtained after reconstruction may have depth loss, which leads to inaccurate calculation of pose information. Complete or wrong; at the same time, the 3D reconstruction based on binocular vision has a large amount of calculation, and the real-time performance is not good

Images