Unmanned aerial vehicle landing pose filtering estimation method and system based on visual anchor points

Abstract

The invention discloses an unmanned aerial vehicle landing pose filtering estimation method and system based on a visual anchor point. According to the invention, an unmanned aerial vehicle pose estimation extended Kalman filtering model is constructed based on visual anchor point measurement for the spatial position and attitude estimation demands in the landing process of an unmanned aerial vehicle, and through an extended Kalman filter theory, the optimal estimation of the pose of the unmanned aerial vehicle under the minimum error two-norm quadratic sum index is realized, the influence ofthe observation error of the ground-based vision on the pose estimation accuracy of the unmanned aerial vehicle in the landing process is effectively reduced, and the pose estimation accuracy and robustness in the landing process of the unmanned aerial vehicle are greatly improved compared with the traditional method.

Description

technical field [0001] The invention relates to the technical field of autonomous landing of drones, in particular to a method and system for filtering and estimating the landing pose of drones based on visual anchor points. Background technique [0002] In the process of autonomous take-off and landing of UAVs, combining the onboard global positioning system and inertial navigation system to achieve real-time acquisition of the UAV's own position and attitude is the main means for current UAVs to perceive their own state. Considering that factors such as magnetic field and temperature in the environment are likely to cause interference to the airborne positioning system, during the entire landing process of the UAV, relying only on the onboard positioning system cannot guarantee to provide stable and accurate position information for the UAV. Using the ground-based monocular vision system to observe the landing process of the drone, computer vision technology can be used to...

AI Technical Summary

Problems solved by technology

[0003] The present invention provides a method and system for filtering and estimating UAV landing position and attitude based on visual anchor points, which are used to overcome the defects of low precision, strong robustness and poor robustness in the prior art.

Images