UAV Autonomous Landing Technology Based on AprilTags Vision Positioning Algorithm

The issue of the autonomous landing of the quadrotor unmanned aerial vehicle (UAV) has become a hot topic in recent years. How to improve the positioning accuracy of autonomous landing, reduce the calculation time, and improve the dynamic tracking effect are all problems that need to be solved. In this paper, an onboard solution to the tracking and landing problems of UAV and ground vehicle is presented. The AprilTags visual positioning algorithm based on monocular camera is used to locate and estimate the UAV's states. The platform used for UAV landing is labeled with different size of tags so that the drone can get good positioning accuracy at different heights. Combined with the PID control algorithm, the performance of dynamic tracking is improved. The experimental results show that the proposed method has good positioning accuracy and fast calculation speed.