A system and method for intelligent tracking flight of unmanned aerial vehicle

Abstract

The invention relates to the field of intelligent autonomous navigation of unmanned aerial vehicles, in particular to an intelligent tracking flight system and method of unmanned aerial vehicles. The flight system includes an image acquisition unit for image acquisition and a flight attitude measurement for detecting flight inertia unit, a neural network processing unit for neural network processing, and a control unit for controlling the flight action of the UAV, and the image collected by the camera in front of the UAV is used as the input, and the input is recognized by the convolutional neural network. Do not, and give obstacle avoidance strategies. During the flight, a flight attitude measurement unit based on the tunnel magnetoresistance effect with high sensitivity characteristics is adopted, and the key position of the change of the flight attitude of the UAV is obtained through the flight attitude measurement unit, and the image acquisition unit is activated to capture the key points. Image, form a three-dimensional model of the flight environment, provide key position images for the UAV to follow the flight route, and improve the overall safety of the UAV's tracking flight.

Description

technical field [0001] The invention relates to the field of intelligent autonomous navigation of unmanned aerial vehicles, in particular to an intelligent tracking flight system and method of unmanned aerial vehicles. Background technique [0002] At present, the core research problem of intelligent UAV is the research of positioning and obstacle avoidance. The obstacle avoidance function is one of the indispensable key indicators to measure the intelligence of intelligent drones. In order to achieve autonomous obstacle avoidance during the walking process of intelligent drones, the problem to be solved is: on the one hand, the external environment information where the robot is located is required, and on the other hand, the acquired environmental information is required to be transformed into control information. The camera on the UAV will capture the image in front of the UAV, and then the image recognition module based on the convolutional neural network will recogniz...

AI Technical Summary

Problems solved by technology

In order to realize autonomous obstacle avoidance during the walking process of the intelligent UAV, the problem to be solved is: on the one hand, the external environment information of the robot is required, and on the other hand, it is required to be able to transform the acquired environmental information into control information

However, the UAVs currently on the market have not yet encountered such problems in terms of tracking methods.

[0004] Further, in the field of drones, since the tunnel magnetoresistance effect is based on the spin effect of electrons, it has the advantages of "high sensitivity, miniaturization, and easy detection", but there is no tunnel for the angular rate detection of drones. Magnetoresistance effect, and in actual work, it is found that the micro gyroscope for tunneling magnetoresistance effect detection is unable to provide a stable detection magnetic field and cannot be properly assembled.

Images