Autonomous landing visual positioning method and system for unmanned aerial vehicle

Abstract

The invention discloses an autonomous landing visual positioning system for an unmanned aerial vehicle. When the unmanned aerial vehicle is close to a landing point and enters an effective range, the relative position and attitude between the unmanned aerial vehicle and the landing point can be accurately estimated by virtue of visual computation and transmitted to a control mechanism of the unmanned aerial vehicle, so that the unmanned aerial vehicle is guided to accurately land to a designated place. The autonomous visual positioning system for the unmanned aerial vehicle, provided by the invention, comprises an unmanned aerial vehicle body, a GPS receiver and an inertia measurement device arranged on the unmanned aerial vehicle body, and an embedded image computer, wherein a photoelectric reconnaissance platform is arranged at the bottom of the unmanned aerial vehicle body; a first camera and a second camera are arranged on the photoelectric reconnaissance platform; the embedded image computer is respectively connected with the first camera and the second camera and is also connected with a flight control computer; and the flight control computer is respectively connected with the GPS receiver and the inertia measurement device.

Description

technical field [0001] The invention relates to the technical field of drones, in particular to a visual positioning method and system for autonomous landing of drones. Background technique [0002] The current hovering aircraft has the function of vertical take-off and landing, and its main navigation and positioning methods mostly rely on satellite navigation systems such as GPS or Beidou. However, due to the development level of systems such as GPS and Beidou, the horizontal positioning accuracy error (X, Y direction) is about ±3m, and the vertical positioning accuracy error (Z direction) is even larger. This leads to poor landing accuracy of the aircraft. It is difficult to achieve cm-level landing accuracy, and many application scenarios that require high-precision autonomous landing cannot be realized, such as; automatic return to the voyage for charging, landing on a ship, etc. Contents of the invention [0003] In order to solve the defects of the prior art, the ...

AI Technical Summary

Problems solved by technology

However, due to the development level of GPS and Beidou and other systems, the horizontal positioning accuracy error (X, Y direction) is about ±3m, and the vertical positioning accuracy error (Z direction) is even larger

lead to poor landing accuracy of the aircraft

It is difficult to achieve cm-level landing accuracy, which is impossible for many application scenarios that require high-precision autonomous landing, such as: automatic return to the voyage for charging, landing on a ship, etc.

Images