Unmanned aerial vehicle mobile platform landing method based on visual guidance

Abstract

The invention discloses an unmanned aerial vehicle mobile platform landing method based on visual guidance. The method comprises the steps that a mobile platform landing identifier is set, an unmannedaerial vehicle searches and identifies the landing identifier, and the unmanned aerial vehicle continuously approaches the landing identifier based on visual guidance until landing is completed. According to the unmanned aerial vehicle mobile platform landing method based on visual guidance, the requirement for the performance of an airborne computer is low, and the unmanned aerial vehicle mobileplatform can rapidly and accurately land on the mobile platform.

Description

technical field [0001] The invention relates to a method for controlling an unmanned aerial vehicle, in particular to a method for landing a mobile platform of an unmanned aerial vehicle based on visual guidance, and belongs to the field of unmanned aerial vehicle control. Background technique [0002] UAVs have the advantages of flexible maneuverability, general convenience, and high usability. They have a large demand in actual production applications and are now widely used in various fields such as reconnaissance, rescue, surveying and mapping, plant protection, and performances. [0003] Autonomous take-off and landing of drones has been a research hotspot in the field of drones for many years. At present, the autonomous landing of drones mostly uses GNSS (Global Navigation Satellite System, Global Navigation Satellite System) navigation and positioning with altitude data for fixed-point landing. Altitude data is usually measured by GNSS, barometer, ultrasound or groun...

AI Technical Summary

Problems solved by technology

However, GNSS signals are easily affected by building occlusion and weather conditions, the data drift is serious, and the accuracy in the height direction is very limited; ranging sensors based on ultrasonic, microwave, laser, etc. are difficult to distinguish the landing platform from the ground, and cannot be directly used for UAVs landing on a mobile platform

[0004] Therefore, the use of traditional GNSS with altitude devices for landing is more limited. It can only be used for fixed-point landing and cannot be applied to a large number of production and living scenarios, which limits the development of drones.

[0005] For mobile landing platforms, the autonomous landing of drones in the prior art usually uses manual guidance and control, which has high requirements for GNSS accuracy and operator proficiency, and cannot achieve autonomous landing

In some complex environments, such as taking off and landing on vehicle-mounted mobile platforms and bumpy moving ground platforms, it is still a severe challenge for the flight control system and controllers of this type of UAV, which restricts the use of UAVs in a wider range of fields.

[0006] In addition, the use of personnel to take off and land will only be controlled within a limited range due to communication distance and visual range.

Under the load limit of the UAV, it is not possible to carry too much equipment load on the UAV. The on-board camera device of the UAV is mostly fixed on the platform, and can only be shot by rotating the camera within the field of view, which cannot be resolved. Calculate the attitude of the UAV for flexible flight

This creates great difficulties for drones to track and land

[0007] In addition, traditional vision-guided algorithms mostly use classic feature algorithms, while the computing power of the onboard computer is relatively low, which cannot meet the performance requirements of traditional algorithms, resulting in insufficient positioning accuracy, making it difficult for drones to land accurately

[0008] In some places, the time allowed for drones to complete landing is limited, and the existing methods for autonomous landing of drones often take a lot of time, reducing the versatility of autonomous landing of drones

Images