US-12619251-B2 - Marker allocation method and apparatus in unmanned aerial vehicle airport and unmanned aerial vehicle landing method and apparatus

US12619251B2US 12619251 B2US12619251 B2US 12619251B2US-12619251-B2

Abstract

Disclosed is a marker allocation method. According to an airport shape and an airport size of an unmanned aerial vehicle airport and a standard shape and a standard size of a takeoff and landing point, a target layout of an unmanned aerial vehicle airport that includes takeoff and landing points is determined. Further, an initial takeoff and landing point is determined from the takeoff and landing points included in the target layout. Markers respectively allocated to the takeoff and landing points are determined from a predetermined marker set that includes markers of different image content, by using the initial takeoff and landing point as a start point, according to a predetermined search algorithm, and with a constraint that similarity between a marker of any one of the multiple takeoff and landing points and markers of other takeoff and landing points in a specified neighborhood thereof is the lowest.

Inventors

Jiancheng CAI
Xinmin Liu
Yinian Mao

Assignees

BEIJING SANKUAI ONLINE TECHNOLOGY CO., LTD.

Dates

Publication Date: 20260505
Application Date: 20230106
Priority Date: 20220111

Claims (6)

1 . A marker allocation method in an unmanned aerial vehicle airport, comprising: when an unmanned aerial vehicle performs visual-guided landing, determining a target layout of the unmanned aerial vehicle airport according to an airport shape and an airport size of the unmanned aerial vehicle airport in a field of view of an image collection device of the unmanned aerial vehicle, and a predetermined standard shape and a predetermined standard size of a takeoff and landing point, wherein the target layout comprises multiple takeoff and landing points; determining an initial takeoff and landing point from the multiple takeoff and landing points comprised in the target layout; and determining markers respectively allocated to the multiple takeoff and landing points from a predetermined marker set by using the initial takeoff and landing point as a start point, according to a predetermined search algorithm, and with a constraint that similarity between a marker of any one of the multiple takeoff and landing points and markers of other takeoff and landing points of the multiple takeoff and landing points in a specified neighborhood thereof is the lowest, wherein image content of each marker in the marker set is different, wherein the unmanned aerial vehicle lands according to the markers respectively allocated to the multiple takeoff and landing points, and wherein determining markers respectively allocated to the multiple takeoff and landing points from the predetermined marker set by using the initial takeoff and landing point as the start point, according to the predetermined search algorithm, and with the constraint that similarity between a marker of any one of the multiple takeoff and landing points and markers of other takeoff and landing points of the multiple takeoff and landing points in the specified neighborhood thereof is the lowest comprises: searching for the multiple takeoff and landing points in the target layout according to the predetermined search algorithm by using the initial takeoff and landing point as the start point, and determining a search sequence that traverses the multiple takeoff and landing points; and determining, for each found takeoff and landing point according to the search sequence, a marker allocated to the found takeoff and landing point from the predetermined marker set with the constraint that similarity between a marker of the found takeoff and landing point and markers of other takeoff and landing points of the multiple takeoff and landing points in the specified neighborhood of the found takeoff and landing point is the lowest.
2 . The method according to claim 1 , wherein determining the target layout of the unmanned aerial vehicle airport according to the airport shape and the airport size of the unmanned aerial vehicle airport and the predetermined standard shape and the predetermined standard size of the takeoff and landing point comprises: determining multiple takeoff and landing point layouts of the unmanned aerial vehicle airport according to the airport shape and the airport size of the unmanned aerial vehicle airport and the predetermined standard shape and the predetermined standard size of the takeoff and landing point; and determining the target layout of the unmanned aerial vehicle airport from the multiple takeoff and landing point layouts according to a quantity of takeoff and landing points comprised in the multiple takeoff and landing point layouts.
3 . The method according to claim 1 , wherein determining the initial takeoff and landing point from the multiple takeoff and landing points comprised in the target layout comprises: determining, according to positions of the multiple takeoff and landing points in the target layout and from the multiple takeoff and landing points comprised in the target layout, the takeoff and landing point positioned in a center of the unmanned aerial vehicle airport as the initial takeoff and landing point.
4 . The method according to claim 3 , wherein determining, according to positions of the multiple takeoff and landing points in the target layout, the takeoff and landing point positioned in the center of the unmanned aerial vehicle airport comprises: determining a central position of the unmanned aerial vehicle airport according to the airport shape and the airport size; for each takeoff and landing point in the target layout, determining a distance between the takeoff and landing point and the central position of the unmanned aerial vehicle airport; and sorting the multiple takeoff and landing points according to determined distances, and determining, according to the sorting, the takeoff and landing point positioned in the center of the unmanned aerial vehicle airport from the multiple takeoff and landing points.
5 . The method according to claim 1 , wherein determining markers respectively allocated to the multiple takeoff and landing points from the predetermined marker set by using the initial takeoff and landing point as the start point, according to the predetermined search algorithm, and with the constraint that similarity between a marker of any one of the multiple takeoff and landing points and markers of other takeoff and landing points of the multiple takeoff and landing points in the specified neighborhood thereof is the lowest comprises: determining a marker corresponding to the initial takeoff and landing point from the predetermined marker set; determining an adjacent takeoff and landing point of the multiple takeoff and landing points to which no marker is allocated and adjacent to the initial takeoff and landing point; determining a marker allocated to the adjacent takeoff and landing point from the marker set by using similarity between the marker of the adjacent takeoff and landing point and markers of other takeoff and landing points of the multiple takeoff and landing points in the specified neighborhood thereof being lowest as the constraint; and re-using the adjacent takeoff and landing point as the initial takeoff and landing point, and continuing to allocate a marker to another takeoff and landing point of the multiple takeoff and landing points to which no marker is allocated until the markers are allocated to the multiple takeoff and landing points.
6 . A non-transitory computer readable storage medium, wherein the storage medium stores a computer program, and the computer program is executed by a processor to implement operations comprising: when an unmanned aerial vehicle performs visual-guided landing, determining a target layout of the unmanned aerial vehicle airport according to an airport shape and an airport size of the unmanned aerial vehicle airport in a field of view of an image collection device of the unmanned aerial vehicle, and a predetermined standard shape and a predetermined standard size of a takeoff and landing point, wherein the target layout comprises multiple takeoff and landing points; determining an initial takeoff and landing point from the multiple takeoff and landing points comprised in the target layout; and determining markers respectively allocated to the multiple takeoff and landing points from a predetermined marker set by using the initial takeoff and landing point as a start point, according to a predetermined search algorithm, and with a constraint that similarity between a marker of any one of the multiple takeoff and landing points and markers of other takeoff and landing points of the multiple takeoff and landing points in a specified neighborhood thereof is the lowest, wherein image content of each marker in the marker set is different, wherein the unmanned aerial vehicle lands according to the markers respectively allocated to the multiple takeoff and landing points, and wherein determining markers respectively allocated to the multiple takeoff and landing points from the predetermined marker set by using the initial takeoff and landing point as the start point, according to the predetermined search algorithm, and with the constraint that similarity between a marker of any one of the multiple takeoff and landing points and markers of other takeoff and landing points of the multiple takeoff and landing points in the specified neighborhood thereof is the lowest comprises: searching for the multiple takeoff and landing points in the target layout according to the predetermined search algorithm by using the initial takeoff and landing point as the start point, and determining a search sequence that traverses the multiple takeoff and landing points; and determining, for each found takeoff and landing point according to the search sequence, a marker allocated to the found takeoff and landing point from the predetermined marker set with the constraint that similarity between a marker of the found takeoff and landing point and markers of other takeoff and landing points of the multiple takeoff and landing points in the specified neighborhood of the found takeoff and landing point is the lowest.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application is a national stage of international PCT Application No. PCT/CN2023/070802, filed on Jan. 6, 2023, the entire contents of which are incorporated herein by reference. TECHNICAL FIELD This specification relates to the field of computer technologies, and in particular, to a marker allocation method and apparatus in an unmanned aerial vehicle airport and an unmanned aerial vehicle landing method and apparatus. BACKGROUND Currently, with advances in technologies and maturity of unmanned driving technologies, an unmanned driving device has successfully met application in the delivery field, and is often applied to scenarios such as take-out and express delivery. In a process of executing a task, an unmanned aerial vehicle usually needs to be controlled to land accurately, so as to ensure safety of the unmanned aerial vehicle. In a related technology, a vision-guided manner is generally used to implement landing of an unmanned aerial vehicle. Specifically, an identifier, such as a marker, used to cause an unmanned aerial vehicle to land may be predetermined in an unmanned aerial vehicle airport. When the unmanned aerial vehicle needs to land, a ground image can be collected first. Then, the unmanned aerial vehicle may perform target identification on the collected ground image, and determine a position of a marker in the image as a position of an unmanned aerial vehicle airport in the image. Finally, the unmanned aerial vehicle is controlled to land in the unmanned aerial vehicle airport according to the position of the unmanned aerial vehicle airport in the image. However, in the related technology, positions of markers in the unmanned aerial vehicle airport are generally determined by means of manual planning, but the long time and high costs of manual planning makes it less efficient to assign markers to takeoff and landing points within the unmanned aerial vehicle airport in the related technology. SUMMARY This specification provides a marker allocation method and apparatus in an unmanned aerial vehicle airport and an unmanned aerial vehicle landing method and apparatus. This specification provides a marker allocation method in an unmanned aerial vehicle airport, including: determining a target layout of an unmanned aerial vehicle airport according to an airport shape and an airport size of the unmanned aerial vehicle airport and a predetermined standard shape and a predetermined standard size of a takeoff and landing point, where the target layout includes multiple takeoff and landing points:determining an initial takeoff and landing point from the multiple takeoff and landing points included in the target layout; anddetermining markers respectively allocated to the multiple takeoff and landing points from a predetermined marker set by using the initial takeoff and landing point as a start point, according to a predetermined search algorithm, and by using a constraint that similarity between a marker of any one of the multiple takeoff and landing points and markers of other takeoff and landing points in a specified neighborhood thereof is the lowest, where image content of each marker in the marker set is different. Optionally, the determining a target layout of an unmanned aerial vehicle airport according to an airport shape and an airport size of the unmanned aerial vehicle airport and a predetermined standard shape and a predetermined standard size of a takeoff and landing point includes: determining multiple takeoff and landing point layouts of the unmanned aerial vehicle airport according to the airport shape and the airport size of the unmanned aerial vehicle airport and the predetermined standard shape and the predetermined standard size of the takeoff and landing point; anddetermining the target layout of the unmanned aerial vehicle airport from the multiple takeoff and landing point layouts according to a quantity of takeoff and landing points included in the multiple takeoff and landing point layouts. Optionally, the determining multiple takeoff and landing point layouts of the unmanned aerial vehicle airport according to the airport shape and the airport size of the unmanned aerial vehicle airport and the predetermined standard shape and the predetermined standard size of the takeoff and landing point includes: randomly determining a takeoff and landing point as a start point within a range of the unmanned aerial vehicle airport according to the airport shape and the airport size of the unmanned aerial vehicle airport: determining, along a normal direction of any boundary of the start point according to the predetermined standard shape and the predetermined standard size of the takeoff and landing point, a takeoff and landing point that is at a predetermined spacing from the start point in the range of the unmanned aerial vehicle airport, re-using the determined takeoff and landing point as a new start point, continuing to determine another t