Unmanned aerial vehicle take-off control method and device and electronic equipment

Abstract

The invention provides an unmanned aerial vehicle takeoff control method and device and electronic equipment, and aims to solve the problem that the safety of takeoff of an unmanned aerial vehicle from a mobile platform is low. The method comprises the following steps: acquiring target information of a reference object arranged on a mobile platform, wherein the mobile platform and the reference object are relatively static in a motion state; under the condition that the vertical distance between the unmanned aerial vehicle and the mobile platform is smaller than a preset distance threshold value, a relative horizontal index between the unmanned aerial vehicle and the reference object is determined according to the target information, and the relative horizontal index comprises a relative horizontal position and / or a relative horizontal distance and / or a relative horizontal speed; a control instruction is generated according to the relative horizontal index, and the control instruction is used for adjusting the position of the unmanned aerial vehicle in the horizontal direction, so that the relative horizontal index between the unmanned aerial vehicle and the reference object is within a preset index range until the vertical distance between the unmanned aerial vehicle and the mobile platform is larger than a preset distance threshold value.

Description

Technical Field

[0001] The present application relates to the technical fields of flight control, computer vision, and intelligent control technology, and more specifically, to a method, device, and electronic equipment for controlling the takeoff of an unmanned aerial vehicle (UAV). Background Art

[0002] In scenarios such as river surveying and highway inspection, drones must take off from mobile platforms (such as ships or vehicles) to complete specific missions. In these applications, it has been found that if the mobile platform itself is in dynamic motion (such as constant speed, acceleration, or turning), the platform's motion can cause the drone's horizontal position to deviate from the platform's actual trajectory after detaching. For example, in river surveying, the movement of a ship can cause the relative position of the drone and the vessel to change rapidly. If the ship is traveling at high speeds (e.g., 5 m / s), the drone can move up to 5 m horizontally within 1 second after detaching from the platform. This could potentially collide with the ship's cabin, fences, or flagpoles, causing damage and interrupting the survey or inspection mission. To address this issue, the mobile platform's speed is typically reduced to below a safety threshold, or even stopped completely before the drone begins takeoff. Consequently, current drone takeoffs from mobile platforms are unsafe. Summary of the Invention

[0003] The purpose of the embodiments of the present application is to provide a drone takeoff control method, device, and electronic equipment for improving the low safety problem of drone takeoff from a mobile platform.

[0004] An embodiment of the present application provides a drone takeoff control method, which is applied to a drone, including: obtaining target information of a reference object set on a mobile platform, where the mobile platform is relatively stationary with respect to the reference object when in motion; when the vertical distance between the drone and the mobile platform is less than a preset distance threshold, determining a relative horizontal index between the drone and the reference object based on the target information, the relative horizontal index including: relative horizontal position and / or relative horizontal distance and / or relative horizontal speed; generating a control instruction based on the relative horizontal index, the control instruction being used to adjust the position of the drone in the horizontal direction so that the relative horizontal index between the drone and the reference object is within a preset indicator range, until the vertical distance between the drone and the mobile platform is greater than the preset distance threshold. In the implementation process of the above scheme, the relative horizontal index between the UAV and the reference object is determined based on the target information of the reference object obtained in real time, and the horizontal position of the UAV is adjusted according to the control instructions generated by the relative horizontal index, so that the relative horizontal index between the UAV and the reference object is within the preset index range, until the UAV climbs to the preset safe height in the vertical direction. The strategy of adjusting the horizontal position by dynamic real-time positioning replaces the static positioning climbing strategy of the traditional UAV, effectively improving the situation in which the traditional UAV crashes when locking the horizontal position of the take-off point and rising in the vertical direction, and ultimately improving the safety of the UAV during the take-off phase.

[0005] Optionally, in an embodiment of the present application, the reference object includes: a two-dimensional visual identifier with coded features set on a mobile platform, and the target information includes a visual image of the two-dimensional visual identifier; determining the relative horizontal index between the drone and the reference object based on the target information includes: identifying the regional position of the two-dimensional visual identifier from the visual image of the two-dimensional visual identifier, and determining the relative horizontal position and / or relative horizontal distance between a preset location point of the drone and the regional position of the two-dimensional visual identifier based on the visual image; and / or determining the relative horizontal speed between the preset location point of the drone and the regional position of the two-dimensional visual identifier from multiple visual images of the two-dimensional visual identifier at different times. In the implementation of the above scheme, by introducing a two-dimensional visual identifier with coded features (such as an ArUco code, a QR code, etc.) as a reference object and combining it with the drone's visual image processing technology, high-precision dynamic positioning, real-time speed calculation, and autonomous synchronous control are achieved between the drone and the mobile platform, thereby improving the dynamic and real-time nature of the calculation of the relative horizontal index between the drone and the reference object.

[0006] Optionally, in an embodiment of the present application, the reference object includes: a positioning device set on a mobile platform, and the target information includes the real-time position and / or real-time speed sent by the positioning device; determining the relative horizontal index between the drone and the reference object based on the target information includes: obtaining the real-time position of the drone, and determining the relative horizontal position and / or relative horizontal distance between the drone and the positioning device based on the real-time position of the drone and the real-time position of the positioning device; and / or, obtaining the real-time speed of the drone, and determining the relative horizontal speed between the drone and the positioning device based on the real-time speed of the drone and the real-time speed of the positioning device. In the implementation process of the above scheme, the real-time relative horizontal index calculation with centimeter-level accuracy between the drone and the mobile platform is achieved by combining the real-time position and speed data of the positioning device on the mobile platform with the sensor information of the drone itself, and dynamic synchronous control of the drone and the mobile platform is achieved based on the relative horizontal index.

[0007] Optionally, in an embodiment of the present application, the reference object includes: a two-dimensional visual marker and a positioning device provided on a mobile platform; the target information includes: a visual image of the two-dimensional visual marker, and a real-time position or real-time speed transmitted by the positioning device; determining a relative horizontal index between the drone and the reference object based on the target information includes: determining a first relative horizontal index between the drone and the two-dimensional visual marker based on the regional position of the two-dimensional visual marker in the visual image and a preset location point of the drone; determining a second relative horizontal index between the drone and the positioning device based on the real-time position and / or real-time speed transmitted by the positioning device; and fusing the first relative horizontal index and the second relative horizontal index to obtain a fused relative horizontal index, the fused relative horizontal index including: a relative horizontal position and / or a relative horizontal distance and / or a relative horizontal speed. In the implementation of the above solution, by fusing the first relative horizontal index and the second relative horizontal index, not only can the accuracy of the fused relative horizontal index (e.g., the accuracy of any one of the relative horizontal position, relative horizontal distance, and relative horizontal speed) be improved, but also the drone can complete its takeoff function on the mobile platform even if either the first relative horizontal index or the second relative horizontal index fails or cannot be obtained, thereby effectively improving the high availability of the drone's takeoff control.

[0008] Optionally, in an embodiment of the present application, the reference object includes: at least one target object set on a mobile platform, and the target information includes image feature points of the target object; obtaining the target information of the reference object set on the mobile platform includes: photographing the at least one target object set on the mobile platform using a camera of the drone to obtain a target image of the at least one target object; extracting feature points from the target image of the at least one target object to obtain image feature points of the target object; and determining a relative horizontal index between the drone and the reference object based on the target information includes: determining the relative horizontal position and / or relative horizontal distance between the preset position points and the image feature points based on preset position points and image feature points of the drone. In the implementation of the above scheme, by photographing the target object on the mobile platform and extracting its image feature points (such as corner points and edge points), the horizontal index deviation, such as the relative horizontal position and / or relative horizontal distance between the drone and the ship, is calculated in real time, and the flight trajectory is dynamically adjusted, thereby achieving high-precision synchronous tracking in an environment without base station support, improving the situation in which traditional drones crash when locking the horizontal position of the takeoff point and ascending in a vertical direction, and ultimately improving the safety of the drone during the takeoff phase.

[0009] Optionally, in an embodiment of the present application, the reference object includes: multiple target objects set on the mobile platform, and the target information includes: radar ranging data of the drone's surround-view radar for the multiple target objects; determining the relative horizontal index between the drone and the reference object based on the target information includes: determining the relative horizontal distance between the drone and the multiple target objects in the horizontal direction based on the radar ranging data of the multiple target objects. In the implementation process of the above scheme, the surround-view radar carried by the drone performs multi-point ranging on the multiple target objects set on the mobile platform, and combines the distance calculation of the multiple target objects in different horizontal directions to achieve high-precision, interference-resistant relative horizontal positioning between the drone and the mobile platform. Even if some target objects are blocked or the radar signal is interfered with, the ranging data of the remaining targets can still support dynamic correction, ensuring that the drone always maintains an accurate horizontal distance from the mobile platform, improving the situation where traditional drones crash when locking the horizontal position of the take-off point and rising in the vertical direction, and ultimately improving the safety of the drone during the take-off phase.

[0010] Optionally, in this embodiment of the present application, after determining the relative horizontality between the drone and the reference object based on the target information, the method further includes determining a vertical ascent strategy for the drone based on the relative horizontality. In implementing this solution, by combining relative horizontality metrics (such as the horizontal distance and speed between the drone and the mobile platform) with the vertical ascent strategy, the limitations of traditional drone takeoff control, which relies on a fixed trajectory or a single GNSS, are overcome, thereby increasing the flexibility of drone takeoff control.

[0011] An embodiment of the present application also provides a drone takeoff control device, which is applied to a drone and includes: a reference information acquisition module, used to acquire target information of a reference object set on a mobile platform, where the mobile platform is relatively stationary with respect to the reference object when in motion; a horizontal index determination module, used to determine the relative horizontal index between the drone and the reference object based on the target information when the vertical distance between the drone and the mobile platform is less than a preset distance threshold, the relative horizontal index including: relative horizontal position and / or relative horizontal distance and / or relative horizontal speed; a control instruction generation module, used to generate a control instruction based on the relative horizontal index, the control instruction being used to adjust the horizontal position of the drone so that the relative horizontal index between the drone and the reference object is within a preset indicator range until the vertical distance between the drone and the mobile platform is greater than the preset distance threshold.

[0012] Optionally, in an embodiment of the present application, the reference object includes: a two-dimensional visual identifier with coding features set on a mobile platform, and the target information includes a visual image of the two-dimensional visual identifier; the horizontal indicator determination module includes: a first position distance determination submodule, which is used to identify the regional position of the two-dimensional visual identifier from the visual image of the two-dimensional visual identifier, and determine the relative horizontal position and / or relative horizontal distance between the preset position point of the drone and the regional position of the two-dimensional visual identifier based on the visual image; and / or, a first relative speed determination submodule, which is used to determine the relative horizontal speed between the preset position point of the drone and the regional position of the two-dimensional visual identifier from the visual images of the two-dimensional visual identifier at multiple different moments.

[0013] Optionally, in an embodiment of the present application, the reference object includes: a positioning device set on a mobile platform, the target information includes the real-time position or real-time speed sent by the positioning device; the horizontal index determination module includes: a second position distance determination submodule, used to obtain the real-time position of the UAV, and determine the relative horizontal position and / or relative horizontal distance between the UAV and the positioning device based on the real-time position of the UAV and the real-time position of the positioning device; and / or, a second relative speed determination submodule, used to obtain the real-time speed of the UAV, and determine the relative horizontal speed between the UAV and the positioning device based on the real-time speed of the UAV and the real-time speed of the positioning device.

[0014] Optionally, in an embodiment of the present application, the reference object includes: a two-dimensional visual identifier and a positioning device set on a mobile platform, and the target information includes: a visual image of the two-dimensional visual identifier, and a real-time position or real-time speed sent by the positioning device; a horizontal index determination module includes: a first horizontal index determination submodule, used to determine a first relative horizontal index between the drone and the two-dimensional visual identifier based on the regional position of the two-dimensional visual identifier in the visual image and a preset position point of the drone; a second horizontal index determination submodule, used to determine a second relative horizontal index between the drone and the positioning device based on the real-time position and / or real-time speed sent by the positioning device; a fused horizontal index determination submodule, used to fuse the first relative horizontal index and the second relative horizontal index to obtain a fused relative horizontal index, and the fused relative horizontal index includes: relative horizontal position and / or relative horizontal distance and / or relative horizontal speed.

[0015] Optionally, in an embodiment of the present application, the reference object includes: at least one target object set on the mobile platform, the target information includes image feature points of the target object; the reference information acquisition module includes: a target image shooting submodule, used to shoot at least one target object set on the mobile platform through the camera of the drone to obtain a target image of at least one target object; an image feature extraction submodule, used to extract feature points of the target image of at least one target object to obtain image feature points of the target object; the horizontal indicator determination module includes: a position distance determination submodule, used to determine the relative horizontal position and / or relative horizontal distance between the preset position point and the image feature point based on the preset position point and image feature point of the drone.

[0016] Optionally, in an embodiment of the present application, the reference object includes: multiple target objects set on the mobile platform, and the target information includes: radar ranging data of the drone's surround radar for the multiple target objects; the horizontal indicator determination module includes: a horizontal distance determination submodule, which is used to determine the relative horizontal distance between the drone and the multiple target objects in the horizontal direction based on the radar ranging data of the multiple target objects.

[0017] An embodiment of the present application further provides an electronic device, including: a processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and the machine-readable instructions execute the method described above when executed by the processor.

[0018] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described above is executed.

[0019] An embodiment of the present application further provides a computer program product, including: a computer program or computer instructions, which executes the method described above when the computer program or computer instructions are executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only illustrate certain embodiments of the embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 A schematic diagram of the process of a UAV taking off from a ship provided by a comparative embodiment is shown; Figure 2 A schematic diagram showing a flow chart of a method for controlling a drone takeoff provided by an embodiment of the present application is shown; Figure 3 A schematic diagram showing a reference object provided on a ship according to an embodiment of the present application; Figure 4 A schematic top view of the relative horizontal distances between a drone and multiple target objects provided by an embodiment of the present application is shown; Figure 5 A schematic structural diagram of a UAV takeoff control device provided in an embodiment of the present application is shown; Figure 6 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the embodiments of the present application only serve the purpose of illustration and description and are not intended to limit the scope of protection of the embodiments of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in the embodiments of the present application illustrate the operations implemented according to some embodiments of the embodiments of the present application. It should be understood that the operations of the flowcharts can be implemented out of sequence, and steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art, guided by the contents of the embodiments of the present application, can add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0023] In addition, the described embodiments are only a portion of the embodiments of the present application, rather than all embodiments. The components of the embodiments of the present application generally described and shown in the accompanying drawings can be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed embodiments of the present application, but rather merely represents selected embodiments of the embodiments of the present application.

[0024] It is understandable that the "first" and "second" in the embodiments of the present application are used to distinguish similar objects. Those skilled in the art will understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit differences. In the description of the embodiments of the present application, the term "and / or" is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the previous and subsequent associated objects are in an "or" relationship. The term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two (including two).

[0025] See Figure 1 The following diagram illustrates a comparative example of a drone taking off from a ship. Conventional drones typically employ a static positioning climb strategy during takeoff. Upon startup, the drone first determines a fixed takeoff point coordinate using the Global Positioning System (GPS) or other positioning system. This coordinate is an absolute horizontal position relative to the Earth's surface. The drone then assumes this horizontal position serves as a reference point that should remain constant throughout the takeoff phase. Using this horizontal position as a reference point, the drone begins its vertical upward takeoff. During this period, the drone does not actively adjust its horizontal position, even if the ship continues to move forward or sideways due to factors such as currents and wind.

[0026] In scenarios like river mapping and highway inspection, river surveying requires drones to launch from mobile platforms, such as ships, to complete river mapping tasks. Highway inspection drones, on the other hand, require launch from fast-moving vehicles to complete highway inspections. During the drone's ascent, relative motion may occur. This means the drone's altitude rises while its horizontal position remains unchanged. However, the mobile platform itself is in dynamic motion (such as constant speed, acceleration, and turning). The ship's movement causes the relative position of the drone and the ship to change rapidly, and the drone will not move synchronously with the ship after detaching. If the ship's speed is too high (for example, 5 m / s), the drone can move up to 5 m horizontally within 1 second after detaching from the platform. While the drone attempts to maintain its relative position relative to its initial launch point, it could collide with the ship's cabin, fence, or flagpole, causing damage and interrupting the specific mapping or inspection mission.

[0027] To address these issues, the mobile platform's speed can be reduced to below a safety threshold, or even stopped completely before the drone begins takeoff. While this approach can reduce the probability of the drone colliding with obstacles like ship cabins, fences, or flagpoles, slowing the platform's speed can deplete specific tasks like surveying or inspections. This approach struggles to meet the efficiency and safety requirements of scenarios like river surveying and highway inspections.

[0028] See Figure 2 The flowchart of the drone takeoff control method provided by the embodiment of the present application is shown; in order to further and better improve the above problems, the drone can still complete the takeoff function normally without reducing the speed of the mobile platform and without colliding with obstacles such as the cabin, fence or flagpole of the ship. The main idea of ​​the above drone takeoff control method is to use a dynamic real-time positioning strategy to adjust the horizontal position instead of the static positioning climbing strategy of the traditional drone. This strategy allows the drone to determine the relative horizontal index between the drone and the reference object by obtaining and adjusting the target information of the reference object in real time, so that the relative horizontal index between the drone and the reference object is within the preset index range until the drone climbs to a preset safe height in the vertical direction. The implementation method of the above drone takeoff control method may include: Step S110: acquiring target information of a reference object set on the mobile platform, where the mobile platform is relatively stationary with respect to the reference object in a moving state.

[0029] A mobile platform refers to the platform that is moving when the drone takes off. It is also the dynamic carrier for the drone to take off, such as a ship in river mapping operations.

[0030] See Figure 3 A schematic diagram of a reference object provided on a ship according to an embodiment of the present application is shown; a reference object refers to a target object that is relatively stationary with respect to the mobile platform in motion, and is used to provide a reference benchmark for the drone to adjust its horizontal position in real time. The mobile platform may be provided with many such reference objects, including: a two-dimensional visual identifier with coding features provided on the mobile platform (e.g., a marker board provided on the ship), a positioning device provided on the mobile platform (e.g., a base station), at least one object such as a cabin, a flagpole, and a deck. It is understandable that the reference object remains relatively stationary with respect to the mobile platform in motion (i.e., it is fixedly mounted on the platform and will not shift due to the movement of the platform). For example, a marker board is a plate-shaped object with a two-dimensional visual identifier with coding features. The two-dimensional visual identifier may be an ArUco code. After being placed on the deck of the ship, the marker board will move synchronously with the ship to facilitate visual recognition by the drone and serve as a reference object for positioning benchmark.

[0031] Target information is information obtained from a reference object in real time, including: a visual image of a two-dimensional visual marker (such as a visual image of a marker board taken by a drone), the real-time position and / or real-time speed sent by the positioning device (such as its own position or speed sent by a base station), etc.

[0032] Step S120: When the vertical distance between the UAV and the mobile platform is less than a preset distance threshold, a relative horizontal index between the UAV and the reference object is determined based on the target information. The relative horizontal index includes: relative horizontal position and / or relative horizontal distance and / or relative horizontal speed.

[0033] The vertical distance is the height difference between the drone and the mobile platform. Assuming that the ship deck height is 0 meters and the current height of the drone is 8 meters, the vertical distance between the drone and the ship deck is 8 meters.

[0034] Relative horizontal indicators refer to indicators used to measure the relative relationship between a drone and a reference object in the horizontal direction, including at least one of the following: relative horizontal position, relative horizontal distance, and relative horizontal speed. In theory, it can also be a relative horizontal indicator after the fusion of multiple relative indicators, such as the fused relative horizontal position and / or relative horizontal distance.

[0035] Relative horizontal position is the relative horizontal positional deviation between a preset location on the drone and a reference object. This preset location can be the center point of the drone's camera, a fixed corner point on the mainframe, or the center point of a specific rotor.

[0036] The relative horizontal distance is the actual physical distance between the drone and the reference object in the horizontal direction. It is usually converted to the real distance by the pixel distance between the image coordinates. For example, you can first obtain the pixel distance between the preset position point of the drone and the image center point of the marker plate, and then use the camera calibration parameters to convert this pixel distance into the real distance between the center point of the drone and the marker plate.

[0037] The relative horizontal velocity is the relative motion speed between the drone and the reference object in the horizontal direction. It can be calculated by the displacement and time interval of consecutive frames and can be expressed as ;in, represents the relative horizontal velocity, Indicates the displacement of consecutive frames, Indicates the time interval between consecutive frames.

[0038] Step S130: Generate a control instruction based on the relative horizontal index, which is used to adjust the horizontal position of the drone so that the relative horizontal index between the drone and the reference object is within a preset index range until the vertical distance between the drone and the mobile platform is greater than a preset distance threshold.

[0039] Control instructions are flight control signal instructions generated based on relative horizontal indicators, which are used to adjust the horizontal position of the drone (such as left and right translation, forward and backward movement).

[0040] The preset indicator range is the maximum deviation range of the relative horizontal position, relative horizontal distance and / or relative horizontal speed between the drone and the reference object. When the range is exceeded, a control command needs to be generated for adjustment. For example, the preset relative horizontal position error range is ,and ,in, and Represent the horizontal and vertical coordinates of the drone, and Represent the horizontal and vertical coordinates of the reference object respectively.

[0041] The preset distance threshold is the height threshold at which the drone triggers the end of horizontal position adjustment. When the vertical distance exceeds this threshold, the drone stops adjusting its horizontal position. Usually, the drone's horizontal position is adjusted only when the vertical distance between the drone and the mobile platform is less than the preset distance threshold.

[0042] In the implementation process of the above scheme, the relative horizontal index between the UAV and the reference object is determined based on the target information of the reference object obtained in real time, and the horizontal position of the UAV is adjusted according to the control instructions generated by the relative horizontal index, so that the relative horizontal index between the UAV and the reference object is within the preset index range, until the UAV climbs to the preset safe height in the vertical direction. The strategy of adjusting the horizontal position by dynamic real-time positioning replaces the static positioning climbing strategy of the traditional UAV, effectively improving the situation in which the traditional UAV crashes when locking the horizontal position of the take-off point and rising in the vertical direction, and ultimately improving the safety of the UAV during the take-off phase.

[0043] As an optional implementation of step S120, the reference object may include a two-dimensional visual marker with a coding feature set on the mobile platform, and the target information may include a visual image of the two-dimensional visual marker. The implementation of determining the relative level index between the drone and the reference object based on the target information may include: Step S121a: Identifying the region position of the two-dimensional visual marker from the visual image of the two-dimensional visual marker.

[0044] For example, in the implementation of step S121a, assuming a marker board with a coding feature (such as an ArUco code) is installed on the deck of a ship, the two-dimensional visual marker with the coding feature installed on the mobile platform can be the marker board installed on the ship, and the drone can be placed on the marker board. The drone can use a camera to capture the marker board in real time to obtain a visual image. Then, a target detection network model or an image processing algorithm (such as the PnP algorithm or OpenCV's detectMarkers function) is used to perform target detection on the visual image to obtain the regional position of the two-dimensional visual marker, that is, the regional position of the marker board in the visual image. The target detection network model can adopt a YOLO model or a Faster R-CNN series model, etc.

[0045] Optionally, in a specific real-time process, the drone can find the four corner points of the ArUco code through corner detection (such as Harris corner detection) or edge detection (such as Canny edge detection), and then calculate the center point coordinates of the ArUco code in the image through the corner point coordinates, and determine the center point coordinates as the area position of the above-mentioned two-dimensional visual identification. The four corner points of the above-mentioned ArUco code can be expressed as follows: , then the center point coordinates of the ArUco code in the image can be expressed as .

[0046] Step S121b: Determine the relative horizontal position and / or relative horizontal distance between the preset location point of the drone and the area position of the two-dimensional visual mark based on the visual image.

[0047] It can be understood that the preset location point of the drone in the embodiment of the present application can be set according to the specific scene conditions. For example, the preset location point can be the center point of the drone's camera, a fixed corner point on the frame host, or the center point of a specific rotor.

[0048] The implementation of the above step S121b includes: converting the pixel distance between the pixel coordinates of the preset position point of the drone and the center point of the regional position of the ArUco code into the actual physical distance, and calculating the relative horizontal position and / or relative horizontal distance between the drone and the ArUco code. The above relative horizontal position can be expressed as follows: , the above relative horizontal distance can be expressed as ;in, and They respectively represent the lateral position deviation and longitudinal position deviation in the relative horizontal position between the preset position point of the drone and the center point of the regional position of the ArUco code, and Respectively represent the horizontal and vertical coordinates of the preset position of the UAV, and Respectively represent the horizontal and vertical coordinates of the center point of the regional position of the ArUco code, Indicates the relative horizontal distance between the preset position point of the drone and the center point of the area position of the ArUco code.

[0049] And / or, as an optional implementation of the above step S120, the implementation of determining the relative level index between the drone and the reference object based on the target information may include: Step S121c: determining the relative horizontal speed between the preset position point of the UAV and the regional position of the two-dimensional visual marker from a plurality of visual images of the two-dimensional visual marker at different times.

[0050] For example, in a river mapping mission, a drone needs to track a two-dimensional visual marker (such as an ArUco code) on a mobile platform (e.g., a ship) in real time and calculate the relative horizontal velocity between itself and the marker. Assuming the ship is moving rightward at a speed of 1 m / s, the drone's camera captures continuous images of the ArUco code at a frequency of 30 frames per second. In each frame, the relative horizontal position of the ArUco code and the pre-set location of the drone can be calculated using steps S121a and S121b. The relative horizontal velocity between the drone and the marker can then be calculated based on the change in relative horizontal position across consecutive frames. Typically, two adjacent frames or a sliding time window (e.g., a three-frame average) are used to calculate the relative horizontal velocity between the drone's pre-set location and the two-dimensional visual marker.

[0051] As an optional implementation of step S120, the reference object may include a positioning device installed on a mobile platform, which may be a Real-Time Kinematic (RTK) base station. The target information may include the real-time position and / or real-time speed transmitted by the positioning device. The implementation of determining the relative level between the drone and the reference object based on the target information may include: Step S122a: Obtain the real-time location of the drone.

[0052] An example of an implementation of step S122a is as follows: the drone may be equipped with a Global Navigation Satellite System (GNSS) receiving module, which can receive GPS signals or BeiDou signals in real time, thereby calculating the drone's real-time position using the GPS signals or BeiDou signals. Optionally, the drone may also be equipped with a dual-frequency antenna that supports real-time keying (RTK) technology. The drone then communicates with a ground base station (RTK base station), receives differential correction data sent by the ground base station, and calculates the drone's real-time position based on the differential correction data. In addition, the ground base station may also send correction data, and the drone can combine this correction data with its own GNSS data and base station data to calculate its real-time position with centimeter-level accuracy based on these three types of data.

[0053] Step S122b: Determine the relative horizontal position and / or relative horizontal distance between the UAV and the positioning device according to the real-time position of the UAV and the real-time position of the positioning device.

[0054] It is understandable that the above-mentioned positioning device is a base station (such as RTK-GNSS) set up on a mobile platform (such as a ship) or a remote control placed thereon. The base station or remote control may have a built-in GNSS module or an external GNSS module. Therefore, the base station or remote control can send its measured real-time position to the drone through the GNSS module.

[0055] For example, in the implementation of step S122b above, it is assumed that the positioning device (such as RTK-GNSS) is fixed on a mobile platform (ship), and the positioning device can directly send its own real-time position to the UAV. Therefore, the UAV can directly receive its own real-time position sent by the positioning device. The relative horizontal position and / or relative horizontal distance between the real-time position of the UAV and the real-time position of the positioning device are calculated. The relative horizontal position is also called the arm compensation value between the UAV and the base station, which can be expressed as follows: , the above relative horizontal distance can be expressed as ;in, and They represent the lateral position deviation and longitudinal position deviation between the real-time position of the UAV and the real-time position of the positioning device, respectively. and Respectively represent the horizontal and vertical coordinates of the real-time position of the UAV, and Respectively represent the horizontal and vertical coordinates of the real-time position of the positioning device, Indicates the relative horizontal distance between the real-time position of the drone and the real-time position of the positioning device.

[0056] And / or, as an optional implementation of step S120, determining the relative level index between the drone and the reference object based on the target information includes: Step S122c: Obtain the real-time speed of the drone.

[0057] An example implementation of step S122c is as follows: obtaining the real-time three-dimensional velocity (east, north, and sky) of the drone through a GNSS receiver, and then calculating the real-time velocity of the drone based on the real-time three-dimensional velocity and the acceleration and angular velocity data of the Inertial Measurement Unit (IMU).

[0058] Step S122d: Determine the relative horizontal speed between the UAV and the positioning device according to the real-time speed of the UAV and the real-time speed of the positioning device.

[0059] It is understandable that the above-mentioned positioning device is a base station (such as RTK-GNSS) installed on a mobile platform (such as a ship) or a remote control placed thereon. The base station or remote control may have a built-in GNSS module or an external GNSS module. Therefore, the base station or remote control may send the real-time speed measured by the GNSS module to the drone. The real-time speed here may be calculated based on the real-time speeds measured at multiple moments.

[0060] The implementation method of the above step S122d is, for example, to use the formula Calculate the real-time speed of the UAV and the real-time speed of the positioning device to obtain the relative horizontal speed between the UAV and the positioning device. Indicates the relative horizontal speed between the drone and the positioning device. Indicates the real-time speed of the drone, Indicates the real-time speed of the positioning device.

[0061] As an optional implementation of step S120, the reference object may include: a two-dimensional visual marker and a positioning device provided on the mobile platform, and the target information may include: a visual image of the two-dimensional visual marker and a real-time position or speed transmitted by the positioning device. The implementation of determining the relative level indicator between the drone and the reference object based on the target information may include: Step S123a: Determine a first relative horizontal index between the drone and the two-dimensional visual identifier based on the regional position of the two-dimensional visual identifier in the visual image and the preset position point of the drone.

[0062] An implementation method of the above-mentioned step S123a is, for example: first, the regional position of the two-dimensional visual identifier is identified from the visual image of the two-dimensional visual identifier, and then, the relative horizontal position, relative horizontal distance and / or relative horizontal speed between the preset position point of the drone and the regional position of the two-dimensional visual identifier are determined based on the visual image. For specific implementation methods, please refer to the implementation methods of the above steps S121a, S121b and S121c; finally, the relative horizontal position, relative horizontal distance and / or relative horizontal speed here are determined as the first relative horizontal indicator between the above-mentioned drone and the two-dimensional visual identifier.

[0063] Step S123b: Determine a second relative horizontal index between the UAV and the positioning device according to the real-time position and / or real-time speed sent by the positioning device.

[0064] An implementation example of the above-mentioned step S123b is as follows: first, the real-time position and / or real-time speed of the UAV is obtained, and then, the relative horizontal position and / or relative horizontal distance between the UAV and the positioning device are determined based on the real-time position of the UAV and the real-time position of the positioning device, or, the relative horizontal speed between the UAV and the positioning device is determined based on the real-time speed of the UAV and the real-time speed of the positioning device. For specific implementation methods, please refer to the implementation methods of steps S122a to S122d above; finally, the relative horizontal position, relative horizontal distance and / or relative horizontal speed here are determined as the second relative horizontal indicator between the above-mentioned UAV and the positioning device.

[0065] Step S123c: Fusing the first relative level index and the second relative level index to obtain a fused relative level index.

[0066] An implementation example of the above-mentioned step S123c is: fusing the relative horizontal position in the above-mentioned first relative horizontal indicator and the relative horizontal position in the second relative horizontal indicator to obtain the fused relative horizontal position; and / or fusing the relative horizontal distance in the above-mentioned first relative horizontal indicator and the relative horizontal distance in the second relative horizontal indicator to obtain the fused relative horizontal distance; and / or fusing the relative horizontal speed in the above-mentioned first relative horizontal indicator and the relative horizontal speed in the second relative horizontal indicator to obtain the fused relative horizontal speed; finally, the relative horizontal position and / or relative horizontal distance and / or relative horizontal speed here can be determined as the fused relative horizontal indicator. It can be seen that the above-mentioned fused relative horizontal indicator may include: at least one of the relative horizontal position, relative horizontal distance and relative horizontal speed.

[0067] In the implementation process of the above-mentioned scheme, by fusing the first relative horizontal indicator and the second relative horizontal indicator, not only the accuracy of the fused relative horizontal indicator (such as the accuracy of the relative horizontal position, relative horizontal distance and / or relative horizontal speed) can be improved, but also when any of the first relative horizontal indicator and the second relative horizontal indicator fails or cannot be obtained, the UAV can complete the function of taking off on the mobile platform, thereby effectively improving the high availability of the UAV take-off control.

[0068] As an optional implementation of the above step S110, the above reference object may include: at least one target object set on the mobile platform, and the above target information may include image feature points of the target object. The above implementation of obtaining the target information of the reference object set on the mobile platform may include: Step S111: photographing at least one target object set on the mobile platform through the camera of the drone to obtain a target image of the at least one target object.

[0069] For example, step S111 may be implemented by continuously photographing at least one target object disposed on the mobile platform using a downward-looking camera or a surround-view camera of the drone to obtain a target image of the at least one target object. The reference object may include at least one target object disposed on the mobile platform, such as a cabin, a fence, a pattern, a sticker, a design, an ArUco code, an AprilTag checkerboard, or a special symbol.

[0070] Step S112: extracting feature points from a target image of at least one target object to obtain image feature points of the target object.

[0071] For example, in a specific practice, the implementation of step S112 may include using a feature extraction algorithm such as the Scale Invariant Feature Transform (SlFT) algorithm, the Speeded Up Robust Features (SURF) algorithm, or the Oriented FAST and Rotated BRIEF (ORB) algorithm to extract feature points from a target image of at least one target object to obtain image feature points of at least one target object. The target information may include the image feature points of the target object.

[0072] As an optional implementation of step S120, the implementation of determining the relative level index between the drone and the reference object based on the target information may include: Step S124a: Determine the relative horizontal position and / or relative horizontal distance between the preset location point and the image feature point according to the preset location point and the image feature point of the drone.

[0073] The implementation of the above step S124a includes: converting the pixel coordinates of the preset position point of the drone and the pixel distance between the image feature point into the actual physical distance, and calculating the relative horizontal position and / or relative horizontal distance between the drone and the target object. The above relative horizontal position can be expressed as follows: , the above relative horizontal distance can be expressed as ;in, and They represent the lateral position deviation and longitudinal position deviation in the relative horizontal position between the preset position point of the drone and the image feature point of the target object, respectively. and Respectively represent the horizontal and vertical coordinates of the preset position of the UAV, and Represent the horizontal and vertical coordinates of the image feature points of the target object, respectively. Indicates the relative horizontal distance between the preset location point of the drone and the image feature point of the target object.

[0074] As another optional implementation of step S120, the implementation of determining the relative level index between the drone and the reference object based on the target information may include: Step S124b: determining the relative horizontal speed between the preset position points and the image feature points when the drone takes the consecutive multiple-frame images.

[0075] For example, in the implementation of step S124b above, for ease of understanding and explanation, the following uses an ArUco code as an example. The drone needs to track the ArUco code on a mobile platform (such as a ship) in real time and calculate the relative horizontal velocity between itself and the ArUco code. Assume that the ship is moving rightward at a speed of 1 m / s, and the drone's camera captures consecutive images of the ArUco code at a frequency of 30 frames per second (fps). Based on the relative horizontal position changes in consecutive frames, the relative horizontal velocity between the drone's preset location and the image feature points of the ArUco code can be calculated based on the preset location and the image feature points of the consecutive frames. Typically, two adjacent frames or a sliding time window (such as a three-frame average) can be selected to calculate the relative horizontal velocity between the drone's preset location and the ArUco code's image feature points.

[0076] See Figure 4 A schematic top view of the relative horizontal distances between a drone and multiple target objects provided by an embodiment of the present application is shown; as an optional implementation of the above-mentioned step S120, the above-mentioned reference objects may include: multiple target objects set on a mobile platform, and the above-mentioned target information may include: radar ranging data of the drone's surround-view radar for the multiple target objects. The above-mentioned implementation method of determining the relative horizontal index between the drone and the reference objects based on the target information may include: Step S125a: Determine the relative horizontal distance between the UAV and the multiple target objects in the horizontal direction according to the radar ranging data of the multiple target objects.

[0077] For example, in step S125a, the drone can use surround-view radar to measure the distances to multiple target objects from multiple directions (e.g., front, back, left, and right), thereby obtaining radar ranging data for the drone in multiple directions. The drone can then determine the relative horizontal distances between the drone and the multiple target objects based on the radar ranging data for the multiple target objects. For example, the multiple relative horizontal distances may be 3 meters from the front of the drone camera to the cabin, 2 meters from the right side to the fence, and 4 meters from the rear to the flagpole. After determining the relative horizontal distances between the drone and the multiple target objects, the drone can maintain the relative horizontal distances to the multiple target objects within a preset indicator range during vertical ascent, e.g., the distance from the front of the drone camera to the cabin is no less than 2.9 meters and no more than 3.1 meters, the distance from the right side to the fence is no less than 1.9 meters and no more than 2.1 meters, and the distance from the rear to the flagpole is no less than 3.9 meters and no more than 4.1 meters, until the vertical distance between the drone and the mobile platform exceeds a preset distance threshold.

[0078] Optionally, after determining the relative horizontal distances between the drone and multiple target objects, the drone can also fuse multi-point radar ranging data and utilize triangulation or least squares optimization algorithms to effectively eliminate single-point ranging errors, significantly improving positioning accuracy and system robustness. For example, when a drone is flying synchronously with a ship, even if some target objects are obscured or the radar signal is interfered with, the ranging data from the remaining targets can still support dynamic corrections, ensuring that the drone always maintains a precise horizontal distance from the mobile platform.

[0079] As an alternative embodiment of step S130, for example, the drone can generate control instructions based on the relative horizontal index, thereby causing the drone's flight control system to adjust the drone's horizontal position and flight attitude so that the relative horizontal index between the drone and the reference object is within a preset index range. It is understood that, ideally, the drone and the reference object should remain relatively stationary in the horizontal direction. However, practical conditions do not allow the drone and the reference object to remain relatively stationary in the horizontal direction at all times. Therefore, the drone needs to generate control instructions based on the relative horizontal index in real time, continuously adjusting the drone's horizontal position and flight attitude until the vertical distance between the drone and the mobile platform exceeds a preset distance threshold. In other words, control instructions need to be continuously generated until the drone climbs vertically to a preset distance threshold. The preset distance threshold here can be understood as a preset safe altitude, which can be set to 2 meters, 3 meters, 5 meters, etc., and can be set according to specific circumstances.

[0080] As an optional implementation of the above-mentioned UAV takeoff control method, after determining the relative level index between the UAV and the reference object based on the target information, the method further includes: Step S140: Determine the vertical ascent strategy of the UAV according to the relative horizontal index.

[0081] For example, an optional implementation of step S140 described above is as follows: It is understood that after determining the relative horizontal indicators (such as relative horizontal position, relative horizontal distance, and / or relative horizontal speed) between the drone and the reference object based on the target information, the drone's vertical ascent strategy can also be determined based on the relative horizontal indicators. Specifically, if the deviation of the relative horizontal indicator between the drone and the reference object is less than the minimum value within a preset tolerance range, the drone's vertical ascent strategy is adjusted to increase the drone's vertical ascent speed. Specifically, this can be done by directing the drone's rotors to output power in the vertical direction to reduce the horizontal force component acting on the drone while simultaneously increasing the vertical force component. In other words, when the horizontal deviation is too small (e.g., if the drone approaches too close to a target object on a mobile platform), the horizontal force can be reduced by increasing vertical lift, thereby mitigating the risk of collision caused by platform movement.

[0082] Similarly, if the deviation of the relative horizontal index between the drone and the reference object is within a preset tolerance range, that is, the index deviation is greater than the minimum value of the preset tolerance range and less than the maximum value of the preset tolerance range, the drone's vertical ascent strategy is adjusted to reduce the drone's vertical ascent speed. Specifically, the drone's rotor can be gradually changed from vertical to horizontal to output power, thereby increasing the horizontal force component of the drone and simultaneously reducing the vertical force component. In other words, when the deviation is within the tolerance range, the power is dynamically allocated to the horizontal direction to assist the platform's synchronous movement, ensuring that the takeoff path matches the platform's movement trajectory. Even if the platform moves, the drone will move with the platform, thereby reducing the risk of collision between the two.

[0083] Similarly, if the deviation in the relative horizontality indicator between the drone and the reference object exceeds the maximum value of the preset tolerance range, the drone will cease vertical ascent and slowly descend to a preset safe altitude or directly onto a mobile platform (such as the deck of a ship) to prevent dangerous operations. For example, in river mapping, if a ship drifts due to currents, the drone can dynamically adjust power distribution to match its movement, avoiding excess lift consumption caused by the platform drifting.

[0084] Optionally, the above-mentioned vertical ascent strategy may also include: dynamically adjusting the timing and angle of vertical ascent according to the real-time relative horizontal position, relative horizontal distance and / or relative horizontal speed (such as the deviation amount when the UAV deviates from the center of the mobile platform). For example, when a horizontal offset between the UAV and the mobile platform is detected, the horizontal correction is prioritized and then the force component of the UAV in the horizontal direction and the force component in the vertical direction are simultaneously controlled to avoid take-off path conflicts caused by platform movement during the vertical ascent process. In addition, the above-mentioned UAV take-off control method can also use the relative horizontal index calculated by multi-sensor fusion (such as radar ranging, visual feature point positioning) to simultaneously control the force component of the UAV in the horizontal direction and the force component in the vertical direction, and correct the take-off trajectory in real time to ensure safe take-off in complex environments. In scenarios with weak GNSS signal coverage or high-speed platform movement (such as water areas and mountainous areas), traditional fixed-trajectory take-off strategies are prone to deviation or collision due to positioning errors. In implementing this solution, by combining relative horizontal indicators with dynamic adjustments to the drone's vertical ascent strategy, the coordinated control of horizontal correction and vertical lift during takeoff was achieved for the first time. This addresses the issues of takeoff deviation and energy waste caused by platform motion or environmental interference in complex dynamic scenarios experienced by traditional drones. By adjusting rotor power distribution in real time, vertical lift is increased only when necessary (such as for rapid ascent), while horizontal power is prioritized to compensate for platform motion in other situations. This significantly reduces energy consumption during takeoff. Furthermore, dynamic correction of the vertical strategy through real-time horizontal indicator feedback ensures that the drone always ascends vertically within a preset tolerance, significantly improving takeoff safety and environmental robustness.

[0085] See Figure 5 FIG2 is a schematic diagram showing the structure of a drone takeoff control device provided in an embodiment of the present application; an embodiment of the present application provides a drone takeoff control device 200, comprising: The reference information acquisition module 210 is used to acquire target information of a reference object set on the mobile platform. The mobile platform is relatively stationary with respect to the reference object in a moving state.

[0086] The horizontal index determination module 220 is used to determine the relative horizontal index between the UAV and the reference object based on the target information when the vertical distance between the UAV and the mobile platform is less than a preset distance threshold. The relative horizontal index includes: relative horizontal position and / or relative horizontal distance and / or relative horizontal speed.

[0087] The control instruction generation module 230 is used to generate control instructions based on the relative horizontal index. The control instructions are used to adjust the horizontal position of the drone so that the relative horizontal index between the drone and the reference object is within a preset index range until the vertical distance between the drone and the mobile platform is greater than a preset distance threshold.

[0088] As an optional embodiment of the above-mentioned device, the reference object includes: a two-dimensional visual marker with a coding feature set on the mobile platform, and the target information includes a visual image of the two-dimensional visual marker; the horizontal index determination module includes: The first position distance determination submodule is used to identify the regional position of the two-dimensional visual marker from the visual image of the two-dimensional visual marker, and determine the relative horizontal position and / or relative horizontal distance between the preset position point of the drone and the regional position of the two-dimensional visual marker based on the visual image.

[0089] And / or, a first relative speed determination submodule is used to determine the relative horizontal speed between a preset position point of the drone and the regional position of the two-dimensional visual marker from multiple visual images of the two-dimensional visual marker at different times.

[0090] As an optional embodiment of the above-mentioned device, the reference object includes: a positioning device set on a mobile platform, the target information includes a real-time position or real-time speed sent by the positioning device; the horizontal index determination module includes: The second position distance determination submodule is used to obtain the real-time position of the UAV and determine the relative horizontal position and / or relative horizontal distance between the UAV and the positioning device based on the real-time position of the UAV and the real-time position of the positioning device.

[0091] And / or, a second relative speed determination submodule is used to obtain the real-time speed of the drone and determine the relative horizontal speed between the drone and the positioning device based on the real-time speed of the drone and the real-time speed of the positioning device.

[0092] As an optional embodiment of the above-mentioned device, the reference object includes: a two-dimensional visual marker and a positioning device provided on a mobile platform; the target information includes: a visual image of the two-dimensional visual marker and a real-time position or real-time speed transmitted by the positioning device; the horizontal index determination module includes: The first level indicator determination submodule is used to determine a first relative level indicator between the UAV and the two-dimensional visual identifier according to the regional position of the two-dimensional visual identifier in the visual image and the preset position point of the UAV.

[0093] The second level index determination submodule is used to determine a second relative level index between the UAV and the positioning device according to the real-time position and / or real-time speed sent by the positioning device.

[0094] The fusion level indicator determination submodule is used to fuse the first relative level indicator and the second relative level indicator to obtain a fused relative level indicator. The fused relative level indicator includes: relative horizontal position and / or relative horizontal distance and / or relative horizontal speed.

[0095] As an optional embodiment of the above-mentioned device, the reference object includes: at least one target object set on the mobile platform, and the target information includes image feature points of the target object; the reference information acquisition module includes: The target image shooting submodule is used to shoot at least one target object set on the mobile platform through the camera of the drone to obtain a target image of the at least one target object.

[0096] The image feature extraction submodule is used to extract feature points from a target image of at least one target object to obtain image feature points of the target object.

[0097] The horizontal index determination module includes: a position distance determination submodule, which is used to determine the relative horizontal position and / or relative horizontal distance between the preset position point of the drone and the image feature point based on the preset position point of the drone and the image feature point.

[0098] As an optional embodiment of the above-mentioned device, the reference objects include: multiple target objects set on the mobile platform, and the target information includes: radar ranging data of the drone's surround radar for the multiple target objects; the horizontal index determination module includes: The horizontal distance determination submodule is used to determine the relative horizontal distance between the UAV and the multiple target objects in the horizontal direction based on the radar ranging data of the multiple target objects.

[0099] It should be understood that this device corresponds to the aforementioned UAV takeoff control method embodiment and is capable of executing each of the steps involved in the aforementioned method embodiment. The specific functions of this device can be found in the description above, and a detailed description is omitted here. The device includes at least one software functional module that can be stored in a memory in the form of software or firmware or embedded in the device's operating system (OS).

[0100] See Figure 6 The electronic device 300 provided in the embodiment of the present application includes a processor 310 and a memory 320, wherein the memory 320 stores machine-readable instructions executable by the processor 310, and when the machine-readable instructions are executed by the processor 310, the method described above is performed.

[0101] The embodiment of the present application further provides a computer-readable storage medium 330, on which a computer program is stored, and the computer program executes the above method when executed by the processor 310. The computer-readable storage medium 330 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0102] An embodiment of the present application further provides a computer program product, including: a computer program or computer instructions, which executes the method described above when the computer program or computer instructions are executed by a processor.

[0103] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similarities between the various embodiments can be referred to in conjunction with each other. For device embodiments, since they are generally similar to method embodiments, their description is relatively simple, and for relevant details, reference can be made to the description of the method embodiments.

[0104] In the several embodiments provided in the embodiments of the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are only schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible implementation architectures, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and a module, a program segment or a part of a code contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also be different from the order of occurrence marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which is mainly based on the functions involved.

[0105] In addition, the functional modules of each embodiment in the embodiments of the present application can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part. In addition, in the description of this specification, the descriptions with reference to the terms "one embodiment", "some embodiments", "example", "specific example", "some examples", etc. mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiments of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in an appropriate manner in any one or more embodiments or examples. In addition, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples without contradiction.

[0106] The above description is only an optional implementation method of the embodiment of the present application, but the protection scope of the embodiment of the present application is not limited to this. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in the embodiment of the present application, and they should all be covered by the protection scope of the embodiment of the present application.

Claims

1. A method for controlling the takeoff of an unmanned aerial vehicle, characterized in that: Applications in drones include: Acquiring target information of a reference object set on a mobile platform, wherein the mobile platform is relatively stationary with respect to the reference object in a moving state; When the vertical distance between the UAV and the mobile platform is less than a preset distance threshold, determining a relative horizontal index between the UAV and the reference object according to the target information, the relative horizontal index including: relative horizontal position and / or relative horizontal distance and / or relative horizontal speed; A control instruction is generated based on the relative horizontal index, and the control instruction is used to adjust the position of the drone in the horizontal direction so that the relative horizontal index between the drone and the reference object is within a preset index range until the vertical distance between the drone and the mobile platform is greater than the preset distance threshold.

2. The method according to claim 1, characterized in that The reference object includes: a two-dimensional visual identifier with a coding feature set on the mobile platform, and the target information includes a visual image of the two-dimensional visual identifier; and determining a relative horizontal index between the drone and the reference object based on the target information includes: Identifying the regional position of the two-dimensional visual marker from the visual image of the two-dimensional visual marker, and determining the relative horizontal position and / or relative horizontal distance between the preset position point of the drone and the regional position of the two-dimensional visual marker based on the visual image; and / or, The relative horizontal speed between the preset position point of the UAV and the regional position of the two-dimensional visual mark is determined from a plurality of visual images of the two-dimensional visual mark at different times.

3. The method according to claim 1, characterized in that The reference object includes: a positioning device provided on the mobile platform; the target information includes a real-time position and / or real-time speed sent by the positioning device; and determining a relative level index between the UAV and the reference object based on the target information includes: Obtaining the real-time position of the UAV, and determining the relative horizontal position and / or relative horizontal distance between the UAV and the positioning device based on the real-time position of the UAV and the real-time position of the positioning device; and / or, The real-time speed of the UAV is obtained, and the relative horizontal speed between the UAV and the positioning device is determined according to the real-time speed of the UAV and the real-time speed of the positioning device.

4. The method according to claim 1, wherein The reference object includes: a two-dimensional visual marker and a positioning device provided on the mobile platform; the target information includes: a visual image of the two-dimensional visual marker and a real-time position or real-time speed transmitted by the positioning device; and determining a relative horizontal index between the UAV and the reference object based on the target information includes: Determining a first relative horizontal index between the drone and the two-dimensional visual marker based on the regional position of the two-dimensional visual marker in the visual image and a preset position point of the drone; determining a second relative horizontal index between the UAV and the positioning device according to the real-time position and / or real-time speed sent by the positioning device; The first relative horizontal index and the second relative horizontal index are fused to obtain a fused relative horizontal index, where the fused relative horizontal index includes: relative horizontal position and / or relative horizontal distance and / or relative horizontal speed.

5. The method according to claim 1, wherein The reference object includes: at least one target object set on the mobile platform, and the target information includes image feature points of the target object; and obtaining the target information of the reference object set on the mobile platform includes: photographing at least one target object disposed on the mobile platform using a camera of the drone to obtain a target image of the at least one target object; Extracting feature points from a target image of the at least one target object to obtain image feature points of the target object; The determining, based on the target information, a relative level index between the drone and the reference object includes: According to the preset location point of the drone and the image feature point, a relative horizontal position and / or relative horizontal distance between the preset location point of the drone and the image feature point is determined.

6. The method according to claim 1, characterized in that The reference objects include: a plurality of target objects set on the mobile platform; the target information includes: radar ranging data of the surround radar of the UAV for the plurality of target objects; and determining the relative level index between the UAV and the reference objects based on the target information includes: The relative horizontal distance between the UAV and the multiple target objects in the horizontal direction is determined according to the radar ranging data of the multiple target objects.

7. The method according to claim 1, characterized in that After determining the relative level index between the UAV and the reference object according to the target information, the method further includes: The vertical ascent strategy of the UAV is determined according to the relative horizontal index.

8. A drone takeoff control device, characterized in that: Applications in drones include: A reference information acquisition module is used to acquire target information of a reference object set on a mobile platform, wherein the mobile platform is relatively stationary with respect to the reference object in a moving state; a horizontal index determining module, configured to determine, when the vertical distance between the UAV and the mobile platform is less than a preset distance threshold, a relative horizontal index between the UAV and the reference object based on the target information, the relative horizontal index including: relative horizontal position and / or relative horizontal distance and / or relative horizontal speed; A control instruction generation module is used to generate a control instruction based on the relative horizontal index, and the control instruction is used to adjust the position of the drone in the horizontal direction so that the relative horizontal index between the drone and the reference object is within a preset index range until the vertical distance between the drone and the mobile platform is greater than the preset distance threshold.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and the machine-readable instructions are executed by the processor to perform the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that include: A computer program or computer instruction, wherein the computer program or the computer instruction is executed by a processor to perform the method according to any one of claims 1 to 7.

Images