A control method and system for guiding an unmanned aerial vehicle to land precisely

Abstract

The present invention discloses a control method and system for guiding an unmanned aerial vehicle (UAV) to land precisely, including: during the landing process of the UAV, images of the landing platform are collected at set intervals; the brightness and contrast of the images are detected to determine whether they meet the set thresholds. If so, image recognition is directly performed; otherwise, image equalization processing is carried out using an image correction algorithm; the position of the visual marker of the landing platform relative to the UAV in the camera coordinate system is obtained, and then the position information of the UAV in the visual marker coordinate system of the landing platform is determined; based on the error between the position information and the position of the expected landing point, considering external disturbances, the position of the UAV is adjusted until the error is adjusted within the set range to control the UAV to land. By setting up a supplementary lighting device on the landing platform, the present invention improves the positioning accuracy of the visual marker of the landing platform when the UAV lands.

Description

Technical Field

[0001] The present invention relates to the technical field of drone inspection, and in particular to a control method and system for guiding a drone to land precisely. Background Art

[0002] The statements in this part merely provide background technical information related to the present invention and do not necessarily constitute prior art.

[0003] In recent years, with the continuous expansion of the power grid scale and the rapid increase in line complexity, drones have gradually become an important tool for line inspection. Deploying airports in a grid within the drone inspection operation range can achieve autonomous line inspection by drones. However, with the increasing demand for power grid inspection services, all-weather intelligent autonomous inspection by drones has become a new requirement for power grid line inspection. In this process, guiding the drone to land precisely at the airport at night is crucial.

[0004] Generally, after a drone completes an inspection task, it receives a return flight command and starts to return to the airport. When the drone reaches above the airport and the preset landing altitude, it starts the precise landing process. However, when the drone lands at the airport at night or in low light conditions, due to the dim light, the drone's camera cannot recognize the visual markers on the airport landing platform. After only relying on RTK positioning, the drone starts to land. During the landing process, the RTK information acquisition frequency is low, the position and attitude adjustment of the drone is slow, and in addition, due to the disturbance of environmental factors such as wind, the drone is prone to deviate from the predetermined landing point, resulting in relatively low landing accuracy. Summary of the Invention

[0005] To solve the above problems, the present invention proposes a control method and system for guiding a drone to land precisely. In the case of night or low light, by designing a supplementary lighting device and combining image vision technology, the position and attitude of the drone are adjusted in real time to guide the drone to land precisely on the landing platform.

[0006] In some embodiments, the following technical solutions are adopted:

[0007] A control method for guiding a drone to land precisely includes:

[0008] During the landing process of the drone, images of the landing platform are collected at a set interval;

[0009] Detect the brightness and contrast of the images, and determine whether they meet the set threshold. If they meet, directly perform image recognition; otherwise, perform image equalization processing using an image correction algorithm;

[0010] Obtain the position of the visual marker of the landing platform relative to the drone in the camera coordinate system, and then determine the position information of the drone in the visual marker coordinate system of the landing platform;

[0011] Based on the error between the position information and the position of the expected landing point, considering external disturbances, adjust the position of the UAV until the error is adjusted within a set range, and control the UAV to land.

[0012] As a further solution, the landing platform is provided with a supplementary lighting device for increasing the brightness of the visual mark on the landing platform;

[0013] Before the UAV returns to the airspace above the airport landing platform and starts automatic landing, first detect the brightness of the acquired visual mark image. If the image brightness is lower than the set first threshold, turn on the supplementary lighting device;

[0014] After the supplementary lighting device is turned on, detect the brightness and contrast of the visual mark image. When the brightness of the visual mark image is lower than the set second threshold, adjust the brightness of the supplementary lighting device by adjusting the PWM duty cycle of the control signal so that the image brightness is not lower than the set second threshold;

[0015] When the adjusted value of the brightness signal of the supplementary lighting device is greater than its adjustable upper limit or less than its adjustable lower limit value, the brightness of the supplementary lighting device is no longer adjusted; if the brightness of the image still does not meet the set threshold at this time, the image correction algorithm performs image equalization processing.

[0016] As a further solution, before collecting the image of the landing platform, perform UAV camera calibration; the specific process is as follows:

[0017] Determine the number of corner points of the calibration board and the actual size of each checkerboard;

[0018] Use the UAV camera to take pictures of the calibration board in different directions and angles to obtain a set of images;

[0019] Detect the feature points in the calibration board image, obtain the pixel coordinates of the corner points of the calibration board, and calculate the physical coordinate values of the corner points of the calibration board according to the actual size of the checkerboard and the world coordinate system coordinates;

[0020] According to the relationship between the obtained physical coordinate values of the corner points and the pixel coordinate values of the corner points, calculate and obtain the internal parameter matrix I and the distortion parameter matrix D of the camera; and optimize the internal parameter matrix I and the distortion parameter matrix D.

[0021] As a further solution, use the image correction algorithm to perform image equalization processing, and the specific process is as follows:

[0022] Convert the collected RGB image into a grayscale image and calculate the pixel gray levels of the grayscale image;

[0023] Normalize the image gray levels and calculate the cumulative distribution function of the gray histogram;

[0024] Perform an inverse image transformation based on the cumulative distribution function to obtain the image after image equalization.

[0025] As a further solution, obtain the position of the landing platform visual marker relative to the UAV in the camera coordinate system, and then determine the position information of the UAV in the landing platform visual marker coordinate system. The specific process is as follows:

[0026] Based on the internal parameter matrix of the UAV camera calibration, obtain the external parameters of the camera to obtain the rotation matrix R and the translation matrix T;

[0027] Obtain the coordinates of the landing platform visual marker in the camera coordinate system, and use the rotation matrix R and the translation matrix T to establish the coordinate transformation relationship between the UAV in the camera coordinate system and the landing platform visual marker coordinate system;

[0028] Based on the coordinates of the UAV in the camera coordinate system, calculate the coordinates of the UAV in the landing platform visual marker coordinate system.

[0029] As a further solution, based on the error between the position information and the expected landing point position, considering external disturbances, adjust the position of the UAV. The specific process includes:

[0030] Determine the landing point position of the UAV in the visual landing platform, and obtain the coordinates of the landing point position in the landing platform visual marker coordinate system;

[0031] Based on the coordinates of the UAV in the landing platform visual marker coordinate system and the coordinates of the landing point position in the landing platform visual marker coordinate system, calculate the landing error;

[0032] Determine the control quantity for the landing error through PID control, add a control compensation term to the control quantity, and use the obtained control quantity to adjust the position of the UAV.

[0033] As a further solution, the control compensation term is determined according to the position error calculated by the pose solution at the current moment and the position error calculated by the pose solution at the previous moment.

[0034] In some other embodiments, the following technical solution is adopted:

[0035] A control system for guiding the precise landing of a UAV, comprising:

[0036] An image acquisition module, configured to acquire images of the landing platform at a set interval during the landing process of the UAV;

[0037] An image preprocessing module, configured to detect the brightness and contrast of the image, determine whether it meets the set threshold. If it meets, directly perform image recognition; otherwise, perform image equalization processing using an image correction algorithm;

[0038] A position conversion module, configured to obtain the position of the vision marker on the landing platform in the camera coordinate system relative to the UAV, and further determine the position information of the UAV in the vision marker coordinate system of the landing platform;

[0039] An error control module, configured to adjust the position of the UAV based on the error between the position information and the expected landing point position, considering external disturbances, until the error is adjusted within a set range, and control the UAV to land.

[0040] In some other embodiments, the following technical solution is adopted:

[0041] A terminal device, which includes a processor and a memory. The processor is used to implement each instruction; the memory is used to store multiple instructions, and the instructions are adapted to be loaded and executed by the processor to perform the above control method for guiding the UAV to land precisely.

[0042] In some other embodiments, the following technical solution is adopted:

[0043] A computer-readable storage medium, in which multiple instructions are stored, and the instructions are adapted to be loaded and executed by the processor of the terminal device to perform the above control method for guiding the UAV to land precisely.

[0044] Compared with the prior art, the beneficial effects of the present invention are:

[0045] (1) The present invention innovatively proposes a control method for guiding the UAV to land precisely. By setting up a supplementary lighting device on the landing platform, the position of the vision marker of the airport landing platform can be clearly displayed by lighting at night or in weak light conditions, improving the positioning accuracy of the vision marker of the landing platform when the UAV lands, solving the problem that the position of the vision marker of the landing platform cannot be obtained at night and only RTK positioning can be relied on, and improving the accuracy of the UAV landing at night.

[0046] (2) The present invention innovatively proposes an image equalization processing method. After obtaining the vision marker image, image preprocessing is added to adjust the brightness or contrast of the image, improving the accuracy of image recognition; solving the problems that affect image recognition such as the image being too dark and the image contrast being low when obtaining images at night.

[0047] Other features and advantages of the additional aspects of the present invention will be partially given in the following description, partially will become apparent from the following description, or will be understood through the practice of this aspect. Description of the Drawings

[0048] Figure 1 It is a flowchart of the control method for guiding the UAV to land precisely in the embodiment of the present invention;

[0049] Figure 2Schematic diagram of the structure disassembly of the lighting device for the landing platform in the embodiment of the present invention;

[0050] Figure 3 Top view of the lighting device for the landing platform in the embodiment of the present invention. Detailed implementation manners

[0051] It should be noted that the following detailed description is exemplary and is intended to provide further illustration of the present application. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present application belongs.

[0052] It should be noted that the terms used herein are only for describing specific implementation manners and are not intended to limit the exemplary implementation manners according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0053] Embodiment 1

[0054] In one or more embodiments, a control method for guiding an unmanned aerial vehicle (UAV) to land precisely is disclosed. Referring to Figure 1 , the specific process is as follows:

[0055] (1) During the landing process of the UAV, images of the landing platform are collected at set intervals;

[0056] In this embodiment, in combination with Figure 2 and Figure 3 , a lighting device is arranged on the landing platform. The lighting device is a supplementary light. A backlight source with uniform light is selected, and a lighting scheme of lighting at the bottom of the visual mark on the landing platform is adopted. According to the size of the UAV landing platform, the lighting source is installed and fixed at the bottom of the visual mark on the landing platform. The light source line is routed by drilling holes in the landing platform and connected to the controller to facilitate the turning on and off of the light source.

[0057] Before the UAV returns to the airport airspace and starts the automatic landing process, the precise landing process is triggered. First, the brightness of the visual marker image is detected. If the image brightness is lower than the set first threshold (the threshold for turning on the fill light), the fill light on the airport landing platform is turned on at this time. After turning on the fill light, the brightness and contrast of the image are detected. When the image brightness is lower than the set second threshold (the threshold for low image brightness, set according to the actual project recognition requirements), first adjust the brightness of the fill light. Send a fill light brightness adjustment signal from the airport to adjust the PWM duty cycle of the fill light to adjust the image brightness, and perform brightness detection. When the adjusted value of the fill light brightness signal is less than the adjustable lower limit or higher than the adjustable upper limit, the brightness of the fill light is no longer adjusted. If the brightness of the image still does not meet the set threshold (the threshold for image equalization processing) at this time, the image correction algorithm performs image equalization processing. Among them, the lower limit or upper limit of the adjusted value of the fill light brightness signal is determined by the selected fill light model.

[0058] Calculate the time according to the landing control process, design the image acquisition time interval of the UAV camera. During the UAV landing process, continuously collect the images of the visual marker on the landing platform to continuously adjust the position of the UAV and guide the UAV to land.

[0059] (2) Detect the brightness and contrast of the image to determine whether it meets the set threshold. If it meets, directly perform image recognition; otherwise, use the image correction algorithm to perform image equalization processing;

[0060] In this embodiment, after obtaining the image of the visual marker on the landing platform collected by the UAV, detect the brightness and contrast of the image. When it meets the set threshold, it can directly perform recognition detection; when it does not meet the set threshold, perform equalization processing on the collected image; the specific processing process is as follows:

[0061] 1) Convert the collected RGB image to a grayscale image;

[0062] 2) Calculate the pixel gray level m of the grayscale image;

[0063] 3) Normalize the image gray level, where 0 represents black and 1 represents white; and use the probability density p m (m) to represent the distribution of the image gray level:

[0064]

[0065] 4) Calculate the cumulative distribution function of the grayscale histogram:

[0066]

[0067] Among them, k represents the k-th gray level of the image, l represents the gray level of the image, m k represents the probability of the current gray level appearing, nk Indicates the number of pixels with a gray level of m k , s k The value after mapping by the cumulative distribution function of the current gray level. n is the total number of pixels in the image, n j is the number of pixels at the current gray level.

[0068] 5) Perform inverse image transformation to obtain the image after histogram equalization, m k .

[0069] m k = T -1 (s k ) (3)

[0070] (3) Obtain the position of the landing platform visual marker relative to the UAV in the camera coordinate system, and then determine the position information of the UAV in the landing platform visual marker coordinate system;

[0071] In this embodiment, before the UAV camera acquires an image, the Zhang Dingyou camera calibration method is first used to calibrate the camera to obtain camera parameters; the specific calibration method is as follows:

[0072] 1) Prepare a camera calibration board, and determine the number of corner points of the calibration board and the actual size of each checkerboard;

[0073] 2) Use the UAV camera to take pictures of the calibration board in different directions and angles to obtain a set of images;

[0074] 3) Detect the feature points in the calibration board image, obtain the pixel coordinates of the corner points of the calibration board, and calculate the physical coordinate values of the corner points of the calibration board according to the actual size of the checkerboard and the world coordinate system coordinates;

[0075] 4) Calculate and obtain the internal parameter matrix I and distortion parameter matrix D of the camera according to the relationship between the obtained physical coordinate values of the corner points and the pixel coordinate values of the corner points;

[0076] 5) Use opencv to optimize the internal parameters I and distortion parameters D of the camera.

[0077] After calibration, obtain the preprocessed image in step (2), and identify the landing platform visual marker in the image through vision. The specific process is as follows:

[0078] 1) Based on the internal parameter matrix of the UAV camera calibration, obtain the external parameters of the camera to obtain the rotation matrix R and translation matrix T;

[0079] 2) Obtain the coordinates of the landing platform visual marker in the camera coordinate system, and use the rotation matrix R and translation matrix T to establish the coordinate transformation relationship between the UAV in the camera coordinate system and the landing platform visual marker coordinate system:

[0080]

[0081] Among them, is the position coordinate of the UAV in the camera coordinate system, is the position coordinate of the UAV in the visual marker coordinate system.

[0082] 3) Based on the coordinates of the UAV in the camera coordinate system, calculate the coordinates of the UAV in the visual marker coordinate system of the landing platform, specifically:

[0083]

[0084] Among them, the coordinates of the UAV in the camera coordinate system are obtained from the translation matrix result automatically returned after the apriltag recognition. The adopted apriltag visual marker relies on the Apriltag open-source library for recognition. Through the open-source library, Apriltag recognition can be performed. After successful recognition, its corresponding ID, the corner coordinates of the visual marker, as well as the rotation matrix and displacement matrix will be returned. Among them, the coordinates of the UAV in the camera coordinate system can be obtained through the acquired displacement matrix.

[0085] (4) Based on the error between the coordinate position information of the UAV in the visual marker coordinate system of the landing platform and the expected landing point position, considering external disturbances, adjust the position of the UAV until the error is adjusted within the set range, and control the UAV to land.

[0086] In this embodiment, first, determine the landing point information of the UAV in the landing platform, and obtain the coordinate information of the UAV in the visual marker coordinate system

[0087] Then, based on the coordinates of the UAV in the visual marker coordinate system, obtain the error e between the real-time position information of the UAV and the expected landing point position 3*1 :

[0088]

[0089] Design a PID controller, and the control result is as follows:

[0090] res = P * error + I * error integral + D * error differential

[0091] At the same time, considering that during the landing process of the UAV, it is vulnerable to external disturbances, resulting in the position adjustment of the UAV may not reach the expected effect. Therefore, a compensation term Δ is added to the control quantity of the UAV. The calculation of the compensation term is as follows:

[0092] Let the position error calculated by the pose solution at the current moment be e k , and the position error calculated by the pose solution at the previous moment be e k-1 , then:

[0093]

[0094] Among them, k > 0, and the value of k is selected according to the actual situation.

[0095] Calculate the control amount and adjust the position of the UAV: control = res + Δ.

[0096] Determine whether to allow the UAV to land, that is, whether the allowable error is satisfied. If it is satisfied, the UAV is allowed to land; if not, the UAV needs to continue to adjust its position to ensure that the UAV lands accurately on the landing platform of the airport.

[0097] The method of this embodiment can add a supplementary lighting device on the landing platform, so that the UAV can accurately obtain the position of the visual marker in the landing platform; and through the method of image equalization processing, adjust the brightness or contrast of the image to improve the accuracy of image recognition, and solve the problems that affect image recognition such as the image being too dark and the image contrast being low when collecting images at night.

[0098] Embodiment 2

[0099] In one or more embodiments, a control system for guiding a UAV to land precisely is disclosed, including:

[0100] An image acquisition module, configured to acquire images of the landing platform at a set interval during the landing process of the UAV;

[0101] An image preprocessing module, configured to detect the brightness and contrast of the image, and determine whether the set threshold is satisfied. If it is satisfied, directly perform image recognition; otherwise, perform image equalization processing using an image correction algorithm;

[0102] A position conversion module, configured to obtain the position of the visual marker of the landing platform relative to the UAV in the camera coordinate system, and further determine the position information of the UAV in the visual marker coordinate system of the landing platform;

[0103] An error control module, configured to adjust the position of the UAV based on the error between the position information and the expected landing point position, considering external disturbances, until the error is adjusted within the set range to control the landing of the UAV.

[0104] It should be noted that the specific implementation manners of the above modules have been described in Embodiment 1, and will not be elaborated here.

[0105] Embodiment 3

[0106] In one or more embodiments, a terminal device is disclosed, including a server. The server includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the control method for guiding an unmanned aerial vehicle to land precisely in the first embodiment. For the sake of brevity, it will not be elaborated here.

[0107] It should be understood that in this embodiment, the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0108] The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A part of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0109] In the implementation process, each step of the above method may be completed by the integrated logic circuit in the hardware of the processor or the instructions in the form of software.

[0110] Embodiment 4

[0111] In one or more embodiments, a computer-readable storage medium is disclosed, in which multiple instructions are stored. The instructions are adapted to be loaded and executed by the processor of the terminal device to implement the control method for guiding an unmanned aerial vehicle to land precisely described in the first embodiment.

[0112] Although the specific implementation manners of the present invention are described above in conjunction with the drawings, it is not a limitation to the protection scope of the present invention. Those skilled in the art should understand that based on the technical solution of the present invention, various modifications or deformations that can be made by those skilled in the art without creative efforts are still within the protection scope of the present invention.

Claims

1. A control method for guiding an unmanned aerial vehicle to land precisely, characterized in that include: During the landing process of the drone, images of the landing platform are collected at set intervals; The brightness and contrast of the image are detected to determine whether they meet the set threshold. If so, image recognition is performed directly; otherwise, image correction algorithm is used to perform image equalization processing; Obtain the position of the landing platform visual mark relative to the UAV in the camera coordinate system, and then determine the position information of the UAV in the landing platform visual mark coordinate system; Based on the error between the position information and the expected landing point, the position of the drone is adjusted taking into account external disturbances until the error is adjusted to within a set range, and the drone is controlled to land. The specific process includes: Determine the landing point position of the UAV in the visual landing platform, and obtain the coordinates of the landing point position in the visual mark coordinate system of the landing platform; Calculate the landing error based on the coordinates of the UAV in the landing platform visual marker coordinate system and the coordinates of the landing point position in the landing platform visual marker coordinate system; Determine the control amount of the landing error by PID control, add a control compensation term to the control amount, and use the obtained control amount to adjust the position of the drone; Determine the landing point information of the UAV on the landing platform and obtain the coordinate information of the UAV in the visual marker coordinate system Then, based on the coordinates of the UAV in the visual marker coordinate system, the error e between the real-time position information of the UAV and the position of the expected landing point is obtained 3*1 : Design a PID controller and the control results are as follows: res = P*error + I*integral error + D*differential error Considering that the UAV is susceptible to external disturbances during landing, a compensation term is added to the control amount of the UAV. The calculation of the compensation term is as follows: Among them, e k is the position error calculated by the pose solution at the current moment, and e k-1 is the position error calculated by the pose solution at the previous moment, k > 0, and the value of k is selected according to the actual situation; Calculate the control amount and adjust the drone position: control = res + Δ; Determine whether the allowable error is met. If it is met, the drone is allowed to land. If not, the drone needs to continue adjusting its position. The control compensation item is determined based on the position error calculated by the posture solution at the current moment and the position error calculated by the posture solution at the previous moment.

2. The control method for guiding an unmanned aerial vehicle to accurately land according to claim 1, characterized in that, The landing platform is provided with a fill light device to increase the brightness of the visual signs of the landing platform; Before the drone returns to the airport landing platform and starts automatic landing, it first detects the brightness of the acquired visual sign image. If the image brightness is lower than the set first threshold, the fill light device is turned on; After the fill light device is turned on, the brightness and contrast of the visual sign image are detected. When the brightness of the visual sign image is lower than a set second threshold, the brightness of the fill light device is adjusted by adjusting the PWM duty cycle of the control signal so that the image brightness is not lower than the set second threshold; When the adjustment value of the fill light device brightness signal is greater than its adjustable upper limit or less than its adjustable lower limit, the fill light device brightness is no longer adjusted; if the image brightness still does not meet the set threshold at this time, the image correction algorithm performs image equalization processing.

3. The control method for guiding an unmanned aerial vehicle to accurately land according to claim 1, characterized in that, Before collecting images of the landing platform, the drone camera is calibrated; the specific process is as follows: Determine the number of corner points on the calibration plate and the actual size of each chessboard grid; Use the drone camera to take pictures of the calibration plate in different directions and angles to obtain a set of images; Detect the feature points in the calibration plate image, obtain the pixel coordinates of the corner points of the calibration plate, and calculate the physical coordinate values of the corner points of the calibration plate according to the actual size of the chessboard and the coordinates of the world coordinate system; According to the relationship between the obtained physical coordinate values and pixel coordinate values of the corner points, calculate and obtain the internal parameter matrix I and distortion parameter matrix D of the camera; optimize the internal parameter matrix I and distortion parameter matrix D.

4. The control method for guiding an unmanned aerial vehicle to land precisely according to claim 1, characterized in that, Use the image correction algorithm to perform image equalization processing. The specific process is as follows: Convert the collected RGB image into a grayscale image and calculate the pixel gray level of the grayscale image; Normalize the image gray level and calculate the cumulative distribution function of the gray histogram; Perform image inverse transformation based on the cumulative distribution function to obtain the image after image equalization.

5. The control method for guiding an unmanned aerial vehicle to accurately land according to claim 1, wherein Obtain the position of the landing platform visual marker relative to the UAV in the camera coordinate system, and then determine the position information of the UAV in the landing platform visual marker coordinate system. The specific process is as follows: Based on the internal parameter matrix of the UAV camera calibration, obtain the external parameters of the camera to obtain the rotation matrix R and translation matrix T; Obtain the coordinates of the landing platform visual marker in the camera coordinate system, and use the rotation matrix R and translation matrix T to establish the coordinate transformation relationship between the UAV in the camera coordinate system and the landing platform visual marker coordinate system; Based on the coordinates of the UAV in the camera coordinate system, calculate the coordinates of the UAV in the landing platform visual marker coordinate system.

6. A control system for guiding an unmanned aerial vehicle to land precisely, characterized in that, It includes: An image acquisition module for collecting images of the landing platform at a set interval during the landing process of the UAV; An image preprocessing module for detecting the brightness and contrast of the image, determining whether it meets the set threshold. If it meets, directly perform image recognition; otherwise, use the image correction algorithm to perform image equalization processing; A position conversion module for obtaining the position of the landing platform visual marker relative to the UAV in the camera coordinate system, and then determining the position information of the UAV in the landing platform visual marker coordinate system; An error control module for adjusting the position of the UAV based on the error between the position information and the expected landing point position, considering external disturbances, until the error is adjusted within the set range to control the landing of the UAV. The specific process includes: Determine the landing point position of the UAV in the visual landing platform and obtain the coordinates of the landing point position in the landing platform visual marker coordinate system; Calculate the landing error based on the coordinates of the UAV in the landing platform visual marker coordinate system and the coordinates of the landing point position in the landing platform visual marker coordinate system; Determine the control quantity for the landing error through PID control, add a control compensation term to the control quantity, and use the obtained control quantity to adjust the position of the UAV; Determine the landing point information of the drone on the landing platform and obtain the coordinate information of the drone in the visual marker coordinate system Then, based on the coordinates of the UAV in the visual marker coordinate system, the error e between the real-time position information of the UAV and the position of the expected landing point is obtained 3*1 : Design a PID controller, and the control result is as follows: res = P * error + I * error integral + D * error derivative Considering that the UAV is vulnerable to external disturbances during the landing process, add a compensation term to the control quantity of the UAV. The calculation of the compensation term is as follows: Among them, e k is the position error calculated by the pose solution at the current moment, and e k-1 is the position error calculated by the pose solution at the previous moment, k > 0, and the value of k is selected according to the actual situation; Calculate the control quantity and adjust the position of the UAV: control = res + Δ; Determine whether the allowable error is met. If it is met, allow the UAV to land; if not, the UAV needs to continue to adjust its position; The control compensation term is determined according to the position error calculated by the pose solution at the current moment and the position error calculated by the pose solution at the previous moment.

7. The control system for guiding an unmanned aerial vehicle to land precisely according to claim 6, wherein The landing platform is provided with a supplementary lighting device for increasing the brightness of the landing platform visual marker; Before the UAV returns to the airspace above the airport landing platform and starts automatic landing, first detect the brightness of the acquired visual marker image. If the image brightness is lower than the set first threshold, turn on the supplementary lighting device; After the supplementary lighting device is turned on, detect the brightness and contrast of the visual marker image. When the brightness of the visual marker image is lower than the set second threshold, adjust the brightness of the supplementary lighting device by adjusting the PWM duty cycle of the control signal so that the image brightness is not lower than the set second threshold; When the adjusted value of the brightness signal of the supplementary lighting device is greater than its adjustable upper limit or less than its adjustable lower limit value, the brightness of the supplementary lighting device is no longer adjusted; if the brightness of the image still does not meet the set threshold at this time, the image correction algorithm performs image equalization processing.

8. A terminal device, comprising a processor and a memory, the processor being configured to implement various instructions; the memory being configured to store multiple instructions, characterized in that, The instruction is suitable for being loaded and executed by a processor to perform the control method for guiding the UAV to land precisely according to any one of claims 1-5.

9. A computer-readable storage medium storing multiple instructions, characterized in that, The instruction is suitable for being loaded and executed by a processor of a terminal device to perform the control method for guiding the UAV to land precisely according to any one of claims 1-5.

Images