Control method for hand landing of unmanned aerial vehicle and unmanned aerial vehicle

Abstract

A method for controlling the palm landing of a drone, a control device and a drone. Under preset conditions, the flight state of the drone is detected (S101). When the flight state of the drone is a hovering state and the palm is located below the drone, the drone is controlled to land on the palm of the user (S102). This can effectively reduce the requirements of the drone on the landing conditions in the prior art, while saving the time of the user to recover the drone and improving the convenience of the drone landing.

Description

Technical Field

[0001] The present invention belongs to the technical field of unmanned aerial vehicles, and more specifically, relates to a control method for palm landing of an unmanned aerial vehicle, a control device and an unmanned aerial vehicle. Background Art

[0002] With the development of science and technology, the functions of drones and other aircraft are constantly enriched, and their application areas are also constantly expanding, including aerial photography, surveying, rescue, agriculture and other fields.

[0003] When a drone needs to land after completing a mission or when the battery is low, the current landing method is to control the drone to land on a flat ground at a distance from the user. However, this landing method will bring inconvenience to the user: first, the drone needs to land on a relatively flat ground. When the drone needs to land, in some cases, such as when the user is in sand, fields, hills, etc., it may be difficult for the user to find a flat ground to control the drone to land, which will reduce the safety of the drone landing; in addition, currently, after the drone lands, the user needs to walk over and pick up the drone, which increases the user's operation time. The lack of a safe and easy landing method may reduce the usefulness of drones in some cases. Summary of the invention

[0004] The embodiment of the present invention provides a control method for palm landing of a drone and a drone, so as to improve the convenience of landing of the drone.

[0005] A first aspect of an embodiment of the present invention provides a method for controlling palm landing of a drone, comprising:

[0006] Controlling the image sensor of the drone to acquire a first image;

[0007] detecting whether the first image includes a user;

[0008] Detecting the flight status of the drone;

[0009] Collecting a second image below the drone based on an image sensor of the drone;

[0010] recognizing a palm according to the second image, and determining a position of the palm;

[0011] If the first image includes the user, the flight state of the drone is a hovering state, and it is determined that the palm is located below the drone, the speed of the driving motor of the drone is reduced, and the drone is controlled to land on the palm according to the position.

[0012] A second aspect of an embodiment of the present invention provides a drone, including:

[0013] body;

[0014] The power system fixed on the fuselage is used to provide flight power;

[0015] A memory for storing program instructions;

[0016] A processor is used to execute the program instructions stored in the memory. When the program instructions are executed, the processor is used to execute the steps of the method described in the first aspect.

[0017] The control method for palm landing of a drone and the drone provided in the embodiments of the present invention detect the flight state of the drone under preset conditions, and when the flight state is a hovering state and the palm is located below the drone, control the drone to land on the palm of the user, which can effectively reduce the requirements of the drone on the landing conditions in the prior art, while saving the user's time to recover the drone and improving the convenience of drone landing. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 is a flow chart of a palm landing control method provided by an embodiment of the present invention;

[0020] Figure 2 A schematic diagram of detecting the flight state of a drone after receiving a palm landing command sent by a control terminal provided by an embodiment of the present invention;

[0021] Figure 3 A schematic diagram of performing user detection and distance determination based on image data output by a second image sensor according to an embodiment of the present invention;

[0022] Figure 4 A schematic diagram of determining that a palm is located below a drone according to a distance sensor provided in an embodiment of the present invention;

[0023] Figure 5 A schematic diagram of controlling a drone to land on a palm according to the palm position provided by an embodiment of the present invention;

[0024] Figure 6 A schematic diagram of the structure of a control device for palm landing of a drone provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the present invention will be described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there can be a central component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there can be a central component at the same time.

[0027] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0028] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0029] An embodiment of the present invention provides a method for controlling the palm landing of an unmanned aerial vehicle. Figure 1 Flow chart of the palm landing control method provided by the embodiment of the present invention. Figure 1 As shown, the method of this embodiment may include:

[0030] S101, detecting the flight status of the UAV under preset conditions;

[0031] Specifically, when the drone is preparing to land, it should detect the flight status. There are several feasible ways to trigger the drone to detect the flight status:

[0032] One possible way: Figure 2 As shown, when a palm landing command sent by the control terminal 201 is received, the flight status of the drone is detected. Specifically, when landing is required, the user can send a command to the drone to enter the landing mode through the control terminal 201. After receiving the command, the sensor system of the drone collects data information, and the flight control system of the drone can detect the flight status of the drone based on the collected data. Among them, the control terminal can be one or more of a remote control, a smart phone, a tablet computer, a laptop, a ground control station, and a wearable device (watch, bracelet).

[0033] Another feasible way: obtain the image data output by the second image sensor; when it is determined that the user is detected according to the image data output by the second image sensor, detect the flight status of the drone. Specifically, the drone can be equipped with a second image sensor 301, wherein the second image sensor 301 can be installed on the nose of the drone, or installed on the gimbal of the drone. This embodiment is schematically illustrated with the second image sensor being located on the nose of the drone. The second image sensor 301 can collect image data in the flight space in real time. When the user is within the collection range of the second image sensor 301, the second image sensor 301 can obtain image data including user information. The processor of the drone can obtain image data including user information and determine that the user is detected according to the image data, for example, determine that the user is located in front of the drone. When it is determined that the user is detected, the drone starts to detect the flight status.

[0034] Further, when it is determined that a user is detected according to the image data output by the second image sensor 301, detecting the flight state of the drone may include: when it is determined that a user is detected according to the image data output by the second image sensor 301, and the distance between the user and the drone is less than or equal to a preset distance, detecting the state of the drone. Figure 3 As shown, when it is determined based on the image data that a user is detected, for example, when the user is in front of the drone, the distance between the user and the drone can be further detected. When the distance between the user and the drone is less than or equal to a preset distance threshold, the drone detects the flight state. The distance between the user and the drone can be determined based on the image data, and can also be determined in other ways in this article. At this time, when it is detected that the user is in front of the drone, and the distance between the user and the drone is less than or equal to the preset distance, the drone starts to detect the flight state.

[0035] In addition, the following part of this article will introduce in detail how to determine the detected user and / or the distance between the user and the drone based on the image data acquired by the second image sensor, which will not be described in detail here.

[0036] It should be noted that the flight status of a drone can be divided into: the drone staying on the ground, hovering, and moving. The moving state can be further divided into descending, climbing, and horizontal flight.

[0037] S102: When the flight state of the drone is a hovering state and the palm is located below the drone, the drone is controlled to land on the palm of the user.

[0038] Specifically, the flight state of the drone is detected, and when it is determined that the flight state of the drone is a hovering state, the user can walk in front of the drone and then extend his palm under the drone. Figure 1The method shown may also include: determining that the palm is located under the drone. Specifically, the drone may use a sensor configured on the belly to detect whether the user's palm is located under the drone. When it is determined that there is a palm under the drone, that is, when it is determined that the user has extended his palm under the drone, the power system of the drone may be controlled, for example, the speed of the driving motor of the drone is reduced, and the drone is controlled to slowly land on the palm of the user. In this way, after the drone stops propellers, the user has achieved the purpose of recovering the drone.

[0039] The control method for palm landing of a drone provided in an embodiment of the present invention detects the flight state of the drone under preset conditions, and when the flight state is a hovering state and the palm is located below the drone, controls the drone to land on the user's palm. This can effectively reduce the requirements for landing conditions of drones in the prior art, while saving the user's time in recovering the drone and improving the convenience of drone landing.

[0040] In some embodiments, detecting the flight state of the drone specifically includes: detecting the flight state of the drone according to one or more of the speed, acceleration, relative height, angular velocity of the body, control stick amount output by the control terminal, and power output acquired by the drone's sensor system. Specifically, the flight control system of the drone includes a flight state machine, wherein the flight state machine is used to detect the flight state of the drone, and the flight state machine can collect data acquired by the drone's sensor system, such as one or more of the speed, acceleration, relative height, angular velocity of the body, control stick amount output by the control terminal, and power output, and detect the flight state of the drone based on the data.

[0041] In some embodiments, since the type of the second sensor used by the drone when acquiring the image data may be different, the following will describe in detail how to detect the user and / or determine the distance between the user and the drone based on the image data. Therefore, the detection of the user based on the image data may be achieved in the following feasible ways:

[0042] A feasible way: when the second image sensor 301 is an RGB camera, the image data may be RGB image data, wherein the RGB camera is any camera that can acquire RGB images, and the RGB image acquired by the RGB camera may be downsampled to a preset resolution, such as 320*240 or 720*360, and then the downsampled image is input to an offline trained neural network, and the neural network may output the user's position in the image, a bounding box, and credibility. When the credibility is greater than or equal to a preset threshold, for example, when the credibility is greater than or equal to 0.8, it is considered that the image data includes user information, i.e., it is determined that the user is detected.

[0043] Furthermore, the distance between the user and the drone can be determined based on the RGB image. As mentioned above, the neural network can output a bounding box, where the bounding box surrounds the user. When the credibility is greater than or equal to a preset threshold, that is, when the user is confirmed to be detected, the distance between the user and the drone can be determined based on the size of the bounding box and the camera parameters. The camera parameters include at least one of the camera's internal parameters and external parameters.

[0044] Another feasible way: when the second image sensor 301 is a TOF (Time of Flight) camera, the image data is depth image data. Since the TOF camera has a short working distance (generally less than 5m) and a low resolution (for example, only 80×60, that is, the width and height of the image are w=80 and h=60), the TOF camera needs to be used to detect the user at a relatively close distance (generally less than 3m). The following will introduce in detail the process of using the depth image data to determine the distance between the detected user and / or the user and the drone:

[0045] Optionally, points within a preset range in the current frame depth image are determined, a connected domain of points within the preset range is determined, and the detected user and / or the distance between the user and the drone is determined based on the connected domain. Specifically, during detection, the user's position in the current frame depth data can be estimated first. and estimated depth Based on the estimated position of the user in the current frame and estimated depth Determine the points within the preset range. The point cloud within the preset range can be:

[0046]

[0047]

[0048] The above preset range is only a schematic illustration, and those skilled in the art can and estimated depth Determine other preset ranges. After determining the points within the preset range, the connected domain of the points can be determined using a flooding algorithm, etc. After obtaining the connected domain, the user can be detected based on the connected domain and the distance between the user and the drone can be determined.

[0049] Further, determining the points within the preset range in the current frame depth image includes: determining the points within the preset range in the current frame depth image according to the previous frame depth image. Specifically, the position of the user in the current frame can be estimated according to the previous frame depth image. and estimated depth The TOF camera acquires multiple depth images at a fixed frame rate. When a user is detected in the previous frame, the estimated position of the user in the current frame can be set to the same as that in the previous frame, that is, the estimated position of the user's body in the current frame is and the estimated depth is If the previous frame does not detect the body but detects the user's hand, the estimated position of the user in the current frame can be the same as the position of the hand detected in the previous frame, and the estimated depth of the user in the current frame is the sum of the depth of the hand detected in the previous frame and the length of the arm. If the previous frame does not detect the user or the current frame is the first frame of image data, it can be considered that the estimated position of the user in the current frame is located at the center of the image. At this time, the estimated depth of the user's body in the current frame can be determined as a preset value. For example, the preset value can range from 1-3m, specifically, it can be 1.3m, 1.5m, 1.7m, etc.

[0050] In some embodiments, determining the detected user and / or the distance between the user and the drone based on the connected domain includes: determining the connected domain with the largest area in the connected domain, and determining the detected user and / or the distance between the user and the drone based on the connected domain with the largest area. Specifically, when using a flooding algorithm to determine the connected domain of points in the preset area, multiple connected domains may be determined. In this case, the connected domain with the largest area is selected to determine the detected user and / or the distance between the user and the drone.

[0051] In some embodiments, determining that a user is detected according to the connected domain includes: normalizing the shape features of the connected domain using the average depth or median depth of the connected domain, and determining that the user is detected using the normalized shape features of the connected domain. Specifically, after obtaining the connected domain, the shape features of the connected domain are determined, wherein the shape features of the connected domain may include at least one of the length, width, and area of ​​the connected domain. When the distance between the user and the drone is different, the size of the user in the image will be different, so it is necessary to eliminate the influence of the distance. At this time, the shape features of the connected domain may be normalized using the average depth of the connected domain or the median depth of the connected domain. For example, the shape features of the connected domain may be multiplied by the average depth of the connected domain or the median depth of the connected domain to obtain the normalized shape features of the connected domain, and the features of the normalized connected domain may be input into a trained classifier, and the classifier may output a sign of whether the user is detected, i.e., determine whether the user is detected. The classifier may be a decision tree, a support vector machine, a naive Bayesian classifier, or the like.

[0052] Further, determining the distance between the user and the drone includes: when it is determined that the user is detected, determining the distance between the user and the drone according to the average depth or median depth of the connected domain. Specifically, when according to the method described above, when it is determined that the user is detected according to the connected domain, the distance between the user and the drone may be the average depth or median depth of the connected domain described above.

[0053] When the mark output by the classifier for detecting users indicates that it is not a user, the shape features of the connected domain after normalization can be input into the trained classifier for detecting palms, and the classifier for detecting palms can output a mark indicating whether the palm is detected.

[0054] In some embodiments, there are other feasible ways to determine whether a palm is detected, for example, determining one or more points with the smallest depth in the depth image, determining the one or more points to determine the point indicating the palm, this point usually indicates the fingertip of the user, and within a preset depth range, taking out all points connected to the point indicating the palm, wherein obtaining all connected points can be achieved by a flood fill algorithm, that is, obtaining a connected domain, and this connected domain is used to indicate the hand, however, the hand includes the palm and the arm, so the point indicating the arm in the connected domain can be deleted, and the connected domain indicating the palm is obtained, and the connected domain indicating the palm can be processed by the normalization processing as described above, and the shape features of the processed connected domain are used to determine whether the palm is detected.

[0055] In some embodiments, it can be determined that the user's palm is located below the drone in the following feasible ways:

[0056] In one feasible way, a relative distance measured by a distance sensor is obtained, wherein the relative distance is the distance between the drone and a reference point below the drone; and the palm is determined to be below the drone based on the distance. Specifically, Figure 4 As shown, a distance sensor can be configured on the belly of the drone, wherein the distance sensor can be any sensor that can measure distance information, such as an ultrasonic sensor, a single-point TOF sensor, a monocular camera, a binocular camera, a TOF camera, etc. When the drone is hovering, when the user has not yet extended his palm under the drone, the distance measured by the distance sensor is the distance from the drone to the ground, that is, the reference point is the ground under the drone, and the distance measured at this time is h1. When the user extends his palm under the user, the distance measured by the distance sensor is the distance from the drone to the user's palm, that is, the reference point is the palm under the drone, and the distance measured at this time is h2. It can be seen that before and after the user extends his palm under the drone, the relative distance measured by the distance sensor changes, so it can be determined that the palm is under the drone based on the change in distance.

[0057] Further, when the change in relative distance meets the preset requirement, it is determined that the user's palm is located below the drone. Specifically, the change in distance is h3 (i.e., h1-h2), and the preset requirement may be: the change in distance is greater than or equal to a preset distance threshold, for example, the preset distance threshold may be set to 0.5m, and when the change in relative distance h3 is greater than or equal to 0.5m, it can be determined that the user has extended his palm below the drone, and the change in distance measured by the distance sensor is caused by the user extending his palm, and the drone can be controlled to land on the user's palm.

[0058] Another feasible way is to obtain the image data of the drone under the first image sensor, and determine whether the palm is under the drone according to the image data. Specifically, the belly of the drone can be the first image sensor, wherein the first image sensor is any sensor that can obtain image information, such as an RGB camera, a monocular camera, a binocular camera, a TOF camera, etc., and the image information can be an RGB image, a grayscale image, a depth image, etc. Among them, the first image sensor and the second image sensor can be the same or different devices. When the user has not yet extended his palm under the drone, the image data acquired by the image sensor does not contain the user's palm information; when the user extends his palm under the drone, the image data acquired by the image sensor will include the user's palm information. Therefore, it can be determined whether the user's palm is under the drone according to the image data. For example, the image data can be input into a neural network model trained offline, and the neural network model will output the credibility and the position of the palm in the image. When the feasibility is greater than a preset threshold (for example, 0.8), it can be considered that the user's palm exists under the drone. At this time, the drone can be controlled to land on the user's palm.

[0059] Furthermore, determining whether the palm is located under the drone based on the image data may include: determining that the palm is located under the drone based on the image data and the change in distance between the drone and a reference point below the drone. Specifically, when it is determined that the image data includes the user's palm information, it may be further determined whether the change in distance caused by the user's palm extending below the drone meets the preset requirements as described above. When the preset requirements are met, it may be determined that the user's palm is located under the drone, and the drone may be controlled to land on the user's palm. The distance here may be determined based on the distance sensor as described above. In addition, when the first image sensor acquires a depth image, the distance may also be determined based on the depth image acquired by the first image sensor.

[0060] In some embodiments, controlling the drone to land on the palm of the user may include: determining the position of the palm, and controlling the drone to land on the palm according to the position. Figure 5 As shown in the figure, when the drone detects that the user's palm is extended under the drone, the user's palm may not be directly under the drone. At this time, the drone may land on the outer edge of the palm, which is not convenient for the user to grab. The drone may fall from the palm or the propeller of the drone may cause damage to the user's palm. The drone can use the sensor configured on the belly to determine the position of the palm relative to the drone. The drone adjusts the landing direction according to the palm position information so that the drone lands accurately in the middle of the user's palm, ensuring landing safety and facilitating the user to grab.

[0061] Furthermore, the drone can use a third image sensor to obtain image data below the drone, and determine the position of the palm in the image based on the image data. The third image sensor can be configured on the belly of the drone. Of course, the distance sensor configured on the belly can determine the relative distance from the palm to the drone, and the position of the palm can be determined based on the position of the palm in the image and the relative distance. In addition, when the third image sensor configured on the belly of the drone can obtain a depth image below the drone, the position of the palm can be determined based on the depth image. Among them, the third image sensor can be the same as or different from the first image sensor; the third image sensor can be the same as or different from the second image sensor.

[0062] In some embodiments, controlling the drone to land on the palm of the user may include: determining a landing speed according to the relative distance between the drone and the palm, and controlling the drone to land on the palm of the user according to the landing speed. Specifically, after determining that the user's palm is below the drone, the drone begins to land. During the landing process, the distance sensor configured on the belly of the drone can measure the relative distance between the drone and the user in real time. After obtaining the relative distance, the motor speed can be controlled according to the relative distance to determine the landing speed of the drone. The landing speed can be determined using a closed-loop control strategy. When the relative distance is large, the landing speed is large, and when the relative distance is small, the landing speed is small. This can ensure the landing safety of the drone.

[0063] An embodiment of the present invention provides a control device for palm landing of a drone. Figure 6 This is a schematic diagram of the structure of a control device for hand landing of a drone provided by an embodiment of the present invention. Figure 6 As shown, the control device 600 for the drone palm landing may include:

[0064] Memory 601, used for storing program instructions;

[0065] The processor 602 is configured to execute the program instructions stored in the memory. When the program instructions are executed, the processor is configured to:

[0066] Under preset conditions, detect the flight status of the drone;

[0067] When the flight state is a hovering state and the palm is located below the drone, the drone is controlled to land on the palm of the user.

[0068] Specifically, when the drone is preparing to land, the processor 602 should detect the flight status. There are several feasible ways to trigger the drone to detect the flight status:

[0069] A feasible manner: the processor 602 is used to detect the flight status of the drone when receiving a palm landing command sent by the control terminal.

[0070] The control terminal may be one or more of a remote controller, a smart phone, a tablet computer, a laptop computer, a ground control station, and a wearable device (a watch, a bracelet). The second image sensor may be mounted on the nose of the drone or on the gimbal of the drone.

[0071] Another feasible manner: the processor 602 is used to obtain image data output by the second image sensor;

[0072] When it is determined that a user is detected according to the image data output by the second image sensor, the flight state of the drone is detected.

[0073] Further, the processor 602, when determining that a user is detected according to the image data output by the second image sensor, is configured to detect the flight state of the drone as follows:

[0074] When the processor 602 determines that a user is detected according to the image data output by the second image sensor, and the distance between the user and the drone is less than or equal to a preset distance, the processor 602 detects the flight state of the drone.

[0075] The distance between the user and the drone can be determined based on the image data, or in other ways. At this time, when it is detected that the user is in front of the drone and the distance between the user and the drone is less than or equal to the preset distance, the processor 602 starts to detect the flight state.

[0076] It should be noted that the flight status of a drone can be divided into: the drone staying on the ground, hovering, and moving. The moving state can be further divided into descending, climbing, and horizontal flight.

[0077] The control device for palm landing of a drone provided in an embodiment of the present invention detects the flight state of the drone under preset conditions, and controls the drone to land on the palm of the user when the flight state is a hovering state and the palm is located below the drone. This can effectively reduce the requirements for landing conditions of drones in the prior art, while saving the user's time in recovering the drone and improving the convenience of drone landing.

[0078] In some embodiments, detecting the flight state of the drone specifically includes: detecting the flight state of the drone according to one or more of the speed, acceleration, relative height, angular velocity of the body, control stick amount output by the control terminal, and power output acquired by the drone's sensor system. Specifically, the flight control system of the drone includes a flight state machine, wherein the flight state machine is used to detect the flight state of the drone, and the flight state machine can collect data acquired by the drone's sensor system, such as one or more of the speed, acceleration, relative height, angular velocity of the body, control stick amount output by the control terminal, and power output, and detect the flight state of the drone based on the data.

[0079] In some embodiments, since the type of the second sensor used by the drone when acquiring the image data may be different, the following will describe in detail how to detect the user and / or determine the distance between the user and the drone based on the image data. Therefore, the detection of the user based on the image data may be achieved in the following feasible ways:

[0080] A feasible manner: when the second image sensor is an RGB camera, the image data may be RGB image data, and the processor 602 is further configured to:

[0081] When the image data is an RGB image, the RGB image is downsampled; and the user and / or the distance between the user and the drone is determined based on the downsampled image.

[0082] Another feasible manner: when the second sensor is a TOF camera, the image data is depth image data, and the processor 602 is further configured to:

[0083] Determine points within a preset range in the depth image of the current frame, determine a connected domain of the points within the preset range, and determine the detected user and / or the distance between the user and the drone based on the connected domain.

[0084] Optionally, the processor 602 for determining points within a preset range in the current frame depth image may be specifically configured as follows: the processor 602 for determining points within a preset range in the current frame depth image according to the previous frame depth image.

[0085] Optionally, the processor 602 is configured to determine, according to the connected domain, that a user is detected and that:

[0086] The processor 602 is configured to normalize the shape features of the connected domain using the average depth or median depth of the connected domain, and determine that the user is detected using the normalized shape features of the connected domain.

[0087] The shape feature of the connected domain includes at least one of the length, width and area of ​​the connected domain.

[0088] In the above feasible manner, the processor 602, for determining the distance between the user and the drone, may be specifically configured as follows:

[0089] The processor 602 is configured to determine the distance between the user and the drone according to the average depth or median depth of the connected domain when it is determined that the user is detected.

[0090] In addition, the processor 602 may also be used to determine that the palm is located below the drone.

[0091] There are multiple feasible ways for the processor 602 to determine that the palm is located below the drone:

[0092] One possible way is:

[0093] The processor 602 is configured to obtain a distance measured by a distance sensor, wherein the distance is a distance between the drone and a reference point below the drone;

[0094] It is determined that the palm is below the drone based on the distance.

[0095] Specifically, the processor 602, for determining that the palm is located below the drone according to the distance, may be specifically configured as follows:

[0096] The processor 602 is configured to determine that the palm is below the drone according to the change in the distance.

[0097] Another possible way is:

[0098] The processor 602 is used to obtain image data of the area below the drone collected by the first image sensor, and determine that the palm is located below the drone according to the image data.

[0099] The processor 602, for determining that the palm is located below the drone according to the image data, may be specifically configured as follows:

[0100] The processor 602 is configured to determine that the palm is located below the drone according to the image data and a change in the distance between the drone and a reference point below the drone.

[0101] In other embodiments of the present invention, the processor 602 controls the drone to land on the palm of the user and can be specifically configured as follows:

[0102] The processor 602 is used to determine the position of the palm;

[0103] The drone is controlled to land on the palm according to the position.

[0104] The processor 602 may determine the position of the palm by:

[0105] The processor 602 is used to determine the position of the palm using the image data below the drone collected by the third image sensor.

[0106] Furthermore, the landing speed of the drone can also be controlled. The processor 602 can be specifically configured to control the drone to land on the palm of the user as follows:

[0107] The processor 602 is used to determine a landing speed according to the distance of the drone relative to the palm, and control the drone to land on the palm of the user according to the landing speed.

[0108] An embodiment of the present invention provides a drone, which may include:

[0109] body;

[0110] The power system fixed on the fuselage is used to provide flight power.

[0111] The control device described in the above embodiment.

[0112] Optionally, the drone may further include: at least one of a first image sensor, a second image sensor, a third image sensor, and a distance sensor.

[0113] Among them, the first image sensor, the second image sensor, the third image sensor, and the distance sensor can be set on the belly, the nose, or the gimbal of the drone. The first image sensor, the second image sensor, and the third image sensor can be an RGB camera, a TOF camera, a monocular camera, a binocular camera, etc. The distance sensor can include an ultrasonic sensor, a single-point TOF sensor, a visual sensor that can obtain distance information, a radar, a laser radar, etc.

[0114] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0115] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0116] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0117] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0118] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example for illustration. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0119] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for controlling the palm landing of a drone, characterized in that: detecting the speed of the drone to detect the flight state of the drone, and detecting the distance between the user's palm and the drone using a flight time sensor on the belly of the drone and identifying the palm under the drone based on an image sensor of the drone; In response to the distance between the user's palm and the drone being less than or equal to a preset distance and the drone being in a hovering state, the rotation speed of the drive motor of the drone is reduced, and the drone is controlled to land on the user's palm.

2. The method according to claim 1, characterized in that The image sensor is used to acquire the first image and / or the second image. The image sensor used to acquire the first image and the image sensor used to acquire the second image are the same image sensor, or are different image sensors.

3. The method according to claim 2, characterized in that The second image includes a depth image, and the position of the palm is determined based on the depth image.

4. The method according to claim 2, characterized in that The first image includes a depth image, and the method further includes: Determine the distance information between the user and the drone according to the depth image; When the first image determines that a user is detected and the distance between the user and the drone is less than or equal to a preset distance, a step of detecting the flight state of the drone is performed.

5. The method according to claim 1, characterized in that: The flight states of the UAV include: staying on the ground, hovering and moving, wherein the moving state includes descending, climbing and horizontal flight.

6. The method according to claim 1, characterized in that The detecting of the flight state of the UAV includes: detecting the flight state according to the sensor information acquired by the sensor system of the UAV, wherein the sensor information includes one or more of the following information: speed, acceleration, relative height, angular velocity of the aircraft body, control stick amount output by the control terminal, and power output.

7. The method according to claim 1, characterized in that The controlling the drone to land on the palm of the user comprises: adjusting the landing direction of the drone according to the position of the palm, and controlling the drone to land on the palm according to the landing direction; and / or The landing speed is determined according to the distance of the drone relative to the palm, and the drone is controlled to land on the palm according to the landing speed.

8. The method according to claim 1, characterized in that: The identifying a palm under the drone based on the image sensor of the drone includes: determining one or more points indicating a palm in an image captured by the image sensor; Determine a connected domain based on the points indicating the palm; It is determined whether the palm is detected according to the shape feature of the connected domain.

9. A drone, characterized in that: include: body; The power system fixed on the fuselage is used to provide flight power; A memory for storing program instructions; A processor, configured to execute the program instructions stored in the memory. When the program instructions are executed, the processor is configured to execute: detecting the speed of the drone to detect the flight state of the drone, and detecting the distance between the user's palm and the drone using a flight time sensor on the belly of the drone; In response to the distance between the user's palm and the drone being less than or equal to a preset distance and the drone being in a hovering state, the rotation speed of the drive motor of the drone is reduced, and the drone is controlled to land on the user's palm.

Images