Unmanned aerial vehicle landing method and apparatus, electronic device, and storage medium

Abstract

The application provides a UAV landing method and device, electronic equipment and storage medium, the method comprises the following steps: when the UAV fails to land in the nest, acquiring the environment data around the nest; based on the environment data, constructing the corresponding terrain model of the environment around the nest; based on the terrain model, determining the landing point around the nest for the UAV to land, so as to control the UAV to land in the landing point. The method, device, electronic equipment and storage medium provided by the application can obtain the environment data around the nest, construct the corresponding terrain model of the environment around the nest, and automatically analyze the landing point for the UAV to land through the terrain model during the UAV emergency landing process, so as to automatically and quickly determine the landing point for the UAV to land when the UAV fails to land in the nest, and ensure the safe landing of the UAV.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicles, and in particular to an unmanned aerial vehicle landing method and device, an electronic device, and a storage medium. BACKGROUND

[0002] When using a nest to carry an unmanned aerial vehicle to work, the unmanned aerial vehicle needs to land back to the nest after completing a task, but due to some reasons, the unmanned aerial vehicle may not be able to land in the nest. For example, there is a strong wind affecting the landing of the unmanned aerial vehicle in the nest, or the nest fails. That is, when the nest cannot safely receive the unmanned aerial vehicle, a backup landing point needs to be selected for the unmanned aerial vehicle to land. In actual work, a reasonable landing point is generally manually selected by a person for the unmanned aerial vehicle to land safely. However, manually collecting the landing point is quite tedious. SUMMARY

[0003] The present application provides an unmanned aerial vehicle landing method, device, electronic device, and storage medium to solve the problem of tedious manual collection of landing points in the prior art.

[0004] The present application provides an unmanned aerial vehicle landing method, comprising:

[0005] When the unmanned aerial vehicle fails to land in the nest, environmental data around the nest is obtained;

[0006] Based on the environmental data, a terrain model corresponding to the environment around the nest is constructed;

[0007] Based on the terrain model, a landing point around the nest for the unmanned aerial vehicle to land is determined to control the unmanned aerial vehicle to land at the landing point.

[0008] According to the unmanned aerial vehicle landing method provided by the present application, the terrain model includes a three-dimensional model; and the determination of the landing point around the nest for the unmanned aerial vehicle to land based on the terrain model comprises:

[0009] Image data of the environment around the nest is obtained;

[0010] Based on the three-dimensional model, the flatness of the environment around the nest is determined, and based on the image data, the terrain type of the environment around the nest is determined;

[0011] Based on the flatness of the environment around the nest and the terrain type, the landing point around the nest for the unmanned aerial vehicle to land is determined.

[0012] The application provides an unmanned aerial vehicle landing method, a laser radar is arranged on the nest, and the laser radar is used for collecting point cloud data in a preset range of the nest; the corresponding terrain model of the environment around the nest is constructed based on the environment data, and the method comprises the following steps:

[0013] The corresponding terrain model of the environment around the nest is obtained based on the point cloud data.

[0014] The application provides an unmanned aerial vehicle landing method, a laser radar is arranged on the nest, and the laser radar is used for collecting point cloud data in a preset range of the nest; the corresponding terrain model of the environment around the nest is constructed based on the environment data, and the method comprises the following steps:

[0015] The corresponding terrain model of the environment around the nest is obtained based on the point cloud data.

[0016] The target terrain model is determined from the multiple terrain models, and the landing point is determined in the target terrain model.

[0017] The application provides an unmanned aerial vehicle landing method, a laser radar is arranged on the nest, and the laser radar is used for collecting point cloud data in a preset range of the nest; the corresponding terrain model of the environment around the nest is constructed based on the environment data, and the method comprises the following steps:

[0018] The corresponding terrain model of the environment around the nest is obtained based on the point cloud data.

[0019] The application provides an unmanned aerial vehicle landing method, a laser radar is arranged on the nest, and the laser radar is used for collecting point cloud data in a preset range of the nest; the corresponding terrain model of the environment around the nest is constructed based on the environment data, and the method comprises the following steps:

[0020] The corresponding terrain model of the environment around the nest is obtained based on the point cloud data.

[0021] The target terrain model is determined from the multiple terrain models, and the landing point is determined in the target terrain model.

[0022] The application provides an unmanned aerial vehicle landing method, a laser radar is arranged on the nest, and the laser radar is used for collecting point cloud data in a preset range of the nest; the corresponding terrain model of the environment around the nest is constructed based on the environment data, and the method comprises the following steps:

[0023] The corresponding terrain model of the environment around the nest is obtained based on the point cloud data.

[0024] The corresponding terrain model of the environment around the nest is obtained based on the point cloud data.

[0025] In combination with the aerial occlusion, the terrain model corresponding to the environment around the nest is marked with obstacles to obtain a terrain model for determining the landing point.

[0026] According to the unmanned aerial vehicle landing method provided by the present application, the nest is further provided with a projection device, the landing point around the nest for the unmanned aerial vehicle to land is determined based on the terrain model, and the unmanned aerial vehicle is controlled to land at the landing point, which comprises the following steps:

[0027] The projection device is instructed to project a landing mark at the landing point.

[0028] Based on the landing mark, the unmanned aerial vehicle is controlled to land at the landing point.

[0029] According to the unmanned aerial vehicle landing method provided by the present application, the unmanned aerial vehicle is controlled to land at the landing point based on the landing mark, which comprises the following steps:

[0030] The identification information of the landing mark identified by the unmanned aerial vehicle is received.

[0031] Based on the identification information, the position of the unmanned aerial vehicle is adjusted to be directly above the landing mark, and the unmanned aerial vehicle is controlled to land at the landing mark.

[0032] According to the unmanned aerial vehicle landing method provided by the present application, the landing mark comprises at least one of a computer identification code, a pattern, and a number.

[0033] According to the unmanned aerial vehicle landing method provided by the present application, the method further comprises:

[0034] In the case that the landing point around the nest for the unmanned aerial vehicle to land is failed to be determined based on the terrain model, prompt information is sent to a user terminal.

[0035] The unmanned aerial vehicle responds to the control operation of the user terminal to land.

[0036] According to the unmanned aerial vehicle landing method provided by the present application, the method further comprises:

[0037] In the case that the landing point around the nest for the unmanned aerial vehicle to land is failed to be determined based on the terrain model, prompt information is sent to a user terminal.

[0038] The identification information of the landing mark identified by the unmanned aerial vehicle is received.

[0039] According to the unmanned aerial vehicle landing method provided by the present application, the method further comprises:

[0040] In a case where the determination of the landing point for the UAV to land around the nest based on the terrain model fails, a prompt information and an overhead image of a current position of the UAV are sent to a user terminal;

[0041] In response to a second point selection operation of the user in the overhead image, the landing point for the UAV to land around the nest is determined to control the UAV to land at the landing point;

[0042] The overhead image is obtained by a camera on the UAV and is taken from below the current position of the UAV.

[0043] The application further provides a UAV landing device, comprising:

[0044] An acquisition unit acquires environmental data around the nest when the UAV fails to land at the nest;

[0045] A modeling unit constructs a terrain model corresponding to the environment around the nest based on the environmental data;

[0046] A landing unit determines a landing point for the UAV to land around the nest based on the terrain model to control the UAV to land at the landing point.

[0047] The application further provides an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the UAV landing method as described above.

[0048] The application further provides a non-transitory computer readable storage medium having a computer program stored thereon, wherein the computer program is executable on a processor to implement the UAV landing method as described above.

[0049] The application further provides a computer program product comprising a computer program, wherein the computer program is executable on a processor to implement the UAV landing method as described above.

[0050] The UAV landing method, device, electronic device and storage medium provided by the application can acquire environmental data around the nest, construct a terrain model corresponding to the environment around the nest, and automatically analyze the landing point for the UAV to land based on the terrain model, so that the landing point for the UAV to land is automatically and quickly determined when the UAV fails to land at the nest, and the safe landing of the UAV is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0051] In order to make the technical solutions in the present application or the prior art clearer, the accompanying drawings needed in the embodiments or prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those of ordinary skill in the art without any creative effort based on these drawings.

[0052] Figure 1 is a flowchart of the unmanned aerial vehicle landing method provided by the present application;

[0053] Figure 2 is one of the schematic diagrams of the nest provided by the present application;

[0054] Figure 3 is the second schematic diagram of the nest provided by the present application

[0055] Figure 4 is a structural schematic diagram of the unmanned aerial vehicle landing device provided by the present application;

[0056] Figure 5 is a structural schematic diagram of the electronic device provided by the present application. DETAILED DESCRIPTION

[0057] In order to make the technical solutions in the present application or the prior art clearer, the accompanying drawings needed in the embodiments or prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those of ordinary skill in the art without any creative effort based on these drawings.

[0058] In view of the above problems, the present application provides an unmanned aerial vehicle landing method to realize automatic confirmation of the landing point of the unmanned aerial vehicle. Figure 1 is a flowchart of the unmanned aerial vehicle landing method provided by the present application, as shown in Figure 1 The method includes steps 110, 120 and 130. The flowchart of the method is only one possible implementation of the present application.

[0059] Step 110: When the unmanned aerial vehicle fails to land in the nest, the environmental data around the nest is acquired.

[0060] Specifically, when the unmanned aerial vehicle is used for operation, the unmanned aerial vehicle can take off from the nest at the beginning of the operation, and can land on the nest to end the operation after completing the operation. In the actual operation process, the nest may fail, so that the unmanned aerial vehicle cannot land on the nest, that is, the unmanned aerial vehicle fails to land on the nest. At this time, the environment data around the nest can be obtained to select a suitable landing point for the unmanned aerial vehicle to land.

[0061] Here, the unmanned aerial vehicle can establish a communication connection with the nest to facilitate data transmission. The unmanned aerial vehicle can be provided with a camera and a laser radar, wherein the camera can be used to obtain image data of a space below the unmanned aerial vehicle during landing; and the laser radar can be used to obtain point cloud data of the space below the unmanned aerial vehicle during landing. In addition, the nest here can be fixed on the ground or other movable equipment, such as the top of a vehicle or the deck of a ship. The nest can also be provided with a camera and a laser radar, wherein the camera can be used to obtain image data around the nest, and the laser radar can be used to obtain point cloud data around the nest.

[0062] Therefore, the environment data around the nest can include point cloud data around the nest, or also include image data around the nest. The image data in the environment data can reflect the terrain conditions around the nest, such as the terrain conditions around the environment of the nest can include a wheat field, a water hole, a road, etc.; and the point cloud data in the environment data can reflect three-dimensional space information of each terrain, such as three-dimensional space coordinates of each point on each terrain. It should be noted that the point cloud data around the nest can be obtained by the laser radar on the nest, or by the laser radar on the unmanned aerial vehicle, or by the laser radar on the nest and the unmanned aerial vehicle. The embodiment of the present application does not make specific limitation. Similarly, the image data around the nest can be obtained by the camera on the nest, or by the camera on the unmanned aerial vehicle, or by the camera on the nest and the unmanned aerial vehicle. The embodiment of the present application does not make specific limitation.

[0063] Step 120, based on the environment data, a terrain model corresponding to the environment around the nest is constructed;

[0064] Specifically, the environment data can be input into the AI system, and the AI system constructs a three-dimensional model corresponding to the environment around the nest based on the point cloud data in the environment data as a terrain model, such as constructing a three-dimensional spatial model of a pond and a hillside in the environment around the nest; or the point cloud data in the environment data is input into the AI model, and the AI model constructs a plane corresponding to the environment around the nest based on the terrain of the environment around the nest analyzed by the point cloud data as a terrain model, such as constructing a plane model of a pond and a hillside in the environment around the nest. In addition, when the environment data also includes image data of the environment around the nest, the image data can be input into the AI model together, and after obtaining the three-dimensional spatial model or the plane model of the environment around the nest, the AI model performs terrain labeling on each terrain region in the model, and labels the terrain conditions corresponding to each region, such as a wheat field, a pond, a road, etc., to obtain a terrain model with richer and more accurate terrain information.

[0065] In step 130, a landing point for the UAV to land around the nest is determined based on the terrain model, so as to control the UAV to land at the landing point.

[0066] Specifically, the AI model can analyze the terrain model to select a position with flat terrain conditions and easy landing in the environment around the nest as a landing point for the UAV. After selecting the landing point, the current position information of the UAV can be adjusted through the coordinate information of the landing point to control the UAV to land at the coordinate information corresponding to the landing point. Here, the landing point refers to a position that can ensure the UAV to land without obstacles and is convenient for the staff to collect the landed UAV, such as a flat road.

[0067] The AI model here can have the ability of terrain modeling and analyzing the terrain model through a pre-established model. The pre-established point cloud data and image data can be used as a sample set to train an initial AI model to obtain an AI model with the ability of terrain modeling. In addition, the initial AI model can be trained by labeling the landing point in the terrain model to obtain an AI model with the ability of analyzing the terrain model and obtaining the landing point.

[0068] The method provided by the embodiment of the application can obtain the environment data around the nest during the UAV standby landing process, construct a terrain model corresponding to the environment around the nest, and automatically analyze the landing point for the UAV to land through the terrain model, so as to automatically and quickly determine the landing point for the UAV to land when the UAV fails to land at the nest, and ensure the safe landing of the UAV.

[0069] Based on any of the above embodiments, the terrain model comprises a three-dimensional model; in step 130, a landing point around the nest for the UAV to land is determined based on the terrain model, comprising:

[0070] Obtaining image data of the environment around the nest;

[0071] Based on the three-dimensional model, determining the flatness of the environment around the nest, based on the image data, determining the terrain type of the environment around the nest;

[0072] Based on the flatness of the environment around the nest and the terrain type, determining the landing point around the nest for the UAV to land.

[0073] Specifically, first, the camera on the nest, such as a visual monitoring probe, a high-definition camera, can be used to record or take pictures of the environment around the nest, obtaining video or photos as image data of the environment around the nest.

[0074] Then, the terrain model here can be a three-dimensional model, then the three-dimensional coordinates of each region in the three-dimensional model can be used to analyze the terrain undulation and height difference of the surrounding environment, and obtain the flatness of each region of the environment around the nest. For example, the greater the terrain undulation, the lower the flatness; on the contrary, the higher the flatness. For example, the greater the height difference, the lower the flatness; on the contrary, the higher the flatness. And the higher the flatness of the environment around the nest, the greater the possibility of selecting a landing point in this area; on the contrary, the smaller the possibility of selecting a landing point in this area.

[0075] Further, the terrain type of the environment around the nest can be obtained by image recognition of the image data, such as can include a wheat field, a road, a pond, a lawn, etc. The terrain type here can reflect the ground texture information of the environment around the nest. The ground texture information can include soil type, vegetation type, road type, etc., such as soil type can include sandy soil, clay, etc., vegetation can include grassland, forest, shrub, etc. It can be understood that the terrain type of the environment around the nest can reflect the ground texture information of the environment around the nest, and through the ground texture information, it can be determined whether the area can be selected as a landing point. For example, when the terrain type of the environment around the nest is green plants, the ground texture information is grassland, which can be used as a landing point for the UAV to land; for example, when the terrain type of the environment around the nest is green plants, the ground texture information is shrub, which is not suitable for being used as a landing point for the UAV to land.

[0076] Further, the area suitable for the UAV to land can be selected as the landing point for the UAV to land based on the flatness of the environment around the nest and the terrain type of the environment around the nest, such as a flat lawn.

[0077] The method provided by the embodiment of the present application obtains the flatness of the three-dimensional model corresponding to the environment around the nest and the terrain type obtained from the image data, and comprehensively analyzes the landing point around the nest available for the unmanned aerial vehicle to land, thereby improving the accuracy of the landing point and further ensuring the safety of the unmanned aerial vehicle landing.

[0078] Based on any of the above embodiments, the nest is provided with a laser radar, and the laser radar is used to collect point cloud data within a preset range of the nest; and the terrain model corresponding to the environment around the nest is constructed based on the environment data, including:

[0079] The terrain model corresponding to the environment around the nest is obtained based on the point cloud data.

[0080] Specifically, the point cloud data within a preset range of the nest can be obtained by the laser radar provided on the nest, such as the point cloud data within a 5m range of the nest. Then, the three-dimensional model corresponding to the environment around the nest, i.e., the terrain model, is obtained by receiving the point cloud data collected by the laser radar on the nest and through the three-dimensional coordinate information in the point cloud data. It should be noted that the preset range can be adjusted by the overall landing environment of the unmanned aerial vehicle, such as 5 meters in a relatively simple environment, and 10 meters in a relatively complex environment.

[0081] In an embodiment, Figure 2 is one of the schematic diagrams of the nest provided by the present application, as Figure 2 shown, the nest can be provided on the ground, and the nest can be considered as fixed. And a laser radar can be provided on one side of the nest, i.e. Figure 2 in which the laser radar is provided at the triangular position marked on the nest, so as to obtain the environment data around the side of the airport. In another embodiment, Figure 3 is the second schematic diagram of the nest provided by the present application, as Figure 3 shown, the nest is provided on the top of the vehicle and can move with the position of the vehicle. Similarly, a laser radar can be provided on one side of the nest, i.e. Figure 3 in which the laser radar is provided at the triangular position marked on the nest, so as to obtain the environment data around the side of the airport.

[0082] Based on any of the above embodiments, the multiple sides of the nest are provided with laser radars for obtaining point cloud data of the multiple sides of the nest; and the landing point around the nest available for the unmanned aerial vehicle to land is determined based on the terrain model, and further includes:

[0083] The terrain model corresponding to the multiple sides of the nest is constructed based on the point cloud data of the multiple sides of the nest.

[0084] determine a target terrain model from the plurality of terrain models, and determine the landing point in the target terrain model.

[0085] Specifically, the laser radar can be arranged on multiple sides of the nest, and the laser radar can be used to acquire point cloud data in a preset range centered on each side of the nest to obtain more comprehensive point cloud data around the nest. Furthermore, the terrain model corresponding to each side of the nest can be constructed respectively by using the point cloud data of each side, and the terrain model corresponding to each side of the nest is obtained. Further, after obtaining the plurality of terrain models, the terrain model with higher flatness can be selected as the target terrain model according to the flatness reflected by each terrain model, so as to determine the landing point of the unmanned aerial vehicle in the target terrain model.

[0086] The method provided by the embodiment of the application realizes more comprehensive modeling of the environment around the nest by arranging laser radars on multiple sides of the nest, acquiring point cloud data of multiple sides of the nest, constructing terrain models corresponding to the multiple sides of the nest, and determining a target terrain model from the plurality of terrain models, and determining the landing point in the target terrain model, and further improves the accuracy of the selected landing point, and further improves the safety of the landing of the unmanned aerial vehicle.

[0087] According to any one of the above embodiments, the laser radar is arranged on the unmanned aerial vehicle and is used to collect point cloud data in a preset range of the nest, and the terrain model corresponding to the environment around the nest is constructed based on the environment data, and the method further comprises:

[0088] The terrain model corresponding to the environment around the nest is obtained based on the point cloud data.

[0089] Specifically, the laser radar can be arranged on the unmanned aerial vehicle and is used to collect point cloud data in a preset range of the nest, such as 5 meters around the nest. And the three-dimensional model corresponding to the environment around the nest is constructed by receiving the point cloud data collected by the laser radar on the unmanned aerial vehicle.

[0090] According to any one of the above embodiments, the laser radar is arranged on the unmanned aerial vehicle and is used to collect point cloud data of multiple sides of the nest; and the landing point around the nest for the unmanned aerial vehicle is determined based on the terrain model, and the method further comprises:

[0091] The terrain model corresponding to the multiple sides of the nest is constructed based on the point cloud data of the multiple sides of the nest.

[0092] A target terrain model is determined from the plurality of terrain models, and the landing point is determined in the target terrain model.

[0093] Specifically, the unmanned aerial vehicle can fly around multiple sides of the nest to collect point cloud data of the multiple sides of the nest within a preset range. By receiving the point cloud data of the multiple sides of the nest, three-dimensional models corresponding to the multiple sides of the nest are respectively constructed. Further, after obtaining the multiple terrain models, a terrain model with higher flatness can be selected as a target terrain model according to the flatness reflected by each terrain model, so as to determine a landing point for the unmanned aerial vehicle to land on the target terrain model.

[0094] It should be noted that, compared with the point cloud data collected by the laser radar arranged on the multiple sides of the nest, the point cloud data of the multiple sides of the nest collected by the laser radar on the unmanned aerial vehicle can avoid the obstruction of ground obstacles, collect more accurate and complete point cloud data, and further improve the accuracy of the terrain model and the accuracy of the selected landing point.

[0095] The method provided by the embodiment of the present application can obtain a plurality of terrain models of the multiple sides of the nest by arranging a laser radar on the unmanned aerial vehicle, receiving the point cloud data of the multiple sides of the nest collected by the unmanned aerial vehicle, obtaining a target terrain model from the plurality of terrain models, and selecting a landing point from the target terrain model, thereby realizing flexible and accurate selection of the landing point.

[0096] Based on any of the above embodiments, the unmanned aerial vehicle is further provided with a camera, and after the terrain model corresponding to the environment around the nest is obtained, the method comprises:

[0097] receiving aerial image data corresponding to the environment around the nest acquired by the camera on the unmanned aerial vehicle;

[0098] determining aerial obstacles in the environment around the nest based on the aerial image data;

[0099] combining the aerial obstacles to mark obstacles on the terrain model corresponding to the environment around the nest to obtain a terrain model for determining the landing point.

[0100] Specifically, a camera, such as a visual monitoring probe or a high-definition camera, can be arranged on the unmanned aerial vehicle to acquire aerial image data corresponding to the environment around the nest. The aerial image data transmitted by the unmanned aerial vehicle can be received, and image recognition can be performed on the aerial image data to obtain aerial obstacles in the environment around the nest, such as branches above the nest. It can be understood that the environment data around the nest obtained by the nest on the ground cannot obtain the environment information corresponding to the environment around the nest in the air, especially the aerial obstacle information. Further, the aerial obstacles can be combined to mark obstacles on the terrain model corresponding to the environment around the nest to obtain a terrain model for determining the landing point. For example, the region with aerial obstacles can be marked, and the landing point is not selected within the region.

[0101] The method provided by the embodiment of the present application considers the factors of the aerial obstacles, and further improves the rationality and accuracy of the determined landing point, and further improves the safety of the landing of the unmanned aerial vehicle.

[0102] When the unmanned aerial vehicle lands, the GPS locator may be offset at some time periods and in some environments, and the positioning may be inaccurate. Therefore, the landing of the unmanned aerial vehicle cannot be directly controlled by the position information of the landing point. To solve this problem, based on any one of the above embodiments, the nest is further provided with a projection device, and the landing point around the nest for the unmanned aerial vehicle to land is determined based on the terrain model, so as to control the unmanned aerial vehicle to land at the landing point, comprising:

[0103] indicating the projection device to project a landing mark at the landing point;

[0104] controlling the unmanned aerial vehicle to land at the landing point based on the landing mark.

[0105] Specifically, the coordinate information of the landing point can be sent to the projection device to instruct the projection device to project a landing mark at the landing point. Then, the unmanned aerial vehicle can be controlled to land at the landing point by recognizing the landing mark. The projection device here can be a laser projector arranged on the nest, which can project a landing mark with high brightness, high resolution and high color restoration.

[0106] Here, the landing mark includes at least one of a computer recognition code, a pattern and a number. The computer recognition code here refers to a two-dimensional code and a bar code that can be recognized by a computer, wherein the two-dimensional code can be an aruco two-dimensional code encoding pattern, a qrcode two-dimensional code encoding pattern and a barcode bar code encoding pattern; the pattern can be various shapes, such as square, triangle, etc.; the number can be a single or multiple numbers, which can be determined according to the number of the unmanned aerial vehicle. For example, when there are multiple unmanned aerial vehicles landing at different landing points in a similar area, the number of the unmanned aerial vehicle can be used to determine that each unmanned aerial vehicle lands at the corresponding landing point. Therefore, the landing mark can include only one of a computer recognition code, a pattern and a number, or can include multiple types, which can be determined according to the complexity of the environment around the nest. If the complexity of the environment around the nest is high, the landing mark can be obtained by combining multiple types of marks; if the complexity of the environment around the nest is low, the landing mark can be a single type of mark.

[0107] The method provided by the embodiment of the application can ensure that the UAV can land on the landing point without deviation, and further ensure the safe landing of the UAV.

[0108] Based on any of the above embodiments, the method further comprises:

[0109] receiving identification information of the landing mark identified by the UAV;

[0110] Based on the identification information, the position of the UAV is adjusted to be directly above the landing mark, and the UAV is controlled to land on the landing mark.

[0111] Specifically, the identification information of the landing mark identified by the UAV can be received, and the identification information can reflect whether the UAV identifies the landing mark, and can include identification and non-identification. For example, during the landing of the UAV, the UAV obtains image data of the environment around the nest through a camera, and compares the identification result with the landing mark through image recognition of the image data to obtain the identification information of the landing mark. In the case of identification, the position of the UAV is adjusted to be directly above the landing mark, and the UAV is controlled to land on the landing mark. It should be noted that the image data can be identified by a central processor on the UAV to obtain the identification information of the landing mark, or the image data can be identified by other servers to obtain the identification information of the landing mark, and the identification information can be sent to the UAV.

[0112] Based on any of the above embodiments, the method further comprises:

[0113] In the case that the determination of the landing point for the UAV to land around the nest based on the terrain model fails, prompt information is sent to a user terminal;

[0114] The UAV responds to the control operation of the user terminal to land.

[0115] Specifically, in the case that the automatic determination of the landing point for the UAV to land around the nest based on the terrain model fails, prompt information can be sent to a user terminal, such as "automatic selection of landing point fails", to instruct the user to manually select the landing point for the UAV to land. Then, the control operation of the user terminal can be received and responded to, for example, when the user terminal is a remote controller, the UAV can receive and respond to the remote control operation of the remote controller to land.

[0116] It should be noted that the UAV can be controlled to land based on the user terminal, which can realize convenient and controllable UAV landing.

[0117] Based on any of the above embodiments, the method further comprises:

[0118] In a case where the determination of the landing point around the nest for the UAV to land based on the terrain model fails, sending a prompt information to a user terminal;

[0119] Receiving and responding to a first point selection operation of a user in the terrain model, determining the landing point around the nest for the UAV to land, to control the UAV to land at the landing point.

[0120] Specifically, in a case where the determination of the landing point around the nest for the UAV to land based on the terrain model fails, a prompt information such as "automatic selection of landing point fails" can be sent to the user terminal to instruct the user to manually select the landing point for the UAV to land. The coordinate information of the landing point can be determined by receiving and responding to a first point selection operation of a user in the terrain model, such as the user selecting a point A in the terrain model, and also receiving a point selection operation of the user in the map of the area around the nest. The projection device can be instructed to project a landing mark at the landing point to indicate the UAV to land at the landing point.

[0121] Based on any of the above embodiments, the method further comprises:

[0122] In a case where the determination of the landing point around the nest for the UAV to land based on the terrain model fails, sending a prompt information and an overhead view image of the current position of the UAV to a user terminal;

[0123] Receiving and responding to a second point selection operation of a user in the overhead view image, determining the landing point around the nest for the UAV to land, to control the UAV to land at the landing point;

[0124] The overhead view image is obtained by a camera on the UAV shooting the area below the current position of the UAV.

[0125] Specifically, in a case where the determination of the landing point around the nest for the UAV to land based on the terrain model fails, a prompt information such as "automatic selection of landing point fails" can be sent to the user terminal to instruct the user to manually select the landing point for the UAV to land. First, the overhead view image obtained by the camera on the UAV shooting the area below the current position of the UAV can be received and displayed to the user. Then, the second point selection operation of the user in the overhead view image, such as the user selecting a point A in the overhead view image, can be received. The position corresponding to the second point selection operation can be determined as the landing point, and the projection device can be instructed to project a landing mark at the landing point to indicate the UAV to land at the landing point.

[0126] The method provided by the embodiment of the present application sends prompt information to the user terminal in the case that the landing point around the nest for the UAV to land is failed to be determined based on the terrain model, so that the user can obtain the selection of the landing point in the UAV landing process in time. In addition, compared with the selection of the landing point by the user directly through naked eye observation, the landing point is determined by responding to the point selection operation of the user on the overhead image obtained by the UAV or the terrain model, so that the rationality and accuracy of the landing point are improved.

[0127] Based on any of the above embodiments, the present application further provides a UAV landing method, which comprises:

[0128] Firstly, the UAV climbs to 30 meters and starts the obstacle avoidance system. Then, the nest starts to scan the environmental information within 5 meters of the nest, which can be specifically obtained by the visual monitoring probe and the laser radar on the nest to obtain image data and point cloud data within 5 meters of the nest. The image data, point cloud data and real-time image data of the UAV are transmitted to the AI model, the terrain model of the environment around the nest is obtained by terrain modeling of the environment around the nest through the AI model, and the landing point of the UAV is obtained by analyzing the terrain model through the AI model. Then, in the case that the landing point is successfully selected, the landing point is projected by the projection device on the nest to control the UAV to land at the landing point. In the case that the landing point is failed to be selected, the UAV can be instructed to climb to 40 meters, and prompt information is sent to the user terminal to receive the landing point selected by the user, so that the UAV lands at the landing point.

[0129] Based on any of the above embodiments, Figure 4 is a structural schematic diagram of the UAV landing device provided by the present application, as Figure 4 shown, the device comprises:

[0130] The acquisition unit 410 acquires the environmental data around the nest when the UAV fails to land on the nest.

[0131] The modeling unit 420 constructs the terrain model corresponding to the environment around the nest based on the environmental data.

[0132] The landing unit 430 determines the landing point around the nest for the UAV to land based on the terrain model, so as to control the UAV to land at the landing point.

[0133] The device provided by the embodiment of the present application acquires the environmental data around the nest, constructs the terrain model corresponding to the environment around the nest, and automatically analyzes the landing point for the UAV to land through the terrain model during the UAV emergency landing process, so as to automatically and quickly determine the landing point for the UAV to land when the UAV fails to land on the nest, thereby ensuring the safe landing of the UAV.

[0134] According to any one of the above embodiments, the landing unit is specifically used for:

[0135] acquiring image data of the environment around the nest;

[0136] determining flatness of the environment around the nest based on the three-dimensional model, and determining a terrain type of the environment around the nest based on the image data;

[0137] determining a landing point for the UAV to land around the nest based on the flatness of the environment around the nest and the terrain type.

[0138] According to any one of the above embodiments, the nest is provided with a laser radar, and the laser radar is used to collect point cloud data within a preset range of the nest; the modeling unit is specifically used for:

[0139] obtaining a corresponding terrain model of the environment around the nest based on the point cloud data.

[0140] According to any one of the above embodiments, the multiple sides of the nest are provided with laser radars, which are used to obtain point cloud data of the multiple sides of the nest; the landing unit is further specifically used for:

[0141] constructing corresponding terrain models of the multiple sides of the nest based on the point cloud data of the multiple sides of the nest;

[0142] determining a target terrain model from the multiple terrain models, and determining the landing point in the target terrain model.

[0143] According to any one of the above embodiments, the UAV is provided with a laser radar, which is used to collect point cloud data within a preset range of the nest; the modeling unit is further specifically used for:

[0144] obtaining a corresponding terrain model of the environment around the nest based on the point cloud data.

[0145] According to any one of the above embodiments, the UAV is provided with a laser radar, which is used to collect point cloud data of multiple sides of the nest; the landing unit is further specifically used for:

[0146] constructing corresponding terrain models of the multiple sides of the nest based on the point cloud data of the multiple sides of the nest;

[0147] determining a target terrain model from the multiple terrain models, and determining the landing point in the target terrain model.

[0148] According to any one of the above embodiments, the UAV is further provided with a camera, and after modeling, the obstacle labeling unit is further included, and the obstacle labeling unit is specifically used for:

[0149] receiving aerial image data corresponding to the environment around the nest acquired by a camera on the UAV;

[0150] determining an aerial occlusion in the environment around the nest based on the aerial image data;

[0151] annotating a terrain model corresponding to the environment around the nest with obstacles in combination with the aerial occlusion, to obtain a terrain model for determining the landing point.

[0152] Based on any of the above embodiments, the landing unit is further specifically configured to:

[0153] instructing the projection device to project a landing mark at the landing point;

[0154] controlling the UAV to land at the landing point based on the landing mark.

[0155] Based on any of the above embodiments, the landing unit is further specifically configured to:

[0156] receiving identification information of the landing mark identified by the UAV;

[0157] adjusting the position of the UAV to be directly above the landing mark based on the identification information, and controlling the UAV to land at the landing mark.

[0158] Based on any of the above embodiments, the landing mark comprises at least one of a computer identification code, a pattern, and a number.

[0159] Based on any of the above embodiments, the landing unit further comprises an interaction unit, which is specifically configured to:

[0160] in a case where the determination of the landing point for the UAV to land around the nest based on the terrain model fails, sending a prompt information to a user terminal;

[0161] the UAV responds to the control operation of the user terminal to land.

[0162] Based on any of the above embodiments, the interaction unit is further specifically configured to:

[0163] in a case where the determination of the landing point for the UAV to land around the nest based on the terrain model fails, sending a prompt information to a user terminal;

[0164] receiving and responding to a first point selection operation of a user in the terrain model to determine a landing point for the UAV to land around the nest, to control the UAV to land at the landing point.

[0165] Based on any of the above embodiments, the interaction unit is further specifically configured to:

[0166] In a case where the determination of the landing point around the nest for the UAV to land based on the terrain model fails, sending prompt information and an overhead image of the current position of the UAV to a user terminal;

[0167] In response to a second point selection operation of the user in the overhead image, determining the landing point around the nest for the UAV to land, to control the UAV to land at the landing point;

[0168] The overhead image is obtained by photographing the area below the current position of the UAV based on a camera on the UAV.

[0169] Figure 5 An example of a schematic diagram of the physical structure of an electronic device is shown in FIG. 1. Figure 5 As shown, the electronic device can include a processor 510, a communications interface 520, a memory 530, and a communications bus 540, wherein the processor 510, the communications interface 520, and the memory 530 can communicate with each other through the communications bus 540. The processor 510 can invoke the logical instructions in the memory 530 to execute a UAV landing method, which includes: when the UAV fails to land at a nest, obtaining environmental data around the nest; based on the environmental data, constructing a terrain model corresponding to the environment around the nest; based on the terrain model, determining a landing point around the nest for the UAV to land, to control the UAV to land at the landing point.

[0170] In addition, the logical instructions in the memory 530 described above can be implemented in the form of a software functional unit and sold or used as an independent product, which can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium, includes several instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0171] In another aspect, the present application also provides a computer program product comprising a computer program, which can be stored on a non-transitory computer readable storage medium, and the computer program is executable by a processor to enable a computer to perform the UAV landing method provided by any of the above methods, the method comprising: obtaining environmental data around a nest when the UAV fails to land on the nest; constructing a terrain model corresponding to an environment around the nest based on the environmental data; determining a landing point around the nest for the UAV to land based on the terrain model, to control the UAV to land on the landing point.

[0172] In yet another aspect, the present application also provides a non-transitory computer readable storage medium having a computer program stored thereon, which is executable by a processor to implement a UAV landing method provided by any of the above methods, the method comprising: obtaining environmental data around a nest when the UAV fails to land on the nest; constructing a terrain model corresponding to an environment around the nest based on the environmental data; determining a landing point around the nest for the UAV to land based on the terrain model, to control the UAV to land on the landing point.

[0173] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the present embodiment scheme according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0174] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software plus necessary general hardware platforms, and of course can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in terms of the contribution to the prior art, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0175] It should be pointed out finally that the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit the same; and although the present application has been described in detail with reference to the foregoing embodiments, it should be appreciated by those skilled in the art that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features thereof can be replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for landing a drone, the method comprising: The method comprises: When the UAV fails to land on the nest, acquiring environmental data around the nest; Based on the environmental data, a terrain model corresponding to the environment around the nest is constructed, and the terrain model comprises a three-dimensional model; Based on the terrain model, a landing point around the nest for the UAV to land is determined, so as to control the UAV to land on the landing point, comprising: Acquiring image data of the environment around the nest; Based on the three-dimensional model, the flatness of the environment around the nest is determined, and based on the image data, the terrain type of the environment around the nest is determined; Based on the flatness of the environment around the nest and the terrain type, a landing point around the nest for the UAV to land is determined; The determination of the flatness of the environment around the nest based on the three-dimensional model comprises: based on the three-dimensional coordinates of each region in the three-dimensional model, analyzing the terrain undulation and height difference value of the environment around the nest to obtain the flatness of each region in the environment around the nest; The terrain type comprises a wheat field, a road, a pond and a lawn, and the terrain type is used to reflect the ground texture information of the environment around the nest; The construction of the terrain model corresponding to the environment around the nest based on the environmental data comprises: The nest is provided with a laser radar, and the laser radar is used to collect point cloud data within a preset range of the nest; based on the point cloud data within the preset range of the nest, the terrain model corresponding to the environment around the nest is obtained; The UAV is also provided with a camera, and after the terrain model corresponding to the environment around the nest is obtained, comprising: Receiving the aerial image data corresponding to the environment around the nest acquired by the camera on the UAV; Based on the aerial image data, determining the aerial occlusion in the environment around the nest; Combining the aerial occlusion, obstacle labeling is performed on the terrain model corresponding to the environment around the nest to obtain a terrain model used to determine the landing point.

2. The UAV landing method of claim 1, wherein, The multiple sides of the nest are provided with laser radars, which are used to obtain point cloud data of the multiple sides of the nest; the determination of the landing point around the nest for the UAV to land based on the terrain model further comprises: Based on the point cloud data of the multiple sides of the nest, a terrain model corresponding to the multiple sides of the nest is constructed; From multiple terrain models, a target terrain model is determined, and the landing point is determined in the target terrain model. 3.The UAV landing method of claim 1, wherein, The UAV is provided with a laser radar, which is used to collect point cloud data within a preset range of the nest; the construction of the terrain model corresponding to the environment around the nest based on the environmental data further comprises: Based on the point cloud data, the terrain model corresponding to the environment around the nest is obtained.

4. The UAV landing method of claim 3, wherein, The UAV is provided with a laser radar, which is used to collect point cloud data of the multiple sides of the nest; the determination of the landing point around the nest for the UAV to land based on the terrain model further comprises: Based on the point cloud data of the multiple sides of the nest, a terrain model corresponding to the multiple sides of the nest is constructed; From multiple terrain models, a target terrain model is determined, and the landing point is determined in the target terrain model.

5. The UAV landing method of any one of claims 1-4, wherein, The nest is further provided with a projection device, and the landing point around the nest for the UAV to land is determined based on the terrain model, so as to control the UAV to land at the landing point, including: indicating the projection device to project a landing mark at the landing point; controlling the UAV to land at the landing point based on the landing mark.

6. The UAV landing method of claim 5, wherein, The controlling the UAV to land at the landing point based on the landing mark includes: receiving identification information of the UAV identifying the landing mark; adjusting the position of the UAV to be directly above the landing mark based on the identification information, and controlling the UAV to land towards the landing mark.

7. The UAV landing method of claim 5 or 6, wherein, The landing mark includes at least one of a computer identification code, a pattern, and a number.

8. The UAV landing method of any one of claims 1-7, wherein, The method further includes: in the case that the determination of the landing point around the nest for the UAV to land based on the terrain model fails, sending prompt information to a user terminal; the UAV responds to the control operation of the user terminal to land.

9. The drone landing method of any one of claims 1-7, wherein, The method further includes: in the case that the determination of the landing point around the nest for the UAV to land based on the terrain model fails, sending prompt information to a user terminal; receiving and responding to a first point selection operation of a user in the terrain model to determine the landing point around the nest for the UAV to land, so as to control the UAV to land at the landing point.

10. The drone landing method of any one of claims 1-7, wherein, The method further includes: in the case that the determination of the landing point around the nest for the UAV to land based on the terrain model fails, sending prompt information and a bird's-eye view image below the current position of the UAV to a user terminal; responding to a second point selection operation of a user in the bird's-eye view image to determine the landing point around the nest for the UAV to land, so as to control the UAV to land at the landing point; the bird's-eye view image is obtained by a camera on the UAV shooting the area below the current position of the UAV.

11. An unmanned aerial vehicle landing apparatus, characterized by, including: an acquisition unit, when the UAV fails to land at the nest, acquires environmental data around the nest; a modeling unit, based on the environmental data, constructs a terrain model corresponding to the environment around the nest, the terrain model including a three-dimensional model; a landing unit, based on the terrain model, determines a landing point around the nest for the UAV to land, so as to control the UAV to land at the landing point; the landing unit is specifically used for: acquiring image data of the environment around the nest; based on the three-dimensional model, determining the flatness of the environment around the nest, and based on the image data, determining the terrain type of the environment around the nest; based on the flatness of the environment around the nest and the terrain type, determining the landing point around the nest for the UAV to land; the determination of the flatness of the environment around the nest based on the three-dimensional model includes: based on the three-dimensional coordinates of each region in the three-dimensional model, analyzing the terrain undulation and height difference value of the environment around the nest to obtain the flatness of each region in the environment around the nest; the terrain type includes a wheat field, a road, a pond, and a lawn, and the terrain type is used to reflect the ground texture information of the environment around the nest; The modeling unit is specifically used for: The nest is provided with a laser radar, and the laser radar is used to collect point cloud data within a preset range of the nest; and a terrain model corresponding to the environment around the nest is obtained based on the point cloud data within the preset range of the nest. The unmanned aerial vehicle is further provided with a camera, and after the terrain model corresponding to the environment around the nest is obtained, the method comprises: receiving aerial image data corresponding to the environment around the nest acquired by the camera on the unmanned aerial vehicle; determining an aerial occlusion object in the environment around the nest based on the aerial image data; combining the aerial occlusion object, performing obstacle labeling on the terrain model corresponding to the environment around the nest, and obtaining a terrain model used to determine the landing point.

12. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to implement the unmanned aerial vehicle landing method according to any one of claims 1 to 10.

13. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the unmanned aerial vehicle landing method according to any one of claims 1 to 10.

14. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the unmanned aerial vehicle landing method according to any one of claims 1 to 10.

Images