Unmanned aerial vehicle landing obstacle avoidance method and device, and unmanned aerial vehicle

Abstract

The embodiment of the present application relates to the technical field of unmanned aerial vehicle control, in particular to an unmanned aerial vehicle landing obstacle avoidance method and device and unmanned aerial vehicle.The unmanned aerial vehicle landing obstacle avoidance method comprises the following steps: obtaining a point cloud distribution map of a region to be landed; determining a safe region in the region to be landed according to the point cloud distribution map; determining a target position in the safe region; controlling the unmanned aerial vehicle to move to the target position, so that the unmanned aerial vehicle is away from the obstacle in the region to be landed.Through the above-mentioned mode, the embodiment of the present application can avoid the obstacle in the region to be landed, and reduce the risk of unmanned aerial vehicle crash.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of unmanned aerial vehicle control, and in particular to an unmanned aerial vehicle landing obstacle avoidance method and device and unmanned aerial vehicle. BACKGROUND

[0002] An unmanned aerial vehicle is a pilotless aircraft that is controlled by a radio remote control device or a self-programmed control device. With the development of unmanned aerial vehicle technology and the complex changes in its application scenarios, there are more and more safety problems in the flight of unmanned aerial vehicles. Therefore, autonomous landing protection technology is provided in unmanned aerial vehicles to prevent crashes when unmanned aerial vehicles land in unknown environments.

[0003] Currently, after the autonomous landing protection technology provided in unmanned aerial vehicles detects a dangerous area in a landing area, the unmanned aerial vehicle can only fly away or hover in the landing area with the dangerous area, and cannot avoid the dangerous area in the landing area. For unmanned aerial vehicles with low battery levels, it is easy to cause the unmanned aerial vehicle to crash after the battery is depleted. SUMMARY

[0004] Embodiments of the present application aim to provide an unmanned aerial vehicle landing obstacle avoidance method, device and unmanned aerial vehicle, which can avoid obstacles in a landing area and reduce the risk of unmanned aerial vehicle crashes.

[0005] To solve the above technical problems, one technical solution adopted by embodiments of the present application is to provide an unmanned aerial vehicle landing obstacle avoidance method, which comprises:

[0006] obtaining a point cloud distribution map of a landing area;

[0007] determining a safe area in the landing area according to the point cloud distribution map;

[0008] determining a target position in the safe area;

[0009] controlling the unmanned aerial vehicle to move to the target position to move the unmanned aerial vehicle away from obstacles in the landing area.

[0010] Optionally, the point cloud distribution map of the landing area is obtained, comprising:

[0011] the point cloud distribution map of the landing area is obtained by a depth sensor of the unmanned aerial vehicle.

[0012] Optionally, the point cloud distribution map of the landing area is obtained by the depth sensor of the unmanned aerial vehicle, comprising:

[0013] point cloud data of the landing area is obtained by the depth sensor;

[0014] projecting the point cloud data to a two-dimensional plane to obtain the point cloud distribution map.

[0015] Optionally, the determining the target position in the safety area comprises:

[0016] determining a gravity position of the safety area;

[0017] determining the gravity position of the safety area as the target position.

[0018] Optionally, the determining the gravity position of the safety area comprises:

[0019] extracting coordinates of each point cloud in the safety area;

[0020] determining the gravity position of the safety area according to the coordinates of each point cloud as:

[0021]

[0022] wherein n is a total number of point clouds in the safety area, Xi is a horizontal coordinate of an i-th point cloud in the safety area, Yi is a vertical coordinate of the i-th point cloud in the safety area, X is a horizontal coordinate of the gravity position, and Y is a vertical coordinate of the gravity position.

[0023] Optionally, the controlling the UAV to move to the target position comprises:

[0024] determining a direction in which the target position is located as a first target direction;

[0025] controlling the UAV to move to the target position along the first target direction.

[0026] Optionally, before the controlling the UAV to move to the target position along the first target direction, the method further comprises:

[0027] determining whether there is an obstacle in the first target direction, and if not, controlling the UAV to move to the target position along the first target direction.

[0028] Optionally, the determining whether there is an obstacle in the first target direction is performed by a perception sensor.

[0029] Optionally, the perception sensor is a one-way perception sensor, and the method further comprises:

[0030] controlling a perception direction of the one-way perception sensor to be consistent with the first target direction.

[0031] Optionally, before the controlling the UAV to move to the target position, the method further comprises:

[0032] determine a center position of the landing area;

[0033] determine whether the target position is consistent with the center position of the landing area, and if so, re-determine the target position.

[0034] Optionally, the re-determination of the target position comprises:

[0035] determining a direction in which there is no obstacle in the landing area as a second target direction;

[0036] controlling the UAV to move a preset distance along the second target direction and then determining a target position in the safe area.

[0037] Optionally, after the UAV is controlled to move to the target position, the method further comprises:

[0038] determining whether there is a dangerous area in a landing area centered on the target position,

[0039] if not, controlling the UAV to land;

[0040] if so, determining a target position in the landing area centered on the target position.

[0041] Optionally, the method further comprises:

[0042] determining whether the number of times of determining the target position in the landing area centered on the target position exceeds a first preset threshold, and if so, controlling the UAV to issue a warning and / or controlling the UAV to stop landing.

[0043] Optionally, before the target position is determined in the safe area, the method further comprises:

[0044] determining a ratio R1 of the number of point clouds of the safe area to the number of point clouds of the landing area;

[0045] determining whether the R1 is greater than a second preset threshold, and if so, determining the target position in the safe area.

[0046] To solve the above technical problems, another technical solution adopted by an embodiment of the present application is to provide a UAV landing obstacle avoidance device, which comprises:

[0047] an acquisition module, configured to acquire a point cloud distribution map of a landing area;

[0048] a determination module, configured to determine a safe area in the landing area according to the point cloud distribution map; and

[0049] determining a target position in the safe area;

[0050] a control module configured to control the UAV to move to the target position so as to keep the UAV away from the obstacle in the landing area.

[0051] Optionally, the acquisition module acquires the point cloud distribution map of the landing area through a depth sensor of the UAV.

[0052] Optionally, the acquisition module is specifically configured to:

[0053] acquire point cloud data of the landing area through the depth sensor;

[0054] project the point cloud data onto a two-dimensional plane to acquire the point cloud distribution map.

[0055] Optionally, the determination module is configured to:

[0056] determine a barycentric position of the safe area;

[0057] determine the barycentric position of the safe area as the target position.

[0058] Optionally, the determination module is further configured to:

[0059] extract coordinates of each point cloud in the safe area;

[0060] determine the barycentric position of the safe area according to the coordinates of each point cloud as:

[0061]

[0062] wherein n is a total number of point clouds in the safe area, Xi is a horizontal coordinate of an i-th point cloud in the safe area, Yi is a vertical coordinate of the i-th point cloud in the safe area, X is a horizontal coordinate of the barycentric position, and Y is a vertical coordinate of the barycentric position.

[0063] Optionally, the control module is configured to:

[0064] determine a direction in which the target position is located as a first target direction;

[0065] control the UAV to move to the target position along the first target direction.

[0066] Optionally, the control module is further configured to:

[0067] determine whether there is an obstacle in the first target direction, and if not, control the UAV to move to the target position along the first target direction.

[0068] Optionally, the control module determines whether there is an obstacle in the first target direction through the perception sensor.

[0069] Optionally, the perception sensor is a one-way sensor, and the control module is further configured to:

[0070] control the perception direction of the one-way perception sensor to be consistent with the first target direction.

[0071] Optionally, the determination module is further configured to:

[0072] determine the center position of the landing area to be;

[0073] determine whether the target position is consistent with the center position of the landing area, and if so, re-determine the target position.

[0074] Optionally, the determination module is further configured to:

[0075] determine a direction in which there is no obstacle in the landing area as a second target direction;

[0076] control the UAV to move a preset distance along the second target direction and then determine a target position in the safe area.

[0077] Optionally, the control module is further configured to:

[0078] determine whether there is a dangerous area in the landing area centered on the target position,

[0079] if not, control the UAV to land;

[0080] if so, determine a target position in the landing area centered on the target position.

[0081] Optionally, the control module is further configured to:

[0082] determine whether the number of times of determining a target position in the landing area centered on the target position exceeds a first preset threshold, and if so, control the UAV to issue a warning and / or control the UAV to stop landing.

[0083] Optionally, the determination module is further configured to:

[0084] determine a ratio R1 of the number of point clouds in the safe area to the number of point clouds in the landing area;

[0085] determine whether the R1 is greater than a second preset threshold, and if so, determine a target position in the safe area.

[0086] To solve the above technical problems, another technical solution adopted by an embodiment of the present application is to provide a UAV, comprising:

[0087] a fuselage;

[0088] an arm connected with the fuselage;

[0089] a power device arranged in the arm;

[0090] at least one processor arranged in the fuselage; and

[0091] a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the unmanned aerial vehicle landing obstacle avoidance method described above.

[0092] To solve the above technical problems, another technical solution adopted by the embodiment of the present application is to provide a non-volatile computer readable storage medium, which stores computer executable instructions, and the computer executable instructions are used to enable an unmanned aerial vehicle to perform the unmanned aerial vehicle landing obstacle avoidance method described above.

[0093] The embodiment of the present application has the beneficial effect that: different from the prior art, the embodiment of the present application provides an unmanned aerial vehicle landing obstacle avoidance method, device and unmanned aerial vehicle, in the unmanned aerial vehicle landing obstacle avoidance method, a target position is determined in a safe area of a landing area, and the unmanned aerial vehicle is controlled to move to the target position, so that the unmanned aerial vehicle can move to the safe area of the landing area, and since the safe area is an area without obstacles, when the unmanned aerial vehicle moves to the safe area, the obstacle avoidance is realized, and the risk of unmanned aerial vehicle crash is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0094] One or more embodiments are exemplarily illustrated by pictures in the drawings corresponding thereto, and these exemplary illustrations do not constitute a limitation on the embodiments, elements with the same reference numerals in the drawings represent similar elements, unless specifically stated otherwise, and the drawings do not constitute a proportional limitation.

[0095] Figure 1 is a structural schematic diagram of an unmanned aerial vehicle provided by an embodiment of the present application;

[0096] Figure 2 is a flowchart of an unmanned aerial vehicle landing obstacle avoidance method provided by an embodiment of the present application;

[0097] Figure 3 is Figure 2 a flowchart of step S400 of the method shown in the figure;

[0098] Figure 4 is Figure 2A flowchart of step S800 of the method shown;

[0099] Figure 5 A flowchart of a UAV landing obstacle avoidance method provided by another embodiment of the application;

[0100] Figure 6 A flowchart of a UAV landing obstacle avoidance method provided by another embodiment of the application;

[0101] Figure 7 A flowchart of a UAV landing obstacle avoidance method provided by another embodiment of the application;

[0102] Figure 8 A structural schematic diagram of a UAV landing obstacle avoidance device provided by an embodiment of the application;

[0103] Figure 9 A hardware structural schematic diagram of a UAV provided by an embodiment of the application. DETAILED DESCRIPTION

[0104] In order to make the objects, technical solutions and advantages of the embodiments of the application clearer, the technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only some of the embodiments of the application, but not all the embodiments of the application. It should be understood that the specific embodiments described herein are only used to explain the application, and are not used to limit the application. Based on the embodiments in the application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the application.

[0105] It should be noted that when an element is described as being "fixed" to another element, it can be directly on the other element or one or more intervening elements can be present therebetween. When an element is described as being "connected" to another element, it can be directly connected to the other element or one or more intervening elements can be present therebetween. The terms "vertical", "horizontal", "left", "right", and similar expressions used in the specification are for illustrative purposes only.

[0106] In addition, the technical features involved in each of the embodiments of the application described below can be combined with each other as long as there is no conflict.

[0107] The application provides a UAV landing obstacle avoidance method and device, which are applied to a UAV, so that the UAV can determine a target position in a safe area of a landing area when detecting that a dangerous area exists in the landing area, and move to the target position to avoid obstacles in the landing area and reduce the risk of crashing. The dangerous area refers to an area with obstacles, and the obstacles include inclined slopes, water surfaces, shrubs, protruding foreign objects, and edge vacancy areas of surface flat areas such as roof tops, cliffs, and deep trenches. The target position refers to a position to which the UAV is about to move.

[0108] The UAV in the application can be any suitable type of high-altitude UAV or low-altitude UAV, including a fixed-wing UAV, a rotor UAV, a parachute UAV, or a flapping-wing UAV.

[0109] In the following, the application will be described through specific embodiments.

[0110] Embodiment one

[0111] Please refer to Figure 1 is a UAV 100 provided by one of the embodiments of the application, which comprises a fuselage 10, arms 20, a power device 30, a depth sensor 40, a landing gear 50, and a flight control system (not shown in the figure). The arms 20, the depth sensor 40, and the landing gear 50 are all connected with the fuselage 10, the flight control system is arranged in the fuselage 10, and the power device 30 is arranged on the arms 20. The power device 30, the depth sensor 40, and the landing gear 50 are all in communication connection with the flight control system, so that the flight control system can control the flight of the UAV 100 through the power device 30, can obtain a point cloud distribution map of a landing area of the UAV 100 through the depth sensor 40, and can also control the landing gear 50 to contact the ground.

[0112] Preferably, the number of the arms 20 is four, which are uniformly distributed around the fuselage 10 and used for bearing the power device 30.

[0113] The power device 30 comprises a motor and a propeller connected with the shaft of the motor. The motor can drive the propeller to rotate to provide lift for the UAV 100 and realize flight. The motor can also change the flight direction of the UAV 100 by changing the rotating speed and direction of the propeller. When the power device 30 is in communication connection with the flight control system, the flight control system can control the flight of the UAV 100 by controlling the motor.

[0114] The power device 30 is arranged at one end of the arm 20 which is not connected with the fuselage 10 and is connected with the arm 20 through the motor.

[0115] Preferably, the power device 30 is arranged on each of the four arms 20 of the UAV 100, so that the UAV 100 can fly stably.

[0116] The depth sensor 40 is arranged at the bottom of the body 10, and is configured to collect point cloud data of the landing area of the UAV 100. Each point cloud in the point cloud data contains three-dimensional coordinates, and some may contain color information or reflectivity information. The distance between the depth sensor 40 and the object in the landing area can be obtained through the point cloud data. When the depth sensor 40 is in communication connection with the flight control system, the flight control system can obtain the point cloud data of the landing area of the UAV 100 from the depth sensor 40, and project the point cloud data to a two-dimensional plane to obtain a point cloud distribution map of the landing area.

[0117] Further, the depth sensor 40 is arranged at the bottom of the body 10 through the gimbal, so that the depth sensor 40 can collect point cloud data of the landing area in all directions.

[0118] The depth sensor 40 includes but is not limited to a binocular camera, a TOF (Time of Flight) camera, a structured light camera, and a laser radar.

[0119] The landing gear 50 is arranged at opposite sides of the bottom of the body 10, and is connected to the body 10 through a driving device. The landing gear 50 can be opened and stowed under the driving of the driving device. When the UAV 100 contacts the ground, the driving device controls the landing gear 50 to open, so that the UAV 100 contacts the ground through the landing gear 50. During the flight of the UAV 100, the driving device controls the landing gear 50 to be stowed, so as to avoid affecting the flight of the UAV 100. When the landing gear 50 is in communication connection with the flight control system, the flight control system can control the landing gear 50 to contact the ground by controlling the driving device.

[0120] It can be understood that when the UAV 100 lands on the ground, only the landing gear 50 contacts the ground. At this time, the actual landing area of the UAV 100 is the area surrounded by the landing gear 50 when contacting the ground.

[0121] When the UAV 100 contacts the ground through the landing gear 50, the projection of the UAV 100 body on the ground forms a projection area. The projection area is coincident with the center point of the actual landing area, and the projection area is larger than the actual landing area. The projection area includes the activity range of the propeller, and represents the minimum area in which the UAV 100 can normally operate.

[0122] Further, a perception sensor (not shown in the figure) is arranged in the body 10, and is configured to determine whether there is an obstacle in the flight direction of the UAV 100.

[0123] The perception sensor is in communication connection with the flight control system, and the flight control system can control the flight direction of the unmanned aerial vehicle 100 according to the judgment result of the perception sensor, for example, if the perception sensor determines that there is an obstacle in the flight direction of the unmanned aerial vehicle 100, the flight direction of the unmanned aerial vehicle 100 is controlled to be changed.

[0124] The perception sensor includes a one-way perception sensor or a multi-way perception sensor.

[0125] When the perception sensor is a one-way perception sensor, the one-way perception sensor can only determine whether there is an obstacle in one direction, and therefore, when the one-way perception sensor is arranged on the fuselage 10, the sensing direction of the one-way perception sensor is consistent with the flight direction of the unmanned aerial vehicle 100, that is, the flight direction of the unmanned aerial vehicle 100 is the sensing direction of the one-way perception sensor, and when the flight direction of the unmanned aerial vehicle 100 is changed, the sensing direction of the one-way perception sensor also changes with the change of the flight direction of the unmanned aerial vehicle 100, so that the one-way perception sensor can always determine whether there is an obstacle in the flight direction of the unmanned aerial vehicle 100.

[0126] When the perception sensor is a multi-way perception sensor, the multi-way perception sensor can determine whether there is an obstacle in any direction of the unmanned aerial vehicle 100, and therefore, when the multi-way perception sensor is arranged on the fuselage 10, the multi-way perception sensor can not change with the change of the flight direction of the unmanned aerial vehicle 100.

[0127] The flight control system is in communication connection with the power device 30, the depth sensor 40, the landing gear 50 and the perception sensor through wired connection or wireless connection. The wireless connection includes but is not limited to WiFi, Bluetooth, ZigBee, etc.

[0128] The flight control system is used to execute the unmanned aerial vehicle landing obstacle avoidance method described in the present application, so that the unmanned aerial vehicle 100 can avoid obstacles in the landing area and reduce the risk of the unmanned aerial vehicle 100 crashing.

[0129] Specifically, when the unmanned aerial vehicle 100 is ready to land, the flight control system obtains the point cloud distribution diagram of the landing area through the depth sensor 40.

[0130] The landing area is the area where the unmanned aerial vehicle 100 is ready to land, and the unmanned aerial vehicle 100 is located at the center of the landing area.

[0131] The point cloud distribution diagram is a diagram that can reflect the point cloud distribution of the landing area.

[0132] In an embodiment of the present application, the flight control system obtains the point cloud distribution diagram of the landing area through the depth sensor 40 specifically includes that the flight control system obtains the point cloud data of the landing area through the depth sensor 40, and projects the obtained point cloud data to a two-dimensional plane to obtain the point cloud distribution diagram.

[0133] Of course, in some alternative embodiments, the flight control system obtaining the point cloud distribution of the landing area through the depth sensor 40 can also include: the flight control system obtaining a depth map of the landing area through the depth sensor 40, and obtaining the point cloud distribution according to the obtained depth map.

[0134] Further, after obtaining the point cloud distribution of the landing area, the flight control system determines a safe area in the landing area according to the point cloud distribution.

[0135] The safe area is an area in the landing area where no obstacles exist, i.e., an area after removing the dangerous area where obstacles exist from the landing area.

[0136] When the flight control system determines the safe area in the landing area according to the point cloud distribution, the safe area can be determined by a plane detection method or a vacancy area detection method.

[0137] Specifically, when the safe area in the landing area is determined by the plane detection method, the safe area is determined as an area where the point cloud is located in a plane after extracting feature points in the point cloud distribution and determining the plane.

[0138] When the safe area in the landing area is determined by the vacancy area detection method, the point cloud distribution of the landing area is divided into detection areas, each detection area is divided into at least two specified areas, and the number of point clouds in each specified area is detected. The specified area with a number of point clouds not less than a threshold value is determined as the safe area.

[0139] Of course, in some embodiments, the plane detection method and the vacancy area detection method can be combined to determine the safe area in the landing area, thereby improving the accuracy of determining the safe area.

[0140] Further, after determining the safe area of the landing area, in order to prevent the safe area from being too small and causing the unmanned aerial vehicle 100 to crash after landing, the flight control system determines a ratio R1 of the number of point clouds in the safe area to the number of point clouds in the landing area, and judges whether the ratio R1 is greater than a second preset threshold value. If the ratio R1 is greater than the second preset threshold value, it indicates that the safe area is large enough to meet the landing requirements of the unmanned aerial vehicle 100, and at this time, a target position is determined in the safe area.

[0141] The second preset threshold value is a fixed value set in advance, and the value range of the second preset threshold value is 10%-30%, including the two end point values of 10% and 30%.

[0142] Of course, in some alternative embodiments, the second preset threshold is related to the projection area of the UAV 100, and the ratio of the projection area of the UAV 100 to the area of the landing area to be determined can be determined as the second preset threshold.

[0143] In an embodiment of the present application, determining the target position in the safety area specifically includes: the flight control system determining the center of gravity position of the safety area, and determining the determined center of gravity position as the target position.

[0144] The center of gravity of the safety area is the "center of mass" of all point clouds in the safety area, and the center of gravity position of the safety area can be determined by the average value of all point cloud coordinates in the safety area.

[0145] When the flight control system determines the center of gravity position of the safety area, the coordinates of each point cloud in the safety area are extracted, and then the center of gravity position of the safety area is determined according to the coordinates of each point cloud, and the center of gravity position of the safety area is:

[0146]

[0147] Wherein, n is the total number of point clouds in the safety area, Xi is the horizontal coordinate of the i-th point cloud in the safety area, Yi is the vertical coordinate of the i-th point cloud in the safety area, X is the horizontal coordinate of the center of gravity position, and Y is the vertical coordinate of the center of gravity position.

[0148] For example: when the total number of point clouds in the safety area is 3, the coordinates of the first point cloud are (X1, Y1), the coordinates of the second point cloud are (X2, Y2), and the coordinates of the third point cloud are (X3, Y3). At this time, the flight control system extracts the coordinates of each point cloud in the safety area, that is, the coordinates of the first point cloud (X1, Y1), the coordinates of the second point cloud (X2, Y2) and the coordinates of the third point cloud (X3, Y3) are extracted, and then the flight control system calculates the center of gravity position of the safety area according to the extracted coordinates of the first point cloud (X1, Y1), the coordinates of the second point cloud (X2, Y2) and the coordinates of the third point cloud (X3, Y3), wherein the horizontal coordinate of the center of gravity position of the safety area is The vertical coordinate of the center of gravity position of the safety area

[0149] Further, when the obstacles in the landing area are symmetrical to the center of the UAV 100, the center of gravity of the determined safety area is consistent with the center of the landing area, which causes the UAV to be unable to avoid the obstacles, and therefore, in order to prevent the center of gravity of the safety area from being consistent with the center of the landing area, after the target position is determined, the flight control system also needs to determine the center of the landing area, and judge whether the target position is consistent with the center of the landing area, if the target position is not consistent with the center of the landing area, the UAV 100 is controlled to move to the target position, and if the target position is consistent with the center of the landing area, the target position is determined again.

[0150] In an embodiment of the present application, the control of the UAV 100 to move to the target position specifically includes: after the flight control system determines that the direction of the target position is the first target direction, the UAV 100 is controlled to move to the target position along the first target direction.

[0151] In order to prevent the UAV 100 from colliding with obstacles during the process of moving to the target position, before the UAV 100 is controlled to move to the target position along the first target direction, the flight control system determines whether there are obstacles in the first target direction through the perception sensor, and if there are no obstacles, the UAV 100 is controlled to move to the target position along the first target direction.

[0152] When the perception sensor is a one-way perception sensor, the flight control system controls the perception direction of the one-way perception sensor to be consistent with the first target direction, specifically including: the flight control system controls the flight direction of the UAV 100 to be toward the first target direction. Since the perception direction of the one-way perception sensor is consistent with the flight direction, the perception direction of the one-way perception sensor can be controlled to be consistent with the first target direction by controlling the flight direction of the UAV 100 to be toward the first target direction.

[0153] In an embodiment of the present application, the determination of the target position again includes: the flight control system determines a direction in which there are no obstacles in the landing area as the second target direction, and then controls the UAV 100 to move a preset distance along the second target direction, and then determines the target position in the safety area.

[0154] The flight control system determines the second target direction through the perception sensor.

[0155] The preset distance is related to the second target direction and the size of the landing area, if the second target direction is the width direction of the landing area, the preset distance is half the width of the landing area, and if the second target direction is the length direction of the landing area, the preset distance is half the length of the landing area, so as to ensure that the UAV 100 can leave the landing area after moving a preset distance along the second target direction, and determine the target position in a new safety area.

[0156] Further, after the UAV moves to the target position, the flight control system determines whether there is a dangerous area in a landing area centered on the target position, and if there is, determines the target position in the landing area centered on the target position; if not, controls the UAV to land.

[0157] In an embodiment of the present application, if it is determined that the number of times of determining the target position in the landing area centered on the target position exceeds a first preset threshold, the UAV is controlled to issue a warning and / or stop landing.

[0158] Preferably, the first preset threshold is a pre-set fixed value, and the value range of the first preset threshold is between 3-5, including the two end point values of 3 and 5.

[0159] In an embodiment of the present application, by determining the target position in the safe area of the landing area and controlling the UAV to move to the target position, the UAV can move to the safe area of the landing area, and since the safe area is an area without obstacles, when the UAV moves to the safe area, it achieves avoidance of obstacles, reducing the risk of UAV crash.

[0160] Embodiment two

[0161] Please refer to Figure 2 is a flowchart of a UAV landing obstacle avoidance method provided by an embodiment of the present application, applied to a UAV, which is the UAV 100 described in the above embodiments, and the method provided by the embodiment of the present application is executed by the flight control system described above, for avoiding obstacles in a landing area and reducing the risk of UAV crash. The UAV landing obstacle avoidance method comprises:

[0162] S100: Obtain a point cloud distribution diagram of a landing area.

[0163] The above-mentioned "landing area" is an area where the UAV is ready to land, and the UAV is located at the center of the landing area.

[0164] The above-mentioned "point cloud distribution diagram" is a diagram that can reflect the point cloud distribution of the landing area.

[0165] In an embodiment of the present application, obtaining the point cloud distribution diagram of the landing area specifically comprises: obtaining the point cloud distribution diagram of the landing area by a depth sensor of the UAV.

[0166] The depth sensor includes but is not limited to a binocular camera, a TOF (Time of Flight) camera, a structured light camera, and a laser radar.

[0167] The depth sensor is used to collect point cloud data of the landing area, each point cloud data containing three-dimensional coordinates, and some possibly containing color information or reflection intensity information, and the distance between the depth sensor and the object in the landing area can be obtained through the point cloud data.

[0168] At this time, the point cloud distribution map of the landing area obtained by the depth sensor specifically includes: obtaining point cloud data of the landing area by the depth sensor; projecting the point cloud data to a two-dimensional plane to obtain the point cloud distribution map.

[0169] S200: determining a safe area in the landing area according to the point cloud distribution map.

[0170] The landing area includes a safe area and a dangerous area. The dangerous area refers to an area with obstacles, including: inclined slopes, water surfaces, shrubs, protruding foreign objects, and edge vacancy areas of surface flat areas such as rooftops, cliffs, and deep trenches; the safe area refers to an area without obstacles, i.e., the area after removing the dangerous area with obstacles from the landing area.

[0171] In an embodiment of the present application, the determination of the safe area in the landing area according to the point cloud distribution map can be achieved by a plane detection method or a vacancy area detection method.

[0172] Specifically, when the safe area in the landing area is determined by the plane detection method, the feature points in the point cloud distribution map are extracted to determine the plane, and the area where the point cloud is located in the plane is determined as the safe area.

[0173] When the safe area in the landing area is determined by the vacancy area detection method, the detection area is divided in the point cloud distribution map of the landing area, the detection area is divided into at least two specified areas, the number of point clouds in each specified area is detected, and the specified area with a point cloud number not less than a threshold value is determined as the safe area.

[0174] Of course, in some embodiments, the plane detection method and the vacancy area detection method can be combined to determine the safe area in the landing area, thereby improving the accuracy of determining the safe area.

[0175] S400: determining a target position in the safe area.

[0176] The above-mentioned "target position" is a position in the safe area that can make the unmanned aerial vehicle away from the obstacle, i.e., the position to which the unmanned aerial vehicle is about to move.

[0177] Please refer to Figure 3 In an embodiment of the present application, the determination of the target position in the safe area specifically includes:

[0178] S410: determine the barycentric position of the safety area;

[0179] S420: determine the barycentric position of the safety area as the target position.

[0180] The determination of the barycentric position of the safety area specifically includes: extracting the coordinates of each point cloud in the safety area; and determining the barycentric position of the safety area according to the coordinates of each point cloud, the barycentric position of the safety area being:

[0181]

[0182] wherein n is the total number of point clouds in the safety area, Xi is the horizontal coordinate of the i-th point cloud in the safety area, Yi is the vertical coordinate of the i-th point cloud in the safety area, X is the horizontal coordinate of the barycentric position, and Y is the vertical coordinate of the barycentric position.

[0183] For example, when the total number of point clouds in the safety area is 3, the coordinates of the 1st point cloud are (X1, Y1), the coordinates of the 2nd point cloud are (X2, Y2), and the coordinates of the 3rd point cloud are (X3, Y3). At this time, the flight control system extracts the coordinates of each point cloud in the safety area, i.e., the coordinates (X1, Y1) of the 1st point cloud, the coordinates (X2, Y2) of the 2nd point cloud, and the coordinates (X3, Y3) of the 3rd point cloud. Then, the flight control system calculates the barycentric position of the safety area according to the extracted coordinates (X1, Y1) of the 1st point cloud, the coordinates (X2, Y2) of the 2nd point cloud, and the coordinates (X3, Y3) of the 3rd point cloud, wherein the horizontal coordinate of the barycentric position of the safety area is the vertical coordinate of the barycentric position of the safety area

[0184] Since the safety area is the area of the landing area excluding the dangerous area, and the obstacles are not symmetrical relative to the center position of the landing area, the barycentric position of the safety area deviates from the center position of the landing area. Therefore, when the barycentric position of the safety area is determined as the target position, the unmanned aerial vehicle moving to the target position can be far away from the obstacles.

[0185] S800: control the unmanned aerial vehicle to move to the target position, so that the unmanned aerial vehicle is far away from the obstacles in the landing area.

[0186] Please refer to Figure 4 In an embodiment of the present application, the control of the unmanned aerial vehicle to move to the target position specifically includes:

[0187] S810: determine the direction of the target position as the first target direction;

[0188] S820: determine whether there are obstacles in the first target direction;

[0189] S830: If not, the UAV is controlled to move to the target position along the first target direction.

[0190] The first target direction is determined by the perception sensor.

[0191] When the perception sensor is a one-way perception sensor, the sensing direction of the one-way perception sensor is controlled to be consistent with the first target direction, specifically including: controlling the flight direction of the UAV to be toward the first target direction. Since the sensing direction of the one-way perception sensor is consistent with the flight direction, the sensing direction of the one-way perception sensor can be controlled to be consistent with the first target direction by controlling the flight direction of the UAV to be toward the first target direction.

[0192] Referring to Figure 5 When the obstacles in the landing area are symmetrical relative to the center of the UAV, the center of gravity of the determined safety area is consistent with the center of the landing area, so that the UAV cannot avoid the obstacles. Therefore, in order to prevent the center of gravity of the safety area from being consistent with the center of the landing area, in another embodiment of the present application, before step S800, the method further comprises:

[0193] S500: determining the center of the landing area;

[0194] S600: determining whether the target position is consistent with the center of the landing area, if yes, step S700 is performed; if not, step S800 is performed.

[0195] S700: re-determining the target position.

[0196] The re-determining of the target position includes: determining a direction in which there is no obstacle in the landing area as a second target direction; and controlling the UAV to move a preset distance along the second target direction, and then determining the target position in the safety area.

[0197] The second target direction can be determined by the perception sensor.

[0198] The preset distance is related to the second target direction and the size of the landing area. If the second target direction is the width direction of the landing area, the preset distance is half the width of the landing area; if the second target direction is the length direction of the landing area, the preset distance is half the length of the landing area, so as to ensure that the UAV 100 can move a preset distance along the second target direction and leave the landing area, and determine the target position in a new safety area.

[0199] Referring to Figure 6 In another embodiment of the present application, after step S800, the method further comprises:

[0200] S900: determining whether a dangerous area exists in the target landing area centered on the target position,

[0201] If not, controlling the UAV to land;

[0202] If so, determining a target position in the target landing area centered on the target position.

[0203] Wherein, when determining whether a dangerous area exists in the target landing area, the determination can be made by a plane detection method or by a vacancy area detection method.

[0204] When determining whether a dangerous area exists in the target landing area by the plane detection method, the feature points in the point cloud distribution map are extracted to determine the plane, and the area outside the plane is determined as the dangerous area.

[0205] When determining whether a dangerous area exists in the target landing area by the vacancy area detection method, the detection area is divided in the point cloud distribution map of the target landing area, the detection area is divided into at least two specified areas, the number of point clouds in each specified area is detected, and the specified area with a number of point clouds less than a threshold value is determined as the dangerous area.

[0206] Of course, in some embodiments, the plane detection method and the vacancy area detection method can be combined to determine the safe area in the target landing area, thereby improving the accuracy of determining the safe area.

[0207] Further, it is determined whether the number of times of determining the target position in the target landing area centered on the target position exceeds a first preset threshold value, and if so, the UAV is controlled to issue a warning and / or stop landing.

[0208] Preferably, the first preset threshold value is a fixed value set in advance, and the value range of the first preset threshold value is between 3 and 5, including the two end point values of 3 and 5.

[0209] Please refer to Figure 7 In another embodiment of the present application, in order to prevent the safe area from being too small and causing the UAV to crash after landing, step S400 further includes:

[0210] S300: determining whether the ratio R1 of the number of point clouds of the safe area to the number of point clouds of the target landing area is greater than a second preset threshold value, and if so, performing step S400.

[0211] Wherein, the second preset threshold value is a fixed value set in advance, and the value range of the second preset threshold value is 10%-30%, including the two end point values of 10% and 30%.

[0212] Of course, in some alternative embodiments, the second preset threshold is related to the projection area of the UAV 100, and the ratio of the projection area of the UAV 100 to the area of the landing area to be landed can be determined as the second preset threshold.

[0213] In the embodiment of the application, the target position is determined in the safe area of the landing area to be landed, and the UAV is controlled to move to the target position, so that the UAV can move to the safe area of the landing area to be landed, and since the safe area is an area without obstacles, when the UAV moves to the safe area, the avoidance of obstacles is realized, and the risk of UAV crash is reduced.

[0214] Embodiment three

[0215] The term "module" used below is a combination of software and / or hardware that can implement a predetermined function. Although the apparatus described in the following embodiments can be implemented in software, implementation of hardware, or a combination of software and hardware, is also possible.

[0216] Please refer to Figure 8 The UAV landing obstacle avoidance device provided by one of the embodiments of the application is applied to a UAV, which is the UAV 100 described in the above embodiments, and the functions of the modules of the device provided by the embodiments of the application are performed by the flight control system described above, for avoiding obstacles in a landing area to be landed and reducing the risk of UAV crash. The UAV landing obstacle avoidance device comprises:

[0217] The acquisition module 200 is configured to acquire a point cloud distribution map of a landing area to be landed.

[0218] The determination module 300 is configured to determine a safe area in the landing area to be landed according to the point cloud distribution map.

[0219] determining a target position in the safe area.

[0220] The control module 400 is configured to control the UAV to move to the target position, so that the UAV moves away from obstacles in the landing area to be landed.

[0221] The acquisition module 200 acquires the point cloud distribution map of the landing area to be landed through a depth sensor of the UAV.

[0222] Further, the acquisition module 200 is specifically configured to:

[0223] acquire point cloud data of the landing area to be landed through the depth sensor;

[0224] project the point cloud data to a two-dimensional plane to acquire the point cloud distribution map.

[0225] Further, the determining module 300 is specifically configured to:

[0226] determine the barycentric position of the safety area;

[0227] determine the barycentric position of the safety area as the target position.

[0228] Further, the determining module 300 is further configured to:

[0229] extract the coordinates of each point cloud in the safety area;

[0230] determine the barycentric position of the safety area according to the coordinates of each point cloud as:

[0231]

[0232] wherein n is the total number of point clouds in the safety area, Xi is the horizontal coordinate of the i-th point cloud in the safety area, Yi is the vertical coordinate of the i-th point cloud in the safety area, X is the horizontal coordinate of the barycentric position, and Y is the vertical coordinate of the barycentric position.

[0233] Further, the control module 400 is specifically configured to:

[0234] determine the direction in which the target position is located as a first target direction;

[0235] control the UAV to move to the target position along the first target direction.

[0236] Further, the control module 400 is further configured to:

[0237] determine whether there is an obstacle in the first target direction, and if not, control the UAV to move to the target position along the first target direction.

[0238] Further, the control module 400 determines whether there is an obstacle in the first target direction through a perception sensor.

[0239] Further, when the perception sensor is a one-way sensor, the control module 400 is further configured to:

[0240] control the perception direction of the one-way perception sensor to be consistent with the first target direction.

[0241] Further, the determining module 300 is further configured to:

[0242] determine the center position of the landing area;

[0243] determine whether the target position is consistent with the center position of the landing area, and if so, re-determine the target position.

[0244] Further, the determining module 300 is further configured to:

[0245] determine a direction in which there is no obstacle in the landing area as a second target direction;

[0246] control the UAV to move a preset distance along the second target direction, and then determine a target position in the safe area.

[0247] Further, the control module 400 is further configured to:

[0248] determine whether there is a dangerous area in the landing area centered on the target position,

[0249] if not, control the UAV to land;

[0250] if yes, determine a target position in the landing area centered on the target position.

[0251] Further, the control module 400 is further configured to:

[0252] determine whether the number of times of determining the target position in the landing area centered on the target position exceeds a first preset threshold, and if yes, control the UAV to issue a warning and / or control the UAV to stop landing.

[0253] Further, the determining module 300 is further configured to:

[0254] determine a ratio R1 of the number of point clouds of the safe area to the number of point clouds of the landing area;

[0255] determine whether the R1 is greater than a second preset threshold, and if yes, determine a target position in the safe area.

[0256] Of course, in some other alternative embodiments, the above-mentioned acquisition module 200 can be a depth sensor to directly acquire the point cloud distribution map of the landing area; and the above-mentioned determining module 300 and control module 400 can be a flight control chip.

[0257] Since the device embodiment and the method embodiment are based on the same concept, the content of the device embodiment can refer to the method embodiment without mutual conflict, which will not be repeated here.

[0258] In the embodiments of the present application, by determining a target position in the safe area of the landing area and controlling the UAV to move to the target position, the UAV can move to the safe area of the landing area, and since the safe area is an area without obstacles, the UAV can avoid obstacles when moving to the safe area, thereby reducing the risk of UAV crash.

[0259] Embodiment Four

[0260] Referring to Figure 9 is a hardware structure schematic diagram of a UAV provided by one of the embodiments of the present application. The hardware module provided by the embodiments of the present application can be integrated into the flight control system described in the above embodiments, or can be directly arranged in the fuselage 10 as the flight control system, so that the UAV 100 can execute the UAV landing obstacle avoidance method described in the above embodiments, and can also realize the functions of each module of the UAV landing obstacle avoidance device described in the above embodiments. The UAV 100 comprises:

[0261] one or more processors 110 and a memory 120. Wherein, Figure 9 In the embodiment, the processor 110 is taken as an example.

[0262] The processor 110 and the memory 120 can be connected through a bus or other means, Figure 9 In the embodiment, the connection through the bus is taken as an example.

[0263] The memory 120 is a non-volatile computer readable storage medium, which can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions corresponding to the UAV landing obstacle avoidance method and modules (for example, the acquisition module 200, the determination module 300 and the control module 400) of the UAV landing obstacle avoidance device in the above embodiments of the present application. The processor 110 executes the various functional applications and data processing of the UAV landing obstacle avoidance method by running the non-volatile software programs, instructions and modules stored in the memory 120, that is, realizes the functions of the UAV landing obstacle avoidance method in the above method embodiments and the functions of each module of the above device embodiments.

[0264] The memory 120 can include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application program required by a function; the data storage area can store data created according to the use of the UAV landing obstacle avoidance device, etc.

[0265] The storage data area also stores preset data, including a first preset threshold, a second preset threshold, a preset distance, etc.

[0266] In addition, the memory 120 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 120 can optionally include a memory remotely arranged relative to the processor 110, and these remote memories can be connected to the processor 110 through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0267] The program instructions and one or more modules are stored in the memory 120, and when executed by the one or more processors 110, perform the steps of the UAV landing obstacle avoidance method of any of the above method embodiments, or implement the functions of the modules of the UAV landing obstacle avoidance device of any of the above device embodiments.

[0268] The above products can perform the methods provided by the above embodiments of the application, have the corresponding function modules and beneficial effects of performing the methods. Technical details not described in detail in the embodiments can be referred to the methods provided by the above embodiments of the application.

[0269] The embodiments of the application also provide a non-volatile computer readable storage medium, the computer readable storage medium stores computer executable instructions, the computer executable instructions are executed by one or more processors, for example, one processor 110 in the computer device 100, so that the computer executes the steps of the UAV landing obstacle avoidance method of any of the above method embodiments, or implements the functions of the modules of the UAV landing obstacle avoidance device of any of the above device embodiments. Figure 9

[0270] The embodiments of the application also provide a computer program product, the computer program product includes a computer program stored on a non-volatile computer readable storage medium, the computer program includes program instructions, when the program instructions are executed by one or more processors, for example, one processor 110 in the computer device 100, so that the computer executes the steps of the UAV landing obstacle avoidance method of any of the above method embodiments, or implements the functions of the modules of the UAV landing obstacle avoidance device of any of the above device embodiments. Figure 9

[0271] The device embodiments described above are only schematic, wherein the modules illustrated as separate components can or can not be physically separated, and the components illustrated as modules can or can not be physical units, that is, can be located in one place, or can be distributed on multiple network units. According to actual needs, part or all of the modules can be selected to achieve the purpose of the embodiments.

[0272] ​​Those skilled in the art can clearly understand the implementation of the embodiments by the above description of the embodiments, and the embodiments can be implemented by means of software plus a general hardware platform, and of course, can also be implemented by hardware. Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by computer program instruction related hardware, and the program can be stored in a computer readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM) or a random access memory (RAM) and the like.

[0273] The above description is only the embodiments of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation, or direct or indirect application in other related technical fields, which is made by using the content of the specification and drawings of the present application, is also included in the patent protection scope of the present application.

[0274] Finally, it should be pointed out that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the patent scope of the present application; under the idea of the present application, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other changes of the different aspects of the present application as described above. In order to be brief, they are not provided in details; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: the technical solutions recorded in the foregoing embodiments can still be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for obstacle avoidance for UAV landing, characterized in that, The method comprises: obtaining point cloud data of a landing area to be landed by a depth sensor, wherein each point cloud in the point cloud data contains three-dimensional coordinates; projecting the point cloud data onto a two-dimensional plane to obtain a point cloud distribution map; determining a safe area in the landing area to be landed according to the point cloud distribution map, wherein the safe area is an area in the landing area to be landed where no obstacles exist; determining a ratio R1 of the number of point clouds in the safe area to the number of point clouds in the landing area to be landed; determining whether the R1 is greater than a second preset threshold, and if so, extracting the coordinates of each point cloud in the safe area and determining a target position of the safe area according to the coordinates of each point cloud; controlling the UAV to move to the target position so as to move the UAV away from the obstacles in the landing area to be landed; before the controlling the UAV to move to the target position, the method further comprises: determining a center position of the landing area to be landed; determining whether the target position is consistent with the center position of the landing area to be landed, and if so, re-determining the target position.

2. The method of any one of claim 1, characterized in that, The determining the target position of the safe area according to the coordinates of each point cloud comprises: determining a barycenter position of the safe area; determining the barycenter position of the safe area as the target position.

3. The method of claim 2, wherein, The determining the barycenter position of the safe area comprises: determining the barycenter position of the safe area according to the coordinates of each point cloud as: ， ， wherein n is the total number of point clouds in the safe area, Xi is the horizontal coordinate of the i-th point cloud in the safe area, Yi is the vertical coordinate of the i-th point cloud in the safe area, X is the horizontal coordinate of the barycenter position, and Y is the vertical coordinate of the barycenter position.

4. The method of claim 3, wherein, The controlling the UAV to move to the target position comprises: determining the direction in which the target position is located as a first target direction; controlling the UAV to move to the target position along the first target direction.

5. The method of claim 4, wherein, Before the controlling the UAV to move to the target position along the first target direction, the method further comprises: determining whether there are obstacles in the first target direction, and if not, controlling the UAV to move to the target position along the first target direction.

6. The method of claim 5, wherein, Determining whether there are obstacles in the first target direction by a perception sensor.

7. The method of claim 6, wherein, The perception sensor is a one-way perception sensor, and the method further comprises: controlling the perception direction of the one-way perception sensor to be consistent with the first target direction.

8. The method of claim 1, wherein, The re-determining the target position comprises: determining a direction in which no obstacles exist in the landing area to be landed as a second target direction; controlling the UAV to move a preset distance along the second target direction and then determining a target position in the safe area.

9. The method of claim 1, wherein, After the controlling the UAV to move to the target position, the method further comprises: determining whether there is a dangerous area in the landing area to be landed centered on the target position, if not, controlling the UAV to land; if so, determining a target position in the landing area to be landed centered on the target position.

10. The method of claim 9, wherein, The method further comprises: Determine whether the number of times of determining the target position in the region to be landed centered on the target position exceeds a first preset threshold, and if so, control the UAV to issue a warning and / or control the UAV to stop landing.

11. A UAV landing obstacle avoidance device, characterized in that, The apparatus comprises: at least one processor; and a memory connected with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to cause the at least one processor to perform the UAV landing obstacle avoidance method according to any one of claims 1-10.

12. A drone, characterized in that, comprise: a fuselage; an arm connected with the fuselage; a power device arranged on the arm; at least one processor arranged in the fuselage; and a memory connected with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to cause the at least one processor to perform the UAV landing obstacle avoidance method according to any one of claims 1-10. The non-volatile computer readable storage medium stores computer executable instructions for causing the UAV to perform the UAV landing obstacle avoidance method according to any one of claims 1-10.

13. A non-transitory computer readable storage medium, comprising: ​

Images