WO2020125726A1 - 一种无人机自主降落方法、装置及无人机 - Google Patents

一种无人机自主降落方法、装置及无人机 Download PDF

Info

Publication number
WO2020125726A1
WO2020125726A1 PCT/CN2019/126720 CN2019126720W WO2020125726A1 WO 2020125726 A1 WO2020125726 A1 WO 2020125726A1 CN 2019126720 W CN2019126720 W CN 2019126720W WO 2020125726 A1 WO2020125726 A1 WO 2020125726A1
Authority
WO
WIPO (PCT)
Prior art keywords
area
landing
point cloud
designated
distribution map
Prior art date
Application number
PCT/CN2019/126720
Other languages
English (en)
French (fr)
Inventor
郑欣
Original Assignee
深圳市道通智能航空技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市道通智能航空技术有限公司 filed Critical 深圳市道通智能航空技术有限公司
Publication of WO2020125726A1 publication Critical patent/WO2020125726A1/zh
Priority to US17/352,697 priority Critical patent/US20220075391A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/10—Simultaneous control of position or course in three dimensions
    • G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/10—Simultaneous control of position or course in three dimensions
    • G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
    • G05D1/102—Simultaneous control of position or course in three dimensions specially adapted for aircraft specially adapted for vertical take-off of aircraft
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B64—AIRCRAFT; AVIATION; COSMONAUTICS
    • B64C—AEROPLANES; HELICOPTERS
    • B64C39/00—Aircraft not otherwise provided for
    • B64C39/02—Aircraft not otherwise provided for characterised by special use
    • B64C39/024—Aircraft not otherwise provided for characterised by special use of the remote controlled vehicle type, i.e. RPV
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B64—AIRCRAFT; AVIATION; COSMONAUTICS
    • B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U60/00—Undercarriages
    • B64U60/50—Undercarriages with landing legs
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B64—AIRCRAFT; AVIATION; COSMONAUTICS
    • B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U70/00—Launching, take-off or landing arrangements
    • B64U70/90—Launching from or landing on platforms
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/20—Instruments for performing navigational calculations
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3885—Transmission of map data to client devices; Reception of map data by client devices
    • G01C21/3889—Transmission of selected map data, e.g. depending on route
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3885—Transmission of map data to client devices; Reception of map data by client devices
    • G01C21/3896—Transmission of map data from central databases
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B64—AIRCRAFT; AVIATION; COSMONAUTICS
    • B64D—EQUIPMENT FOR FITTING IN OR TO AIRCRAFT; FLIGHT SUITS; PARACHUTES; ARRANGEMENT OR MOUNTING OF POWER PLANTS OR PROPULSION TRANSMISSIONS IN AIRCRAFT
    • B64D45/00—Aircraft indicators or protectors not otherwise provided for
    • B64D45/04—Landing aids; Safety measures to prevent collision with earth's surface
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B64—AIRCRAFT; AVIATION; COSMONAUTICS
    • B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U10/00—Type of UAV
    • B64U10/10—Rotorcrafts
    • B64U10/13—Flying platforms
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B64—AIRCRAFT; AVIATION; COSMONAUTICS
    • B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U2101/00—UAVs specially adapted for particular uses or applications
    • B64U2101/30—UAVs specially adapted for particular uses or applications for imaging, photography or videography
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B64—AIRCRAFT; AVIATION; COSMONAUTICS
    • B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U2201/00—UAVs characterised by their flight controls
    • B64U2201/10—UAVs characterised by their flight controls autonomous, i.e. by navigating independently from ground or air stations, e.g. by using inertial navigation systems [INS]
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B64—AIRCRAFT; AVIATION; COSMONAUTICS
    • B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U50/00—Propulsion; Power supply
    • B64U50/10—Propulsion
    • B64U50/19—Propulsion using electrically powered motors
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B64—AIRCRAFT; AVIATION; COSMONAUTICS
    • B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U70/00—Launching, take-off or landing arrangements

Definitions

  • the embodiments of the present invention relate to the technical field of drone control, and in particular, to a method, device and drone for drone autonomous landing.
  • UAV is an unmanned aerial vehicle operated by radio remote control equipment or its own program control device.
  • the drone is equipped with autonomous landing protection technology to prevent unmanned The plane crashed when it landed in an unknown environment.
  • the inventor discovered in the process of implementing the present invention:
  • the autonomous landing protection technology equipped in the drone only analyzes the overall situation of the area to be landed, and can only detect the overall flatness of the area to be landed, and cannot detect it. Buildings, cliffs, deep trenches and other dangerous areas that are flat but have obvious edge vacancies are not fully tested, so that there is still a risk of crashing when the drone is landing.
  • the embodiment of the present invention aims to provide a method and device for autonomous landing of an unmanned aerial vehicle, and an unmanned aerial vehicle, which can realize the local detection of the unmanned aerial vehicle, improve the accuracy of the detection, and reduce the risk of the unmanned aerial vehicle crash.
  • a technical solution adopted by the embodiments of the present invention is to provide an autonomous landing method for an unmanned aerial vehicle.
  • the method includes:
  • the acquiring the point cloud distribution map of the area to be landed includes:
  • the acquiring the point cloud distribution map of the area to be landed through the depth sensor of the drone includes:
  • the acquiring the point cloud distribution map of the area to be landed through the depth sensor of the drone includes:
  • the detection area is the area corresponding to the point cloud distribution map excluding the actual landing area and added by a risk tolerance error area.
  • the point cloud distribution map is a rectangular structure, and the at least two designated areas include:
  • the detection area does not include the area where the four corners in the point cloud distribution map are located.
  • the mathematical expressions of the first designated area S1, the second designated area S2, the third designated area S3, and the fourth designated area S4 are as follows:
  • x 1 is the abscissa of the point falling within the first specified area S1
  • y 1 is the ordinate of the point falling within the first specified area S1
  • x 2 is the The abscissa of the points in the second designated area S2
  • y 2 is the ordinate of the points falling in the second designated area S2
  • x 3 is the abscissa of the points falling in the third designated area S3
  • Y 3 is the vertical coordinate of the point falling within the third specified area S3
  • x 4 is the horizontal coordinate of the point falling within the fourth specified area S4
  • y 4 is the falling point of the The vertical coordinate of the point in the fourth designated area S4, length is half the length of the point cloud distribution map, width is half the width of the point cloud distribution map, and l is half the length of the actual landing area, w is half the width of the actual landing area, and d is the hazard tolerance error.
  • the preset threshold is within a range of 15-50.
  • an autonomous landing device for an unmanned aerial vehicle including:
  • An obtaining module the obtaining module is used to obtain a point cloud distribution map of the area to be landed;
  • a first determining module is used to determine the detection area in the point cloud distribution map according to the actual landing area of the drone in the point cloud distribution map, wherein the detection area Refers to the area used to detect the number of point clouds in the point cloud distribution map;
  • a dividing module configured to divide the detection area into at least two designated areas, and each of the at least two designated areas corresponds to a part of the area to be landed;
  • a second determination module which is used to determine whether the number of point clouds in each of the at least two designated areas is less than a preset threshold
  • control module is configured to control the drone to fly away from the designated area where the number of point clouds is less than the preset threshold or control the none if the number of point clouds in each designated area is less than a preset threshold The man-machine stopped landing.
  • the acquisition module acquires the point cloud distribution map of the area to be landed through the depth sensor of the drone.
  • the acquisition module is specifically used to:
  • the acquisition module is specifically used to:
  • the detection area is the area corresponding to the point cloud distribution map excluding the actual landing area and added by a risk tolerance error area.
  • the point cloud distribution map is a rectangular structure, and the at least two designated areas include:
  • the detection area does not include the area where the four corners in the point cloud distribution map are located.
  • the mathematical expressions of the first designated area S1, the second designated area S2, the third designated area S3, and the fourth designated area S4 are as follows:
  • x 1 is the abscissa of the point falling within the first specified area S1
  • y 1 is the ordinate of the point falling within the first specified area S1
  • x 2 is the The abscissa of the points in the second designated area S2
  • y 2 is the ordinate of the points falling in the second designated area S2
  • x 3 is the abscissa of the points falling in the third designated area S3
  • Y 3 is the vertical coordinate of the point falling within the third specified area S3
  • x 4 is the horizontal coordinate of the point falling within the fourth specified area S4
  • y 4 is the falling point of the The vertical coordinate of the point in the fourth designated area S4, length is half the length of the point cloud distribution map, width is half the width of the point cloud distribution map, and l is half the length of the actual landing area, w is half the width of the actual landing area, and d is the hazard tolerance error.
  • the preset threshold is within a range of 15-50.
  • a drone including:
  • At least one processor At least one processor
  • the device can be used to perform the above-mentioned UAV autonomous landing method.
  • another technical solution adopted by the embodiments of the present invention is to provide a non-volatile computer-readable storage medium that stores computer-executable instructions.
  • the computer-executable instructions are used to make the drone execute the drone autonomous landing method described above.
  • the embodiments of the present invention provide a drone autonomous landing method, device and unmanned aerial vehicle.
  • the point cloud distribution map of the area divides the specified area, and judges the number of point clouds in each specified area to achieve local detection, and because the local detection of the specified area is relative to the overall detection of the area to be landed, the point cloud
  • the small number base allows the drone to determine each dangerous designated area more accurately, improves the detection accuracy, and reduces the risk of the drone crashing.
  • FIG. 1 is a schematic structural diagram of a drone according to an embodiment of the present invention
  • FIG. 3a is a schematic diagram of dividing a designated area according to an embodiment of the present invention.
  • 3b is a schematic diagram of the division of a designated area provided by an embodiment of the present invention.
  • 4a is a schematic diagram of the division of a designated area provided by an embodiment of the present invention.
  • FIG. 4b is a schematic diagram of the designated area shown in FIG. 4a in the oblique danger boundary L;
  • FIG. 5a is a schematic diagram of dividing a designated area according to an embodiment of the present invention.
  • FIG. 5b is a schematic diagram of the designated area shown in FIG. 5a in the oblique danger boundary L;
  • FIG. 6 is a schematic flowchart of a method for autonomous landing of a drone according to an embodiment of the present invention
  • FIG. 7 is a schematic structural diagram of an autonomous landing device for an unmanned aerial vehicle according to an embodiment of the present invention.
  • FIG. 8 is a schematic diagram of a hardware structure of an unmanned aerial vehicle according to an embodiment of the present invention.
  • the invention provides a method and device for autonomous landing of an unmanned aerial vehicle.
  • the method and the device are applied to an unmanned aerial vehicle, so that the unmanned aerial vehicle can determine whether there is a local dangerous area in the area to be landed when preparing to land, and if there is a local In the danger zone, the drone is controlled to fly away from the local danger zone or the drone is stopped to prevent the drone from crashing in the local danger zone.
  • the local dangerous area is an edge vacant area of a flat surface area such as a roof, a cliff, and a deep trench.
  • the drone in the present invention may be any suitable type of high-altitude drone or low-altitude drone, including fixed-wing unmanned aerial vehicle, rotary-wing unmanned aerial vehicle, umbrella-wing unmanned aerial vehicle or flapping-wing unmanned aerial vehicle.
  • FIG. 1 is a drone 100 according to an embodiment of the present invention, including a housing 10, an arm 20, a power device 30, a depth sensor 40, a landing gear 50, and a flight control system (not shown) .
  • the arm 20, the depth sensor 40 and the landing gear 50 are all connected to the housing 10, the flight control system is installed in the housing 10, and the power device 30 is installed on the arm 20.
  • the power device 30, the depth sensor 40, and the landing gear 50 are all connected to the flight control system, so that the flight control system can control the flight of the drone 100 through the power device 30, and can obtain the drone 100 standby through the depth sensor 40.
  • the point cloud distribution map of the landing area can also control the landing gear 50 to contact the ground.
  • the number of the arm 20 is four, which is evenly distributed around the housing 10 and used for carrying the power device 30.
  • the power unit 30 includes a motor and a propeller connected to the motor shaft.
  • the motor can drive the propeller to rotate to provide lift for the drone 100 to achieve flight.
  • the motor can also change the flying direction of the drone 100 by changing the rotation speed and direction of the propeller.
  • the flight control system can control the flight of the drone 100 by controlling the motor.
  • the power device 30 is disposed at the end of the arm 20 that is not connected to the housing 10, and is connected to the arm 20 through a motor.
  • a power device is provided on all four arms of the drone 100, so that the drone 100 can fly smoothly.
  • the depth sensor 40 is provided at the bottom of the housing 10 and is used to collect a depth map (Depth Map) of the area where the drone 100 is to be landed.
  • the depth map is an image or image channel containing information about the surface distance of the scene object at the viewpoint.
  • each pixel value represents the actual distance of the depth sensor from the object. Therefore, the depth sensor 40 collects the depth map, that is, the actual distance between the depth sensor 40 and the object in the area to be landed.
  • the flight control system can obtain the depth map of the area to be landed by the drone 100 from the depth sensor 40, and obtain the point cloud distribution map of the area to be landed according to the depth map.
  • the depth sensor 40 is used to collect point cloud data of the area to be landed by the drone 100.
  • each point contains three-dimensional coordinates, and some may contain color information or reflection intensity information.
  • the flight control system can obtain the point cloud data of the area where the drone 100 is to land from the depth sensor 40, and project the point cloud data onto a two-dimensional plane to obtain Point cloud distribution map of the landing area.
  • the depth sensor 40 is provided on the bottom of the housing 10 through a gimbal, so that the depth sensor 40 can comprehensively collect depth maps or point cloud data of the area to be landed.
  • the depth sensor 40 includes, but is not limited to: a binocular camera, a TOF (Time of Flight) camera, a structured light camera, a laser radar, and the like.
  • the landing gear 50 is disposed on opposite sides of the bottom of the housing 10 and connected to the housing 10 through a driving device.
  • the landing gear 50 can be opened and retracted under the driving of the driving device.
  • the driving device controls the landing gear 50 to open, so that the drone 100 contacts the ground through the landing gear 50; during the flight of the drone 100, the driving device controls the landing gear 50 to retract, In order to avoid the landing gear 50 affecting the drone 100 flight.
  • the landing gear 50 is in communication with the flight control system, the flight control system can control the landing gear 50 to contact the ground by controlling the driving device.
  • the drone 100 when the drone 100 is landed on the ground, it only contacts the ground through the landing gear 50. At this time, the actual landing area of the drone 100 is the area enclosed by the landing gear 50 when it contacts the ground.
  • the projection of the body of the drone 100 on the ground encloses a projection area, the center point of the projection area coincides 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 range of motion of the propeller, and represents the smallest area where the drone 100 can normally move.
  • the flight control system and the power device 30, the depth sensor 40, and the landing gear 50 are communicatively connected by a wired connection or a wireless connection.
  • the wireless connection includes but is not limited to: WiFi, Bluetooth, ZigBee, etc.
  • the flight control system is used to execute the autonomous landing method of the drone according to the present invention, so that the drone 100 can realize local detection, improve the detection accuracy, and reduce the risk of the drone crash.
  • the flight control system obtains a point cloud distribution map of the area to be landed through the depth sensor 40.
  • the area to be landed is an area where the surface determined according to the existing UAV landing protection method is flat and suitable for the landing of the drone, including: ground, roof, platform, cliff and other areas.
  • the surface In areas where the surface is flat and suitable for drone landing, there may be edge vacant areas such as cliffs, roofs, etc. If local hazard judgment is not performed on the edge vacant area, the drone 100 will land in the edge vacant area At times, it is easy to crash due to landing on the edge. Therefore, the present invention performs risk detection based on the area to be landed with a flat surface and suitable for landing by the drone 100.
  • the point cloud distribution diagram is a schematic diagram that can reflect the distribution of point clouds in the area to be landed.
  • the flight control system obtains a point cloud distribution map of the area to be landed centering on the center of the drone.
  • the flight control system acquiring the point cloud distribution map of the area to be landed through the depth sensor 40 specifically includes: the flight control system acquiring the depth map of the area to be landed through the depth sensor 40, and according to the acquired depth map Get the point cloud distribution map.
  • the flight control system acquiring the point cloud distribution map of the area to be landed through the depth sensor 40 specifically includes: the flight control system acquiring the point cloud data of the area to be landed through the depth sensor 40, and combining the acquired Point cloud data is projected onto a two-dimensional plane to obtain a point cloud distribution map.
  • the flight control system determines the detection area in the point cloud distribution map according to the actual landing area of the drone 100 in the point cloud distribution map.
  • the area to be landed is a certain surface that is flat and suitable for the drone 100 to land, at this time, there is no need to consider the problem of the propeller rotating and colliding with obstacles, only the problem of whether the drone 100 will land to the vacant area of the edge
  • the vacant area that will land to the edge is related to the landing position of the drone landing gear 50, that is, to the actual landing area of the drone 100, so in the present invention, the flight control system is based on the drone 100 at the point
  • the actual landing area in the cloud distribution map determines the detection area in the point cloud distribution map.
  • the detection area refers to an area used to detect the number of point clouds in the point cloud distribution map.
  • the drone 100 since the drone 100 has a detection error in the actual detection process, the drone 100 has a danger tolerance error in the actual landing process.
  • the risk tolerance error is to allow the drone 100 to enter the vacancy
  • the maximum distance of the area that is, the drone 100 falls into the vacant area on the edge at the distance of the danger tolerance error, the drone 100 will not crash, so when determining the detection area, it is necessary to combine the area composed of the danger tolerance error consider.
  • the detection area is the area corresponding to the point cloud distribution excluding the actual landing area and the area composed of the hazard tolerance error.
  • the determined detection area is the maximum detection area, which can make the detection result more Accurate, to avoid missing the detection of the area constituted by the risk tolerance error.
  • the risk tolerance error depends on the size of the UAV 100 and the accuracy of the depth sensor 40, and its value range is between 1 cm-5 cm, including 1 cm and 5 cm.
  • the area corresponding to the point cloud distribution map is the area to be landed, the area to be landed is A, and the actual landed area is B.
  • the area A corresponding to the point cloud distribution map excludes the actual landed area B the area is obtained A1; the area composed of the hazard tolerance error d is B1.
  • the detection area obtained is A1+ B1.
  • the landing area B2 is obtained, and the landing area B2 can also be the detection area A1+B1 for the area A corresponding to the point cloud distribution map After the area, the landing area B2 is not used to detect the number of point clouds.
  • the flight control system divides the detection area into at least two designated areas, and each of the at least two designated areas corresponds to a part of the area to be landed respectively.
  • the detection area When the flight control system divides the detection area into at least two designated areas, the detection area may be divided into at least two designated areas with equal areas, or the detection area may be divided into at least two designated areas with unequal areas.
  • the flight control system divides the detection area, it can be divided according to the landing area B2, for example: the detection area can be divided according to the extension line of at least one boundary line of the landing area B2; it can also correspond to the area A to be landed according to at least two corners of the landing area B2 The corner line divides the detection area.
  • the flight control system divides the detection area A1+B1 into a designated area C1 and a designated area C2 with unequal areas according to the extension line of one side of the landing area B2.
  • the flight control system divides the detection area A1+B1 into a designated area C1 and a designated area C2 with the same area according to the connection line between the two opposite corners of the landing area B2 and the corresponding corner of the landing area A.
  • the point cloud distribution map has a rectangular structure
  • the flight control system divides the detection area into 4 designated areas, as shown in FIG. 4a
  • the divided 4 designated areas include: located in the landing area B2 The first designated area S1 on the left, the second designated area S2 located on the right side of the landing area B2, the first designated area S3 located above the landing area B2, and the fourth designated area S4 located below the landing area B2.
  • the designated areas are divided in the four directions of the landing area B2, and the situation of the edge vacant area is fully considered, and the detection accuracy is improved.
  • the left side of the oblique danger boundary L is the danger zone
  • the right side of the oblique danger boundary L is the safety zone.
  • the designated area divided according to FIG. 4a is used to judge whether each designated area in the oblique danger boundary L is dangerous
  • the flight control system determines that the first designated area S1 and the second designated area S2 are safe and can land, but the actual A designated area S1 and a second designated area S2 are unsafe, and landing may easily cause a crash. That is, the method of dividing the designated area shown in FIG. 4a cannot accurately judge the danger of the oblique dangerous boundary, and the detection accuracy is not high.
  • the detection area determined by the flight control system does not include the area where the four corners in the point cloud distribution map are located.
  • the flight control system removes the area where the four corners of the detection area overlap according to the extension of the boundary line of the landing area B2, and when the area where the four corners of the detection area are located is removed, the detection area is divided into The four designated areas shown include: the first designated area S1 located on the left side of the landing area B2, the second designated area S2 located on the right side of the landing area B2, the first designated area S3 located above the landing area B2, and the landing area The fourth designated area S4 below the area B2.
  • the left side of the oblique danger boundary L is the danger zone
  • the right side of the oblique danger boundary L is the safety zone.
  • the flight control system determines that the first designated area S1 and the second designated area S2 are safe and can land, but the actual A designated area S1 and a second designated area S2 are safe, that is, the method of dividing the designated area shown in FIG. 5a can improve the detection accuracy of the oblique dangerous boundary.
  • x 1 is the abscissa of the point falling within the first specified area S1
  • y 1 is the ordinate of the point falling within the first specified area S1
  • x 2 is the The abscissa of the points in the second designated area S2
  • y 2 is the ordinate of the points falling in the second designated area S2
  • x 3 is the abscissa of the points falling in the third designated area S3
  • Y 3 is the vertical coordinate of the point falling within the third specified area S3
  • x 4 is the horizontal coordinate of the point falling within the fourth specified area S4
  • y 4 is the falling point of the The vertical coordinate of the point in the fourth designated area S4, length is half the length of the point cloud distribution map, width is half the width of the point cloud distribution map, and l is half the length of the actual landing area, w is half the width of the actual landing area, and d is the hazard tolerance error.
  • the flight control system determines whether the number of point clouds in each of the at least two designated areas is less than a preset threshold, and if so, controls the drone to fly The designated area whose number of point clouds is less than the preset threshold or control the drone to stop landing.
  • the flight control system judges the number of point clouds in each designated area divided, if the number of point clouds in each designated area is less than a preset threshold, it means that each designated area divided It is a dangerous area, that is, the area to be landed cannot be landed. At this time, the flight control system controls the drone to stop landing;
  • the number of point clouds in at least one specified area is not less than the preset threshold, it means that there is at least one safe area in the specified area. At this time, the number of point clouds that the flight control system controls the drone to fly away from is less than the preset threshold The designated area of is closer to the designated area where the number of point clouds is not less than the preset threshold.
  • the preset threshold is determined based on the accuracy of the depth map or point cloud data collected by the depth sensor 40, and its value range is between 15-50, including the two endpoint values of 15 and 50.
  • the local detection is achieved by dividing the designated area in the point cloud distribution map of the area to be landed, and judging the number of point clouds in each designated area, and since the local detection of the designated area is relative to In terms of the overall detection of the landing area, the base point of the point cloud is relatively small, which enables the UAV to more accurately identify each dangerous designated area, improves the accuracy of the detection, and reduces the risk of the UAV crashing.
  • FIG. 6 is a schematic flow chart of a method for autonomous landing of a drone provided by one embodiment of the present invention, which is applied to a drone.
  • the drone is the drone 100 described in the above embodiment, and
  • the method provided by the embodiment of the present invention is executed by the above-mentioned flight control system, and is used to realize the local detection of the drone, improve the detection accuracy, and reduce the risk of drone autonomous landing.
  • the autonomous landing method of the drone includes:
  • the above “area to be landed” refers to an area determined by the existing drone landing protection method that has a flat surface and is suitable for drone landing.
  • the area to be landed does not include water surface, bushes, slopes, etc., including flat ground and platform , Roofs, cliffs, etc.
  • point cloud distribution map is a schematic diagram that can reflect the distribution of point clouds in the area to be landed.
  • acquiring the point cloud distribution map of the area to be landed specifically includes: acquiring the point cloud distribution map of the area to be landed through a depth sensor of the drone.
  • the depth sensor includes but is not limited to: binocular camera, TOF (Time of Flight) camera, structured light camera, lidar.
  • the depth sensor is used to collect depth maps or point cloud data of the area to be landed.
  • the depth map is an image or image channel that contains information about the surface distance of the scene object of the viewpoint.
  • each pixel value represents the actual distance of the depth sensor from the object.
  • each point contains three-dimensional coordinates, some may contain color information or reflection intensity information
  • acquiring the point cloud distribution map of the area to be landed through the depth sensor of the drone specifically includes:
  • acquiring the point cloud distribution map of the area to be landed through the depth sensor of the drone specifically includes:
  • S200 Determine the detection area in the point cloud distribution map according to the actual landing area of the drone in the point cloud distribution map.
  • actual landing area is the area enclosed by the landing gear of the drone when it contacts the ground.
  • the actual landing area coincides with the center point of the area to be landed in the point cloud distribution diagram.
  • detection area refers to an area for detecting the number of point clouds in the point cloud distribution map.
  • the drone Due to the detection error of the drone during the actual detection process, the drone has a danger tolerance error during the actual landing process.
  • the danger tolerance error is the maximum distance that can allow the drone to enter the vacant area, that is, the drone is The distance of the error falls into the vacant area on the edge, and the drone will not crash. Therefore, in an embodiment of the present invention, the detection area is the area corresponding to the point cloud distribution map. The actual landing area is removed and the danger is added. Tolerate the area formed by errors. At this time, the determined detection area is the maximum detection area, which can make the detection result more accurate and avoid missing the detection of the area constituted by the risk tolerance error.
  • the risk tolerance error depends on the size of the UAV 100 and the accuracy of the depth sensor 40, and its value range is between 1 cm-5 cm, including 1 cm and 5 cm.
  • S300 Divide the detection area into at least two designated areas, and each designated area in the at least two designated areas respectively corresponds to a part of the area to be landed.
  • the "at least two designated areas” may be at least two designated areas with equal areas, or may be at least two designated areas with unequal areas.
  • the detection area When the detection area is divided into at least two designated areas, it is divided according to the landing area, which is the area corresponding to the point cloud distribution map after the detection area is removed, and the landing area is not used to detect the number of point clouds.
  • Dividing the detection area into at least two designated areas according to the landing area specifically includes: dividing the detection area into at least two designated areas according to the extension of at least one boundary line of the landing area; or, corresponding to the area to be landed according to at least two corners of the landing area The connecting line of the corner divides the detection area into at least two designated areas.
  • the point cloud distribution map is a rectangular structure, and the at least two designated areas include:
  • the designated areas are divided in the four directions of the landing area, and the situation of the edge vacant area is fully considered, and the detection accuracy is improved.
  • the detection area in order to improve the detection accuracy of the oblique danger boundary, does not include the area where the four corners in the point cloud distribution map are located.
  • the detection area is divided into four designated areas as shown in FIG. 5a Including: a first designated area S1 located on the left side of the landing area, a second designated area S2 located on the right side of the landing area, a first designated area S3 located above the landing area, and a fourth designated area S4 located below the landing area.
  • the first designated area S1, the second designated area S2, the third designated area S3, and the fourth designated area S4 are all rectangular, which makes calculation easier.
  • x 1 is the abscissa of the point falling within the first specified area S1
  • y 1 is the ordinate of the point falling within the first specified area S1
  • x 2 is the The abscissa of the points in the second designated area S2
  • y 2 is the ordinate of the points falling in the second designated area S2
  • x 3 is the abscissa of the points falling in the third designated area S3
  • Y 3 is the vertical coordinate of the point falling within the third specified area S3
  • x 4 is the horizontal coordinate of the point falling within the fourth specified area S4
  • y 4 is the falling point of the The vertical coordinate of the point in the fourth designated area S4, length is half the length of the point cloud distribution map, width is half the width of the point cloud distribution map, and l is half the length of the actual landing area, w is half the width of the actual landing area, and d is the hazard tolerance error.
  • S400 Determine whether the number of point clouds in each of the at least two designated areas is less than a preset threshold
  • the number of point clouds in at least one specified area is not less than the preset threshold, it means that there is at least one safe area in the specified area. At this time, the number of point clouds that the flight control system controls the drone to fly away from is less than the preset threshold The designated area of is closer to the designated area where the number of point clouds is not less than the preset threshold.
  • the preset threshold is determined according to the accuracy of the depth map or point cloud data collected by the depth sensor, and its value range is between 15-50, including the two endpoint values of 15 and 50.
  • the content of the method embodiment may refer to the first embodiment without the content conflicting with each other, and will not be repeated here.
  • the local detection is achieved by dividing the designated area in the point cloud distribution map of the area to be landed, and judging the number of point clouds in each designated area, and since the local detection of the designated area is relative to In terms of the overall detection of the landing area, the base point of the point cloud is relatively small, which enables the UAV to more accurately identify each dangerous designated area, improves the accuracy of the detection, and reduces the risk of the UAV crashing.
  • module is a combination of software and/or hardware that can realize a predetermined function.
  • devices described in the following embodiments may be implemented in software, implementation of hardware or a combination of software and hardware may also be conceived.
  • FIG. 7 is an autonomous drone landing device provided by one embodiment of the present invention.
  • the device is applied to a drone.
  • the drone is the drone 100 described in the above embodiment, and the present
  • the function of each module of the device provided by the embodiment of the invention is performed by the above-mentioned flight control system, which is used to realize the local detection of the drone, improve the detection accuracy, and reduce the risk of the drone's autonomous landing.
  • the drone's autonomous landing device include:
  • An obtaining module 200 which is used to obtain a point cloud distribution map of the area to be landed;
  • the first determining module 300 is used to determine the detection area in the point cloud distribution map according to the actual landing area of the drone in the point cloud distribution map, where the detection area refers to the point cloud distribution map The area used to detect the number of point clouds in
  • a dividing module 400 which is used to divide the detection area into at least two designated areas, each of the at least two designated areas corresponding to a part of the area to be landed;
  • a second determination module 500 which is used to determine whether the number of point clouds in each of the at least two designated areas is less than a preset threshold
  • the control module 600 is used to control the drone to fly away from the designated area where the number of point clouds is less than the preset threshold or control the drone to stop landing if the number of point clouds in the designated area is less than the preset threshold.
  • the acquisition module 200 acquires the point cloud distribution map of the area to be landed through the depth sensor of the drone.
  • the acquisition module 200 may also be a depth sensor, which can directly acquire the point cloud distribution map of the area to be landed.
  • the acquisition module 200 is specifically used to:
  • the acquisition module 200 is specifically used to:
  • the detection area is the area corresponding to the point cloud distribution map excluding the actual landing area and adding the area formed by the hazard tolerance error.
  • the point cloud distribution map has a rectangular structure, and at least two designated areas include:
  • the detection area does not include the area where the four corners in the point cloud distribution map are located.
  • the mathematical expressions of the first designated area S1, the second designated area S2, the third designated area S3, and the fourth designated area S4 are as follows:
  • x 1 is the abscissa of the point falling within the first specified area S1
  • y 1 is the ordinate of the point falling within the first specified area S1
  • x 2 is the point falling within the second specified area S2 Abscissa
  • y 2 is the ordinate of the point falling within the second designated area S2
  • x 3 is the abscissa of the point falling within the third designated area S3
  • y 3 is the point falling within the third designated area S3
  • the vertical coordinate of x 4 is the horizontal coordinate of the point falling within the fourth specified area S4
  • the y 4 is the vertical coordinate of the point falling within the fourth specified area S4
  • length is half the length of the point cloud distribution map
  • width It is half the width of the point cloud distribution map
  • l is half the length of the actual landing area
  • w is half the width of the actual landing area
  • d is the hazard tolerance error.
  • the preset threshold is within a range of 15-50.
  • the above-mentioned acquisition module 200 may be a depth sensor to directly acquire the point cloud distribution map of the area to be landed; the above-mentioned first determination module 300, division module 400, second determination module 500 and control
  • the module 600 may be a flight control chip.
  • the content of the device embodiment may refer to the method embodiment under the premise that the content does not conflict with each other, and details are not repeated here.
  • the local detection is achieved by dividing the designated area in the point cloud distribution map of the area to be landed, and judging the number of point clouds in each designated area, and since the local detection of the designated area is relative to In terms of the overall detection of the landing area, the base point of the point cloud is relatively small, which enables the UAV to more accurately identify each dangerous designated area, improves the accuracy of the detection, and reduces the risk of the UAV crashing.
  • FIG. 8 is a schematic diagram of the hardware structure of a drone according to an embodiment of the present invention.
  • the drone 100 can execute the autonomous drone landing method described in the above embodiment, and can also achieve the above The functions of each module of an autonomous landing device of an unmanned aerial vehicle described in the embodiments.
  • the drone 100 includes:
  • processors 110 and memory 120. Among them, one processor 110 is taken as an example in FIG. 8.
  • the processor 110 and the memory 120 may be connected through a bus or in other ways. In FIG. 8, the connection through a bus is used as an example.
  • the memory 120 is a non-volatile computer-readable storage medium, and can be used to store non-volatile software programs, non-volatile computer executable programs, and modules, such as an autonomous drone in the foregoing embodiments of the present invention
  • a program instruction corresponding to the landing method and a module corresponding to an autonomous landing device of the drone for example, the acquisition module 200, the first determination module 300, the division module 400, the second determination module 500, and the control module 600, etc.
  • the processor 110 executes various functional applications and data processing of an autonomous drone landing method by running non-volatile software programs, instructions, and modules stored in the memory 120, that is, one of the above method embodiments is implemented A drone autonomous landing method and the function of each module of the above device embodiments.
  • the memory 120 may include a storage program area and a storage data area, wherein the storage program area may store an operating system and application programs required by at least one function; the storage data area may store a program created according to the use of an autonomous drone landing device Data etc.
  • the stored data area also stores preset data, including preset thresholds and the like.
  • the memory 120 may include a high-speed random access memory, and may 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 devices.
  • the memory 120 may optionally include memories that are remotely located with respect to the processor 110, and these remote memories may be connected to the processor 110 through a network. Examples of the aforementioned network include, but are not limited to, the Internet, intranet, local area network, mobile communication network, and combinations thereof.
  • the program instructions and one or more modules are stored in the memory 120, and when executed by the one or more processors 110, each of the autonomous landing methods of the drone in any of the above method embodiments is executed Steps, or, to realize the functions of each module of an autonomous drone landing device in any of the above device embodiments.
  • the above products can execute the method provided by the above embodiments of the present invention, and have corresponding function modules and beneficial effects of the execution method.
  • the above products can execute the method provided by the above embodiments of the present invention, and have corresponding function modules and beneficial effects of the execution method.
  • An embodiment of the present invention also provides a non-volatile computer-readable storage medium that stores computer-executable instructions that are executed by one or more processors, for example, FIG. 8
  • a processor 110 in may cause the computer to execute the steps of an autonomous drone landing method in any of the above method embodiments, or implement the various steps of an autonomous drone landing device in any of the above device embodiments The function of the module.
  • An embodiment of the present invention also provides 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.
  • the program instructions are Or multiple processors, for example, a processor 110 in FIG. 8, may cause the computer to execute the steps of an autonomous landing method of an unmanned aerial vehicle in any of the above method embodiments, or implement any of the above device embodiments A function of each module of the UAV autonomous landing device.
  • the device embodiments described above are only schematic, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, may be located in One place, or it can be distributed to multiple network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each embodiment can be implemented by means of software plus a general hardware platform, or of course, by hardware. Persons of ordinary skill in the art may understand that all or part of the processes in the method of the above embodiments may be completed by computer program instructions related hardware.
  • the program may be stored in a computer-readable storage medium, and the program is being executed At this time, it may include the flow of the method for implementing the above methods.
  • the storage medium may be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM) or a random access memory (Random Access Memory, RAM), etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Databases & Information Systems (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

一种无人机（100）自主降落方法、装置及无人机（100）。方法包括：获取待降落区域（A）的点云分布图（S100）；根据无人机（100）在点云分布图中的实际降落区域（B），确定点云分布图中的检测区域（A1+B1），其中，检测区域（A1+B1）是指在点云分布图中用于检测点云数量的区域（S200）；将检测区域（A1+B1）划分为至少两个指定区域，至少两个指定区域中的每一个指定区域分别对应待降落区域（A）的一部分（S300）；确定至少两个指定区域中的每一个指定区域中的点云数量是否小于预设阈值（S400）；若是，则控制无人机（100）飞离点云数量小于预设阈值的指定区域或者控制无人机（100）停止降落（S500）。方法能够实现无人机（100）的局部检测，提高检测的准确度，减少无人机（100）坠毁风险。

Description

一种无人机自主降落方法、装置及无人机 技术领域
本发明实施例涉及无人机控制技术领域，特别是涉及一种无人机自主降落方法、装置及无人机。
背景技术
无人机是一种由无线电遥控设备或自身程序控制装置操纵的无人驾驶飞行器。随着无人机相关技术的发展及其应用场景的复杂变化，无人机在飞行过程中出现的安全问题越来越多，于是，在无人机中配备自主降落保护技术，以防止无人机在未知环境中降落时出现坠毁的情况。
但发明人在实现本发明的过程中发现：目前，无人机中配备的自主降落保护技术只针对待降落区域的整体情况进行分析，只能检测出待降落区域整体的平整性，无法检测出楼顶、悬崖、深沟等平整但存在明显边缘空缺的危险区域，检测不够全面，使得无人机降落仍然存在坠毁风险。
发明内容
本发明实施例旨在提供一种无人机自主降落方法、装置及无人机，能够实现无人机的局部检测，提高检测的准确度，减少无人机坠毁风险。
为解决上述技术问题，本发明实施例采用的一个技术方案是：提供一种无人机自主降落方法，所述方法包括：
获取待降落区域的点云分布图；
根据所述无人机在所述点云分布图中的实际降落区域，确定所述点云分布图中的检测区域，其中，所述检测区域是指在所述点云分布图中用于检测点云数量的区域；
将所述检测区域划分为至少两个指定区域，所述至少两个指定区域中的每一个指定区域分别对应所述待降落区域的一部分；
确定所述至少两个指定区域中的每一个指定区域中的点云数量是 否小于预设阈值；
若是，则控制所述无人机飞离点云数量小于所述预设阈值的指定区域或者控制所述无人机停止降落。
可选地，所述获取所述待降落区域的所述点云分布图，包括：
通过所述无人机的深度传感器获取所述待降落区域的所述点云分布图。
可选地，所述通过所述无人机的深度传感器获取所述待降落区域的所述点云分布图，包括：
通过所述深度传感器获取所述待降落区域的深度图；
根据所述深度图，获取所述点云分布图。
可选地，所述通过所述无人机的深度传感器获取所述待降落区域的所述点云分布图，包括：
通过所述深度传感器获取所述待降落区域的点云数据；
将所述点云数据投影至二维平面，以获取所述点云分布图。
可选地，所述检测区域为所述点云分布图所对应的区域中除去所述实际降落区域并加上由危险容忍误差所构成的区域。
可选地，所述点云分布图为矩形结构，所述至少两个指定区域包括：
位于降落区域左侧的第一指定区域、位于降落区域右侧的第二指定区域、位于降落区域上方的第三指定区域以及位于降落区域下方的第四指定区域。
可选地，所述检测区域不包括所述点云分布图中四个角所在的区域。
可选地，所述第一指定区域S1、第二指定区域S2、第三指定区域S3和第四指定区域S4的数学表达式分别如下：
S1:-length<x 1<-(l-d)，y 1<|w-d|；
S2:(l-d)<x 2<length，y 2<|w-d|；
S3:x 3<|l-d|，(w-d)<y 3<width；
S4:x 4<|l-d|，-width<y 4<-(w-d)；
其中，x 1为落在所述第一指定区域S1内的点的横坐标，y 1为所述落在所述第一指定区域S1内的点的纵坐标，x 2为落在所述第二指定区域S2内的点的横坐标，y 2为所述落在所述第二指定区域S2内的点的纵坐标，x 3为落在所述第三指定区域S3内的点的横坐标，y 3为所述落在所述第三指定区域S3内的点的纵坐标，x 4为落在所述第四指定区域S4内的点的横坐标，y 4为所述落在所述第四指定区域S4内的点的纵坐标，length为所述点云分布图的长度的一半，width为所述点云分布图的宽度的一半，l为所述实际降落区域的长度的一半，w为所述实际降落区域的宽度的一半，d为危险容忍误差。
可选地，所述预设阈值在15-50范围内取值。
为解决上述技术问题，本发明实施例采用的另一个技术方案是：提供一种无人机自主降落装置，所述装置包括：
获取模块，所述获取模块用于获取待降落区域的点云分布图；
第一确定模块，所述第一确定模块用于根据所述无人机在所述点云分布图中的实际降落区域，确定所述点云分布图中的检测区域，其中，所述检测区域是指在所述点云分布图中用于检测点云数量的区域；
划分模块，所述划分模块用于将所述检测区域划分为至少两个指定区域，所述至少两个指定区域中的每一个指定区域分别对应所述待降落区域的一部分；
第二确定模块，所述第二确定模块用于确定所述至少两个指定区域中的每一个指定区域中的点云数量是否小于预设阈值；
控制模块，所述控制模块用于若每一个指定区域中的点云数量小于预设阈值，则控制所述无人机飞离点云数量小于所述预设阈值的指定区域或者控制所述无人机停止降落。
可选地，所述获取模块通过所述无人机的深度传感器获取所述待降落区域的所述点云分布图。
可选地，所述获取模块具体用于：
通过所述深度传感器获取所述待降落区域的深度图；
根据所述深度图，获取所述点云分布图。
可选地，所述获取模块具体用于：
通过所述深度传感器获取所述待降落区域的点云数据；
将所述点云数据投影至二维平面，以获取所述点云分布图。
可选地，所述检测区域为所述点云分布图所对应的区域中除去所述实际降落区域并加上由危险容忍误差所构成的区域。
可选地，所述点云分布图为矩形结构，所述至少两个指定区域包括：
位于降落区域左侧的第一指定区域、位于降落区域右侧的第二指定区域、位于降落区域上方的第三指定区域以及位于降落区域下方的第四指定区域。
可选地，所述检测区域不包括所述点云分布图中四个角所在的区域。
可选地，所述第一指定区域S1、第二指定区域S2、第三指定区域S3和第四指定区域S4的数学表达式分别如下：
S1:-length<x 1<-(l-d)，y 1<|w-d|；
S2:(l-d)<x 2<length，y 2<|w-d|；
S3:x 3<|l-d|，(w-d)<y 3<width；
S4:x 4<|l-d|，-width<y 4<-(w-d)；
其中，x 1为落在所述第一指定区域S1内的点的横坐标，y 1为所述落在所述第一指定区域S1内的点的纵坐标，x 2为落在所述第二指定区域S2内的点的横坐标，y 2为所述落在所述第二指定区域S2内的点的纵坐标，x 3为落在所述第三指定区域S3内的点的横坐标，y 3为所述落在所述第三指定区域S3内的点的纵坐标，x 4为落在所述第四指定区域S4内的点的横坐标，y 4为所述落在所述第四指定区域S4内的点的纵坐标，length为所述点云分布图的长度的一半，width为所述点云分布图的宽度的一半，l为所述实际降落区域的长度的一半，w为所述实际降落区域的宽度的一半，d为危险容忍误差。
可选地，所述预设阈值在15-50范围内取值。
为解决上述技术问题，本发明实施例采用的另一个技术方案是：提供一种无人机，包括：
至少一个处理器；以及
与所述至少一个处理器通信连接的存储器；其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够用于执行以上所述的无人机自主降落方法。
为解决上述技术问题，本发明实施例采用的另一个技术方案是：提供一种非易失性计算机可读存储介质，所述非易失性计算机可读存储介质存储有计算机可执行指令，所述计算机可执行指令用于使无人机执行以上所述的无人机自主降落方法。
本发明实施例的有益效果是：区别于现有技术的情况下，本发明实施例提供一种无人机自主降落方法、装置及无人机，所述无人机自主降落方法通过在待降落区域的点云分布图中划分指定区域，并对每个指定区域中的点云数量进行判断来实现局部检测，并且由于对指定区域的局部检测相对于对待降落区域的整体检测而言，点云数量基数较小，使得无人机能够更为精准地确定出每一个危险的指定区域，提高了检测的准确度，减少了无人机坠毁的风险。
附图说明
一个或多个实施例通过与之对应的附图中的图片进行示例性说明，这些示例性说明并不构成对实施例的限定，附图中具有相同参考数字标号的元件表示为类似的元件，除非有特别申明，附图中的图不构成比例限制。
图1是本发明一实施例提供的一种无人机的结构示意图；
图2是本发明一实施例提供的各区域的关系图；
图3a是本发明一实施例提供的指定区域的划分示意图；
图3b是本发明一实施例提供的指定区域的划分示意图；
图4a是本发明一实施例提供的指定区域的划分示意图；
图4b是图4a所示的指定区域在斜向危险边界L中的示意图；
图5a是本发明一实施例提供的指定区域的划分示意图；
图5b是图5a所示的指定区域在斜向危险边界L中的示意图；
图6是本发明一实施例提供的一种无人机自主降落方法的流程示意图；
图7是本发明一实施例提供的一种无人机自主降落装置的结构示意图；
图8是本发明一实施例提供的一种无人机的硬件结构示意图。
具体实施方式
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整的描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。应当理解，此处所描述的具体实施例仅用以解释本发明，并不用于限定本发明。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
需要说明的是，当元件被表述“固定于”另一个元件，它可以直接在另一个元件上、或者其间可以存在一个或多个居中的元件。当一个元件被表述“连接”另一个元件，它可以是直接连接到另一个元件、或者其间可以存在一个或多个居中的元件。本说明书所使用的术语“垂直的”、“水平的”、“左”、“右”以及类似的表述只是为了说明的目的。
此外，下面所描述的本发明各个实施例中所涉及到的技术特征只要彼此之间未构成冲突就可以相互组合。
本发明提供了一种无人机自主降落方法及装置，该方法及装置应用于无人机，从而使得该无人机能够在准备降落时判断待降落区域中是否存在局部危险区域，若存在局部危险区域，则控制无人机飞离局部危险 区域或者控制无人机停止降落，以避免无人机降落在局部危险区域坠毁。其中，在本发明实施例中，局部危险区域为楼顶、悬崖、深沟等表面平整区域的边缘空缺区域。
本发明中的无人机可以是任何合适类型的高空无人机或者低空无人机，包括固定翼无人机、旋翼无人机、伞翼无人机或者扑翼无人机等。
下面，将通过具体实施例对本发明进行阐述。
实施例一
请参阅图1，是本发明其中一实施例提供的一种无人机100，包括壳体10、机臂20、动力装置30、深度传感器40、起落架50以及飞控系统(图未示)。机臂20、深度传感器40以及起落架50均与壳体10连接，飞控系统则设置于壳体10内，动力装置30则设置于机臂20上。其中，动力装置30、深度传感器40以及起落架50均与飞控系统通信连接，使得飞控系统能够通过动力装置30来控制无人机100的飞行、能够通过深度传感器40获得无人机100待降落区域的点云分布图、还能够控制起落架50与地面接触。
优选地，机臂20数量为4，均匀分布于壳体10四周，用于承载动力装置30。
动力装置30包括电机以及与电机轴连接的螺旋桨，电机能够带动螺旋桨旋转以为无人机100提供升力，实现飞行；电机还能够通过改变螺旋桨的转速及方向来改变无人机100的飞行方向。当动力装置30与飞控系统通信连接时，飞控系统能够通过控制电机来控制无人机100的飞行。
该动力装置30设置于机臂20未与壳体10连接的一端，并通过电机连接机臂20。
优选地，在无人机100的4个机臂上均设置有动力装置，以使无人机100能够平稳飞行。
深度传感器40设置于壳体10底部，用于采集无人机100待降落区域的深度图(Depth Map)，该深度图是包含与视点的场景对象的表面距 离有关的信息的图像或图像通道，在深度图中，其每个像素值表示深度传感器距离物体的实际距离。故深度传感器40采集深度图也即采集深度传感器40与待降落区域物体的实际距离。当深度传感器40与飞控系统通信连接时，飞控系统能够从深度传感器40获取无人机100待降落区域的深度图，并根据深度图获取待降落区域的点云分布图。
当然，在其他一些实施例中，深度传感器40用于采集无人机100待降落区域的点云数据，点云数据中，每一个点包含有三维坐标，有些可能含有颜色信息或反射强度信息。此时，当深度传感器40与飞控系统通信连接时，飞控系统能够从深度传感器40获取无人机100待降落区域的点云数据，并将点云数据投影至二维平面，以获取待降落区域的点云分布图。
进一步地，深度传感器40通过云台设置于壳体10底部，以使深度传感器40能够全方位采集待降落区域的深度图或者点云数据。
该深度传感器40包括但不限于：双目相机、TOF(Time of Flight，飞行时间)相机、结构光相机、激光雷达等。
起落架50设置于壳体10底部相对两侧，通过驱动装置连接于壳体10，起落架50在驱动装置的驱动下能够进行打开与收起。在无人机100与地面接触时，驱动装置控制起落架50打开，以使无人机100通过起落架50与地面接触；在无人机100飞行过程中，驱动装置控制起落架50收起，以避免起落架50影响无人机100飞行。当起落架50与飞控系统通信连接时，飞控系统能够通过控制驱动装置来控制起落架50与地面接触。
可以理解的是，无人机100降落于地面时，只通过起落架50与地面接触，此时，无人机100的实际降落区域即起落架50与地面接触时所围成的区域。
当无人机100通过起落架50与地面接触时，无人机100机体在地面的投影围成投影区域，该投影区域的中心点与实际降落区域的中心点重合，并且投影区域大于实际降落区域。该投影区域包括螺旋桨的活动范围，表征无人机100能够正常活动的最小区域。
飞控系统与动力装置30、深度传感器40以及起落架50通过有线连接或者无线连接的方式进行通信连接。其中，无线连接包括但不限于：WiFi、蓝牙、ZigBee等。
该飞控系统用于执行本发明所述的无人机自主降落方法，以使得无人机100能够实现局部检测，提高检测的准确度，减少无人机坠毁风险。
具体地，在无人机100准备降落时，飞控系统通过深度传感器40获取待降落区域的点云分布图。
其中，待降落区域为根据现有的无人机降落保护方法确定的表面平整并适合无人机降落的区域，包括：地面、屋顶、平台、悬崖等区域。在表面平整并适合无人机降落的区域中，可能存在如悬崖、屋顶等边缘空缺的区域，若不对边缘空缺的区域进行局部危险性判断，则无人机100降落至该边缘空缺的区域中时，容易因降落到边缘而出现坠毁。故本发明基于表面平整并适合无人机100降落的待降落区域进行危险性检测。
点云分布图为能够反映待降落区域的点云分布情况的示意图。
飞控系统获取以无人机的中心为中心的待降落区域的点云分布图。
在本发明的一实施例中，飞控系统通过深度传感器40获取待降落区域的点云分布图具体包括：飞控系统通过深度传感器40获取待降落区域的深度图，并根据所获取的深度图获取点云分布图。
在本发明的另一实施例中，飞控系统通过深度传感器40获取待降落区域的点云分布图具体包括：飞控系统通过深度传感器40获取待降落区域的点云数据，并将所获取的点云数据投影至二维平面，以获取点云分布图。
进一步地，在获取了待降落区域的点云分布图后，飞控系统根据无人机100在点云分布图中的实际降落区域确定点云分布图中的检测区域。
由于待降落区域为确定的表面平整并且适合无人机100降落的区域，此时，不需要考虑螺旋桨转动碰撞障碍物的问题，只需要考虑无人机100是否会降落至边缘的空缺区域的问题，而是否会降落至边缘的空缺区域与无人机起落架50的落地位置有关，即与无人机100的实际降 落区域有关，故在本发明中，飞控系统根据无人机100在点云分布图中的实际降落区域来确定点云分布图中的检测区域。
其中，检测区域是指在点云分布图中用于检测点云数量的区域。
在本发明的一实施例中，由于无人机100在实际检测过程存在检测误差，使得无人机100在实际降落过程中存在危险容忍误差，该危险容忍误差为能够允许无人机100进入空缺区域的最大距离，即无人机100以危险容忍误差的距离落入边缘的空缺区域，无人机100也不会发生坠毁，故在确定检测区域时，需要将由危险容忍误差所构成的区域一同考虑。具体地，检测区域为点云分布图所对应的区域中除去实际降落区域并加上由危险容忍误差所构成的区域，此时，所确定的检测区域为最大检测区域，能够使得检测结果更为准确，避免遗漏对危险容忍误差所构成的区域的检测。其中，危险容忍误差取决于无人机100的大小和深度传感器40的精度，其取值范围在1cm-5cm之间，包括1cm和5cm。
请参阅图2，点云分布图所对应的区域即待降落区域，该待降落区域为A，实际降落区域为B，当点云分布图所对应的区域A除去实际降落区域B时，得到区域A1；由危险容忍误差d所构成的区域为B1，当点云分布图所对应的区域A除去实际降落区域B并加上由危险容忍误差所构成的区域B1时，得到的检测区域为A1+B1。
请继续参阅图2，实际降落区域B除去由危险容忍误差d所构成的区域B1后，得到降落区域B2，该降落区域B2还可以为点云分布图所对应的区域A除去检测区域A1+B1后的区域，该降落区域B2不用于检测点云数量。
进一步地，在确定了点云分布图中的检测区域后，飞控系统将检测区域划分为至少两个指定区域，该至少两个指定区域中的每一个指定区域分别对应待降落区域的一部分。
其中，飞控系统将检测区域划分为至少两个指定区域时，可以将检测区域划分为面积相等的至少两个指定区域，也可以将检测区域划分为面积不相等的至少两个指定区域。
飞控系统在划分检测区域时，可以依照降落区域B2进行划分，比 如：可根据降落区域B2至少一边边界线的延长线划分检测区域；还可根据降落区域B2至少两角与待降落区域A对应角的连线划分检测区域。
请参阅图3a，飞控系统根据降落区域B2一边边界线的延长线将检测区域A1+B1划分为面积不相等的指定区域C1和指定区域C2。
请参阅图3b，飞控系统根据降落区域B2相对的两角与待降落区域A对应角的连线将检测区域A1+B1划分为面积相等的指定区域C1和指定区域C2。
以上所述仅为本发明其中两个实施例，上述方法任意组合得到的方案均为本发明所能实现的方案。
在本发明的一实施例中，点云分布图为矩形结构，并且飞控系统将检测区域划分为4个指定区域，如图4a所示，所划分的4个指定区域包括：位于降落区域B2左侧的第一指定区域S1、位于降落区域B2右侧的第二指定区域S2、位于降落区域B2上方的第一指定区域S3以及位于降落区域B2下方的第四指定区域S4。在降落区域B2的四个方位分别划分指定区域，全面考虑了边缘空缺区域可能出现的情况，提高了检测的准确度。
其中，上述“左侧”、“右侧”、“上方”和“下方”均为图示方向。
如图4b所示，斜向危险边界L以左为危险区，斜向危险边界L以右为安全区，当按照图4a划分的指定区域来判断在斜向危险边界L中各指定区域是否危险时，第一指定区域S1和第二指定区域S2中的点云数量(图示黑色区域)大于阈值，飞控系统判断第一指定区域S1和第二指定区域S2安全，可以降落，而实际第一指定区域S1和第二指定区域S2不安全，降落容易造成坠毁，即图4a所示的划分指定区域的方法不能准确地对斜向危险边界的危险性进行判断，检测准确度不高。
在本发明的另一实施例中，为了提高斜向危险边界的检测准确度，飞控系统确定的检测区域不包括点云分布图中四个角所在的区域。
具体地，请参阅图5a，飞控系统根据降落区域B2边界线的延长线将检测区域四个角重叠的区域去除，并且当检测区域四个角所在的区域去除后，检测区域分割成如图所示的4个指定区域，包括：位于降落区 域B2左侧的第一指定区域S1、位于降落区域B2右侧的第二指定区域S2、位于降落区域B2上方的第一指定区域S3以及位于降落区域B2下方的第四指定区域S4。
如图5b所示，斜向危险边界L以左为危险区，斜向危险边界L以右为安全区，当按照图5a划分的指定区域来判断在斜向危险边界L中各指定区域是否危险时，第一指定区域S1和第二指定区域S2中的点云数量(图示黑色区域)小于阈值，飞控系统判断第一指定区域S1和第二指定区域S2安全，可以降落，而实际第一指定区域S1和第二指定区域S2安全，即图5a所示的划分指定区域的方法能够提高斜向危险边界的检测准确度。
并且，通过去除检测区域在点云分布图中四个角所在的区域，能够避免由于畸变等原因造成的数据不稳定，提高检测稳定性。
在本发明的一实施例中，当坐标系原点位于待降落区域中心时，图5a所示的第一指定区域S1、第二指定区域S2、第三指定区域S3和第四指定区域S4的数学表达式分别如下：
S1:-length<x 1<-(l-d)，y 1<|w-d|；
S2:(l-d)<x 2<length，y 2<|w-d|；
S3:x 3<|l-d|，(w-d)<y 3<width；
S4:x 4<|l-d|，-width<y 4<-(w-d)；
其中，x 1为落在所述第一指定区域S1内的点的横坐标，y 1为所述落在所述第一指定区域S1内的点的纵坐标，x 2为落在所述第二指定区域S2内的点的横坐标，y 2为所述落在所述第二指定区域S2内的点的纵坐标，x 3为落在所述第三指定区域S3内的点的横坐标，y 3为所述落在所述第三指定区域S3内的点的纵坐标，x 4为落在所述第四指定区域S4内的点的横坐标，y 4为所述落在所述第四指定区域S4内的点的纵坐标，length为所述点云分布图的长度的一半，width为所述点云分布图的宽度的一半，l为所述实际降落区域的长度的一半，w为所述实际降落区 域的宽度的一半，d为危险容忍误差。
进一步地，在将检测区域划分为至少两个指定区域后，飞控系统确定至少两个指定区域中的每一个指定区域中的点云数量是否小于预设阈值，若是，则控制无人机飞离点云数量小于预设阈值的指定区域或者控制无人机停止降落。
具体地，飞控系统对所划分出的每个指定区域中的点云数量进行判断，若每个指定区域中的点云数量均小于预设阈值，则表示所划分出的每个指定区域均为危险区域，即该待降落区域不能降落，此时，飞控系统控制无人机停止降落；
若至少一个指定区域中的点云数量不小于预设阈值，则表示所划分出的指定区域中存在至少一个安全区域，此时，飞控系统控制无人机飞离点云数量小于预设阈值的指定区域，向点云数量不小于预设阈值的指定区域靠近。
其中，预设阈值根据深度传感器40采集深度图或者点云数据的精度确定，其取值范围在15-50之间，包括15和50两个端点数值。
在本发明实施例中，通过在待降落区域的点云分布图中划分指定区域，并对每个指定区域中的点云数量进行判断来实现局部检测，并且由于对指定区域的局部检测相对于对待降落区域的整体检测而言，点云数量基数较小，使得无人机能够更为精准地确定出每一个危险的指定区域，提高了检测的准确度，减少了无人机坠毁的风险。
实施例二
请参阅图6，是本发明其中一实施例提供的一种无人机自主降落方法的流程示意图，应用于无人机，该无人机为上述实施例中所述的无人机100，而本发明实施例提供的方法由上述飞控系统执行，用于实现无人机的局部检测，提高检测的准确度，减少无人机自主降落坠毁的风险，该无人机自主降落方法包括：
S100：获取待降落区域的点云分布图。
上述“待降落区域”为根据现有的无人机降落保护方法确定的表面 平整并适合无人机降落的区域，该待降落区域不包括水面、灌木丛、坡面等，包括平整地面、平台、屋顶、悬崖等。
上述“点云分布图”为能够反映待降落区域的点云分布情况的示意图。
获取待降落区域的点云分布图时，优选获取以无人机的中心为中心的点云分布图。
在本发明的一实施例中，获取待降落区域的点云分布图具体包括：通过所述无人机的深度传感器获取所述待降落区域的所述点云分布图。
其中，深度传感器包括但不限于：双目相机、TOF(Time of Flight，飞行时间)相机、结构光相机、激光雷达。
深度传感器用于采集待降落区域的深度图或者点云数据。
深度图是包含与视点的场景对象的表面距离有关的信息的图像或图像通道，在深度图中，其每个像素值表示深度传感器距离物体的实际距离。
点云数据中，每一个点包含有三维坐标，有些可能含有颜色信息或反射强度信息
当深度传感器采集待降落区域的深度图时，通过所述无人机的深度传感器获取所述待降落区域的所述点云分布图具体包括：
通过所述深度传感器获取所述待降落区域的深度图；
根据所述深度图，获取所述点云分布图。
当深度传感器采集待降落区域的点云数据时，通过所述无人机的深度传感器获取所述待降落区域的所述点云分布图具体包括：
通过所述深度传感器获取所述待降落区域的点云数据；
将所述点云数据投影至二维平面，以获取所述点云分布图。
S200：根据所述无人机在所述点云分布图中的实际降落区域，确定所述点云分布图中的检测区域。
上述“实际降落区域”为无人机起落架与地面接触时所围成的区域，该实际降落区域在点云分布图中与待降落区域中心点重合。
上述“检测区域”是指在点云分布图中用于检测点云数量的区域。
由于无人机在实际检测过程存在检测误差，使得无人机在实际降落过程中存在危险容忍误差，该危险容忍误差为能够允许无人机进入空缺区域的最大距离，即无人机以危险容忍误差的距离落入边缘的空缺区域，无人机也不会发生坠毁，故在本发明的一实施例中，检测区域为点云分布图所对应的区域中除去实际降落区域并加上由危险容忍误差所构成的区域。此时，所确定的检测区域为最大检测区域，能够使得检测结果更为准确，避免遗漏对危险容忍误差所构成的区域的检测。
其中，危险容忍误差取决于无人机100的大小和深度传感器40的精度，其取值范围在1cm-5cm之间，包括1cm和5cm。
S300：将所述检测区域划分为至少两个指定区域，所述至少两个指定区域中的每一个指定区域分别对应所述待降落区域的一部分。
上述“至少两个指定区域”可以为面积相等的至少两个指定区域，也可以为面积不相等的至少两个指定区域。
在将检测区域划分为至少两个指定区域时，根据降落区域进行划分，该降落区域为点云分布图所对应的区域除去检测区域后的区域，该降落区域不用于检测点云数量。
根据降落区域将检测区域划分为至少两个指定区域具体包括：根据降落区域至少一边边界线的延长线将检测区域划分为至少两个指定区域；或者，根据降落区域至少两角与待降落区域对应角的连接线将检测区域划分为至少两个指定区域。
在本发明的一实施例中，所述点云分布图为矩形结构，所述至少两个指定区域包括：
位于降落区域左侧的第一指定区域、位于降落区域右侧的第二指定区域、位于降落区域上方的第三指定区域以及位于降落区域下方的第四指定区域。
上述“左侧”、“右侧”、“上方”以及“下方”均为图4a所示的方位。
在降落区域的四个方位分别划分指定区域，全面考虑了边缘空缺区域可能出现的情况，提高了检测的准确度。
在本发明的另一实施例中，为了提高斜向危险边界的检测准确度，所述检测区域不包括所述点云分布图中四个角所在的区域。
具体地，根据降落区域边界线的延长线将检测区域在四个角重叠的区域去除，并且当检测区域四个角所在的区域去除后，检测区域分割成如图5a所示的4个指定区域，包括：位于降落区域左侧的第一指定区域S1、位于降落区域右侧的第二指定区域S2、位于降落区域上方的第一指定区域S3以及位于降落区域下方的第四指定区域S4。
此时，第一指定区域S1、第二指定区域S2、第三指定区域S3以及第四指定区域S4均为矩形，计算更为简便。
通过去除检测区域在点云分布图中四个角所在的区域，能够避免由于畸变等原因造成的数据不稳定，提高检测稳定性。
基于此，当坐标系原点位于待降落区域中心时，如图5a所示的第一指定区域S1、第二指定区域S2、第三指定区域S3和第四指定区域S4的数学表达式分别如下：
S1:-length<x 1<-(l-d)，y 1<|w-d|；
S2:(l-d)<x 2<length，y 2<|w-d|；
S3:x 3<|l-d|，(w-d)<y 3<width；
S4:x 4<|l-d|，-width<y 4<-(w-d)；
其中，x 1为落在所述第一指定区域S1内的点的横坐标，y 1为所述落在所述第一指定区域S1内的点的纵坐标，x 2为落在所述第二指定区域S2内的点的横坐标，y 2为所述落在所述第二指定区域S2内的点的纵坐标，x 3为落在所述第三指定区域S3内的点的横坐标，y 3为所述落在所述第三指定区域S3内的点的纵坐标，x 4为落在所述第四指定区域S4内的点的横坐标，y 4为所述落在所述第四指定区域S4内的点的纵坐标，length为所述点云分布图的长度的一半，width为所述点云分布图的宽度的一半，l为所述实际降落区域的长度的一半，w为所述实际降落区域的宽度的一半，d为危险容忍误差。
S400：确定所述至少两个指定区域中的每一个指定区域中的点云数量是否小于预设阈值；
S500：若是，则控制所述无人机飞离点云数量小于所述预设阈值的指定区域或者控制所述无人机停止降落。
对所划分出的每个指定区域中的点云数量进行判断，若每个指定区域中的点云数量均小于预设阈值，则表示所划分出的每个指定区域均为危险区域，即该待降落区域不能降落，此时，飞控系统控制无人机停止降落；
若至少一个指定区域中的点云数量不小于预设阈值，则表示所划分出的指定区域中存在至少一个安全区域，此时，飞控系统控制无人机飞离点云数量小于预设阈值的指定区域，向点云数量不小于预设阈值的指定区域靠近。
其中，预设阈值根据深度传感器采集深度图或者点云数据的精度确定，其取值范围在15-50之间，包括15和50两个端点数值。
由于方法实施例和实施例一是基于同一构思，在内容不互相冲突的前提下，方法实施例的内容可以引用实施例一的，在此不再一一赘述。
在本发明实施例中，通过在待降落区域的点云分布图中划分指定区域，并对每个指定区域中的点云数量进行判断来实现局部检测，并且由于对指定区域的局部检测相对于对待降落区域的整体检测而言，点云数量基数较小，使得无人机能够更为精准地确定出每一个危险的指定区域，提高了检测的准确度，减少了无人机坠毁的风险。
实施例三
以下所使用的术语“模块”为可以实现预定功能的软件和/或硬件的组合。尽管以下实施例所描述的装置可以以软件来实现，但是硬件，或者软件和硬件的组合的实现也是可能被构想的。
请参阅图7，是本发明其中一实施例提供的一种无人机自主降落装置，该装置应用于无人机，该无人机为上述实施例中所述的无人机100，而本发明实施例提供的装置各个模块的功能由上述飞控系统执行，用于 实现无人机的局部检测，提高检测的准确度，减少无人机自主降落坠毁的风险，该无人机自主降落装置包括：
获取模块200，该获取模块200用于获取待降落区域的点云分布图；
第一确定模块300，该第一确定模块300用于根据无人机在点云分布图中的实际降落区域，确定点云分布图中的检测区域，其中，检测区域是指在点云分布图中用于检测点云数量的区域；
划分模块400，该划分模块400用于将检测区域划分为至少两个指定区域，至少两个指定区域中的每一个指定区域分别对应待降落区域的一部分；
第二确定模块500，该第二确定模块500用于确定至少两个指定区域中的每一个指定区域中的点云数量是否小于预设阈值；
控制模块600，该控制模块600用于若指定区域中的点云数量小于预设阈值，则控制无人机飞离点云数量小于预设阈值的指定区域或者控制无人机停止降落。
在本发明的一实施例中，获取模块200通过无人机的深度传感器获取待降落区域的点云分布图。当然，在其他一些可替代实施例中，该获取模块200也可以为深度传感器，能够直接获取待降落区域的点云分布图。
在本发明的一实施例中，该获取模块200具体用于：
通过深度传感器获取待降落区域的深度图；
根据深度图，获取点云分布图。
在本发明的另一实施例中，该获取模块200具体用于：
通过深度传感器获取待降落区域的点云数据；
将点云数据投影至二维平面，以获取点云分布图。
在本发明的一实施例中，检测区域为点云分布图所对应的区域中除去实际降落区域并加上由危险容忍误差所构成的区域。
在本发明的一实施例中，点云分布图为矩形结构，至少两个指定区域包括：
位于降落区域左侧的第一指定区域、位于降落区域右侧的第二指定 区域、位于降落区域上方的第三指定区域以及位于降落区域下方的第四指定区域。
在本发明的一实施例中，检测区域不包括点云分布图中四个角所在的区域。
在本发明的一实施例中，第一指定区域S1、第二指定区域S2、第三指定区域S3和第四指定区域S4的数学表达式分别如下：
S1:-length<x 1<-(l-d)，y 1<|w-d|；
S2:(l-d)<x 2<length，y 2<|w-d|；
S3:x 3<|l-d|，(w-d)<y 3<width；
S4:x 4<|l-d|，-width<y 4<-(w-d)；
其中，x 1为落在第一指定区域S1内的点的横坐标，y 1为落在第一指定区域S1内的点的纵坐标，x 2为落在第二指定区域S2内的点的横坐标，y 2为落在第二指定区域S2内的点的纵坐标，x 3为落在第三指定区域S3内的点的横坐标，y 3为落在第三指定区域S3内的点的纵坐标，x 4为落在第四指定区域S4内的点的横坐标，y 4为落在第四指定区域S4内的点的纵坐标，length为点云分布图的长度的一半，width为点云分布图的宽度的一半，l为实际降落区域的长度的一半，w为实际降落区域的宽度的一半，d为危险容忍误差。
在本发明的一实施例中，预设阈值在15-50范围内取值。
当然，在其他一些可替代实施例中，上述获取模块200可以为深度传感器，以直接获取待降落区域的点云分布图；上述第一确定模块300、划分模块400、第二确定模块500和控制模块600可以为飞控芯片。
由于装置实施例和方法实施例是基于同一构思，在内容不互相冲突的前提下，装置实施例的内容可以引用方法实施例的，在此不再一一赘述。
在本发明实施例中，通过在待降落区域的点云分布图中划分指定区域，并对每个指定区域中的点云数量进行判断来实现局部检测，并且由 于对指定区域的局部检测相对于对待降落区域的整体检测而言，点云数量基数较小，使得无人机能够更为精准地确定出每一个危险的指定区域，提高了检测的准确度，减少了无人机坠毁的风险。
实施例四
请参阅图8，是本发明其中一实施例提供的一种无人机的硬件结构示意图，该无人机100能够执行以上实施例所述的一种无人机自主降落方法，还能实现以上实施例所述的一种无人机自主降落装置的各个模块的功能。该无人机100包括：
一个或多个处理器110以及存储器120。其中，图8中以一个处理器110为例。
处理器110和存储器120可以通过总线或者其他方式连接，图8中以通过总线连接为例。
存储器120作为一种非易失性计算机可读存储介质，可用于存储非易失性软件程序、非易失性计算机可执行程序以及模块，如本发明上述实施例中的一种无人机自主降落方法对应的程序指令以及一种无人机自主降落装置对应的模块(例如，获取模块200、第一确定模块300、划分模块400、第二确定模块500和控制模块600等)。处理器110通过运行存储在存储器120中的非易失性软件程序、指令以及模块，从而执行一种无人机自主降落方法的各种功能应用以及数据处理，即实现上述方法实施例中的一种无人机自主降落方法以及上述装置实施例的各个模块的功能。
存储器120可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储根据一种无人机自主降落装置的使用所创建的数据等。
所述存储数据区还存储有预设的数据，包括预设阈值等。
此外，存储器120可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实施例中，存储器120可选包括相对于处理器110 远程设置的存储器，这些远程存储器可以通过网络连接至处理器110。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
所述程序指令以及一个或多个模块存储在所述存储器120中，当被所述一个或者多个处理器110执行时，执行上述任意方法实施例中的一种无人机自主降落方法的各个步骤，或者，实现上述任意装置实施例中的一种无人机自主降落装置的各个模块的功能。
上述产品可执行本发明上述实施例所提供的方法，具备执行方法相应的功能模块和有益效果。未在本实施例中详尽描述的技术细节，可参见本发明上述实施例所提供的方法。
本发明实施例还提供了一种非易失性计算机可读存储介质，所述计算机可读存储介质存储有计算机可执行指令，该计算机可执行指令被一个或多个处理器执行，例如图8中的一个处理器110，可使得计算机执行上述任意方法实施例中的一种无人机自主降落方法的各个步骤，或者，实现上述任意装置实施例中的一种无人机自主降落装置的各个模块的功能。
本发明实施例还提供了一种计算机程序产品，所述计算机程序产品包括存储在非易失性计算机可读存储介质上的计算机程序，所述计算机程序包括程序指令，当所述程序指令被一个或多个处理器执行，例如图8中的一个处理器110，可使得计算机执行上述任意方法实施例中的一种无人机自主降落方法的各个步骤，或者，实现上述任意装置实施例中的一种无人机自主降落装置的各个模块的功能。
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的模块可以是或者也可以不是物理上分开的，作为模块显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
通过以上的实施例的描述，本领域普通技术人员可以清楚地了解到各实施例可借助软件加通用硬件平台的方式来实现，当然也可以通过硬 件。本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程是可以通过计算机程序指令相关的硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施方法的流程。其中，所述存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory,ROM)或随机存储记忆体(RandomAccessMemory,RAM)等。
以上所述仅为本发明的实施例，并非因此限制本发明的专利范围，凡是利用本发明说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本发明的专利保护范围内。
最后应说明的是：以上实施例仅用以说明本发明的技术方案，而非对其限制；在本发明的思路下，以上实施例或者不同实施例中的技术特征之间也可以进行组合，步骤可以以任意顺序实现，并存在如上所述的本发明的不同方面的许多其它变化，为了简明，它们没有在细节中提供；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的范围。

Claims (20)

  1. 一种无人机自主降落方法，其特征在于，所述方法包括：
    获取待降落区域的点云分布图；
    根据所述无人机在所述点云分布图中的实际降落区域，确定所述点云分布图中的检测区域，其中，所述检测区域是指在所述点云分布图中用于检测点云数量的区域；
    将所述检测区域划分为至少两个指定区域，所述至少两个指定区域中的每一个指定区域分别对应所述待降落区域的一部分；
    确定所述至少两个指定区域中的每一个指定区域中的点云数量是否小于预设阈值；
    若是，则控制所述无人机飞离点云数量小于所述预设阈值的指定区域或者控制所述无人机停止降落。
  2. 根据权利要求1所述的无人机自主降落方法，其特征在于，所述获取所述待降落区域的所述点云分布图，包括：
    通过所述无人机的深度传感器获取所述待降落区域的所述点云分布图。
  3. 根据权利要求2所述的无人机自主降落方法，其特征在于，所述通过所述无人机的深度传感器获取所述待降落区域的所述点云分布图，包括：
    通过所述深度传感器获取所述待降落区域的深度图；
    根据所述深度图，获取所述点云分布图。
  4. 根据权利要求2所述的无人机自主降落方法，其特征在于，所述通过所述无人机的深度传感器获取所述待降落区域的所述点云分布图，包括：
    通过所述深度传感器获取所述待降落区域的点云数据；
    将所述点云数据投影至二维平面，以获取所述点云分布图。
  5. 根据权利要求1-4中任一项所述的无人机自主降落方法，其特征在于，所述检测区域为所述点云分布图所对应的区域中除去所述实际降落区域并加上由危险容忍误差所构成的区域。
  6. 根据权利要求1-5中任一项所述的无人机自主降落方法，其特征在于，所述点云分布图为矩形结构，所述至少两个指定区域包括：
    位于降落区域左侧的第一指定区域、位于降落区域右侧的第二指定区域、位于降落区域上方的第三指定区域以及位于降落区域下方的第四指定区域。
  7. 根据权利要求6所述的无人机自主降落方法，其特征在于，所述检测区域不包括所述点云分布图中四个角所在的区域。
  8. 根据权利要求7所述的无人机自主降落方法，其特征在于，所述第一指定区域S1、第二指定区域S2、第三指定区域S3和第四指定区域S4的数学表达式分别如下：
    S1:-length<x 1<-(l-d)，y 1<|w-d|；
    S2:(l-d)<x 2<length，y 2<|w-d|；
    S3:x 3<|l-d|，(w-d)<y 3<width；
    S4:x 4<|l-d|，-width<y 4<-(w-d)；
    其中，x 1为落在所述第一指定区域S1内的点的横坐标，y 1为所述落在所述第一指定区域S1内的点的纵坐标，x 2为落在所述第二指定区域S2内的点的横坐标，y 2为所述落在所述第二指定区域S2内的点的纵坐标，x 3为落在所述第三指定区域S3内的点的横坐标，y 3为所述落在所述第三指定区域S3内的点的纵坐标，x 4为落在所述第四指定区域S4 内的点的横坐标，y 4为所述落在所述第四指定区域S4内的点的纵坐标，length为所述点云分布图的长度的一半，width为所述点云分布图的宽度的一半，l为所述实际降落区域的长度的一半，w为所述实际降落区域的宽度的一半，d为危险容忍误差。
  9. 根据权利要求1-8中任一项所述的无人机自主降落方法，其特征在于，所述预设阈值在15-50范围内取值。
  10. 一种无人机自主降落装置，其特征在于，所述装置包括：
    获取模块，所述获取模块用于获取待降落区域的点云分布图；
    第一确定模块，所述第一确定模块用于根据所述无人机在所述点云分布图中的实际降落区域，确定所述点云分布图中的检测区域，其中，所述检测区域是指在所述点云分布图中用于检测点云数量的区域；
    划分模块，所述划分模块用于将所述检测区域划分为至少两个指定区域，所述至少两个指定区域中的每一个指定区域分别对应所述待降落区域的一部分；
    第二确定模块，所述第二确定模块用于确定所述至少两个指定区域中的每一个指定区域中的点云数量是否小于预设阈值；
    控制模块，所述控制模块用于若指定区域中的点云数量小于预设阈值，则控制所述无人机飞离点云数量小于所述预设阈值的指定区域或者控制所述无人机停止降落。
  11. 根据权利要求10所述的无人机自主降落装置，其特征在于，所述获取模块通过所述无人机的深度传感器获取所述待降落区域的所述点云分布图。
  12. 根据权利要求11所述的无人机自主降落装置，其特征在于，所述获取模块具体用于：
    通过所述深度传感器获取所述待降落区域的深度图；
    根据所述深度图，获取所述点云分布图。
  13. 根据权利要求11所述的无人机自主降落装置，其特征在于，所述获取模块具体用于：
    通过所述深度传感器获取所述待降落区域的点云数据；
    将所述点云数据投影至二维平面，以获取所述点云分布图。
  14. 根据权利要求10-13中任一项所述的无人机自主降落装置，其特征在于，所述检测区域为所述点云分布图所对应的区域中除去所述实际降落区域并加上由危险容忍误差所构成的区域。
  15. 根据权利要求10-14中任一项所述的无人机自主降落装置，其特征在于，所述点云分布图为矩形结构，所述至少两个指定区域包括：
    位于降落区域左侧的第一指定区域、位于降落区域右侧的第二指定区域、位于降落区域上方的第三指定区域以及位于降落区域下方的第四指定区域。
  16. 根据权利要求15所述的无人机自主降落装置，其特征在于，所述检测区域不包括所述点云分布图中四个角所在的区域。
  17. 根据权利要求16所述的无人机自主降落装置，其特征在于，所述第一指定区域S1、第二指定区域S2、第三指定区域S3和第四指定区域S4的数学表达式分别如下：
    S1:-length<x 1<-(l-d)，y 1<|w-d|；
    S2:(l-d)<x 2<length，y 2<|w-d|；
    S3:x 3<|l-d|，(w-d)<y 3<width；
    S4:x 4<|l-d|，-width<y 4<-(w-d)；
    其中，x 1为落在所述第一指定区域S1内的点的横坐标，y 1为所述 落在所述第一指定区域S1内的点的纵坐标，x 2为落在所述第二指定区域S2内的点的横坐标，y 2为所述落在所述第二指定区域S2内的点的纵坐标，x 3为落在所述第三指定区域S3内的点的横坐标，y 3为所述落在所述第三指定区域S3内的点的纵坐标，x 4为落在所述第四指定区域S4内的点的横坐标，y 4为所述落在所述第四指定区域S4内的点的纵坐标，length为所述点云分布图的长度的一半，width为所述点云分布图的宽度的一半，l为所述实际降落区域的长度的一半，w为所述实际降落区域的宽度的一半，d为危险容忍误差。
  18. 根据权利要求10-17中任一项所述的无人机自主降落装置，其特征在于，所述预设阈值在15-50范围内取值。
  19. 一种无人机，其特征在于，包括：
    至少一个处理器；以及
    与所述至少一个处理器通信连接的存储器；其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够用于执行如权利要求1-9任一项所述的无人机自主降落方法。
  20. 一种非易失性计算机可读存储介质，其特征在于，所述非易失性计算机可读存储介质存储有计算机可执行指令，所述计算机可执行指令用于使无人机执行如权利要求1-9任一项所述的无人机自主降落方法。
PCT/CN2019/126720 2018-12-20 2019-12-19 一种无人机自主降落方法、装置及无人机 WO2020125726A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/352,697 US20220075391A1 (en) 2018-12-20 2021-06-21 Autonomous landing method and apparatus of unmanned aerial vehicle and unmanned aerial vehicle

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811563917.7 2018-12-20
CN201811563917.7A CN109343572B (zh) 2018-12-20 2018-12-20 一种无人机自主降落方法、装置及无人机

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/352,697 Continuation US20220075391A1 (en) 2018-12-20 2021-06-21 Autonomous landing method and apparatus of unmanned aerial vehicle and unmanned aerial vehicle

Publications (1)

Publication Number Publication Date
WO2020125726A1 true WO2020125726A1 (zh) 2020-06-25

Family

ID=65304318

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/126720 WO2020125726A1 (zh) 2018-12-20 2019-12-19 一种无人机自主降落方法、装置及无人机

Country Status (3)

Country Link
US (1) US20220075391A1 (zh)
CN (1) CN109343572B (zh)
WO (1) WO2020125726A1 (zh)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220284544A1 (en) * 2021-03-02 2022-09-08 Fyusion, Inc. Vehicle undercarriage imaging
US11562474B2 (en) 2020-01-16 2023-01-24 Fyusion, Inc. Mobile multi-camera multi-view capture
US11727626B2 (en) 2019-01-22 2023-08-15 Fyusion, Inc. Damage detection from multi-view visual data
US11748907B2 (en) 2019-01-22 2023-09-05 Fyusion, Inc. Object pose estimation in visual data
US11776142B2 (en) 2020-01-16 2023-10-03 Fyusion, Inc. Structuring visual data
US11783443B2 (en) 2019-01-22 2023-10-10 Fyusion, Inc. Extraction of standardized images from a single view or multi-view capture

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109343572B (zh) * 2018-12-20 2021-07-30 深圳市道通智能航空技术股份有限公司 一种无人机自主降落方法、装置及无人机
CN109992001A (zh) * 2019-04-22 2019-07-09 西安忠林世纪电子科技有限公司 一种无人机安全降落方法、装置及无人机
CN111913492B (zh) * 2019-05-09 2024-04-19 丰翼科技(深圳)有限公司 无人机安全降落方法和装置
CN112306083B (zh) * 2019-07-30 2023-12-05 广州极飞科技股份有限公司 无人机降落区域的确定方法、装置、无人机和存储介质
CN112306086B (zh) * 2019-07-30 2023-09-01 广州极飞科技股份有限公司 无人机降落区域的确定方法、装置、无人机和存储介质
WO2021056139A1 (zh) * 2019-09-23 2021-04-01 深圳市大疆创新科技有限公司 获取降落位置的方法、设备、无人机、系统及存储介质
CN114489119B (zh) * 2021-12-29 2023-10-03 华中师范大学 一种由结构光引导的多旋翼无人机精准降落方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105775150A (zh) * 2016-03-17 2016-07-20 英华达（上海）科技有限公司 无人飞行载具及其降落方法
US20170283087A1 (en) * 2016-03-31 2017-10-05 Sikorsky Aircraft Corporation Sensor-based detection of landing zones
CN107291093A (zh) * 2017-07-04 2017-10-24 西北工业大学 基于视觉slam的复杂环境下无人机自主降落区域选择方法
CN107444665A (zh) * 2017-07-24 2017-12-08 长春草莓科技有限公司 一种无人机自主降落方法
CN109343572A (zh) * 2018-12-20 2019-02-15 深圳市道通智能航空技术有限公司 一种无人机自主降落方法、装置及无人机

Family Cites Families (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
ATE514055T1 (de) * 2007-11-07 2011-07-15 Tele Atlas Bv Computeranordnung und verfahren zum berechnen von bewegungsvektoren unter verwendung von entfernungsdaten
US8600589B2 (en) * 2012-04-24 2013-12-03 Exelis, Inc. Point cloud visualization of acceptable helicopter landing zones based on 4D LIDAR
US9063544B2 (en) * 2012-09-19 2015-06-23 The Boeing Company Aerial forest inventory system
CN103365299B (zh) * 2013-08-02 2015-12-23 中国科学院自动化研究所 一种无人机的避障方法及其装置
US9933521B2 (en) * 2014-04-14 2018-04-03 The Boeing Company Aerial positioning systems and methods
CN107655461B (zh) * 2014-05-05 2020-07-24 赫克斯冈技术中心 测量子系统和测量系统
WO2016033795A1 (en) * 2014-09-05 2016-03-10 SZ DJI Technology Co., Ltd. Velocity control for an unmanned aerial vehicle
CN111506109B (zh) * 2014-12-31 2023-08-25 深圳市大疆创新科技有限公司 传感器数据的选择性处理
US9645582B2 (en) * 2015-06-25 2017-05-09 Bell Helicopter Textron Inc. Landing aircrafts with optimal landing spot selection
CN105204515B (zh) * 2015-08-27 2018-04-10 泉州装备制造研究所 无人机自主着陆的测量解析及控制方法和装置
US10121117B1 (en) * 2016-09-08 2018-11-06 Amazon Technologies, Inc. Drone location signature filters
CN106657882A (zh) * 2016-10-18 2017-05-10 国网湖北省电力公司检修公司 基于无人机的输变电系统实时监控方法
CN106688017B (zh) * 2016-11-28 2019-03-01 深圳市大疆创新科技有限公司 生成点云地图的方法、计算机系统和装置
CN106828899B (zh) * 2017-01-06 2023-05-30 润泰救援装备科技河北有限公司 救援无人机及其调控消防系统
US11017679B2 (en) * 2017-01-13 2021-05-25 Skydio, Inc. Unmanned aerial vehicle visual point cloud navigation
CN107167814A (zh) * 2017-04-12 2017-09-15 深圳市速腾聚创科技有限公司 机载遥测系统
CN107424193B (zh) * 2017-04-27 2020-10-13 巧夺天宫（深圳）科技有限公司 一种门窗信息提取方法及其装置
CN107977992A (zh) * 2017-12-05 2018-05-01 深圳大学 一种基于无人机激光雷达的建筑物变化检测方法及装置
CN108629968B (zh) * 2018-06-26 2023-10-17 吉林大学 一种基于激光雷达的行人过街安全控制装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105775150A (zh) * 2016-03-17 2016-07-20 英华达（上海）科技有限公司 无人飞行载具及其降落方法
US20170283087A1 (en) * 2016-03-31 2017-10-05 Sikorsky Aircraft Corporation Sensor-based detection of landing zones
CN107291093A (zh) * 2017-07-04 2017-10-24 西北工业大学 基于视觉slam的复杂环境下无人机自主降落区域选择方法
CN107444665A (zh) * 2017-07-24 2017-12-08 长春草莓科技有限公司 一种无人机自主降落方法
CN109343572A (zh) * 2018-12-20 2019-02-15 深圳市道通智能航空技术有限公司 一种无人机自主降落方法、装置及无人机

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
黄建宇 等 (HUANG, JIANYU ET AL.): "无人飞行器自主降落区识别方法研究 (Method for Identifying the Landing Area of Unmanned Aerial Vehicle)", 液晶与显示 (CHINESE JOURNAL OF LIQUID CRYSTALS AND DISPLAYS), vol. 33, no. 3, 31 March 2018 (2018-03-31), DOI: 20200218112258A *

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11727626B2 (en) 2019-01-22 2023-08-15 Fyusion, Inc. Damage detection from multi-view visual data
US11748907B2 (en) 2019-01-22 2023-09-05 Fyusion, Inc. Object pose estimation in visual data
US11783443B2 (en) 2019-01-22 2023-10-10 Fyusion, Inc. Extraction of standardized images from a single view or multi-view capture
US11989822B2 (en) 2019-01-22 2024-05-21 Fyusion, Inc. Damage detection from multi-view visual data
US11562474B2 (en) 2020-01-16 2023-01-24 Fyusion, Inc. Mobile multi-camera multi-view capture
US11776142B2 (en) 2020-01-16 2023-10-03 Fyusion, Inc. Structuring visual data
US11972556B2 (en) 2020-01-16 2024-04-30 Fyusion, Inc. Mobile multi-camera multi-view capture
US20220284544A1 (en) * 2021-03-02 2022-09-08 Fyusion, Inc. Vehicle undercarriage imaging
US11605151B2 (en) * 2021-03-02 2023-03-14 Fyusion, Inc. Vehicle undercarriage imaging
US11893707B2 (en) 2021-03-02 2024-02-06 Fyusion, Inc. Vehicle undercarriage imaging

Also Published As

Publication number Publication date
CN109343572B (zh) 2021-07-30
CN109343572A (zh) 2019-02-15
US20220075391A1 (en) 2022-03-10

Similar Documents

Publication Publication Date Title
WO2020125726A1 (zh) 一种无人机自主降落方法、装置及无人机
WO2020125725A1 (zh) 一种无人机降落避障方法、装置及无人机
WO2020103034A1 (zh) 一种无人机路径规划方法、装置及无人机
WO2021013110A1 (zh) 一种基于目标跟踪的无人机避障方法、装置及无人机
JP7456537B2 (ja) 飛行体制御装置、飛行体制御方法、及びプログラム
US11721225B2 (en) Techniques for sharing mapping data between an unmanned aerial vehicle and a ground vehicle
US10379545B2 (en) Detecting optical discrepancies in captured images
US20200344464A1 (en) Systems and Methods for Improving Performance of a Robotic Vehicle by Managing On-board Camera Defects
US9658619B1 (en) Unmanned aerial vehicle modular command priority determination and filtering system
US10672283B2 (en) Obstacle avoidance method and device, moveable object and computer readable storage medium
CN109562844B (zh) 自动着陆表面地形评估以及相关的系统和方法
CN117369489A (zh) 碰撞规避系统、深度成像系统、交通工具、地图生成器及其方法
WO2020143576A1 (zh) 调整机载雷达的主探测方向的方法、装置和无人机
US20240159557A1 (en) Techniques for collaborative map construction between an unmanned aerial vehicle and a ground vehicle
WO2018072133A1 (zh) 控制移动设备的方法、控制系统和移动设备
US11245848B2 (en) Method of controlling gimbal, gimbal and UAV
WO2019106714A1 (ja) 無人航空機、無人航空機の飛行制御装置、無人航空機の飛行制御方法、及びプログラム
US20220342419A1 (en) Method and apparatus for auxiliary focusing and unmanned aerial vehicle
WO2021056139A1 (zh) 获取降落位置的方法、设备、无人机、系统及存储介质
WO2021237462A1 (zh) 无人飞行器的限高方法、装置、无人飞行器及存储介质
WO2022061614A1 (zh) 可移动平台的控制方法、控制装置、可移动平台和计算机存储介质
US20230095700A1 (en) Vehicle flight control method and apparatus for unmanned aerial vehicle, and unmanned aerial vehicle
JP7031997B2 (ja) 飛行体システム、飛行体、位置測定方法、プログラム
CN111615677A (zh) 一种无人机的安全降落方法、装置、无人机及介质
WO2022133911A1 (zh) 目标检测方法、装置、可移动平台及计算机可读存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19901344

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19901344

Country of ref document: EP

Kind code of ref document: A1