WO2020125725A1 - 一种无人机降落避障方法、装置及无人机 - Google Patents

一种无人机降落避障方法、装置及无人机 Download PDF

Info

Publication number
WO2020125725A1
WO2020125725A1 PCT/CN2019/126715 CN2019126715W WO2020125725A1 WO 2020125725 A1 WO2020125725 A1 WO 2020125725A1 CN 2019126715 W CN2019126715 W CN 2019126715W WO 2020125725 A1 WO2020125725 A1 WO 2020125725A1
Authority
WO
WIPO (PCT)
Prior art keywords
area
landed
drone
target position
point cloud
Prior art date
Application number
PCT/CN2019/126715
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 WO2020125725A1 publication Critical patent/WO2020125725A1/zh
Priority to US17/352,721 priority Critical patent/US20220055748A1/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
    • G05D1/04—Control of altitude or depth
    • G05D1/06—Rate of change of altitude or depth
    • G05D1/0607—Rate of change of altitude or depth specially adapted for aircraft
    • G05D1/0653—Rate of change of altitude or depth specially adapted for aircraft during a phase of take-off or landing
    • G05D1/0676—Rate of change of altitude or depth specially adapted for aircraft during a phase of take-off or landing specially adapted for landing
    • 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
    • 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
    • G05D1/106—Change initiated in response to external conditions, e.g. avoidance of elevated terrain or of no-fly zones
    • 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
    • B64U10/00—Type of UAV
    • B64U10/10—Rotorcrafts
    • B64U10/13—Flying platforms
    • B64U10/14—Flying platforms with four distinct rotor axes, e.g. quadcopters
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B64—AIRCRAFT; AVIATION; COSMONAUTICS
    • B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U2201/00—UAVs characterised by their flight controls
    • 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

  • Embodiments of the present invention relate to the technical field of drone control, and in particular, to a method and device for drone landing and obstacle avoidance and a drone.
  • 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 autonomous landing protection technology equipped with the drone After detecting the existence of a dangerous area in the area to be landed by the autonomous landing protection technology equipped with the drone, it can only fly away or hover over the area to be landed in the dangerous area, and cannot avoid the dangerous area in the area to be landed. For low-power UAVs, it is easy to cause the UAV to crash after the power is exhausted.
  • the embodiment of the present invention aims to provide a method, device and drone for drone landing and obstacle avoidance, which can avoid obstacles in the area to be landed and reduce the risk of drone crash.
  • a technical solution adopted by the embodiments of the present invention is: to provide a method for landing and avoiding obstacles for a drone, the method including:
  • the obtaining a 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 determining the target position in the safe area includes:
  • the center of gravity position of the safety area is determined as the target position.
  • the determining the position of the center of gravity of the safe area includes:
  • n is the total number of point clouds in the safe area
  • Xi is the abscissa of the ith point cloud in the safe area
  • Yi is the ordinate of the ith point cloud in the safe area
  • X is the The abscissa of the position of the center of gravity
  • Y is the ordinate of the position of the center of gravity.
  • controlling the UAV to move to the target position includes:
  • the method before controlling the UAV to move to the target position in the first target direction, the method further includes:
  • the drone is controlled to move to the target position along the first target direction.
  • whether there is an obstacle in the first target direction is determined by a sensing sensor.
  • the sensing sensor is a unidirectional sensing sensor, and the method further includes:
  • the method before the controlling the UAV to move to the target position, the method further includes:
  • the re-determining the target position includes:
  • the target position is determined in the safe area.
  • the method further includes:
  • a target position is determined in the area to be landed centered on the target position.
  • the method further includes:
  • the method before determining the target position in the security area, the method further includes:
  • a drone landing obstacle avoidance device which includes:
  • An obtaining module the obtaining module is used to obtain a point cloud distribution map of the area to be landed;
  • a determination module configured to determine a safe area in the area to be landed according to the point cloud distribution map
  • control module the control module is used to control the drone to move to the target position, so that the drone is away from obstacles in the area to be landed.
  • 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 determination module is used to:
  • the center of gravity position of the safety area is determined as the target position.
  • the determination module is also used to:
  • n is the total number of point clouds in the safe area
  • Xi is the abscissa of the ith point cloud in the safe area
  • Yi is the ordinate of the ith point cloud in the safe area
  • X is the The abscissa of the position of the center of gravity
  • Y is the ordinate of the position of the center of gravity.
  • control module is used to:
  • control module is also used to:
  • the drone is controlled to move to the target position along the first target direction.
  • control module determines whether there is an obstacle in the first target direction through a sensing sensor.
  • the sensing sensor is a unidirectional sensor
  • the control module is further used to:
  • the determination module is also used to:
  • the determination module is also used to:
  • the target position is determined in the safe area.
  • control module is also used to:
  • a target position is determined in the area to be landed centered on the target position.
  • control module is also used to:
  • the determination module is also used to:
  • a drone including:
  • the machine arm is connected to the fuselage
  • the power device is provided on the arm;
  • At least one processor inside the fuselage At least one processor inside the fuselage;
  • the device can be used to perform the above-mentioned UAV landing obstacle avoidance 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 landing obstacle avoidance method described above.
  • the embodiments of the present invention provide a UAV landing obstacle avoidance method, device and UAV, in the UAV landing obstacle avoidance method, through Determine the target position in the safe area of the area to be landed, and control the drone to move to the target position, so that the drone can move to the safe area of the area to be landed, and because the safe area is an area without obstacles, there is no When the man-machine moves to a safe area, it avoids obstacles 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. 2 is a schematic flowchart of a method for landing and avoiding obstacles of a drone according to an embodiment of the present invention
  • FIG. 3 is a schematic flowchart of step S400 of the method shown in FIG. 2;
  • step S800 of the method shown in FIG. 2 is a schematic flowchart of step S800 of the method shown in FIG. 2;
  • FIG. 5 is a schematic flow chart of a method for landing and avoiding obstacles of a drone according to another embodiment of the present invention.
  • FIG. 6 is a schematic flowchart of a method for landing and avoiding obstacles of a drone according to another embodiment of the present invention.
  • FIG. 7 is a schematic flowchart of a method for landing and avoiding obstacles for a drone according to another embodiment of the present invention.
  • FIG. 8 is a schematic structural diagram of a landing and obstacle avoidance device for a drone according to an embodiment of the present invention.
  • FIG. 9 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 drone landing obstacle avoidance.
  • the method and device are applied to a drone, thereby enabling the drone to detect the presence of a dangerous area in the area to be landed.
  • the dangerous area refers to the area where there are obstacles
  • the obstacles include: inclined slopes, water, bushes, raised foreign objects and edge vacant areas such as roofs, cliffs, deep trenches and other flat surface areas
  • the target location is Refers to the location where the drone is about to move.
  • 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 fuselage 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 fuselage 10, the flight control system is installed in the fuselage 10, and the power unit 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 arms 20 is four, which are evenly distributed around the fuselage 10 and used to carry 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 body 10, and is connected to the arm 20 through a motor.
  • the four arms 20 of the drone 100 are all provided with a power device 30 to enable the drone 100 to fly smoothly.
  • the depth sensor 40 is disposed at the bottom of the fuselage 10 and is used to collect point cloud data of the area where the drone 100 is to land.
  • each point cloud contains three-dimensional coordinates, and some may contain color information or reflection intensity information.
  • the distance between the depth sensor 40 and the object in the area to be landed can be obtained through the point cloud data.
  • the flight control system can obtain the point cloud data of the area to be landed by the drone 100 from the depth sensor 40, and project the point cloud data onto a two-dimensional plane to obtain the area of the area to be landed Point cloud distribution map.
  • the depth sensor 40 is installed at the bottom of the fuselage 10 through the gimbal, so that the depth sensor 40 can collect point cloud data of the area to be landed in all directions.
  • 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 lidar.
  • the landing gear 50 is disposed on opposite sides of the bottom of the fuselage 10 and connected to the fuselage 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, which 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.
  • a sensing sensor (not shown) is also provided in the fuselage 10, and the sensing sensor is used to determine whether there is an obstacle in the flying direction of the drone 100.
  • the sensing sensor is in communication with the flight control system.
  • the flight control system can control the flying direction of the drone 100 according to the judgment result of the sensing sensor. For example, if the sensing sensor determines that there is an obstacle in the flying direction of the drone 100, the control is disabled.
  • the man-machine 100 changes the flight direction.
  • the sensing sensor includes a unidirectional sensing sensor or a multidirectional sensing sensor.
  • the unidirectional sensing sensor can only determine whether there is an obstacle in one direction, so when the unidirectional sensing sensor is installed in the fuselage 10, the sensing direction is the same as the flying direction of the drone 100 Consistent, that is, the flying direction of the drone 100 is the sensing direction of the unidirectional sensing sensor.
  • the sensing direction of the unidirectional sensing sensor also changes as the flying direction of the drone 100 changes. In this way, the unidirectional sensing sensor can always determine whether there is an obstacle in the flying direction of the drone 100.
  • the multi-directional sensing sensor can determine whether there is an obstacle in any direction of the drone 100, so when the multi-directional sensing sensor is provided in the fuselage 10, it can not fly with the drone 100 The direction changes.
  • the flight control system and the power device 30, the depth sensor 40, the landing gear 50, and the sensing sensor are communicatively connected through 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 perform the drone landing obstacle avoidance method described in the present invention, so that the drone 100 can avoid obstacles in the area to be landed, and reduce the risk of the drone 100 crashing.
  • 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 drone 100 is ready to land, and the drone 100 is located in the center of the area to be landed.
  • the point cloud distribution map is a schematic diagram that can reflect the distribution of point clouds in the area to be landed.
  • 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 points Cloud data is projected onto a two-dimensional plane to obtain a 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 may further include: 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 to obtain point cloud distribution map.
  • the flight control system determines the safe area in the area to be landed according to the point cloud distribution map.
  • the safe area is an area where no obstacle exists in the area to be landed, that is, an area after the danger area where the obstacle is present is removed from the area to be landed.
  • the flight control system determines the safe area in the area to be landed according to the point cloud distribution map, it can be determined by the plane detection method or the vacancy area detection method.
  • the safe area in the area to be landed is determined by the plane detection method, after extracting the feature points in the point cloud distribution map to determine the plane, the area where the point clouds are all located in the plane is determined as the safe area.
  • the detection area is divided in the point cloud distribution map of the area to be landed, the detection area is divided into at least two designated areas, and the points in each designated area The number of clouds is detected, and the designated area where the number of point clouds is not less than the threshold is determined as a safe area.
  • the plane detection method and the vacancy area detection method can also be combined to determine the safety area in the area to be landed, thereby improving the accuracy of determining the safety area.
  • the flight control system determines the number of point clouds in the safety area and the points of the area to be landed The ratio R1 of the number of clouds, and determine whether the ratio R1 is greater than the second preset threshold. If the ratio R1 is greater than the second preset threshold, it means that the safe area is large enough to meet the landing requirements of the drone 100. Then determine the target position in the safe area.
  • the second preset threshold is a preset fixed value, and the value range of the second preset threshold is 10%-30%, including two endpoint values of 10% and 30%.
  • the second preset threshold is related to the projected area of the drone 100, and the ratio of the projected area of the drone 100 to the area of the area to be landed can be determined as the second preset threshold .
  • determining the target position in the safe area specifically includes: the flight control system determines the position of the center of gravity of the safe area, and determines the determined position of the center of gravity as the target position.
  • the center of gravity of the safety area is the "mass center" of all point clouds in the safety area, and the position of the center of gravity of the safety area can be determined by the average value of the coordinates of all point clouds in the safety area.
  • the flight control system determines the position of the center of gravity of the safety area
  • the coordinates of each point cloud in the safety area are extracted, and then the position of the center of gravity of the safety area is determined according to the coordinates of each point cloud.
  • the position of the center of gravity of the safety area is:
  • n is the total number of point clouds in the safe area
  • Xi is the abscissa of the ith point cloud in the safe area
  • Yi is the ordinate of the ith point cloud in the safe area
  • X is the abscissa of the position of the center of gravity
  • Y is The ordinate of the center of gravity.
  • the flight control system extracts the coordinates of each point cloud in the safe area, that is, the coordinates of the first point cloud (X1, Y1) and the coordinates of the second point cloud (X2, Y2) ) And the coordinates of the third point cloud (X3, Y3), and then the flight control system according to the extracted coordinates of the first point cloud (X1, Y1), the coordinates of the second point cloud (X2, Y2) and the first The coordinates of the three point clouds (X3, Y3) to calculate the position of the center of gravity of the safe area, where the horizontal coordinate of the position of the center of gravity of the safe area The ordinate of the center of gravity of the safety zone
  • the position of the center of gravity of the determined safety area is consistent with the center position of the area to be landed, resulting in the drone unable to dodge the obstacle, so in order to prevent
  • the position of the center of gravity of the safety area is consistent with the center position of the area to be landed.
  • the flight control system After determining the target position, the flight control system also needs to determine the center position of the area to be landed, to determine whether the target position is consistent with the center position of the area to be landed. If the target position is not consistent with the center position of the area to be landed, the drone 100 is controlled to move to the target position; if the target position is consistent with the center position of the area to be landed, the target position is re-determined.
  • controlling the UAV 100 to move to the target location specifically includes: after the flight control system determines that the direction of the target location is the first target direction, controlling the UAV 100 to move to the target along the first target direction position.
  • the flight control system determines whether the first target direction exists through a sensor Obstacles, if there are no obstacles, the drone 100 is controlled to move to the target position in the first target direction.
  • the flight control system controls the sensing direction of the unidirectional sensing sensor to be consistent with the first target direction, which specifically includes: the flight control system controls the flying direction of the drone 100 toward the first target direction. Since the sensing direction of the unidirectional sensing sensor is consistent with the flying direction, it is possible to control the sensing direction of the unidirectional sensing sensor to be consistent with the first target direction by controlling the flying direction of the drone 100 toward the first target direction.
  • re-determining the target position includes: the flight control system determines that the direction in which the obstacle is not present in the area to be landed is the second target direction, and then controls the drone 100 to move the preset distance along the second target direction After that, determine the target position in the safe area.
  • the flight control system determines the second target direction through the sensing sensor.
  • the preset distance is related to the second target direction and the size of the area to be landed, if the second target direction is the width direction of the area to be landed, the preset distance is the half width of the area to be landed; if the second target direction is the area to be landed In the length direction of, the preset distance is half the length of the area to be landed, to ensure that the UAV 100 can leave the area to be landed after moving the preset distance in the second target direction and determine the target position in the new safe area.
  • the flight control system determines whether there is a dangerous area in the area to be landed centered on the target position, and if so, determines the target position in the area to be landed centered on the target position; If it does not exist, control the drone to land.
  • the drone if it is determined that the number of times the target position is determined in the area to be landed centered on the target position exceeds the first preset threshold, the drone is controlled to issue a warning and/or the drone is stopped from landing .
  • the first preset threshold is a preset fixed value, and the value range of the first preset threshold is between 3-5, including two endpoint values of 3 and 5.
  • the drone by determining the target position in the safe area of the area to be landed and controlling the drone to move to the target position, the drone can move to the safe area of the area to be landed, and since the safe area is not There are areas with obstacles, so when the drone moves to a safe area, it avoids obstacles and reduces the risk of the drone crashing.
  • FIG. 2 is a schematic flow chart of a method for landing and avoiding obstacles of a drone according to an embodiment of the present invention.
  • the method provided by the embodiment of the present invention is executed by the above-mentioned flight control system and used to evade obstacles in the area to be landed to reduce the risk of the drone crashing.
  • the drone landing obstacle avoidance method includes:
  • the above “area to be landed” is the area where the drone is ready to land, and the drone is located in the center of the area to be landed.
  • 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.
  • depth sensors include but are not limited to: binocular cameras, TOF (Time of Flight) cameras, structured light cameras, and lidar.
  • the depth sensor is used to collect point cloud data of the area to be landed.
  • Each point cloud data contains three-dimensional coordinates, and some may contain color information or reflection intensity information.
  • the distance between the depth sensor and the object to be landed can be obtained through the point cloud data.
  • obtaining the point cloud distribution map of the area to be landed through the depth sensor specifically includes: obtaining the point cloud data of the area to be landed through the depth sensor; projecting the point cloud data onto a two-dimensional plane to obtain the point cloud distribution map.
  • S200 Determine a safe area in the area to be landed according to the point cloud distribution map.
  • the area to be landed includes a safe area and a dangerous area.
  • the dangerous area refers to the area where there are obstacles
  • the obstacles include: inclined slopes, water, bushes, raised foreign objects and edge vacant areas such as roofs, cliffs, deep trenches and other flat surface areas; safe areas are Refers to the area where there are no obstacles, that is, the area to be landed after removing the dangerous area with obstacles.
  • determining the safe area in the area to be landed according to the point cloud distribution map can pass the plane detection method or the vacant area detection method.
  • the safe area in the area to be landed is determined by the plane detection method, after extracting the feature points in the point cloud distribution map to determine the plane, the area where the point clouds are all located in the plane is determined as the safe area.
  • the detection area is divided in the point cloud distribution map of the area to be landed, the detection area is divided into at least two designated areas, and the points in each designated area The number of clouds is detected, and the designated area where the number of point clouds is not less than the threshold is determined as a safe area.
  • the plane detection method and the vacancy area detection method can also be combined to determine the safety area in the area to be landed, thereby improving the accuracy of determining the safety area.
  • S400 Determine a target position in the safe area.
  • target position is a position in the safe area that can keep the drone away from obstacles, that is, the position where the drone is about to move.
  • determining the target location in the security area specifically includes:
  • S420 Determine the position of the center of gravity of the safe area as the target position.
  • determining the position of the center of gravity of the safety area specifically includes: extracting the coordinates of each point cloud in the safety area; determining the position of the center of gravity of the safety area according to the coordinates of each point cloud, the position of the center of gravity of the safety area is:
  • n is the total number of point clouds in the safe area
  • Xi is the abscissa of the ith point cloud in the safe area
  • Yi is the ordinate of the ith point cloud in the safe area
  • X is the abscissa of the position of the center of gravity
  • Y is The ordinate of the center of gravity.
  • the flight control system extracts the coordinates of each point cloud in the safe area, that is, the coordinates of the first point cloud (X1, Y1) and the coordinates of the second point cloud (X2, Y2) ) And the coordinates of the third point cloud (X3, Y3), and then the flight control system according to the extracted coordinates of the first point cloud (X1, Y1), the coordinates of the second point cloud (X2, Y2) and the first The coordinates of the three point clouds (X3, Y3) to calculate the position of the center of gravity of the safe area, where the horizontal coordinate of the position of the center of gravity of the safe area The ordinate of the center of gravity of the safety zone
  • the safety area is the area after the danger area is removed from the landing area, if the obstacle is not symmetrical with respect to the center position of the area to be landed, the center of gravity of the safety area deviates from the center of the area to be landed, so the center of gravity of the safety area
  • the drone moving to the target position can be kept away from obstacles.
  • S800 Control the drone to move to the target position, so that the drone is away from obstacles in the area to be landed.
  • controlling the UAV to move to a target location specifically includes:
  • S810 Determine that the direction where the target position is located is the first target direction
  • S820 Determine whether there is an obstacle in the first target direction
  • controlling the sensing direction of the unidirectional sensing sensor is consistent with the first target direction, which specifically includes: controlling the flying direction of the drone toward the first target direction. Since the sensing direction of the unidirectional sensing sensor is consistent with the flying direction, it is possible to control the sensing direction of the unidirectional sensing sensor to be consistent with the first target direction by controlling the flying direction of the drone toward the first target direction.
  • the method further includes:
  • step S600 Determine whether the target position is consistent with the center position of the area to be landed, and if so, perform step S700; if not, perform step S800;
  • re-determining the target position includes: determining that the direction in which no obstacle exists in the area to be landed is the second target direction; after controlling the UAV to move a preset distance along the second target direction, determining the target position in the safe area.
  • the second target direction can be determined by the sensing sensor.
  • the preset distance is related to the second target direction and the size of the area to be landed, if the second target direction is the width direction of the area to be landed, the preset distance is the half width of the area to be landed; if the second target direction is the area to be landed In the length direction of, the preset distance is half the length of the area to be landed, to ensure that the UAV 100 can leave the area to be landed after moving the preset distance in the second target direction and determine the target position in the new safe area.
  • step S800 the method further includes:
  • a target position is determined in the area to be landed centered on the target position.
  • determining whether there is a dangerous area in the area to be landed it can be determined by the plane detection method or by the vacant area detection method.
  • the plane detection method When determining whether there is a dangerous area in the area to be landed by the plane detection method, after extracting the feature points in the point cloud distribution map to determine the plane, the area where the point cloud is outside the plane is determined as the dangerous area.
  • the plane detection method and the vacancy area detection method can also be combined to determine the safety area in the area to be landed, thereby improving the accuracy of determining the safety area.
  • the drone is controlled to issue a warning and/or the no The man-machine stopped landing.
  • the first preset threshold is a preset fixed value, and the value range of the first preset threshold is between 3-5, including two endpoint values of 3 and 5.
  • the method further includes:
  • step S300 Determine whether the ratio R1 of the number of point clouds in the safe area to the number of point clouds in the area to be landed is greater than a second preset threshold, and if so, step S400 is executed.
  • the second preset threshold is a preset fixed value, and the value range of the second preset threshold is 10%-30%, including two endpoint values of 10% and 30%.
  • the second preset threshold is related to the projected area of the drone 100, and the ratio of the projected area of the drone 100 to the area of the area to be landed can be determined as the second preset threshold .
  • the drone by determining the target position in the safe area of the area to be landed and controlling the drone to move to the target position, the drone can move to the safe area of the area to be landed, and since the safe area is not There are areas with obstacles, so when the drone moves to a safe area, it avoids obstacles and reduces the risk of the drone 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. 8 is a drone landing obstacle avoidance device provided by one embodiment of the present invention.
  • the device is applied to a drone, and the drone is the drone 100 described in the above embodiment, and The functions of each module of the device provided by the embodiment of the present invention are performed by the above-mentioned flight control system, used to evade obstacles in the area to be landed, and reduce the risk of a drone crash.
  • the drone landing obstacle avoidance device includes:
  • An obtaining module 200 which is used to obtain a point cloud distribution map of the area to be landed;
  • a determining module 300 the determining module 300 is configured to determine a safe area in the area to be landed according to the point cloud distribution map;
  • a control module 400 which is used to control the drone to move to the target position, so that the drone is away from obstacles in the area to be landed.
  • the obtaining module 200 obtains the point cloud distribution map of the area to be landed through the depth sensor of the drone.
  • the obtaining module 200 is specifically used for:
  • determination module 300 is specifically used for:
  • the center of gravity position of the safety area is determined as the target position.
  • determining module 300 is also used to:
  • n is the total number of point clouds in the safe area
  • Xi is the abscissa of the ith point cloud in the safe area
  • Yi is the ordinate of the ith point cloud in the safe area
  • X is the The abscissa of the position of the center of gravity
  • Y is the ordinate of the position of the center of gravity.
  • control module 400 is specifically used for:
  • control module 400 is also used to:
  • the drone is controlled to move to the target position along the first target direction.
  • control module 400 determines whether there is an obstacle in the first target direction through a sensing sensor.
  • control module 400 is also used to:
  • determining module 300 is also used to:
  • determining module 300 is also used to:
  • the target position is determined in the safe area.
  • control module 400 is also used to:
  • a target position is determined in the area to be landed centered on the target position.
  • control module 400 is also used to:
  • determining module 300 is also used to:
  • the acquisition module 200 may be a depth sensor to directly acquire the point cloud distribution map of the area to be landed; the determination module 300 and the control module 400 may be flight control chips.
  • 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 drone by determining the target position in the safe area of the area to be landed and controlling the drone to move to the target position, the drone can move to the safe area of the area to be landed, and since the safe area is not There are areas with obstacles, so when the drone moves to a safe area, it avoids obstacles and reduces the risk of the drone crashing.
  • FIG. 9 is a schematic diagram of the hardware structure of an unmanned aerial vehicle provided by one embodiment of the present invention.
  • the hardware module provided by this embodiment of the present invention can be integrated into the flight control system described in the above embodiment, and can also be used directly as a flight control system.
  • the control system is installed in the fuselage 10, so that the drone 100 can perform the drone landing obstacle avoidance method described in the above embodiment, and can also realize the drone landing obstacle avoidance device described in the above embodiment The function of each module.
  • the drone 100 includes:
  • processors 110 and memory 120. Among them, one processor 110 is taken as an example in FIG. 9.
  • the processor 110 and the memory 120 may be connected by a bus or other means.
  • a bus or other means.
  • FIG. 9 the connection by a bus is used as an example.
  • the memory 120 serves as 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 a drone landing in the foregoing embodiments of the present invention
  • a program instruction corresponding to the obstacle avoidance method and a module corresponding to the UAV landing obstacle avoidance device for example, the acquisition module 200, the determination module 300, and the control module 400, etc.
  • the processor 110 executes various functional applications and data processing of a drone landing obstacle avoidance method by running non-volatile software programs, instructions, and modules stored in the memory 120, that is, to implement the A drone landing obstacle avoidance method and functions of various modules in 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 an application created by using a drone landing obstacle avoidance device Data etc.
  • the stored data area also stores preset data, including a first preset threshold, a second preset threshold, a preset distance, and so on.
  • 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 remotely disposed relative 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, execute a drone landing obstacle avoidance method in any of the above method 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, such as FIG. 9
  • a processor 110 in the computer can cause the computer to execute the steps of a method for drone landing obstacle avoidance in any of the above method embodiments, or implement a device for landing obstacle avoidance in any of the above device embodiments The function of each 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. When the program instructions are Or executed by multiple processors, such as a processor 110 in FIG. 9, which can cause the computer to execute the steps of a method for landing and avoiding obstacles of a drone in any of the above method embodiments, or implement any of the above device embodiments The function of each module of a UAV landing obstacle avoidance 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, and of course, it can also be implemented 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 (RandomAccessMemory, RAM), etc.

Landscapes

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

Abstract

一种无人机降落避障方法、装置及无人机。该无人机降落避障方法包括：获取待降落区域的点云分布图（S100）；根据点云分布图确定待降落区域中的安全区域（S200）；在安全区域中确定目标位置（S400）；控制无人机移动至目标位置，以使无人机远离待降落区域中的障碍物（S800）。通过该方法，能够使无人机闪避待降落区域中的障碍物，减少无人机坠毁的风险。

Description

一种无人机降落避障方法、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降落避障方法、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。
目前，无人机配备的自主降落保护技术检测待降落区域存在危险区域后，只能飞离或者悬停于该存在危险区域的待降落区域，而无法在待降落区域中对危险区域进行闪避，对于低电量的无人机而言，容易造成无人机在电量耗尽后坠毁。
发明内容
本发明实施例旨在提供一种无人机降落避障方法、装置及无人机，能够闪避待降落区域中的障碍物，减少无人机坠毁的风险。
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：提供一种无人机降落避障方法，所述方法包括：
获取待降落区域的点云分布图；
根据所述点云分布图确定所述待降落区域中的安全区域；
在所述安全区域中确定目标位置；
控制所述无人机移动至所述目标位置，以使所述无人机远离所述待降落区域中的障碍物。
可选地，所述获取待降落区域的点云分布图，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，所述在所述安全区域中确定目标位置，包括：
确定所述安全区域的重心位置；
将所述安全区域的重心位置确定为所述目标位置。
可选地，所述确定所述安全区域的重心位置，包括：
提取所述安全区域中每个点云的坐标；
根据所述每个点云的坐标确定所述安全区域的重心位置为：
Figure PCTCN2019126715-appb-000001
其中，n为所述安全区域中的点云总数，Xi为所述安全区域中第i个点云的横坐标，Yi为所述安全区域中第i个点云的纵坐标，X为所述重心位置的横坐标，Y为所述重心位置的纵坐标。
可选地，所述控制所述无人机移动至所述目标位置，包括：
确定所述目标位置所在的方向为第一目标方向；
控制所述无人机沿所述第一目标方向移动至所述目标位置。
可选地，所述控制所述无人机沿所述第一目标方向移动至所述目标位置之前，所述方法还包括：
确定所述第一目标方向是否存在障碍物，若否，则控制所述无人机沿所述第一目标方向移动至所述目标位置。
可选地，通过感知传感器确定所述第一目标方向是否存在障碍物。
可选地，所述感知传感器为单向感知传感器，所述方法还包括：
控制所述单向感知传感器的感知方向与所述第一目标方向一致。
可选地，所述控制所述无人机移动至所述目标位置之前，所述方法还包括：
确定所述待降落区域的中心位置；
判断所述目标位置与所述待降落区域的中心位置是否一致，若是， 则重新确定目标位置。
可选地，所述重新确定目标位置，包括：
确定待降落区域中不存在障碍物的方向为第二目标方向；
控制所述无人机沿所述第二目标方向移动预设距离后，在所述安全区域中确定目标位置。
可选地，所述控制所述无人机移动至所述目标位置之后，所述方法还包括：
确定以所述目标位置为中心的待降落区域是否存在危险区域，
若不存在，则控制所述无人机降落；
若存在，则在所述以所述目标位置为中心的待降落区域中确定目标位置。
可选地，所述方法还包括：
确定在所述以所述目标位置为中心的待降落区域中确定目标位置的次数是否超过第一预设阈值，若是，则控制所述无人机发出警告和/或控制所述无人机停止降落。
可选地，所述在所述安全区域中确定目标位置之前，所述方法还包括：
确定所述安全区域的点云数量与所述待降落区域的点云数量的比值R1；
判断所述R1是否大于第二预设阈值，若是，则在所述安全区域中确定目标位置。
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：提供一种无人机降落避障装置，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；
确定模块，所述确定模块用于根据所述点云分布图确定所述待降落区域中的安全区域；以及
用于在所述安全区域中确定目标位置；
控制模块，所述控制模块用于控制所述无人机移动至所述目标位置，以使所述无人机远离所述待降落区域中的障碍物。
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，所述确定模块用于：
确定所述安全区域的重心位置；
将所述安全区域的重心位置确定为所述目标位置。
可选地，所述确定模块还用于：
提取所述安全区域中每个点云的坐标；
根据所述每个点云的坐标确定所述安全区域的重心位置为：
Figure PCTCN2019126715-appb-000002
其中，n为所述安全区域中的点云总数，Xi为所述安全区域中第i个点云的横坐标，Yi为所述安全区域中第i个点云的纵坐标，X为所述重心位置的横坐标，Y为所述重心位置的纵坐标。
可选地，所述控制模块用于：
确定所述目标位置所在的方向为第一目标方向；
控制所述无人机沿所述第一目标方向移动至所述目标位置。
可选地，所述控制模块还用于：
确定所述第一目标方向是否存在障碍物，若否，则控制所述无人机沿所述第一目标方向移动至所述目标位置。
可选地，所述控制模块通过感知传感器确定所述第一目标方向是否存在障碍物。
可选地，所述感知传感器为单向传感器，所述控制模块还用于：
控制所述单向感知传感器的感知方向与所述第一目标方向一致。
可选地，所述确定模块还用于：
确定所述待降落区域的中心位置；
判断所述目标位置与所述待降落区域的中心位置是否一致，若是， 则重新确定目标位置。
可选地，所述确定模块还用于：
确定待降落区域中不存在障碍物的方向为第二目标方向；
控制所述无人机沿所述第二目标方向移动预设距离后，在所述安全区域中确定目标位置。
可选地，所述控制模块还用于：
确定以所述目标位置为中心的待降落区域是否存在危险区域，
若不存在，则控制所述无人机降落；
若存在，则在所述以所述目标位置为中心的待降落区域中确定目标位置。
可选地，所述控制模块还用于：
确定在所述以所述目标位置为中心的待降落区域中确定目标位置的次数是否超过第一预设阈值，若是，则控制所述无人机发出警告和/或控制所述无人机停止降落。
可选地，所述确定模块还用于：
确定所述安全区域的点云数量与所述待降落区域的点云数量的比值R1；
判断所述R1是否大于第二预设阈值，若是，则在所述安全区域中确定目标位置。
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：
机身；
机臂，与所述机身相连；
动力装置，设于所述机臂；
至少一个处理器，设于所述机身内；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降落避障方法。
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降落避障方法。
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降落避障方法、装置及无人机，在无人机降落避障方法中，通过在待降落区域的安全区域中确定目标位置，并控制无人机移动至目标位置，使得无人机能够向待降落区域的安全区域移动，且由于安全区域是不存在障碍物的区域，故无人机向安全区域移动时，即实现了对障碍物的闪避，减少无人机坠毁的风险。
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一种无人机降落避障方法的流程示意图；
图3是图2所示方法的步骤S400的流程示意图；
图4是图2所示方法的步骤S800的流程示意图；
图5是本发明另一实施例提供的一种无人机降落避障方法的流程示意图；
图6是本发明另一实施例提供的一种无人机降落避障方法的流程示意图；
图7是本发明另一实施例提供的一种无人机降落避障方法的流程示意图；
图8是本发明一实施例提供的一种无人机降落避障装置的结构示意 图；
图9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降落避障方法及装置，该方法及装置应用于无人机，从而使得该无人机能够在检测到待降落区域中存在危险区域时，在待降落区域的安全区域中确定目标位置，并移动至该目标位置，以实现在待降落区域中对障碍物的闪避，减少坠毁风险。其中，危险区域是指存在障碍物的区域，该障碍物包括：倾斜坡面、水面、灌木丛、凸起的异物以及楼顶、悬崖、深沟等表面平整区域的边缘空缺区域；目标位置则指无人机即将移动到的位置。
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，包括机身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均与机身10连接，飞控系统则设置于机身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，均匀分布于机身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未与机身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20上，均设置有动力装置30，以使无人机100能够平稳飞行。
深度传感器40则设置于机身10底部，用于采集无人机100待降落区域的点云数据。点云数据中，每一个点云包含有三维坐标，有些可能含有颜色信息或者反射强度信息，通过点云数据能够获得深度传感器40与待降落区域物体的距离。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通过云台设置于机身10底部，以使深度传感器40能够全方位采集待降落区域的点云数据。
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、结构光相机和激光雷达。
起落架50设置于机身10底部相对两侧，通过驱动装置连接于机身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，该投影区域与实际降落区域中心点重合，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。
进一步地，在机身10中还设置有感知传感器(图未示)，该感知传感器用于确定无人机100的飞行方向上是否存在障碍物。
该感知传感器与飞控系统通信连接，飞控系统能够根据感知传感器的判断结果控制无人机100的飞行方向，比如：若感知传感器确定无人机100的飞行方向上存在障碍物，则控制无人机100改变飞行方向。
该感知传感器包括单向感知传感器或者多向感知传感器。
当感知传感器为单向感知传感器时，该单向感知传感器只能确定一个方向上是否存在障碍物，故该单向感知传感器设置于机身10时，其感知方向与无人机100的飞行方向一致，即无人机100的飞行方向为单向感知传感器的感知方向，当无人机100改变飞行方向时，单向感知传感器的感知方向也随着无人机100飞行方向的改变而改变，以使单向感知传感器始终能够确定无人机100的飞行方向上是否存在障碍物。
当感知传感器为多向感知传感器时，该多向感知传感器能够确定无人机100任意一个方向上是否存在障碍物，故该多向感知传感器设置于 机身10时，能够不随无人机100飞行方向的改变而改变。
飞控系统与动力装置30、深度传感器40、起落架50以及感知传感器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降落避障方法，以使得无人机100能够闪避待降落区域中的障碍物，减少无人机100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，待降落区域为无人机100准备降落的区域，无人机100位于待降落区域的中心。
点云分布图则为能够反映待降落区域的点云分布情况的示意图。
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。
当然，在一些可替代实施例中，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还可以包括：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。
进一步地，在获取了待降落区域的点云分布图后，飞控系统根据点云分布图确定待降落区域中的安全区域。
其中，安全区域为待降落区域中不存在障碍物的区域，即为待降落区域除去存在障碍物的危险区域后的区域。
飞控系统根据点云分布图确定待降落区域中的安全区域时，能够通过平面检测法进行确定，也能够通过空缺区域检测法进行确定。
具体地，当通过平面检测法确定待降落区域中的安全区域时，提取点云分布图中的特征点确定平面后，将点云均位于平面内的区域确定为安全区域。
当通过空缺区域检测法确定待降落区域中的安全区域时，在待降落区域的点云分布图中划分检测区域，将检测区域划分为至少两个指定区 域后，对每一个指定区域中的点云数量进行检测，将点云数量不小于阈值的指定区域确定为安全区域。
当然，在一些实施例中，还能够将平面检测法和空缺区域检测法结合后确定待降落区域中的安全区域，提高确定安全区域的精确度。
进一步地，在确定了待降落区域的安全区域后，为了防止安全区域过小而造成无人机100降落后仍出现坠毁的情况，飞控系统确定安全区域的点云数量与待降落区域的点云数量的比值R1,并判断该比值R1是否大于第二预设阈值，若该比值R1大于第二预设阈值，则表示安全区域足够大，能够满足无人机100的降落需求，此时，则在安全区域中确定目标位置。
其中，第二预设阈值为预先设置的固定值，该第二预设阈值的取值范围为10％-30％，包括10％和30％两个端点数值。
当然，在一些可替代实施方式中，第二预设阈值与无人机100的投影区域面积相关，能够将无人机100的投影区域面积与待降落区域面积的比值确定为第二预设阈值。
在本发明的一实施例中，在安全区域中确定目标位置具体包括：飞控系统确定安全区域的重心位置，并将所确定的重心位置确定为目标位置。
其中，安全区域的重心为安全区域中所有点云的“质量中心”，能够通过安全区域中所有点云坐标的平均值确定安全区域的重心位置。
飞控系统确定安全区域的重心位置时，提取安全区域中每个点云的坐标，然后根据每个点云的坐标来确定安全区域的重心位置，该安全区域的重心位置为：
Figure PCTCN2019126715-appb-000003
其中，n为安全区域中的点云总数，Xi为安全区域中第i个点云的横坐标，Yi为安全区域中第i个点云的纵坐标，X为重心位置的横坐标，Y为重心位置的纵坐标。
比如：当安全区域中的点云总数为3时，第1个点云的坐标为 (X1,Y1)，第2个点云的坐标为(X2,Y2)，第3个点云的坐标为(X3,Y3)，此时，飞控系统提取安全区域中每个点云的坐标，即分别提取第1个点云的坐标(X1,Y1)、第2个点云的坐标(X2,Y2)和第3个点云的坐标(X3,Y3)，然后飞控系统根据所提取的第1个点云的坐标(X1,Y1)、第2个点云的坐标(X2,Y2)和第3个点云的坐标(X3,Y3)来计算安全区域的重心位置，其中，安全区域的重心位置的横坐标
Figure PCTCN2019126715-appb-000004
安全区域的重心位置的纵坐标
Figure PCTCN2019126715-appb-000005
进一步地，当待降落区域中的障碍物相对于无人机100中心对称时，所确定的安全区域的重心位置与待降落区域的中心位置一致，导致无人机无法闪避障碍物，故为了防止安全区域的重心位置与待降落区域的中心位置一致的情况出现，在确定了目标位置后，飞控系统还需要确定待降落区域的中心位置，判断目标位置与待降落区域的中心位置是否一致，若目标位置与待降落区域的中心位置不一致，则控制无人机100移动至目标位置；若目标位置与待降落区域的中心位置一致，则重新确定目标位置。
在本发明的一实施例中，控制无人机100移动至目标位置具体包括：飞控系统确定目标位置所在的方向为第一目标方向后，控制无人机100沿第一目标方向移动至目标位置。
其中，为了防止无人机100移动至目标位置的过程中碰撞到障碍物，在控制无人机100沿第一目标方向移动至目标位置之前，飞控系统通过感知传感器确定第一目标方向是否存在障碍物，若不存在障碍物才控制无人机100沿第一目标方向移动至目标位置。
当感知传感器为单向感知传感器时，飞控系统控制单向感知传感器的感知方向与第一目标方向一致，具体包括：飞控系统控制无人机100的飞行方向朝向第一目标方向。由于单向感知传感器的感知方向与飞行方向一致，故能够通过控制无人机100的飞行方向朝向第一目标方向而实现控制单向感知传感器的感知方向与第一目标方向一致。
在本发明的一实施例中，重新确定目标位置包括：飞控系统确定待 降落区域中不存在障碍物的方向为第二目标方向，然后控制无人机100沿第二目标方向移动预设距离后，在安全区域中确定目标位置。
其中，飞控系统通过感知传感器确定第二目标方向。
预设距离与第二目标方向以及待降落区域的大小相关，若第二目标方向为待降落区域的宽度方向，则预设距离为待降落区域的半宽；若第二目标方向为待降落区域的长度方向，则预设距离为待降落区域的半长，以保证无人机100沿第二目标方向移动预设距离后，能够离开该待降落区域，在新的安全区域中确定目标位置。
进一步地，当无人机移动至目标位置之后，飞控系统确定以目标位置为中心的待降落区域是否存在危险区域，若存在，则在以目标位置为中心的待降落区域中确定目标位置；若不存在，则控制无人机降落。
在本发明的一实施例中，若确定在以目标位置为中心的待降落区域中确定目标位置的次数超过第一预设阈值，则控制无人机发出警告和/或控制无人机停止降落。
优选地，第一预设阈值为预先设置的固定值，该第一预设阈值的取值范围在3-5之间，包括3和5两个端点数值。
在本发明实施例中，通过在待降落区域的安全区域中确定目标位置，并控制无人机移动至目标位置，使得无人机能够向待降落区域的安全区域移动，且由于安全区域是不存在障碍物的区域，故无人机向安全区域移动时，即实现了对障碍物的闪避，减少无人机坠毁的风险。
实施例二
请参阅图2，是本发明其中一实施例提供的一种无人机降落避障方法的流程示意图，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，用于闪避待降落区域中的障碍物，减少无人机坠毁的风险，该无人机降落避障方法包括：
S100：获取待降落区域的点云分布图。
上述“待降落区域”为无人机准备降落的区域，无人机位于该待降 落区域的中心。
上述“点云分布图”则为能够反映待降落区域的点云分布情况的示意图。
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：通过无人机的深度传感器获取待降落区域的点云分布图。
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、结构光相机和激光雷达。
深度传感器用于采集待降落区域的点云数据，每一个点云数据包含有三维坐标，有些可能含有颜色信息或者反射强度信息，通过点云数据能够获得深度传感器与待降落区域物体的距离。
此时，通过深度传感器获取待降落区域的点云分布图具体包括：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。
S200：根据所述点云分布图确定所述待降落区域中的安全区域。
待降落区域包括安全区域和危险区域。其中，危险区域是指存在障碍物的区域，该障碍物包括：倾斜坡面、水面、灌木丛、凸起的异物以及楼顶、悬崖、深沟等表面平整区域的边缘空缺区域；安全区域是指不存在障碍物的区域，即为待降落区域除去存在障碍物的危险区域后的区域。
在本发明的一实施例中，根据点云分布图确定待降落区域中的安全区域能够通过平面检测法，也能够通过空缺区域检测法。
具体地，当通过平面检测法确定待降落区域中的安全区域时，提取点云分布图中的特征点确定平面后，将点云均位于平面内的区域确定为安全区域。
当通过空缺区域检测法确定待降落区域中的安全区域时，在待降落区域的点云分布图中划分检测区域，将检测区域划分为至少两个指定区域后，对每一个指定区域中的点云数量进行检测，将点云数量不小于阈值的指定区域确定为安全区域。
当然，在一些实施例中，还能够将平面检测法和空缺区域检测法结 合后确定待降落区域中的安全区域，提高确定安全区域的精确度。
S400：在所述安全区域中确定目标位置。
上述“目标位置”为安全区域中能够使无人机远离障碍物的位置，也即无人机即将移动到的位置。
请参阅图3，在本发明的一实施例中，在所述安全区域中确定目标位置具体包括：
S410：确定所述安全区域的重心位置；
S420：将所述安全区域的重心位置确定为所述目标位置。
其中，确定安全区域的重心位置具体包括：提取安全区域中每个点云的坐标；根据每个点云的坐标确定安全区域的重心位置，该安全区域的重心位置为：
Figure PCTCN2019126715-appb-000006
其中，n为安全区域中的点云总数，Xi为安全区域中第i个点云的横坐标，Yi为安全区域中第i个点云的纵坐标，X为重心位置的横坐标，Y为重心位置的纵坐标。
比如：当安全区域中的点云总数为3时，第1个点云的坐标为(X1,Y1)，第2个点云的坐标为(X2,Y2)，第3个点云的坐标为(X3,Y3)，此时，飞控系统提取安全区域中每个点云的坐标，即分别提取第1个点云的坐标(X1,Y1)、第2个点云的坐标(X2,Y2)和第3个点云的坐标(X3,Y3)，然后飞控系统根据所提取的第1个点云的坐标(X1,Y1)、第2个点云的坐标(X2,Y2)和第3个点云的坐标(X3,Y3)来计算安全区域的重心位置，其中，安全区域的重心位置的横坐标
Figure PCTCN2019126715-appb-000007
安全区域的重心位置的纵坐标
Figure PCTCN2019126715-appb-000008
由于安全区域是待降落区域除去危险区域后的区域，在障碍物不相对待降落区域的中心位置对称的情况下，安全区域的重心位置偏离待降落区域的中心位置，故将安全区域的重心位置确定为目标位置时，能够使得移动至目标位置的无人机远离障碍物。
S800：控制所述无人机移动至所述目标位置，以使所述无人机远离所述待降落区域中的障碍物。
请参阅图4，在本发明的一实施例中，控制无人机移动至目标位置具体包括：
S810：确定所述目标位置所在的方向为第一目标方向；
S820：确定所述第一目标方向是否存在障碍物；
S830：若否，则控制所述无人机沿所述第一目标方向移动至所述目标位置。
其中，通过感知传感器确定第一目标方向是否存在障碍物。
当感知传感器为单向感知传感器时，控制单向感知传感器的感知方向与第一目标方向一致，具体包括：控制无人机的飞行方向朝向第一目标方向。由于单向感知传感器的感知方向与飞行方向一致，故能够通过控制无人机的飞行方向朝向第一目标方向而实现控制单向感知传感器的感知方向与第一目标方向一致。
请参阅图5，当待降落区域中的障碍物相对于无人机中心对称时，所确定的安全区域的重心位置与待降落区域的中心位置一致，导致无人机无法闪避障碍物，故为了防止安全区域的重心位置与待降落区域的中心位置一致的情况出现，在本发明的另一实施例中，步骤S800之前还包括：
S500：确定所述待降落区域的中心位置；
S600：判断所述目标位置与所述待降落区域的中心位置是否一致，若是，则执行步骤S700；若否，则执行步骤S800；
S700：重新确定目标位置。
其中，重新确定目标位置包括：确定待降落区域中不存在障碍物的方向为第二目标方向；控制无人机沿第二目标方向移动预设距离后，在安全区域中确定目标位置。
能够通过感知传感器确定第二目标方向。
预设距离与第二目标方向以及待降落区域的大小相关，若第二目标方向为待降落区域的宽度方向，则预设距离为待降落区域的半宽；若第 二目标方向为待降落区域的长度方向，则预设距离为待降落区域的半长，以保证无人机100沿第二目标方向移动预设距离后，能够离开该待降落区域，在新的安全区域中确定目标位置。
请参阅图6，在本发明的另一实施例中，步骤S800之后还包括：
S900：确定以所述目标位置为中心的待降落区域是否存在危险区域，
若不存在，则控制所述无人机降落；
若存在，则在所述以所述目标位置为中心的待降落区域中确定目标位置。
其中，确定待降落区域是否存在危险区域时，能够通过平面检测法进行确定，也能够通过空缺区域检测法进行确定。
当通过平面检测法确定待降落区域中是否存在危险区域时，提取点云分布图中的特征点确定平面后，将点云位于平面外的区域确定为危险区域。
当通过空缺区域检测法确定待降落区域中是否存在危险区域时，在待降落区域的点云分布图中划分检测区域，将检测区域划分为至少两个指定区域后，对每一个指定区域中的点云数量进行检测，将点云数量小于阈值的指定区域确定为危险区域。
当然，在一些实施例中，还能够将平面检测法和空缺区域检测法结合后确定待降落区域中的安全区域，提高确定安全区域的精确度。
进一步地，确定在所述以所述目标位置为中心的待降落区域中确定目标位置的次数是否超过第一预设阈值，若是，则控制所述无人机发出警告和/或控制所述无人机停止降落。
优选地，第一预设阈值为预先设置的固定值，该第一预设阈值的取值范围在3-5之间，包括3和5两个端点数值。
请参阅图7，在本发明的另一实施例中，为了防止安全区域过小而造成无人机降落后仍出现坠毁的情况，步骤S400之前还包括：
S300：判断所述安全区域的点云数量与所述待降落区域的点云数量的比值R1是否大于第二预设阈值，若是，则执行步骤S400。
其中，第二预设阈值为预先设置的固定值，该第二预设阈值的取值范围为10％-30％，包括10％和30％两个端点数值。
当然，在一些可替代实施方式中，第二预设阈值与无人机100的投影区域面积相关，能够将无人机100的投影区域面积与待降落区域面积的比值确定为第二预设阈值。
在本发明实施例中，通过在待降落区域的安全区域中确定目标位置，并控制无人机移动至目标位置，使得无人机能够向待降落区域的安全区域移动，且由于安全区域是不存在障碍物的区域，故无人机向安全区域移动时，即实现了对障碍物的闪避，减少无人机坠毁的风险。
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8，是本发明其中一实施例提供的一种无人机降落避障装置，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，用于闪避待降落区域中的障碍物，减少无人机坠毁的风险，该无人机降落避障装置包括：
获取模块200，所述获取模块200用于获取待降落区域的点云分布图；
确定模块300，所述确定模块300用于根据所述点云分布图确定所述待降落区域中的安全区域；以及
用于在所述安全区域中确定目标位置；
控制模块400，所述控制模块400用于控制所述无人机移动至所述目标位置，以使所述无人机远离所述待降落区域中的障碍物。
其中，获取模块200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。
进一步地，获取模块200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。
进一步地，确定模块300具体用于：
确定所述安全区域的重心位置；
将所述安全区域的重心位置确定为所述目标位置。
进一步地，确定模块300还用于：
提取所述安全区域中每个点云的坐标；
根据所述每个点云的坐标确定所述安全区域的重心位置为：
Figure PCTCN2019126715-appb-000009
其中，n为所述安全区域中的点云总数，Xi为所述安全区域中第i个点云的横坐标，Yi为所述安全区域中第i个点云的纵坐标，X为所述重心位置的横坐标，Y为所述重心位置的纵坐标。
进一步地，控制模块400具体用于：
确定所述目标位置所在的方向为第一目标方向；
控制所述无人机沿所述第一目标方向移动至所述目标位置。
进一步地，控制模块400还用于：
确定所述第一目标方向是否存在障碍物，若否，则控制所述无人机沿所述第一目标方向移动至所述目标位置。
进一步地，控制模块400通过感知传感器确定所述第一目标方向是否存在障碍物。
进一步地，感知传感器为单向传感器时，所述控制模块400还用于：
控制所述单向感知传感器的感知方向与所述第一目标方向一致。
进一步地，确定模块300还用于：
确定所述待降落区域的中心位置；
判断所述目标位置与所述待降落区域的中心位置是否一致，若是，则重新确定目标位置。
进一步地，确定模块300还用于：
确定待降落区域中不存在障碍物的方向为第二目标方向；
控制所述无人机沿所述第二目标方向移动预设距离后，在所述安全区域中确定目标位置。
进一步地，控制模块400还用于：
确定以所述目标位置为中心的待降落区域是否存在危险区域，
若不存在，则控制所述无人机降落；
若存在，则在所述以所述目标位置为中心的待降落区域中确定目标位置。
进一步地，控制模块400还用于：
确定在所述以所述目标位置为中心的待降落区域中确定目标位置的次数是否超过第一预设阈值，若是，则控制所述无人机发出警告和/或控制所述无人机停止降落。
进一步地，确定模块300还用于：
确定所述安全区域的点云数量和所述待降落区域的点云数量的比值R1；
判断所述R1是否大于第二预设阈值，若是，则在所述安全区域中确定目标位置。
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；上述确定模块300、控制模块400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安全区域中确定目标位置，并控制无人机移动至目标位置，使得无人机能够向待降落区域的安全区域移动，且由于安全区域是不存在障碍物的区域，故无人机向安全区域移动时，即实现了对障碍物的闪避，减少无人机坠毁的风险。
实施例四
请参阅图9，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，本发明实施例提供的硬件模块能够集成于上述实施例所述的飞控系统，也能够直接作为飞控系统设置于机身10内，使得无人机100能够执行以上实施例所述的一种无人机降落避障方法，还能实现以上实施例所述的一种无人机降落避障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9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9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降落避障方法对应的程序指令以及一种无人机降落避障装置对应的模块(例如，获取模块200、确定模块300和控制模块400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降落避障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降落避障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降落避障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，包括第一预设阈值、第二预设阈值、预设距离等。
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降落避障方法的各个步骤，或者，实现上述任意装置实施例中的一种无人机降落避障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9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降落避障方法的各个步骤，或者，实现上述任意装置实施例中的一种无人机降落避障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9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降落避障方法的各个步骤，或者，实现上述任意装置实施例中的一种无人机降落避障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 (30)

  1. 一种无人机降落避障方法，其特征在于，所述方法包括：
    获取待降落区域的点云分布图；
    根据所述点云分布图确定所述待降落区域中的安全区域；
    在所述安全区域中确定目标位置；
    控制所述无人机移动至所述目标位置，以使所述无人机远离所述待降落区域中的障碍物。
  2. 根据权利要求1所述的方法，其特征在于，所述获取待降落区域的点云分布图，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。
  4. 根据权利要求1-3中任一项所述的方法，其特征在于，所述在所述安全区域中确定目标位置，包括：
    确定所述安全区域的重心位置；
    将所述安全区域的重心位置确定为所述目标位置。
  5. 根据权利要求4所述的方法，其特征在于，所述确定所述安全区域的重心位置，包括：
    提取所述安全区域中每个点云的坐标；
    根据所述每个点云的坐标确定所述安全区域的重心位置为：
    Figure PCTCN2019126715-appb-100001
    其中，n为所述安全区域中的点云总数，Xi为所述安全区域中第i个点云的横坐标，Yi为所述安全区域中第i个点云的纵坐标，X为所述重心位置的横坐标，Y为所述重心位置的纵坐标。
  6. 根据权利要求1-5中任一项所述的方法，其特征在于，所述控制所述无人机移动至所述目标位置，包括：
    确定所述目标位置所在的方向为第一目标方向；
    控制所述无人机沿所述第一目标方向移动至所述目标位置。
  7. 根据权利要求6所述的方法，其特征在于，所述控制所述无人机沿所述第一目标方向移动至所述目标位置之前，所述方法还包括：
    确定所述第一目标方向是否存在障碍物，若否，则控制所述无人机沿所述第一目标方向移动至所述目标位置。
  8. 根据权利要求7所述的方法，其特征在于，通过感知传感器确定所述第一目标方向是否存在障碍物。
  9. 根据权利要求8所述的方法，其特征在于，所述感知传感器为单向感知传感器，所述方法还包括：
    控制所述单向感知传感器的感知方向与所述第一目标方向一致。
  10. 根据权利要求1-9中任一项所述的方法，其特征在于，所述控制所述无人机移动至所述目标位置之前，所述方法还包括：
    确定所述待降落区域的中心位置；
    判断所述目标位置与所述待降落区域的中心位置是否一致，若是，则重新确定目标位置。
  11. 根据权利要求10所述的方法，其特征在于，所述重新确定目标位置，包括：
    确定待降落区域中不存在障碍物的方向为第二目标方向；
    控制所述无人机沿所述第二目标方向移动预设距离后，在所述安全区域中确定目标位置。
  12. 根据权利要求1-11中任一项所述的方法，其特征在于，所述控制所述无人机移动至所述目标位置之后，所述方法还包括：
    确定以所述目标位置为中心的待降落区域是否存在危险区域，
    若不存在，则控制所述无人机降落；
    若存在，则在所述以所述目标位置为中心的待降落区域中确定目标位置。
  13. 根据权利要求12所述的方法，其特征在于，所述方法还包括：
    确定在所述以所述目标位置为中心的待降落区域中确定目标位置的次数是否超过第一预设阈值，若是，则控制所述无人机发出警告和/或控制所述无人机停止降落。
  14. 根据权利要求1-13中任一项所述的方法，其特征在于，所述在所述安全区域中确定目标位置之前，所述方法还包括：
    确定所述安全区域的点云数量与所述待降落区域的点云数量的比值R1；
    判断所述R1是否大于第二预设阈值，若是，则在所述安全区域中确定目标位置。
  15. 一种无人机降落避障装置，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；
    确定模块，所述确定模块用于根据所述点云分布图确定所述待降落区域中的安全区域；以及
    用于在所述安全区域中确定目标位置；
    控制模块，所述控制模块用于控制所述无人机移动至所述目标位置，以使所述无人机远离所述待降落区域中的障碍物。
  16. 根据权利要求15所述的装置，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。
  17. 根据权利要求16所述的装置，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。
  18. 根据权利要求15-17中任一项所述的装置，其特征在于，所述确定模块用于：
    确定所述安全区域的重心位置；
    将所述安全区域的重心位置确定为所述目标位置。
  19. 根据权利要求18所述的装置，其特征在于，所述确定模块还用于：
    提取所述安全区域中每个点云的坐标；
    根据所述每个点云的坐标确定所述安全区域的重心位置为：
    Figure PCTCN2019126715-appb-100002
    其中，n为所述安全区域中的点云总数，Xi为所述安全区域中第i个点云的横坐标，Yi为所述安全区域中第i个点云的纵坐标，X为所述重心位置的横坐标，Y为所述重心位置的纵坐标。
  20. 根据权利要求15-19中任一项所述的装置，其特征在于，所述控制模块用于：
    确定所述目标位置所在的方向为第一目标方向；
    控制所述无人机沿所述第一目标方向移动至所述目标位置。
  21. 根据权利要求20所述的装置，其特征在于，所述控制模块还用于：
    确定所述第一目标方向是否存在障碍物，若否，则控制所述无人机沿所述第一目标方向移动至所述目标位置。
  22. 根据权利要求21所述的装置，其特征在于，所述控制模块通过感知传感器确定所述第一目标方向是否存在障碍物。
  23. 根据权利要求22所述的装置，其特征在于，所述感知传感器为单向传感器，所述控制模块还用于：
    控制所述单向感知传感器的感知方向与所述第一目标方向一致。
  24. 根据权利要求15-23中任一项所述的装置，其特征在于，所述确定模块还用于：
    确定所述待降落区域的中心位置；
    判断所述目标位置与所述待降落区域的中心位置是否一致，若是，则重新确定目标位置。
  25. 根据权利要求24所述的装置，其特征在于，所述确定模块还用于：
    确定待降落区域中不存在障碍物的方向为第二目标方向；
    控制所述无人机沿所述第二目标方向移动预设距离后，在所述安全区域中确定目标位置。
  26. 根据权利要求15-25中任一项所述的装置，其特征在于，所述控制模块还用于：
    确定以所述目标位置为中心的待降落区域是否存在危险区域，
    若不存在，则控制所述无人机降落；
    若存在，则在所述以所述目标位置为中心的待降落区域中确定目标位置。
  27. 根据权利要求26所述的装置，其特征在于，所述控制模块还用于：
    确定在所述以所述目标位置为中心的待降落区域中确定目标位置的次数是否超过第一预设阈值，若是，则控制所述无人机发出警告和/或控制所述无人机停止降落。
  28. 根据权利要求15-27中任一项所述的装置，其特征在于，所述确定模块还用于：
    确定所述安全区域的点云数量与所述待降落区域的点云数量的比值R1；
    判断所述R1是否大于第二预设阈值，若是，则在所述安全区域中确定目标位置。
  29. 一种无人机，其特征在于，包括：
    机身；
    机臂，与所述机身相连；
    动力装置，设于所述机臂；
    至少一个处理器，设于所述机身内；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1-14中任一项所述的无人机降落避障方法。
  30. 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1-14中任一项所述的无人机降落避障方法。
PCT/CN2019/126715 2018-12-20 2019-12-19 一种无人机降落避障方法、装置及无人机 WO2020125725A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/352,721 US20220055748A1 (en) 2018-12-20 2021-06-21 Obstacle avoidance method and apparatus for unmanned aerial vehicle landing, and unmanned aerial vehilce

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811563918.1 2018-12-20
CN201811563918.1A CN109739256B (zh) 2018-12-20 2018-12-20 一种无人机降落避障方法、装置及无人机

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/352,721 Continuation US20220055748A1 (en) 2018-12-20 2021-06-21 Obstacle avoidance method and apparatus for unmanned aerial vehicle landing, and unmanned aerial vehilce

Publications (1)

Publication Number Publication Date
WO2020125725A1 true WO2020125725A1 (zh) 2020-06-25

Family

ID=66360820

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/126715 WO2020125725A1 (zh) 2018-12-20 2019-12-19 一种无人机降落避障方法、装置及无人机

Country Status (3)

Country Link
US (1) US20220055748A1 (zh)
CN (2) CN114706405A (zh)
WO (1) WO2020125725A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116859953A (zh) * 2023-08-14 2023-10-10 北京小米机器人技术有限公司 机器人的控制方法、装置、介质及机器人

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114706405A (zh) * 2018-12-20 2022-07-05 深圳市道通智能航空技术股份有限公司 一种无人机降落避障方法、装置及无人机
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
CN110503040B (zh) * 2019-08-23 2022-05-27 斯坦德机器人（深圳）有限公司 障碍物检测方法及装置
CN112585553A (zh) * 2020-02-26 2021-03-30 深圳市大疆创新科技有限公司 用于可移动平台的控制方法、可移动平台、设备和存储介质
CN113448345B (zh) * 2020-03-27 2023-04-28 北京三快在线科技有限公司 一种无人机降落方法及装置
US11994407B2 (en) * 2020-07-31 2024-05-28 Aurora Flight Sciences Corporation, a subsidiary of The Boeing Company Evaluation of a ground region for landing a robot
CN112859893A (zh) * 2021-01-08 2021-05-28 中国商用飞机有限责任公司北京民用飞机技术研究中心 一种飞行器避障方法、装置
CN112906479B (zh) * 2021-01-22 2024-01-26 成都纵横自动化技术股份有限公司 一种无人机辅助降落方法及其系统
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 (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105204515A (zh) * 2015-08-27 2015-12-30 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
CN105700551A (zh) * 2016-01-27 2016-06-22 浙江大华技术股份有限公司 无人机降落区域确定方法、无人机降落方法及相关装置
CN105787192A (zh) * 2016-03-15 2016-07-20 联想(北京)有限公司 一种信息处理方法及飞行器
US20160378121A1 (en) * 2015-06-25 2016-12-29 Bell Helicopter Textron Inc. Landing aircrafts with optimal landing spot selection
US20170076616A1 (en) * 2015-09-11 2017-03-16 Qualcomm Incorporated Unmanned aerial vehicle obstacle detection and avoidance
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
CN109739256A (zh) * 2018-12-20 2019-05-10 深圳市道通智能航空技术有限公司 一种无人机降落避障方法、装置及无人机

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE602007012321D1 (de) * 2007-11-07 2011-03-10 Tele Atlas Bv Verfahren und anordnung zur abbildung von entfernungssensordaten auf bildsensordaten
US8600589B2 (en) * 2012-04-24 2013-12-03 Exelis, Inc. Point cloud visualization of acceptable helicopter landing zones based on 4D LIDAR
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
US10029804B1 (en) * 2015-05-14 2018-07-24 Near Earth Autonomy, Inc. On-board, computerized landing zone evaluation system for aircraft
US9947232B2 (en) * 2015-12-08 2018-04-17 Honeywell International Inc. Methods and apparatus for identifying terrain suitable for aircraft landing
US10121117B1 (en) * 2016-09-08 2018-11-06 Amazon Technologies, Inc. Drone location signature filters
CN106772435B (zh) * 2016-12-12 2019-11-19 浙江华飞智能科技有限公司 一种无人机避障方法和装置
US11017679B2 (en) * 2017-01-13 2021-05-25 Skydio, Inc. Unmanned aerial vehicle visual point cloud navigation
FR3062720B1 (fr) * 2017-02-08 2019-03-15 Airbus Helicopters Systeme et procede d'aide a l'atterrissage d'un aeronef, et aeronef correspondant
CN107990876A (zh) * 2017-11-20 2018-05-04 北京科技大学 基于无人飞行器的地下矿山采空区快速扫描装置及方法
WO2019113966A1 (zh) * 2017-12-15 2019-06-20 深圳市道通智能航空技术有限公司 一种避障方法、装置和无人机

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160378121A1 (en) * 2015-06-25 2016-12-29 Bell Helicopter Textron Inc. Landing aircrafts with optimal landing spot selection
CN105204515A (zh) * 2015-08-27 2015-12-30 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
US20170076616A1 (en) * 2015-09-11 2017-03-16 Qualcomm Incorporated Unmanned aerial vehicle obstacle detection and avoidance
CN105700551A (zh) * 2016-01-27 2016-06-22 浙江大华技术股份有限公司 无人机降落区域确定方法、无人机降落方法及相关装置
CN105787192A (zh) * 2016-03-15 2016-07-20 联想(北京)有限公司 一种信息处理方法及飞行器
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
CN109739256A (zh) * 2018-12-20 2019-05-10 深圳市道通智能航空技术有限公司 一种无人机降落避障方法、装置及无人机

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116859953A (zh) * 2023-08-14 2023-10-10 北京小米机器人技术有限公司 机器人的控制方法、装置、介质及机器人

Also Published As

Publication number Publication date
US20220055748A1 (en) 2022-02-24
CN109739256B (zh) 2022-04-19
CN109739256A (zh) 2019-05-10
CN114706405A (zh) 2022-07-05

Similar Documents

Publication Publication Date Title
WO2020125725A1 (zh) 一种无人机降落避障方法、装置及无人机
WO2020125726A1 (zh) 一种无人机自主降落方法、装置及无人机
US11693428B2 (en) Methods and system for autonomous landing
JP7456537B2 (ja) 飛行体制御装置、飛行体制御方法、及びプログラム
WO2021013110A1 (zh) 一种基于目标跟踪的无人机避障方法、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
TWI817962B (zh) 基於環境的可預測性的可調整的物件避開接近度閾值的方法、機器人式運載工具及處理設備
WO2018094583A1 (zh) 无人机避障控制方法、飞行控制器及无人飞行器
WO2018218516A1 (zh) 无人机返航路径规划方法及装置
GB2557715A (en) Unmanned aerial vehicles
WO2020143576A1 (zh) 调整机载雷达的主探测方向的方法、装置和无人机
WO2019119199A1 (zh) 无人机的控制方法、控制装置、无人机及农业无人机
WO2021037071A1 (zh) 一种飞行控制方法及相关装置
WO2021237462A1 (zh) 无人飞行器的限高方法、装置、无人飞行器及存储介质
US20220221879A1 (en) Moving body, control method, and program
WO2021056139A1 (zh) 获取降落位置的方法、设备、无人机、系统及存储介质
CN106354148A (zh) 一种无人机飞行控制方法和装置
EP3728043B1 (en) Water surface detection method, unmanned aerial vehicle landing method and unmanned aerial vehicle
WO2021146973A1 (zh) 无人机返航的控制方法、设备、可移动平台和存储介质
US20230095700A1 (en) Vehicle flight control method and apparatus for unmanned aerial vehicle, and unmanned aerial vehicle
WO2020107248A1 (zh) 一种无人机的安全降落方法、装置、无人机及介质
Priambodo et al. A Vision and GPS Based System for Autonomous Precision Vertical Landing of UAV Quadcopter
WO2019071444A1 (zh) 一种摄像装置的转动控制方法、控制设备以及飞行器
WO2022104746A1 (zh) 返航控制方法、装置、无人机及计算机可读存储介质
Jhan et al. Development of low-cost camera-based UAV control strategy

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: 19900754

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: 19900754

Country of ref document: EP

Kind code of ref document: A1