WO2020103034A1 - 一种无人机路径规划方法、装置及无人机 - Google Patents

一种无人机路径规划方法、装置及无人机

Info

Publication number
WO2020103034A1
WO2020103034A1 PCT/CN2018/116701 CN2018116701W WO2020103034A1 WO 2020103034 A1 WO2020103034 A1 WO 2020103034A1 CN 2018116701 W CN2018116701 W CN 2018116701W WO 2020103034 A1 WO2020103034 A1 WO 2020103034A1
Authority
WO
WIPO (PCT)
Prior art keywords
drone
flight direction
path planning
map
uav
Prior art date
Application number
PCT/CN2018/116701
Other languages
English (en)
French (fr)
Inventor
黄金鑫
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
Priority to CN202410357193.XA priority Critical patent/CN118259692A/zh
Priority to PCT/CN2018/116701 priority patent/WO2020103034A1/zh
Priority to EP18940701.8A priority patent/EP3876070B1/en
Priority to CN201880099092.XA priority patent/CN112912811B/zh
Publication of WO2020103034A1 publication Critical patent/WO2020103034A1/zh
Priority to US17/322,135 priority patent/US12025996B2/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
    • G05D1/40—Control within particular dimensions
    • G05D1/49—Control of attitude, i.e. control of roll, pitch or yaw
    • 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
    • G05D1/60—Intended control result
    • G05D1/606—Compensating for or utilising external environmental conditions, e.g. wind or water currents
    • 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
    • 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
    • G05D1/40—Control within particular dimensions
    • G05D1/46—Control of position or course in three dimensions
    • 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
    • G05D1/60—Intended control result
    • G05D1/652—Take-off
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/50—Depth or shape recovery
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G5/00—Traffic control systems for aircraft, e.g. air-traffic control [ATC]
    • G08G5/0017—Arrangements for implementing traffic-related aircraft activities, e.g. arrangements for generating, displaying, acquiring or managing traffic information
    • G08G5/0021—Arrangements for implementing traffic-related aircraft activities, e.g. arrangements for generating, displaying, acquiring or managing traffic information located in the aircraft
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G5/00—Traffic control systems for aircraft, e.g. air-traffic control [ATC]
    • G08G5/003—Flight plan management
    • G08G5/0039—Modification of a flight plan
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G5/00—Traffic control systems for aircraft, e.g. air-traffic control [ATC]
    • G08G5/0047—Navigation or guidance aids for a single aircraft
    • G08G5/0052—Navigation or guidance aids for a single aircraft for cruising
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G5/00—Traffic control systems for aircraft, e.g. air-traffic control [ATC]
    • G08G5/0047—Navigation or guidance aids for a single aircraft
    • G08G5/0069—Navigation or guidance aids for a single aircraft specially adapted for an unmanned aircraft
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G5/00—Traffic control systems for aircraft, e.g. air-traffic control [ATC]
    • G08G5/0073—Surveillance aids
    • G08G5/0086—Surveillance aids for monitoring terrain
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G5/00—Traffic control systems for aircraft, e.g. air-traffic control [ATC]
    • G08G5/04—Anti-collision systems
    • G08G5/045—Navigation or guidance aids, e.g. determination of anti-collision manoeuvers
    • 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
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D2101/00—Details of software or hardware architectures used for the control of position
    • G05D2101/10—Details of software or hardware architectures used for the control of position using artificial intelligence [AI] techniques
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D2109/00—Types of controlled vehicles
    • G05D2109/20—Aircraft, e.g. drones
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes

Definitions

  • the embodiments of the present application relate to the field of robot control technology, and in particular, to a UAV path planning method, device, and UAV.
  • UAV is an unmanned aerial vehicle operated by radio remote control equipment or its own program control device.
  • UAV-related technologies and the complex changes in application scenarios the requirements for UAV automatic perception capabilities and path planning algorithms are becoming higher and higher, especially in the autonomous flight technology of UAVs, UAV By perceiving its own motion state and surrounding environment, combined with path planning algorithm, it can reach the target point safely and without collision in the environment with obstacles, avoiding collision and bombing.
  • unmanned aerial vehicles commonly use global path planning methods to obtain better flight paths to prevent the UAV from colliding with obstacles during flight.
  • the global path planning method is only applicable to the static environment, and it is impossible to accurately judge the obstacles existing in the unknown environment and the dynamic environment, and the real-time performance cannot be guaranteed.
  • the embodiments of the present application aim to provide a UAV path planning method, device, and unmanned aerial vehicle, which can accurately judge obstacles suddenly appearing in an unknown environment and a dynamic environment, and realize real-time path planning.
  • a technical solution adopted by the embodiments of the present application is to provide a path planning method for an unmanned aerial vehicle.
  • the method includes:
  • the drone is controlled to fly along the optimal flight direction to avoid obstacles in the environment in front of the drone.
  • the acquiring the depth map of the environment in front of the drone includes:
  • the determining the candidate flight direction of the drone according to the grid map includes:
  • the candidate flight direction of the drone is determined according to the passable area.
  • the determining the passable area of the drone according to the raster map includes:
  • the dividing the raster map into the plurality of regions includes:
  • the grid map is divided to obtain the plurality of regions.
  • the coordinates of the sampling obstacle include:
  • the center point coordinates of the grid occupied by the obstacle and / or the corner coordinates of the grid occupied by the obstacle in the sampling grid map are sampled.
  • the method further includes:
  • the grid map is re-divided.
  • the determining the optimal flight direction of the drone in the candidate flight direction includes:
  • the optimal flight direction of the drone among the candidate flight directions is determined according to the cost function.
  • the cost function is:
  • g (direc goal , direc cur ) represents the consistency of one of the candidate flight directions with the target flying direction of the drone
  • g (direc pre , direc cur ) represents the candidate flight
  • the direction is consistent with the optimal flight direction of the previous decision
  • sum represents the number of the passable areas
  • k 1 , k 2 , and k 3 are weight coefficients.
  • the determining the optimal flight direction of the drone in the candidate flight direction according to the cost function includes:
  • the candidate flight direction corresponding to the minimum cost function value is the optimal flight direction of the UAV.
  • the method further includes:
  • the method further includes:
  • the drone is controlled to continue flying along the optimal flight direction.
  • the method before acquiring the grid map centered on the body of the drone according to the depth map, the method further includes:
  • the depth compensation of the depth map includes:
  • row_see tan ⁇ ⁇ f, where ⁇ is the pitch angle of the drone and f is the focal length of the drone camera;
  • the row index of the image plane of the drone on the depth map is determined according to the number of pixel rows of the depth compensation, and the row index row_horizon of the image plane of the drone on the depth map is:
  • row_horizon row_half + row_see, where row_half is half the number of rows in the depth map.
  • the device includes:
  • An acquisition module for acquiring a depth map of the environment in front of the drone.
  • a determination module for determining the candidate flight direction of the drone according to the grid map
  • control module the control module is used to control the drone to fly along the optimal flight direction to avoid obstacles in the environment in front of the drone.
  • the acquisition module acquires the depth map of the environment in front of the drone through a depth sensor.
  • the determination module is specifically used to:
  • the determination module is specifically used to:
  • the area for determining that the coordinate does not fall is the passable area.
  • the determination module is specifically used to:
  • the grid map is divided to obtain the plurality of regions.
  • the determination module is specifically used to:
  • the center point coordinates of the grid occupied by the obstacle and / or the corner coordinates of the grid occupied by the obstacle in the sampling grid map are sampled.
  • the determination module is also used to:
  • the grid map is re-divided.
  • the determination module is specifically used to:
  • the cost function is:
  • g (direc goal , direc cur ) represents the consistency of one of the candidate flight directions with the target flying direction of the drone
  • g (direc pre , direc cur ) represents the candidate flight
  • the direction is consistent with the optimal flight direction of the previous decision
  • sum represents the number of the passable areas
  • k 1 , k 2 , and k 3 are weight coefficients.
  • the determination module is specifically used to:
  • the candidate flight direction corresponding to the minimum cost function value is the optimal flight direction of the UAV.
  • the device further includes:
  • a judging module the judging module is used to judge whether the distance of the drone flying along the optimal flight direction reaches a preset distance
  • the determination module re-determines the optimal flight direction.
  • control module is also used to:
  • the drone is controlled to continue flying along the optimal flight direction.
  • the judgment module is also used to:
  • the device further includes a depth compensation module, which is used to perform depth compensation on the depth map when the drone has a pitch angle.
  • the depth compensation module is specifically used to:
  • row_see tan ⁇ ⁇ f, where ⁇ is the pitch angle of the drone and f is the focal length of the drone camera;
  • the row index of the image plane of the drone on the depth map is determined according to the number of pixel rows of the depth compensation, and the row index row_horizon of the image plane of the drone on the depth map is:
  • row_horizon row_half + row_see, where row_half is half the number of rows in the depth map.
  • a drone including:
  • a machine arm 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 execute the above-mentioned UAV path planning method.
  • another technical solution adopted by the embodiments of the present application is to provide a non-volatile computer-readable storage medium that stores computer-executable instructions.
  • the computer-executable instructions are used to make the UAV execute the above-mentioned UAV path planning method.
  • the beneficial effects of the embodiments of the present application are: different from the prior art, the embodiments of the present application provide a UAV path planning method, device and UAV, the UAV path planning method includes: Depth map of the environment in front of the man-machine, and obtain a grid map centered on the drone according to the depth map; determine the candidate flight direction of the drone according to the grid map, and determine the optimal drone in the candidate flight direction Flight direction; control the drone to fly in the optimal flight direction so that the drone can avoid obstacles in the environment ahead.
  • the depth map of the environment in front of the drone when used to determine the optimal flight direction of the drone to avoid obstacles, since the depth map of the environment in front of the drone can follow the flight process of the drone Real-time reflection of the environment on the flight path of the drone, so obtaining the depth map of the front environment allows the drone to accurately judge the obstacles that suddenly appear in the unknown environment and the dynamic environment. Depth map to determine the optimal flight direction, so that the UAV can adjust the flight path in real time according to the actual flight situation, and realize real-time path planning.
  • FIG. 1 is a schematic structural diagram of a drone provided by an embodiment of the present application.
  • FIG. 2 is a schematic diagram of the principle of performing depth compensation on a depth map in a drone path planning method provided by an embodiment of the present application when the drone has a pitch angle;
  • FIG. 3 is a schematic flowchart of a UAV path planning method provided by an embodiment of the present application.
  • step S400 is a schematic flowchart of step S400 in the method shown in FIG. 3;
  • step S410 in the method shown in FIG. 4;
  • step S500 is a schematic flowchart of step S500 in the method shown in FIG. 3;
  • FIG. 7 is a partial process schematic diagram of a path planning method for a drone provided by another embodiment of the present application.
  • FIG. 8 is a schematic flowchart of a UAV path planning method according to another embodiment of the present application.
  • step S200 is a schematic flowchart of step S200 in the method shown in FIG. 8;
  • FIG. 10 is a schematic structural diagram of a UAV path planning device provided by an embodiment of the present application.
  • FIG. 11 is a schematic structural diagram of a UAV path planning device according to another embodiment of the present application.
  • FIG. 12 is a schematic structural diagram of a UAV path planning device according to another embodiment of the present application.
  • FIG. 13 is a schematic diagram of a hardware structure of a drone provided by an embodiment of the present application.
  • the present application provides a method and device for path planning of an unmanned aerial vehicle.
  • the method and the device are applied to an unmanned aerial vehicle, thereby enabling the unmanned aerial vehicle to suddenly appear in front of obstacles in an unknown environment and a dynamic environment during flight make accurate judgments and plan the optimal flight direction in real time according to the actual flight situation and fly in the optimal flight direction to avoid obstacles.
  • the optimal flight direction refers to the direction without obstacles.
  • the drone in this application may be any suitable type of high-altitude drone or low-altitude drone, including fixed-wing drone, rotary-wing drone, umbrella-wing drone, or flapping-wing drone.
  • FIG. 1 is a drone 100 according to an embodiment of the present application, including a fuselage 10, an arm 20, a power device 30, a depth sensor 40 and a flight control system 50.
  • the arm 20 and the depth sensor 40 are both connected to the fuselage 10, the flight control system 50 is installed in the fuselage 10, and the power device 30 is installed on the arm 20.
  • the power device 30 and the depth sensor 40 are both in communication with the flight control system 50, so that the flight control system 50 can control the flying attitude of the drone 100 through the power device 30, and can also obtain the flight of the drone 100 through the depth sensor 40.
  • the environmental conditions ahead of the path is not limited to the path.
  • the number of arms 20 is four, which are evenly distributed around the fuselage 10 and used to carry the power device 30.
  • the arm 20 may be fixedly connected to the fuselage 10, integrally formed, or foldable or unfoldable relative to the fuselage 10.
  • the power unit 30 is disposed at the end of the arm 20 away from the fuselage 10, and includes a motor provided on the arm 20 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 flying direction of the drone 100 is changed by changing the rotation speed and direction of the propeller.
  • the flight control system 50 can control the flying attitude of the drone 100 by controlling the motor.
  • a power device is provided on the four arms of the drone 100, so that the drone 100 can fly smoothly.
  • the depth sensor 40 is used to collect a depth map (DepthMap) of the environment in front of the drone 100.
  • the depth map is an image or image channel containing information about the surface distance of the scene object of the viewpoint.
  • each The 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 surrounding environment object.
  • the flight control system 50 can obtain the depth map of the environment in front of the drone 100 from the depth sensor 40, that is, the actual distance between the depth sensor 40 and the object in the environment in front The environment in front of the flight path of the human-machine 100.
  • the flight control system 50 communicates with the power device 30 and the depth sensor 40 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 50 is used to execute the drone path planning method described in this application, so that the drone 100 can accurately judge obstacles that suddenly appear in front of the unknown environment and the dynamic environment, and can be based on actual flight The situation plans the optimal flight direction in real time and flies along the optimal flight direction to avoid obstacles.
  • the flight control system 50 obtains the depth map of the environment in front of the drone 100 through the depth sensor 40, and after obtaining the depth map of the environment in front of the drone 100 The flight control system 50 obtains a grid map centered on the body of the drone 100 according to the depth map.
  • the grid map is formed by mapping the depth information in the depth map to a plane grid map centered on the body, where each grid is given a possible value, indicating the probability that the grid is occupied by an obstacle .
  • the obstacle occupies the grid in the grid map, and the position of the obstacle can be known by the coordinates of the occupied grid.
  • the forward view of the drone 100 is no longer horizontal.
  • the depth map collected by the depth sensor 40 is no longer
  • the depth map in front of the drone 100 is horizontal, causing errors in the depth information reflected in the depth map, resulting in an inaccurate grid map. Therefore, before the flight control system 50 obtains a grid map centered on the body of the drone 100 according to the depth map, it is also necessary to determine whether there is a pitch angle of the drone 100. If there is a pitch angle, the flight control system 50 needs to determine the depth After performing depth compensation on the map, a grid map centered on the body of the drone 100 is obtained according to the depth map after depth compensation.
  • the flight control system 50 can measure the three-axis attitude angle of the UAV 100 through an inertial measurement unit (IMU) to determine whether the drone 100 has a pitch angle according to the three-axis attitude angle.
  • IMU inertial measurement unit
  • the inertial measurement unit is integrated in the flight control system 50.
  • the flight control system 50 performing depth compensation on the depth map specifically includes: the flight control system 50 calculates the number of pixel rows for depth compensation, and after calculating the number of pixel rows for depth compensation, determines the UAV's The row index of the image plane on the depth map.
  • row_see tan ⁇ ⁇ f, where ⁇ is the pitch angle of the drone 100, and f is the focal length of the drone camera (depth sensor 40);
  • the row index of the image plane of the drone on the depth map row_horizon is:
  • row_horizon row_half + row_see, where row_half is half the number of rows in the depth map.
  • the compensated depth information is mapped to a plane grid map centered on the body to obtain a grid map centered on the body of the drone 100, and then, the flight control system 50 further Determine the candidate flight direction of the UAV.
  • the flight control system 50 determining the candidate flight direction of the drone according to the grid map specifically includes: the flight control system 50 determines the passable area of the drone 100 according to the grid map, and determines After the passable area of the man-machine 100, the candidate flight direction of the drone 100 is determined according to the passable area.
  • the passable area is an area where no obstacle exists in the grid map
  • the candidate flight direction determined based on the passable area is the direction where there is no obstacle
  • the flight control system 50 determines the directions corresponding to all accessible areas as candidate flight directions.
  • the flight control system 50 determining the accessible area of the drone 100 according to the grid map specifically includes: the flight control system 50 divides the grid map into multiple areas and samples the coordinates of obstacles, The flight control system 50 determines whether the sampled obstacle coordinates fall within the area divided by the grid map, and determines the area where the obstacle coordinates do not fall as a passable area.
  • the flight control system 50 dividing the grid map into multiple areas specifically includes: the flight control system 50 divides the grid map with the center of the grid map as the center and the preset angle as the interval to obtain multiple areas. At this time, each area divided in the raster map is a fan-shaped area.
  • the coordinates of the obstacles sampled by the flight control system 50 specifically include: the coordinates of the center point of the grid occupied by the obstacles and / or the coordinates of the corner points of the grid occupied by the obstacles in the flight control system 50 sampling grid map.
  • the flight control system 50 determines an area where neither the center point coordinates of the grid occupied by obstacles and / or the corner coordinates of the grid occupied by obstacles fall within is a passable area. Based on this, if the area of the raster map is too small, it is easy to appear that the area is covered by obstacles, but none of the sampled coordinates fall into the area. At this time, the impassable area is misjudged as a passable area; If the area of the grid map is too large, it will lead to too few flight directions, which is not conducive to the determination of the optimal flight direction. Therefore, in order to ensure the reliability of the path planning of the flight control system 50, the flight control system 50 will adjust the size of the preset angle according to the actual flight effect.
  • the flight control system 50 adjusts the preset angle according to the robustness of the depth map data and the accuracy of the planned direction.
  • the flight control system 50 is also used to perform the following method: When there is no passable area, the flight control system 50 Re-divide the grid map. Among them, the flight control system 50 takes the center of the grid map as the center and divides the grid map at the adjusted preset angle intervals to obtain multiple areas to determine the passable area.
  • the flight control system 50 determines the optimal flight direction of the drone 100 among the candidate flight directions.
  • the flight control system 50 determining the optimal flight direction of the drone 100 in the candidate flight direction specifically includes: the flight control system 50 calculates a cost function, and determines the candidate flight direction according to the calculated cost function The optimal flight direction of the drone.
  • the calculation of the cost function by the flight control system 50 specifically includes: the flight control system 50 calculates the flight cost of each candidate flight direction determined by the cost function.
  • the flight control system 50 determines the optimal flight direction of the drone 100 among the candidate flight directions according to the cost function. Specifically, it includes determining that the candidate flight direction corresponding to the minimum cost function value is the optimal flight direction of the drone 100.
  • the cost function is:
  • g (direc goal , direc cur ) represents the consistency of one of the candidate flight directions and the target flight direction of the drone 100
  • g (direc pre , direc cur ) represents the candidate flight direction and the previous decision
  • the consistency of the optimal flight direction of , sum represents the number of passable areas
  • k 1 , k 2 and k 3 are the weighting coefficients.
  • the relative sizes of k 1 , k 2 , and k 3 determine the priority order of the three factors. To make the determined candidate flight direction as consistent as possible with the target flight direction, make k 1 > k 2 , k 3 ; if the determined candidate flight direction is as consistent as possible with the optimal flight direction of the previous decision, then make k 2 > k 1 and k 3 ; to ensure that the determined candidate flight direction is sufficiently safe, make k 3 > k 2 and k 1 .
  • the above target flight direction may be determined by a preset target position, or may be determined according to the position of the tracking target.
  • the flight control system 50 controls the drone 100 to fly along the optimal flight direction to avoid obstacles in the environment in front of the drone 100.
  • the flight control system 50 controls the motor to change the rotation speed of the propeller and the rotation direction of the propeller (counterclockwise or clockwise) to change the flight direction of the drone 100, so that the drone 100 flies along the determined optimal flight direction.
  • the flight control system 50 controls the drone 100 to fly in the optimal flight direction
  • the flight control system 50 can also execute the following method: the flight control system 50 determines whether the distance of the drone 100 in the optimal flight direction reaches the preset distance, and if the distance of the drone 100 in the optimal flight direction reaches the pre-set distance Set the distance, the flight control system 50 re-determines the optimal flight direction; if the distance of the drone 100 flying in the optimal flight direction does not reach the preset distance, the flight control system controls the drone 100 to continue flying in the optimal flight direction .
  • the preset distance is the distance between the obstacle and the drone 100 when an obstacle appears in the optimal flight direction of the previous decision.
  • the flight control system 50 controls the flight distance of the drone 100 in the optimal flight direction to reach the distance between the obstacle and the drone 100 in the optimal flight direction of the previous decision, it means that the drone 100 has bypassed Obstacles in the optimal flight direction of the previous decision, at this time, re-determining the optimal flight direction can make the drone 100 approach the optimal flight direction of the previous decision (the optimal flight direction of the previous decision is better than the current decision Optimal flight direction).
  • the drone 100 in the optimal flight direction When the distance controlled by the flight control system 50 to control the drone 100 in the optimal flight direction does not reach the distance between the obstacle and the drone 100 in the optimal flight direction previously determined, it means that the drone 100 has not yet Bypassing the obstacle in the optimal flight direction of the previous decision, at this time, continue to fly in the optimal flight direction, keeping the decision direction unchanged, preventing the drone 100 from changing the flight direction frequently.
  • the optimal flight direction is determined by obtaining a depth map of the environment in front of the drone, so that the drone can accurately judge obstacles that suddenly appear in front of the unknown environment and the dynamic environment during flight , And can adjust the flight route in real time according to the actual flight situation to achieve real-time path planning.
  • a depth sensor may be used to obtain a depth map of the environment in front 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 map (DepthMap) 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. Therefore, obtaining the depth map of the environment in front of the drone through the depth sensor is to obtain the actual distance between the depth sensor and the objects in the front environment.
  • S300 Obtain a grid map centered on the body of the drone according to the depth map.
  • the grid map is formed by dividing the depth map into a series of grids, each grid is given a possible value, which represents the probability that the grid is occupied.
  • the obstacle occupies the grid in the grid map, and the position of the obstacle can be known by the coordinates of the occupied grid.
  • Each grid of the grid map is arranged in a matrix.
  • the grid map is a 10 * 10 matrix.
  • S400 Determine the candidate flight direction of the drone according to the grid map.
  • determining the candidate flight direction of the drone according to the grid map specifically includes:
  • S410 Determine a passable area of the drone according to the grid map, wherein the passable area is an area where there are no obstacles.
  • determining the accessible area of the drone according to the raster map specifically includes:
  • the dividing the grid map into the plurality of areas specifically includes:
  • the grid map is divided to obtain the plurality of regions.
  • each area divided in the raster map is a fan-shaped area.
  • the coordinates of the sampling obstacle specifically include:
  • the center point coordinates of the grid occupied by the obstacle and / or the corner coordinates of the grid occupied by the obstacle in the sampling grid map are sampled.
  • S413 Determine that the area where the coordinates do not fall is the passable area.
  • the area where neither the center coordinate of the grid occupied by the obstacle and / or the corner coordinate of the grid occupied by the obstacle falls within is determined as a passable area. Based on this, if the area of the raster map is too small, it is easy to appear that the area is covered by obstacles, but none of the sampled coordinates fall into the area. At this time, the impassable area is misjudged as a passable area; If the area of the grid map is too large, it will lead to too few flight directions, which is not conducive to the determination of the optimal flight direction. Therefore, in order to ensure the reliability of the path planning, the size of the preset angle is adjusted according to the actual flight effect.
  • the adjustment of the preset angle depends on the robustness of the depth map data and the accuracy of the planning direction.
  • step S420 determine whether there is a passable area, if there is a passable area, perform step S430, if there is no passable area, execute step S440;
  • S430 Determine the candidate flight direction of the drone according to the passable area.
  • the candidate flight directions of the UAV are determined according to the passable area, that is, the directions corresponding to all the passable areas are determined as candidate flight directions.
  • the candidate flight direction determined based on the passable area is the direction where there is no obstacle.
  • the grid map needs to be re-divided, which includes: taking the center of the grid map as the center and dividing the adjusted preset angle as the interval, the grid map is divided to obtain multiple areas to Determine the passable area.
  • S500 Determine the optimal flight direction of the drone among the candidate flight directions.
  • the determining the optimal flight direction of the drone in the candidate flight direction specifically includes:
  • the calculation of the cost function specifically includes: calculating the flight cost of each candidate flight direction determined by the cost function.
  • the cost function is:
  • g (direc goal , direc cur ) represents the consistency of one of the candidate flight directions with the target flying direction of the drone
  • g (direc pre , direc cur ) represents the candidate flight
  • the direction is consistent with the optimal flight direction of the previous decision
  • sum represents the number of accessible areas
  • k 1 , k 2 , and k 3 are the weighting coefficients.
  • the relative sizes of k 1 , k 2 , and k 3 determine the priority order of the three factors. To make the determined candidate flight direction as consistent as possible with the target flight direction, make k 1 > k 2 , k 3 ; if the determined candidate flight direction is as consistent as possible with the optimal flight direction of the previous decision, then make k 2 > k 1 and k 3 ; to ensure that the determined candidate flight direction is sufficiently safe, make k 3 > k 2 and k 1 .
  • the target flight direction may be determined by a preset target position, or may be determined according to the position of the tracking target.
  • S520 Determine the optimal flight direction of the drone in the candidate flight direction according to the cost function.
  • the determining the optimal flight direction of the drone in the candidate flight direction according to the cost function specifically includes: determining the candidate flight direction corresponding to the minimum cost function value as the optimal flight direction of the drone.
  • the above minimum cost function value is the minimum flight cost calculated by the cost function, that is, the candidate flight direction with the smallest flight cost is determined as the optimal flight direction of the drone.
  • S600 Control the drone to fly along the optimal flight direction to avoid obstacles in the environment in front of the drone.
  • the flying direction of the drone is changed by controlling the motor to change the rotation speed of the propeller and the rotation direction of the propeller (counterclockwise or clockwise), so that the drone flies in the determined optimal flight direction.
  • step S600 the method further includes:
  • step S700 Determine whether the flying distance of the drone in the optimal flight direction reaches a preset distance; if yes, perform step S800; if not, perform step 900.
  • S900 Control the drone to continue flying in the optimal flight direction.
  • the preset distance is the distance between the obstacle and the drone when an obstacle appears in the optimal flight direction of the previous decision.
  • the flight distance of the drone in the optimal flight direction reaches the distance between the obstacle and the drone in the optimal flight direction of the previous decision, it means that the drone has bypassed the optimal flight direction of the previous decision
  • re-determining the optimal flight direction can make the UAV approach the optimal flight direction of the previous decision (the optimal flight direction of the previous decision is better than the optimal flight direction of the current decision).
  • the drone in the optimal flight direction does not reach the distance between the obstacle and the drone in the optimal flight direction of the previous decision, it means that the drone has not yet bypassed the optimal decision of the previous decision Obstacles in the flight direction, at this time, continue to fly in the optimal flight direction, keep the decision direction unchanged, prevent the drone from frequently changing the flight direction, and reduce the difficulty of control in the real-time planning process.
  • step S300 the method further includes:
  • S200 Determine whether the drone has a pitch angle, and if so, perform depth compensation on the depth map.
  • the forward view of the drone is no longer horizontal.
  • the depth map collected by the depth sensor is no longer the depth map in front of the drone, making the depth map reflect
  • There is an error in the depth information resulting in an inaccurate grid map. Therefore, it is necessary to perform depth compensation on the depth map when the drone has a pitch angle, and after the depth compensation, obtain the body of the drone according to the depth map after depth compensation Centered raster map.
  • the three-axis attitude angle of the UAV 100 can be measured by the inertial measurement unit to determine whether the drone has a pitch angle according to the three-axis attitude angle.
  • the depth compensation of the depth map specifically includes:
  • row_see tan ⁇ ⁇ f, where ⁇ is the pitch angle of the drone, and f is the focal length of the drone camera (depth sensor);
  • S220 Determine the row index of the image plane of the drone on the depth map according to the number of pixel rows of the depth compensation.
  • the row index row_horizon of the image plane of the drone on the depth map is:
  • row_horizon row_half + row_see, where row_half is half the number of rows in the depth map.
  • the optimal flight direction is determined by obtaining a depth map of the environment in front of the drone, so that the drone can accurately judge obstacles that suddenly appear in front of the unknown environment and the dynamic environment during flight , And can adjust the flight route in real time according to the actual flight situation to achieve real-time path planning.
  • 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. 10 is a drone path planning device provided in one embodiment of the present application.
  • the device is applied to a drone, and the drone is the drone 100 described in the above embodiment, and this
  • the functions of each module of the device provided in the application example are executed by the above-mentioned flight control system 50, and are used to implement real-time path planning.
  • the UAV path planning device includes:
  • a determination module 300 which is used to determine the candidate flight direction of the drone according to the grid map.
  • the control module 400 is used to control the drone to fly in the optimal flight direction to avoid obstacles in the environment in front of the drone.
  • the acquisition module 200 acquires a depth map of the environment in front of the drone through the depth sensor.
  • determination module 300 is specifically used for:
  • determination module 300 is specifically used for:
  • the area for determining that the coordinates do not fall is a passable area.
  • determination module 300 is specifically used for:
  • the grid map is divided to obtain multiple areas.
  • determination module 300 is specifically used for:
  • determination module 300 is also used to:
  • determination module 300 is specifically used for:
  • the cost function is:
  • g (direc goal , direc cur ) represents the consistency of one of the candidate flight directions and the target flight direction of the drone
  • g (direc pre , direc cur ) represents the candidate flight direction and the previous decision Consistency of the optimal flight direction
  • sum represents the number of passable areas
  • k 1 , k 2 , and k 3 are weight coefficients.
  • determination module 300 is specifically used for:
  • the candidate flight direction corresponding to the minimum cost function value is determined as the optimal flight direction of the drone.
  • the UAV path planning device further includes:
  • Judgment module 500 which is used to judge whether the distance of the drone flying along the optimal flight direction reaches the preset distance
  • the determination module 300 re-determines the optimal flight direction.
  • control module 400 is also used to:
  • the drone is controlled to continue flying in the optimal flight direction.
  • judgment module 500 is also used to:
  • the UAV path planning device further includes a depth compensation module 600, which is used to perform depth compensation on the depth map when the drone has a pitch angle.
  • depth compensation module 600 is specifically used for:
  • the number of pixel rows for depth compensation is:
  • row_see tan ⁇ ⁇ f, where ⁇ is the pitch angle of the drone and f is the focal length of the drone camera;
  • the row index of the image plane of the drone on the depth map row_horizon is:
  • row_horizon row_half + row_see, where row_half is half the number of rows in the depth map.
  • the above acquisition module 200 may be a depth sensor to directly acquire the depth map of the environment in front of the drone; the above determination module 300, control module 400, judgment module 500, and depth compensation module 600 may It is a flight control chip.
  • the content of the device embodiment can refer to the method embodiment under the premise that the content does not conflict with each other, and details are not repeated here.
  • the optimal flight direction is determined by obtaining a depth map of the environment in front of the drone, so that the drone can accurately judge obstacles that suddenly appear in front of the unknown environment and the dynamic environment during flight , And can adjust the flight route in real time according to the actual flight situation to achieve real-time path planning.
  • FIG. 13 is a schematic diagram of the hardware structure of an unmanned aerial vehicle provided by one embodiment of the present application.
  • the flight control system 50 is installed in the fuselage 10, so that the drone 100 can execute the drone path planning method described in the above embodiment, and can also implement the drone path planning 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. 13.
  • the processor 110 and the memory 120 may be connected through a bus or in other ways.
  • 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 a drone path in the foregoing embodiments of the present application
  • Program instructions corresponding to the planning method and modules corresponding to a UAV path planning device eg, acquisition module 200, determination module 300, control module 400, etc.
  • the processor 110 executes various functional applications and data processing of a UAV path planning 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 UAV path planning method and the function of each module of the above device embodiments is implemented
  • the memory 120 may include a storage program area and a storage data area, where the storage program area may store an operating system and at least one function required application program; the storage data area may store an application created by using a drone path planning device Data etc.
  • the stored data area also stores preset data, including preset angles 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 remotely disposed relative to the processor 110, and these remote memories may be connected to the processor 110 through a network. Examples of the above 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 each of the methods of a drone path planning method in any of the above method embodiments Step, or, implement the functions of each module of a UAV path planning device in any of the above device embodiments.
  • the above-mentioned products can execute the method provided by the above-mentioned embodiments of the present application, and have functional modules and beneficial effects corresponding to the execution method.
  • functional modules and beneficial effects corresponding to the execution method For technical details that are not described in detail in this embodiment, refer to the method provided in the above embodiments of the present application.
  • Embodiments of the present application also provide a non-volatile computer-readable storage medium that stores computer-executable instructions, which are executed by one or more processors, for example, FIG. 13
  • a processor 110 in may cause the computer to execute the steps of a UAV path planning method in any of the above method embodiments, or implement each of the UAV path planning devices in any of the above device embodiments The function of the module.
  • An embodiment of the present application 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, and when the program instructions are Or executed by multiple processors, such as a processor 110 in FIG. 13, may cause the computer to execute the steps of a UAV path planning method in any of the above method embodiments, or implement any of the above device embodiments A function of each module of a UAV path planning 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 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.
  • a person of ordinary skill in the art may understand that all or part of the processes in the method of the above embodiments can be completed by computer program instructions related hardware, the program can be stored in a computer readable storage medium, and the program is being executed At this time, it may include the flow of the implementation method of each method as described above.
  • 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)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

一种无人机路径规划方法、装置及无人机，属于机器人控制技术领域。其中，无人机路径规划方法包括：获取无人机前方环境的深度图（S100）；根据深度图，获取以无人机的机体为中心的栅格地图（S300）；根据栅格地图确定无人机的候选飞行方向（S400）；确定候选飞行方向中无人机的最优飞行方向（S500）；控制无人机沿最优飞行方向飞行，以躲避无人机前方环境中的障碍物（S600）。通过上述方式，能够对未知环境及动态环境中突然出现的障碍物进行准确判断，从而实现实时路径规划。

Description

一种无人机路径规划方法、装置及无人机 技术领域
本申请实施例涉及机器人控制技术领域，特别是涉及一种无人机路径规划方法、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，对无人机自动感知能力及路径规划算法的要求越来越高，尤其在无人机的自主飞行技术中，需要无人机通过感知自身的运动状态和周围的环境，并结合路径规划算法，在有障碍物的环境中安全地、无碰撞地达到目标点，避免发生碰撞及炸机情况。
目前，无人机常用全局路径规划方法来获得较好的飞行路径，以防止无人机在飞行过程中与障碍物碰撞。但全局路径规划方法只适用于静态环境，无法对未知环境及动态环境中存在的障碍物进行准确判断，实时性无法得到保证。
发明内容
本申请实施例旨在提供一种无人机路径规划方法、装置及无人机，能够对未知环境及动态环境中突然出现的障碍物进行准确判断，实现实时路径规划。
为解决上述技术问题，本申请实施例采用的一个技术方案是：提供一种无人机路径规划方法，所述方法包括：
获取所述无人机前方环境的深度图；
根据所述深度图，获取以所述无人机的机体为中心的栅格地图；
根据所述栅格地图确定所述无人机的候选飞行方向；
确定所述候选飞行方向中所述无人机的最优飞行方向；
控制所述无人机沿所述最优飞行方向飞行，以躲避所述无人机前方环境中的障碍物。
可选地，所述获取所述无人机前方环境的所述深度图，包括：
通过深度传感器获取所述无人机前方环境的所述深度图。
可选地，所述根据所述栅格地图确定所述无人机的候选飞行方向，包括：
根据所述栅格地图确定所述无人机的可通行区域，其中，所述可通行区域为不存在障碍物的区域；
根据所述可通行区域，确定所述无人机的所述候选飞行方向。
可选地，所述根据所述栅格地图确定所述无人机的所述可通行区域，包括：
将所述栅格地图划分为多个区域；
采样障碍物的坐标；
确定所述坐标未落入的区域为所述可通行区域。
可选地，所述将所述栅格地图划分为所述多个区域，包括：
以所述栅格地图的中心为中心，预设角度为间隔，对所述栅格地图进行划分，以获取所述多个区域。
可选地，所述采样障碍物的坐标包括：
采样栅格地图中被所述障碍物占据的栅格的中心点坐标和/或被所述障碍物占据的栅格的角点坐标。
可选地，所述方法还包括：
当不存在所述可通行区域时，重新划分所述栅格地图。
可选地，所述确定所述候选飞行方向中所述无人机的最优飞行方向，包括：
计算代价函数；
根据所述代价函数确定所述候选飞行方向中所述无人机的最优飞行方向。
可选地，所述代价函数为：
f＝k 1×g(direc goal,direc cur)+k 2×g(direc pre,direc cur)-k 3×sum
其中，g(direc goal,direc cur)表示所述候选飞行方向中的其中一个候选飞行方向与所述无人机的目标飞行方向的一致性，g(direc pre,direc cur)表示所述候选飞行方向与前一次决策的最优飞行方向的一致性，sum表示所述可通行区域的数量，k 1、k 2、k 3为权重系数。
可选地，所述根据所述代价函数确定所述候选飞行方向中所述无人机的最优飞行方向，包括：
确定最小代价函数值对应的候选飞行方向为所述无人机的最优飞行方向。
可选地，所述方法还包括：
判断所述无人机沿所述最优飞行方向飞行的距离是否达到预设距离；
若是，则重新确定最优飞行方向。
可选地，所述方法还包括：
若所述无人机沿所述最优飞行方向飞行的距离未达到预设距离，则控制所述无人机沿所述最优飞行方向继续飞行。
可选地，在所述根据所述深度图，获取以所述无人机的机体为中心的栅格地图之前，所述方法还包括：
判断所述无人机是否存在俯仰角；
若是，则对所述深度图进行深度补偿。
可选地，若所述无人机存在俯仰角，则所述对所述深度图进行深度 补偿，包括：
计算所述深度补偿的像素行数，所述深度补偿的像素行数为：
row_see＝tanθ×f，其中，θ为所述无人机的俯仰角，f为无人机相机的焦距；
根据所述深度补偿的像素行数确定所述无人机的像平面在所述深度图上的行索引，所述无人机的像平面在所述深度图上的行索引row_horizon为：
row_horizon＝row_half+row_see，其中，row_half为所述深度图行数的一半。
为解决上述技术问题，本申请实施例采用的另一个技术方案是：提供一种无人机路径规划装置，所述装置包括：
获取模块，所述获取模块用于获取所述无人机前方环境的深度图；以及
用于根据所述深度图，获取以所述无人机的机体为中心的栅格地图；
确定模块，所述确定模块用于根据所述栅格地图确定所述无人机的候选飞行方向；以及
用于确定所述候选飞行方向中所述无人机的最优飞行方向；
控制模块，所述控制模块用于控制所述无人机沿所述最优飞行方向飞行，以躲避所述无人机前方环境中的障碍物。
可选地，所述获取模块通过深度传感器获取所述无人机前方环境的所述深度图。
可选地，所述确定模块具体用于：
根据所述栅格地图确定所述无人机的可通行区域，其中，所述可通行区域为不存在障碍物的区域；以及
用于根据所述可通行区域，确定所述无人机的所述候选飞行方向。
可选地，所述确定模块具体用于：
将所述栅格地图划分为多个区域；
用于采样障碍物的坐标；以及
用于确定所述坐标未落入的区域为所述可通行区域。
可选地，所述确定模块具体用于：
以所述栅格地图的中心为中心，预设角度为间隔，对所述栅格地图进行划分，以获取所述多个区域。
可选地，所述确定模块具体用于：
采样栅格地图中被所述障碍物占据的栅格的中心点坐标和/或被所述障碍物占据的栅格的角点坐标。
可选地，所述确定模块还用于：
当不存在所述可通行区域时，重新划分所述栅格地图。
可选地，所述确定模块具体用于：
计算代价函数；以及
用于根据所述代价函数确定所述候选飞行方向中所述无人机的最优飞行方向。
可选地，所述代价函数为：
f＝k 1×g(direc goal,direc cur)+k 2×g(direc pre,direc cur)-k 3×sum
其中，g(direc goal,direc cur)表示所述候选飞行方向中的其中一个候选飞行方向与所述无人机的目标飞行方向的一致性，g(direc pre,direc cur)表示所述候选飞行方向与前一次决策的最优飞行方向的一致性，sum表示所述可通行区域的数量，k 1、k 2、k 3为权重系数。
可选地，所述确定模块具体用于：
确定最小代价函数值对应的候选飞行方向为所述无人机的最优飞行方向。
可选地，所述装置还包括：
判断模块，所述判断模块用于判断所述无人机沿所述最优飞行方向飞行的距离是否达到预设距离；
若是，则由所述确定模块重新确定最优飞行方向。
可选地，所述控制模块还用于：
若所述无人机沿所述最优飞行方向飞行的距离未达到预设距离，则控制所述无人机沿所述最优飞行方向继续飞行。
可选地，所述判断模块还用于：
判断所述无人机是否存在俯仰角；
所述装置还包括深度补偿模块，所述深度补偿模块用于当所述无人机存在俯仰角时，对所述深度图进行深度补偿。
可选地，所述深度补偿模块具体用于：
计算所述深度补偿的像素行数，所述深度补偿的像素行数为：
row_see＝tanθ×f，其中，θ为所述无人机的俯仰角，f为无人机相机的焦距；
根据所述深度补偿的像素行数确定所述无人机的像平面在所述深度图上的行索引，所述无人机的像平面在所述深度图上的行索引row_horizon为：
row_horizon＝row_half+row_see，其中，row_half为所述深度图行数的一半。
为解决上述技术问题，本申请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上述无人机路径规划方法。
为解决上述技术问题，本申请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上述无人机路径规划方法。
本申请实施例的有益效果是：区别于现有技术的情况下，本申请实施例提供一种无人机路径规划方法、装置及无人机，所述无人机路径规划方法包括：获取无人机前方环境的深度图，并根据深度图获取以无人机为中心的栅格地图；根据栅格地图确定无人机的候选飞行方向，并在候选飞行方向中确定无人机的最优飞行方向；控制无人机沿最优飞行方向飞行，以使无人机能够躲避前方环境中的障碍物。在本申请实施例中，通过无人机前方环境的深度图来确定无人机能够躲避障碍物的最优飞行方向时，由于无人机前方环境的深度图能够随着无人机的飞行过程实时反映无人机飞行路径上的环境情况，因此获取前方环境的深度图使得无人机能够对未知环境及动态环境中突然出现的障碍物进行准确判断，此时，通过无人机前方环境的深度图来确定最优飞行方向，使得无人机能够根据实际飞行情况实时调整飞行路线，实现实时路径规划。
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是本申请实施例提供的一种无人机的结构示意图；
图2是本申请实施例提供的一种无人机路径规划方法中当无人机存在俯仰角，对深度图进行深度补偿的原理示意图；
图3是本申请实施例提供的一种无人机路径规划方法的流程示意图；
图4是图3所示方法中步骤S400的流程示意图；
图5是图4所示方法中步骤S410的流程示意图；
图6是图3所示方法中步骤S500的流程示意图；
图7是本申请另一实施例提供的一种无人机路径规划方法的部分流程示意图；
图8是本申请又一实施例提供的一种无人机路径规划方法的流程示意图；
图9是图8所示方法中步骤S200的流程示意图；
图10是本申请实施例提供的一种无人机路径规划装置的结构示意图；
图11是本申请另一实施例提供的一种无人机路径规划装置的结构示意图；
图12是本申请又一实施例提供的一种无人机路径规划装置的结构示意图；
图13是本申请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
为使本申请实施例的目的、技术方案和优点更加清楚，下面将结合本申请实施例中的附图，对本申请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申请一部分实施例，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申请，并不用于限定本申请。基于本申请中的实施例，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，都属于本申请保护的范围。
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，下面所描述的本申请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。
本申请提供了一种无人机路径规划方法及装置，该方法及装置应用于无人机，从而使得该无人机能够在飞行过程中对未知环境及动态环境中突然出现在前方的障碍物进行准确判断，且能够根据实际飞行情况实时规划出最优飞行方向并沿最优飞行方向飞行，以躲避障碍物。其中，最优飞行方向指不存在障碍物的方向。
本申请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申请进行阐述。
请参阅图1，是本申请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以及飞控系统50。机臂20以及深度传感器40均与机身10连接，飞控系统50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和深度传感器40均与飞控系统50通信连接，使得飞控系统50能够通过动力装置30来控制无人机100的飞行姿态，还能够通过深度传感器40获得无人机100飞行路径前方的环境情况。
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。机臂20可以与机身10固定连接、一体成型或相对于机身10可折叠或展开。
动力装置30设置于机臂20远离机身10的一端，包括设于机臂20的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50通信连接时，飞控系统50能够通过控制电机来控制无人机100的飞行姿态。
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用于采集无人机100前方环境的深度图(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与前方环境物体的实际距离。当深度传感器40与飞控系统50通信连接时，飞控系统50能够从深度传感器40获取无人机100前方环境的深度图，也即获取深度传感器40与前方环境物体的实际距离，以获得无人机100飞行路径前方的环境情况。
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。
飞控系统50与动力装置30以及深度传感器40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50用于执行本申请所述的无人机路径规划方法，以使得无人机100能够对未知环境及动态环境中突然出现在前方的障碍物进行准确判断，且能够根据实际飞行情况实时规划出最优飞行方向并沿最优飞行方向飞行，以躲避障碍物。
具体地，在无人机100准备飞行时以及飞行过程中，飞控系统50 通过深度传感器40获取无人机100前方环境的深度图，并在获取了无人机100前方环境的深度图之后，该飞控系统50根据深度图获取以无人机100的机体为中心的栅格地图。
该栅格地图是通过将深度图中的深度信息映射到以机体为中心的平面栅格图中形成的，其中，每一栅格给定一个可能值，表示该栅格被障碍物占据的概率。当环境深度图中存在障碍物时，障碍物在栅格地图中占据栅格，能够通过被占据栅格的坐标获知障碍物的位置。
栅格地图的栅格排列成矩阵，优选地，在本申请实施例中，栅格地图为10*10的矩阵。
在本申请的另一实施例中，若无人机100在飞行过程中产生俯仰角，会使得无人机100前视不再是水平的，此时，深度传感器40采集的深度图不再是无人机100水平前方的深度图，使得深度图所反映的深度信息出现误差，造成栅格地图的不准确。故飞控系统50在根据深度图获取以无人机100的机体为中心的栅格地图之前，还需要判断无人机100是否存在俯仰角，若存在俯仰角，则飞控系统50需要对深度图进行深度补偿后再根据深度补偿后的深度图获取以无人机100的机体为中心的栅格地图。
其中，飞控系统50能够通过惯性测量单元(IMU)测量无人机100的三轴姿态角，以根据三轴姿态角判断无人机100是否存在俯仰角。该惯性测量单元集成于飞控系统50中。
飞控系统50对深度图进行深度补偿具体包括：飞控系统50计算深度补偿的像素行数，并在计算得到深度补偿的像素行数之后，根据该深度补偿的像素行数确定无人机的像平面在深度图上的行索引。
请参阅图2，该深度补偿的像素行数row_see为：
row_see＝tanθ×f，其中，θ为无人机100的俯仰角，f为无人机相机(深度传感器40)的焦距；
该无人机的像平面在深度图上的行索引row_horizon为：
row_horizon＝row_half+row_see，其中，row_half为深度图行数的一半。
进一步地，将补偿后的深度信息映射到以机体为中心的平面栅格地图中，以获取以无人机100的机体为中心的栅格地图，而后，飞控系统50根据该栅格地图进一步确定无人机的候选飞行方向。
在本申请的一些实施例中，飞控系统50根据栅格地图确定无人机的候选飞行方向具体包括：飞控系统50根据栅格地图确定无人机100的可通行区域，并在确定无人机100的可通行区域之后，根据可通行区域确定无人机100的候选飞行方向。
其中，可通行区域为栅格地图中不存在障碍物的区域，基于可通行区域确定的候选飞行方向为不存在障碍物的方向。
飞控系统50将所有可通行区域对应的方向确定为候选飞行方向。
在本申请的一些实施例中，飞控系统50根据栅格地图确定无人机100的可通行区域具体包括：飞控系统50将栅格地图划分为多个区域，并采样障碍物的坐标，飞控系统50判断采样得到的障碍物坐标是否落入栅格地图划分的区域中，将障碍物坐标未落入的区域确定为可通行区域。
其中，飞控系统50将栅格地图划分为多个区域具体包括：飞控系统50以栅格地图的中心为中心，预设角度为间隔，对栅格地图进行划分，以获取多个区域。此时，栅格地图中划分出的每个区域均为扇形区域。
预设角度越大，划分的区域越大，划分出的区域数量则越少；预设角度越小，划分的区域越小，划分出的区域数量则越多。
飞控系统50采样障碍物的坐标具体包括：飞控系统50采样栅格地图中被障碍物占据的栅格的中心点坐标和/或被障碍物占据的栅格的角点坐标。
飞控系统50将被障碍物占据的栅格的中心点坐标和/或被障碍物占 据的栅格的角点坐标均未落入的区域确定为可通行区域。基于此，若栅格地图的区域划分的过小，则容易出现区域被障碍物覆盖，但采样的坐标均未落入区域的情况，此时，不可通行区域被误判为可通行区域；而栅格地图的区域划分若过大，则会导致飞行方向过少，不利于最优飞行方向的判定。于是，为了保证飞控系统50路径规划的可靠性，飞控系统50会根据实际飞行效果调整预设角度的大小。
飞控系统50调整预设角度依据深度图数据的鲁棒性以及规划方向的精确度。
在本申请的另一实施例中，若区域划分不准确，则可能出现不存在可通行区域的情况，故飞控系统50还用于执行以下方法：当不存在可通行区域时，飞控系统50重新划分栅格地图。其中，飞控系统50以栅格地图的中心为中心，以调整后的预设角度为间隔，对栅格地图进行划分，以获取多个区域来确定可通行区域。
进一步地，在确定了无人机的候选飞行方向后，飞控系统50确定候选飞行方向中无人机100的最优飞行方向。
在本申请的一些实施例中，飞控系统50确定候选飞行方向中无人机100的最优飞行方向具体包括：飞控系统50计算代价函数，并根据计算出的代价函数确定候选飞行方向中无人机的最优飞行方向。
其中，飞控系统50计算代价函数具体包括：飞控系统50通过代价函数计算所确定的每个候选飞行方向的飞行代价。
飞控系统50根据代价函数确定候选飞行方向中无人机100的最优飞行方向具体包括：确定最小代价函数值对应的候选飞行方向为无人机100的最优飞行方向。
上述最小代价函数值即通过代价函数计算出的最小飞行代价，即确定飞行代价最小的候选飞行方向为无人机100的最优飞行方向。
在本申请的一些实施例中，代价函数为：
f＝k 1×g(direc goal,direc cur)+k 2×g(direc pre,direc cur)-k 3×sum，
其中，g(direc goal,direc cur)表示候选飞行方向中的其中一个候选飞行方向与无人机100的目标飞行方向的一致性，g(direc pre,direc cur)表示候选飞行方向与前一次决策的最优飞行方向的一致性，sum表示可通行区域的数量，k 1、k 2、k 3为权重系数。
与无人机100的目标飞行方向的一致性越高、与前一次决策的最优飞行方向的一致性越高以及可通行区域的数量越多的候选飞行方向的代价越小。
k 1、k 2、k 3的相对大小决定三种因素的优先级顺序。若要使得确定的候选飞行方向与目标飞行方向尽量保持一致，则使得k 1>k 2、k 3；若要使得确定的候选飞行方向与前一次决策的最优飞行方向尽量保持一致，则使得k 2>k 1、k 3；若要保证确定的候选飞行方向足够安全，则使得k 3>k 2、k 1。
进一步地，上述目标飞行方向可以由预设目标位置确定，也可以根据跟踪目标的位置确定。
进一步地，在确定了无人机100的最优飞行方向后，飞控系统50控制无人机100沿最优飞行方向飞行，以躲避无人机100前方环境中的障碍物。
具体地，飞控系统50通过控制电机改变螺旋桨的转速及螺旋桨的旋转方向(逆时针或顺时针)来改变无人机100的飞行方向，使得无人机100沿确定的最优飞行方向飞行。
在本申请的另一实施例中，若实时规划过程中最优飞行方向的改变过于频繁，则容易造成控制困难，为了减少控制难度，飞控系统50控制无人机100沿最优飞行方向飞行之后，飞控系统50还可以执行以下方法：飞控系统50判断无人机100沿最优飞行方向飞行的距离是否达到预设距离，若无人机100沿最优飞行方向飞行的距离达到预设距离，则飞控系统50重新确定最优飞行方向；若无人机100沿最优飞行方向飞行的距离未达到预设距离，则飞控系统控制无人机100沿最优飞行方向继续飞行。
其中，预设距离为前一次决策的最优飞行方向上出现障碍物时，障碍物与无人机100之间的距离。
当飞控系统50控制无人机100沿最优飞行方向飞行的距离达到前一次决策的最优飞行方向上障碍物与无人机100之间的距离时，则表示无人机100已绕过前一次决策的最优飞行方向上的障碍物，此时，重新确定最优飞行方向能够使得无人机100接近前一次决策的最优飞行方向(前一次决策的最优飞行方向优于当前决策的最优飞行方向)。
当飞控系统50控制无人机100沿最优飞行方向飞行的距离未达到前一次决策的最优飞行方向上障碍物与无人机100之间的距离时，则表示无人机100还未绕过前一次决策的最优飞行方向上的障碍物，此时，继续沿最优飞行方向飞行，保持决策方向不变，防止无人机100频繁改变飞行方向。
在本申请实施例中，通过获取无人机前方环境的深度图来确定最优飞行方向，使得无人机能够在飞行过程中对未知环境及动态环境中突然出现在前方的障碍物进行准确判断，且能够根据实际飞行情况实时调整飞行路线，实现实时路径规划。
请参阅图3，是本申请其中一实施例提供的一种无人机路径规划方法的流程示意图，应用于无人机，该无人机为上述实施例中所述的无人机100，而本申请实施例提供的方法由上述飞控系统50执行，用于实现实时路径规划，该无人机路径规划方法包括：
S100：获取所述无人机前方环境的深度图。
在本申请的一实施例中，可通过深度传感器来获取无人机前方环境的深度图。
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。
其中，深度图(Depth Map)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。故通过深度传感器获取无人机前方环境的深度图即获取深度传感器与前方环境物体的实际距离。
S300：根据所述深度图，获取以所述无人机的机体为中心的栅格地图。
其中，栅格地图是通过将深度图划分成一系列栅格形成的，每一栅格给定一个可能值，表示该栅格被占据的概率。当环境深度图中存在障碍物时，障碍物在栅格地图中占据栅格，能够通过被占据栅格的坐标获知障碍物的位置。
栅格地图的每个栅格排列成矩阵，优选地，在本申请实施例中，栅格地图为10*10的矩阵。
S400：根据所述栅格地图确定所述无人机的候选飞行方向。
请参阅图4，在本申请的一实施例中，根据所述栅格地图确定所述无人机的候选飞行方向具体包括：
S410：根据所述栅格地图确定所述无人机的可通行区域，其中，所述可通行区域为不存在障碍物的区域。
请参阅图5，在本申请的一实施例中，根据所述栅格地图确定所述无人机的所述可通行区域具体包括：
S411：将所述栅格地图划分为多个区域。
所述将所述栅格地图划分为所述多个区域具体包括：
以所述栅格地图的中心为中心，预设角度为间隔，对所述栅格地图进行划分，以获取所述多个区域。
其中，栅格地图中划分出的每个区域均为扇形区域。
预设角度越大，划分的区域越大，划分出的区域数量则越少；预设角度越小，划分的区域越小，划分出的区域数量则越多。
S412：采样障碍物的坐标。
所述采样障碍物的坐标具体包括：
采样栅格地图中被所述障碍物占据的栅格的中心点坐标和/或被所述障碍物占据的栅格的角点坐标。
S413：确定所述坐标未落入的区域为所述可通行区域。
将被障碍物占据的栅格的中心点坐标和/或被障碍物占据的栅格的角点坐标均未落入的区域确定为可通行区域。基于此，若栅格地图的区域划分的过小，则容易出现区域被障碍物覆盖，但采样的坐标均未落入区域的情况，此时，不可通行区域被误判为可通行区域；而栅格地图的区域划分若过大，则会导致飞行方向过少，不利于最优飞行方向的判定。于是，为了保证路径规划的可靠性，根据实际飞行效果调整预设角度的大小。
其中，调整预设角度依据深度图数据的鲁棒性以及规划方向的精确度。
S420：判断是否存在可通行区域，若存在可通行区域，则执行步骤S430，若不存在可通行区域，则执行步骤S440；
S430：根据所述可通行区域，确定所述无人机的所述候选飞行方向。
当存在可通行区域时，才根据可通行区域确定无人机的候选飞行方向，即将所有可通行区域对应的方向确定为候选飞行方向。
其中，因为可通行区域为不存在障碍物的区域，故基于可通行区域确定的候选飞行方向为不存在障碍物的方向。
S440：重新划分所述栅格地图。
当不存在可通行区域时，需要重新划分栅格地图，具体包括：以栅格地图的中心为中心，以调整后的预设角度为间隔，对栅格地图进行划分，以获取多个区域来确定可通行区域。
S500：确定所述候选飞行方向中所述无人机的最优飞行方向。
请参阅图6，在本申请的一实施例中，所述确定所述候选飞行方向中所述无人机的最优飞行方向具体包括：
S510：计算代价函数。
计算代价函数具体包括：通过代价函数计算所确定的每个候选飞行方向的飞行代价。
代价函数为：
f＝k 1×g(direc goal,direc cur)+k 2×g(direc pre,direc cur)-k 3×sum
其中，g(direc goal,direc cur)表示所述候选飞行方向中的其中一个候选飞行方向与所述无人机的目标飞行方向的一致性，g(direc pre,direc cur)表示所述候选飞行方向与前一次决策的最优飞行方向的一致性，sum表示可通行区域的数量，k 1、k 2、k 3为权重系数。
与无人机的目标飞行方向的一致性越高、与前一次决策的最优飞行方向的一致性越高以及连续可通行区域的数量越多的候选飞行方向的代价越小。
k 1、k 2、k 3的相对大小决定三种因素的优先级顺序。若要使得确定的候选飞行方向与目标飞行方向尽量保持一致，则使得k 1>k 2、k 3；若要使得确定的候选飞行方向与前一次决策的最优飞行方向尽量保持一致，则使得k 2>k 1、k 3；若要保证确定的候选飞行方向足够安全，则使得k 3>k 2、k 1。
其中，目标飞行方向可以由预设目标位置确定，也可以根据跟踪目标的位置确定。
S520：根据所述代价函数确定所述候选飞行方向中所述无人机的最优飞行方向。
所述根据所述代价函数确定所述候选飞行方向中所述无人机的最优飞行方向具体包括：确定最小代价函数值对应的候选飞行方向为所述无人机的最优飞行方向。
上述最小代价函数值即通过代价函数计算出的最小飞行代价，即确定飞行代价最小的候选飞行方向为无人机的最优飞行方向。
S600：控制所述无人机沿所述最优飞行方向飞行，以躲避所述无人机前方环境中的障碍物。
具体地，通过控制电机改变螺旋桨的转速及螺旋桨的旋转方向(逆时针或顺时针)来改变无人机的飞行方向，使得无人机沿确定的最优飞行方向飞行。
请参阅图7，在本申请的另一实施例中，步骤S600之后还包括：
S700：判断所述无人机沿所述最优飞行方向飞行的距离是否达到预设距离；若是则执行步骤S800；若否，则执行步骤900。
S800：重新确定最优飞行方向。
S900：控制所述无人机沿所述最优飞行方向继续飞行。
其中，预设距离为前一次决策的最优飞行方向上出现障碍物时，障碍物与无人机之间的距离。
当无人机沿最优飞行方向飞行的距离达到前一次决策的最优飞行方向上障碍物与无人机之间的距离时，则表示无人机已绕过前一次决策的最优飞行方向上的障碍物，此时，重新确定最优飞行方向能够使得无人机接近前一次决策的最优飞行方向(前一次决策的最优飞行方向优于当前决策的最优飞行方向)。
当无人机沿最优飞行方向飞行的距离未达到前一次决策的最优飞行方向上障碍物与无人机之间的距离时，则表示无人机还未绕过前一次决策的最优飞行方向上的障碍物，此时，继续沿最优飞行方向飞行，保持决策方向不变，防止无人机频繁改变飞行方向，减少实时规划过程中的控制难度。
请参阅图8，在本申请的另一实施例中，步骤S300之前还包括：
S200：判断所述无人机是否存在俯仰角，若是，则对所述深度图进 行深度补偿。
若无人机前进过程中产生俯仰角，会使得无人机前视不再是水平的，此时，深度传感器采集的深度图不再是无人机水平前方的深度图，使得深度图所反映的深度信息出现误差，造成栅格地图的不准确，故需要在无人机存在俯仰角时对深度图进行深度补偿，并在深度补偿后根据深度补偿后的深度图获取以无人机的机体为中心的栅格地图。
其中，能够通过惯性测量单元测量无人机100的三轴姿态角，以根据三轴姿态角判断无人机是否存在俯仰角。
请参阅图9，在本申请的一实施例中，若所述无人机存在俯仰角，则对所述深度图进行深度补偿具体包括：
S210：计算所述深度补偿的像素行数，所述深度补偿的像素行数为：
row_see＝tanθ×f，其中，θ为所述无人机的俯仰角，f为无人机相机(深度传感器)的焦距；
S220：根据所述深度补偿的像素行数确定所述无人机的像平面在所述深度图上的行索引，所述无人机的像平面在所述深度图上的行索引row_horizon为：
row_horizon＝row_half+row_see，其中，row_half为所述深度图行数的一半。
在本申请实施例中，通过获取无人机前方环境的深度图来确定最优飞行方向，使得无人机能够在飞行过程中对未知环境及动态环境中突然出现在前方的障碍物进行准确判断，且能够根据实际飞行情况实时调整飞行路线，实现实时路径规划。
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10，是本申请其中一实施例提供的一种无人机路径规划装置，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，而本申请实施例提供的装置各个模块的功能由上述飞控系统50执行，用于实现实时路径规划，该无人机路径规划装置包括：
获取模块200，该获取模块200用于获取无人机前方环境的深度图；以及
用于根据深度图，获取以无人机的机体为中心的栅格地图；
确定模块300，该确定模块300用于根据栅格地图确定无人机的候选飞行方向；以及
用于确定候选飞行方向中无人机的最优飞行方向；
控制模块400，该控制模块400用于控制无人机沿最优飞行方向飞行，以躲避无人机前方环境中的障碍物。
其中，获取模块200通过深度传感器获取无人机前方环境的深度图。
进一步地，确定模块300具体用于：
根据栅格地图确定无人机的可通行区域，其中，可通行区域为不存在障碍物的区域；以及
用于根据可通行区域，确定无人机的候选飞行方向。
进一步地，确定模块300具体用于：
将栅格地图划分为多个区域；
用于采样障碍物的坐标；以及
用于确定坐标未落入的区域为可通行区域。
进一步地，确定模块300具体用于：
以栅格地图的中心为中心，预设角度为间隔，对栅格地图进行划分，以获取多个区域。
进一步地，确定模块300具体用于：
采样栅格地图中被障碍物占据的栅格的中心点坐标和/或被障碍物占据的栅格的角点坐标。
进一步地，确定模块300还用于：
当不存在可通行区域时，重新划分栅格地图。
进一步地，确定模块300具体用于：
计算代价函数；以及
用于根据代价函数确定候选飞行方向中无人机的最优飞行方向。
其中，代价函数为：
f＝k 1×g(direc goal,direc cur)+k 2×g(direc pre,direc cur)-k 3×sum
其中，g(direc goal,direc cur)表示候选飞行方向中的其中一个候选飞行方向与无人机的目标飞行方向的一致性，g(direc pre,direc cur)表示候选飞行方向与前一次决策的最优飞行方向的一致性，sum表示所述可通行区域的数量，k 1、k 2、k 3为权重系数。
进一步地，确定模块300具体用于：
确定最小代价函数值对应的候选飞行方向为无人机的最优飞行方向。
进一步地，请参阅图11，该无人机路径规划装置还包括：
判断模块500，该判断模块500用于判断无人机沿最优飞行方向飞行的距离是否达到预设距离；
若是，则由确定模块300重新确定最优飞行方向。
进一步地，控制模块400还用于：
若无人机沿最优飞行方向飞行的距离未达到预设距离，则控制无人机沿最优飞行方向继续飞行。
进一步地，判断模块500还用于：
判断无人机是否存在俯仰角；
此时，请参阅图12，该无人机路径规划装置还包括：深度补偿模块600，该深度补偿模块600用于当无人机存在俯仰角时，对深度图进行深度补偿。
进一步地，深度补偿模块600具体用于：
计算深度补偿的像素行数，深度补偿的像素行数为：
row_see＝tanθ×f，其中，θ为无人机的俯仰角，f为无人机相机的焦距；
根据深度补偿的像素行数确定无人机的像平面在深度图上的行索引，无人机的像平面在深度图上的行索引row_horizon为：
row_horizon＝row_half+row_see，其中，row_half为深度图行数的一半。
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，以直接获取无人机前方环境的深度图；上述确定模块300、控制模块400、判断模块500以及深度补偿模块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。
在本申请实施例中，通过获取无人机前方环境的深度图来确定最优飞行方向，使得无人机能够在飞行过程中对未知环境及动态环境中突然出现在前方的障碍物进行准确判断，且能够根据实际飞行情况实时调整飞行路线，实现实时路径规划。
请参阅图13，是本申请其中一实施例提供的一种无人机的硬件结构示意图，本申请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50，也能够直接作为飞控系统50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路径规划方法，还能实现以上实施例所述的一种无人机路径规划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13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13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，如本申请上述实施例中的一种无人机路径规划方法对应的程序指令以及一种无人机路径规划装置对应的模块(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路径规划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路径规划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路径规划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，包括预设角度等。
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路径规划方法的各个步骤，或者，实现上述任意装置实施例中的一种无人机路径规划装置的各个模块的功能。
上述产品可执行本申请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，可参见本申请上述实施例所提供的方法。
本申请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13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路径规划方法的各个步骤，或者，实现上述任意装置实施例中的一种无人机路径规划装置的各个模块的功能。
本申请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13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路径规划方法的各个步骤，或者，实现上述任意装置实施例中的一种无人机路径规划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。
以上所述仅为本申请的实施例，并非因此限制本申请的专利范围，凡是利用本申请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，均同理包括在本申请的专利保护范围内。
最后应说明的是：以上实施例仅用以说明本申请的技术方案，而非对其限制；在本申请的思路下，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申请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申请进行了详细的说明，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. 一种无人机路径规划方法，其特征在于，所述方法包括：
    获取所述无人机前方环境的深度图；
    根据所述深度图，获取以所述无人机的机体为中心的栅格地图；
    根据所述栅格地图确定所述无人机的候选飞行方向；
    确定所述候选飞行方向中所述无人机的最优飞行方向；
    控制所述无人机沿所述最优飞行方向飞行，以躲避所述无人机前方环境中的障碍物。
  2. 根据权利要求1所述的无人机路径规划方法，其特征在于，所述获取所述无人机前方环境的所述深度图，包括：
    通过深度传感器获取所述无人机前方环境的所述深度图。
  3. 根据权利要求1或2所述的无人机路径规划方法，其特征在于，所述根据所述栅格地图确定所述无人机的候选飞行方向，包括：
    根据所述栅格地图确定所述无人机的可通行区域，其中，所述可通行区域为不存在障碍物的区域；
    根据所述可通行区域，确定所述无人机的所述候选飞行方向。
  4. 根据权利要求3所述的无人机路径规划方法，其特征在于，所述根据所述栅格地图确定所述无人机的所述可通行区域，包括：
    将所述栅格地图划分为多个区域；
    采样障碍物的坐标；
    确定所述坐标未落入的区域为所述可通行区域。
  5. 根据权利要求4所述的无人机路径规划方法，其特征在于，所述将所述栅格地图划分为所述多个区域，包括：
    以所述栅格地图的中心为中心，预设角度为间隔，对所述栅格地图 进行划分，以获取所述多个区域。
  6. 根据权利要求4或5所述的无人机路径规划方法，其特征在于，所述采样障碍物的坐标包括：
    采样栅格地图中被所述障碍物占据的栅格的中心点坐标和/或被所述障碍物占据的栅格的角点坐标。
  7. 根据权利要求3-6中任一项所述的无人机路径规划方法，其特征在于，所述方法还包括：
    当不存在所述可通行区域时，重新划分所述栅格地图。
  8. 根据权利要求1-7中任一项所述的无人机路径规划方法，其特征在于，所述确定所述候选飞行方向中所述无人机的最优飞行方向，包括：
    计算代价函数；
    根据所述代价函数确定所述候选飞行方向中所述无人机的最优飞行方向。
  9. 根据权利要求8所述的无人机路径规划方法，其特征在于，所述代价函数为：
    f＝k 1×g(direc goal,direc cur)+k 2×g(direc pre,direc cur)-k 3×sum
    其中，g(direc goal,direc cur)表示所述候选飞行方向中的其中一个候选飞行方向与所述无人机的目标飞行方向的一致性，g(direc pre,direc cur)表示所述候选飞行方向与前一次决策的最优飞行方向的一致性，sum表示所述可通行区域的数量，k 1、k 2、k 3为权重系数。
  10. 根据权利要求8或9所述的无人机路径规划方法，其特征在于，所述根据所述代价函数确定所述候选飞行方向中所述无人机的最优飞行方向，包括：
    确定最小代价函数值对应的候选飞行方向为所述无人机的最优飞行方向。
  11. 根据权利要求1-10中任一项所述的无人机路径规划方法，其特征在于，所述方法还包括：
    判断所述无人机沿所述最优飞行方向飞行的距离是否达到预设距离；
    若是，则重新确定最优飞行方向。
  12. 根据权利要求11所述的无人机路径规划方法，其特征在于，所述方法还包括：
    若所述无人机沿所述最优飞行方向飞行的距离未达到预设距离，则控制所述无人机沿所述最优飞行方向继续飞行。
  13. 根据权利要求1-12中任一项所述的无人机路径规划方法，其特征在于，在所述根据所述深度图，获取以所述无人机的机体为中心的栅格地图之前，所述方法还包括：
    判断所述无人机是否存在俯仰角；
    若是，则对所述深度图进行深度补偿。
  14. 根据权利要求13所述的无人机路径规划方法，其特征在于，若所述无人机存在俯仰角，则所述对所述深度图进行深度补偿，包括：
    计算所述深度补偿的像素行数，所述深度补偿的像素行数为：
    row_see＝tanθ×f，其中，θ为所述无人机的俯仰角，f为无人机相机的焦距；
    根据所述深度补偿的像素行数确定所述无人机的像平面在所述深度图上的行索引，所述无人机的像平面在所述深度图上的行索引row_horizon为：
    row_horizon＝row_half+row_see，其中，row_half为所述深度图行数的一半。
  15. 一种无人机路径规划装置，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所述无人机前方环境的深度图；以及
    用于根据所述深度图，获取以所述无人机的机体为中心的栅格地图；
    确定模块，所述确定模块用于根据所述栅格地图确定所述无人机的候选飞行方向；以及
    用于确定所述候选飞行方向中所述无人机的最优飞行方向；
    控制模块，所述控制模块用于控制所述无人机沿所述最优飞行方向飞行，以躲避所述无人机前方环境中的障碍物。
  16. 根据权利要求15所述的无人机路径规划装置，其特征在于，所述获取模块通过深度传感器获取所述无人机前方环境的所述深度图。
  17. 根据权利要求15或16所述的无人机路径规划装置，其特征在于，所述确定模块具体用于：
    根据所述栅格地图确定所述无人机的可通行区域，其中，所述可通行区域为不存在障碍物的区域；以及
    用于根据所述可通行区域，确定所述无人机的所述候选飞行方向。
  18. 根据权利要求17所述的无人机路径规划装置，其特征在于，所述确定模块具体用于：
    将所述栅格地图划分为多个区域；
    用于采样障碍物的坐标；以及
    用于确定所述坐标未落入的区域为所述可通行区域。
  19. 根据权利要求18所述的无人机路径规划装置，其特征在于，所述确定模块具体用于：
    以所述栅格地图的中心为中心，预设角度为间隔，对所述栅格地图进行划分，以获取所述多个区域。
  20. 根据权利要求18或19所述的无人机路径规划装置，其特征在于，所述确定模块具体用于：
    采样栅格地图中被所述障碍物占据的栅格的中心点坐标和/或被所述障碍物占据的栅格的角点坐标。
  21. 根据权利要求17-20中任一项所述的无人机路径规划装置，其特征在于，所述确定模块还用于：
    当不存在所述可通行区域时，重新划分所述栅格地图。
  22. 根据权利要求15-21中任一项所述的无人机路径规划装置，其特征在于，所述确定模块具体用于：
    计算代价函数；以及
    用于根据所述代价函数确定所述候选飞行方向中所述无人机的最优飞行方向。
  23. 根据权利要求22所述的无人机路径规划装置，其特征在于，所述代价函数为：
    f＝k 1×g(direc goal,direc cur)+k 2×g(direc pre,direc cur)-k 3×sum
    其中，g(direc goal,direc cur)表示所述候选飞行方向中的其中一个候选飞行方向与所述无人机的目标飞行方向的一致性，g(direc pre,direc cur)表示所述候选飞行方向与前一次决策的最优飞行方向的一致性，sum表示所述可通行区域的数量，k 1、k 2、k 3为权重系数。
  24. 根据权利要求22或23所述的无人机路径规划装置，其特征在于，所述确定模块具体用于：
    确定最小代价函数值对应的候选飞行方向为所述无人机的最优飞行方向。
  25. 根据权利要求15-24中任一项所述的无人机路径规划装置，其特征在于，所述装置还包括：
    判断模块，所述判断模块用于判断所述无人机沿所述最优飞行方向飞行的距离是否达到预设距离；
    若是，则由所述确定模块重新确定最优飞行方向。
  26. 根据权利要求25所述的无人机路径规划装置，其特征在于，所述控制模块还用于：
    若所述无人机沿所述最优飞行方向飞行的距离未达到预设距离，则控制所述无人机沿所述最优飞行方向继续飞行。
  27. 根据权利要求25所述的无人机路径规划装置，其特征在于，所述判断模块还用于：
    判断所述无人机是否存在俯仰角；
    所述装置还包括深度补偿模块，所述深度补偿模块用于当所述无人机存在俯仰角时，对所述深度图进行深度补偿。
  28. 根据权利要求27所述的无人机路径规划装置，其特征在于，所述深度补偿模块具体用于：
    计算所述深度补偿的像素行数，所述深度补偿的像素行数为：
    row_see＝tanθ×f，其中，θ为所述无人机的俯仰角，f为无人机相机的焦距；
    根据所述深度补偿的像素行数确定所述无人机的像平面在所述深度图上的行索引，所述无人机的像平面在所述深度图上的行索引row_horizon为：
    row_horizon＝row_half+row_see，其中，row_half为所述深度图行数的一半。
  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路径规划方法。
  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路径规划方法。
PCT/CN2018/116701 2018-11-21 2018-11-21 一种无人机路径规划方法、装置及无人机 WO2020103034A1 (zh)

Priority Applications (5)

Application Number Priority Date Filing Date Title
CN202410357193.XA CN118259692A (zh) 2018-11-21 2018-11-21 一种无人机路径规划方法、装置及无人机
PCT/CN2018/116701 WO2020103034A1 (zh) 2018-11-21 2018-11-21 一种无人机路径规划方法、装置及无人机
EP18940701.8A EP3876070B1 (en) 2018-11-21 2018-11-21 Method and device for planning path of unmanned aerial vehicle, and unmanned aerial vehicle
CN201880099092.XA CN112912811B (zh) 2018-11-21 2018-11-21 一种无人机路径规划方法、装置及无人机
US17/322,135 US12025996B2 (en) 2018-11-21 2021-05-17 Unmanned aerial vehicle path planning method and apparatus and unmanned aerial vehicle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/116701 WO2020103034A1 (zh) 2018-11-21 2018-11-21 一种无人机路径规划方法、装置及无人机

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/322,135 Continuation US12025996B2 (en) 2018-11-21 2021-05-17 Unmanned aerial vehicle path planning method and apparatus and unmanned aerial vehicle

Publications (1)

Publication Number Publication Date
WO2020103034A1 true WO2020103034A1 (zh) 2020-05-28

Family

ID=70773276

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/116701 WO2020103034A1 (zh) 2018-11-21 2018-11-21 一种无人机路径规划方法、装置及无人机

Country Status (4)

Country Link
US (1) US12025996B2 (zh)
EP (1) EP3876070B1 (zh)
CN (2) CN118259692A (zh)
WO (1) WO2020103034A1 (zh)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111811513A (zh) * 2020-06-28 2020-10-23 西安电子科技大学 一种多无人机协同覆盖及避障的航迹规划方法
CN112069941A (zh) * 2020-08-24 2020-12-11 河南省交通规划设计研究院股份有限公司 一种基于视频技术的线路规划系统及其方法
CN112486195A (zh) * 2020-11-27 2021-03-12 远传融创(杭州)科技有限公司 一种无人机无线通信链路资源动态调整方法
CN113120235A (zh) * 2021-05-28 2021-07-16 之江实验室 一种基于能量分析的载重无人机任务规划方法
CN113639750A (zh) * 2021-07-20 2021-11-12 中国地质大学（武汉） 顾及时变需求的高峰时段无人机监视路径规划方法及装置
CN114138006A (zh) * 2021-11-04 2022-03-04 中国电子科技集团公司电子科学研究院 一种面向城市低空环境的无人机路径规划方法及设备
CN115390589A (zh) * 2022-10-27 2022-11-25 汕头大学 无人机集群控制方法、装置、电子设备及存储介质

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113570910B (zh) * 2021-06-30 2022-09-27 北京百度网讯科技有限公司 空中交通流量管理方法、装置和电子设备
CN113741522B (zh) * 2021-09-03 2024-04-16 北京航空航天大学 一种基于无人机协同对峙监视的有害物扩散源搜索方法
CN113741523B (zh) * 2021-09-08 2024-03-19 北京航空航天大学 一种基于边界和采样的混合无人机自主探测方法
TWI800102B (zh) * 2021-11-16 2023-04-21 財團法人工業技術研究院 載具頭向補償方法及系統
CN115435787B (zh) * 2022-07-28 2024-05-28 南京航空航天大学 一种基于改进蝴蝶算法的无人机三维路径规划方法及系统
CN115421520A (zh) * 2022-10-14 2022-12-02 深圳市华赛睿飞智能科技有限公司 一种无人机路径规划方法、无人机及存储介质
CN115661204B (zh) * 2022-11-01 2023-11-10 中国人民解放军军事科学院国防科技创新研究院 一种无人机集群对运动目标的协同搜寻与跟踪定位方法
CN115833905B (zh) * 2022-11-08 2023-12-12 同济大学 一种地下空间移固协同检测方法及系统
CN118012110B (zh) * 2024-04-10 2024-06-21 山东省国土测绘院 一种基于无人机航测的智能测绘方法及系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103809597A (zh) * 2014-02-18 2014-05-21 清华大学 无人机的飞行路径规划方法及无人机
WO2018142395A1 (en) * 2017-01-31 2018-08-09 Arbe Robotics Ltd A radar-based system and method for real-time simultaneous localization and mapping
CN108521807A (zh) * 2017-04-27 2018-09-11 深圳市大疆创新科技有限公司 无人机的控制方法、设备及障碍物的提示方法、设备
CN108827306A (zh) * 2018-05-31 2018-11-16 北京林业大学 一种基于多传感器融合的无人机slam导航方法及系统

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2010122652A1 (ja) * 2009-04-23 2010-10-28 株式会社ナビタイムジャパン 経路案内システム、経路探索サーバ、経路案内仲介サーバおよび経路案内方法
EP3428766B1 (en) * 2014-09-05 2021-04-07 SZ DJI Technology Co., Ltd. Multi-sensor environmental mapping
JP6073387B2 (ja) * 2015-01-16 2017-02-01 富士重工業株式会社 飛行経路探索装置及び飛行経路探索プログラム
JP6559535B2 (ja) * 2015-10-22 2019-08-14 株式会社東芝 障害物マップ生成装置、その方法、及び、そのプログラム
US11461912B2 (en) * 2016-01-05 2022-10-04 California Institute Of Technology Gaussian mixture models for temporal depth fusion
US10665115B2 (en) * 2016-01-05 2020-05-26 California Institute Of Technology Controlling unmanned aerial vehicles to avoid obstacle collision
CN106092102A (zh) * 2016-07-20 2016-11-09 广州极飞电子科技有限公司 一种无人机路径规划方法及装置
WO2018095278A1 (zh) * 2016-11-24 2018-05-31 腾讯科技（深圳）有限公司 飞行器的信息获取方法、装置及设备
CN106529495B (zh) * 2016-11-24 2020-02-07 腾讯科技（深圳）有限公司 一种飞行器的障碍物检测方法和装置
CN106681353B (zh) * 2016-11-29 2019-10-25 南京航空航天大学 基于双目视觉与光流融合的无人机避障方法及系统
US11017679B2 (en) * 2017-01-13 2021-05-25 Skydio, Inc. Unmanned aerial vehicle visual point cloud navigation
JP6729794B2 (ja) * 2017-03-31 2020-07-22 日産自動車株式会社 運転制御方法及び運転制御装置
US11530921B2 (en) * 2018-09-28 2022-12-20 Intel Corporation Method of generating a collision free path of travel and computing system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103809597A (zh) * 2014-02-18 2014-05-21 清华大学 无人机的飞行路径规划方法及无人机
WO2018142395A1 (en) * 2017-01-31 2018-08-09 Arbe Robotics Ltd A radar-based system and method for real-time simultaneous localization and mapping
CN108521807A (zh) * 2017-04-27 2018-09-11 深圳市大疆创新科技有限公司 无人机的控制方法、设备及障碍物的提示方法、设备
CN108827306A (zh) * 2018-05-31 2018-11-16 北京林业大学 一种基于多传感器融合的无人机slam导航方法及系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3876070A4 *

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111811513A (zh) * 2020-06-28 2020-10-23 西安电子科技大学 一种多无人机协同覆盖及避障的航迹规划方法
CN111811513B (zh) * 2020-06-28 2023-03-28 西安电子科技大学 一种多无人机协同覆盖及避障的航迹规划方法
CN112069941A (zh) * 2020-08-24 2020-12-11 河南省交通规划设计研究院股份有限公司 一种基于视频技术的线路规划系统及其方法
CN112486195A (zh) * 2020-11-27 2021-03-12 远传融创(杭州)科技有限公司 一种无人机无线通信链路资源动态调整方法
CN113120235A (zh) * 2021-05-28 2021-07-16 之江实验室 一种基于能量分析的载重无人机任务规划方法
CN113639750A (zh) * 2021-07-20 2021-11-12 中国地质大学（武汉） 顾及时变需求的高峰时段无人机监视路径规划方法及装置
CN113639750B (zh) * 2021-07-20 2023-05-26 中国地质大学（武汉） 顾及时变需求的高峰时段无人机监视路径规划方法及装置
CN114138006A (zh) * 2021-11-04 2022-03-04 中国电子科技集团公司电子科学研究院 一种面向城市低空环境的无人机路径规划方法及设备
CN115390589A (zh) * 2022-10-27 2022-11-25 汕头大学 无人机集群控制方法、装置、电子设备及存储介质
CN115390589B (zh) * 2022-10-27 2023-02-28 汕头大学 无人机集群控制方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
US20210271269A1 (en) 2021-09-02
EP3876070A1 (en) 2021-09-08
EP3876070B1 (en) 2024-02-28
CN112912811B (zh) 2024-03-29
US12025996B2 (en) 2024-07-02
CN118259692A (zh) 2024-06-28
CN112912811A (zh) 2021-06-04
EP3876070A4 (en) 2021-11-24

Similar Documents

Publication Publication Date Title
WO2020103034A1 (zh) 一种无人机路径规划方法、装置及无人机
CN110262568B (zh) 一种基于目标跟踪的无人机避障方法、装置及无人机
US10914590B2 (en) Methods and systems for determining a state of an unmanned aerial vehicle
US20200026720A1 (en) Construction and update of elevation maps
US11709073B2 (en) Techniques for collaborative map construction between an unmanned aerial vehicle and a ground vehicle
WO2020181419A1 (en) Techniques for sharing mapping data between an unmanned aerial vehicle and a ground vehicle
WO2020125726A1 (zh) 一种无人机自主降落方法、装置及无人机
WO2016033797A1 (en) Multi-sensor environmental mapping
WO2018045538A1 (zh) 无人机及其避障方法和避障系统
WO2020125725A1 (zh) 一种无人机降落避障方法、装置及无人机
EP3128386A1 (en) Method and device for tracking a moving target from an air vehicle
CN111615677B (zh) 一种无人机的安全降落方法、装置、无人机及介质
WO2021047502A1 (zh) 一种目标状态估计方法、装置和无人机
WO2020237471A1 (zh) 飞行航线生成方法、终端和无人机
US11982758B2 (en) Relay point generation method and apparatus, and unmanned aerial vehicle
US20210229810A1 (en) Information processing device, flight control method, and flight control system
WO2021259253A1 (zh) 一种轨迹跟踪方法及无人机
JP2021117502A (ja) 着陸制御装置、着陸制御方法およびプログラム。
JP2021162572A (ja) 位置算出方法及び情報処理システム
JP7031997B2 (ja) 飛行体システム、飛行体、位置測定方法、プログラム
US20230073120A1 (en) Method for Controlling an Unmanned Aerial Vehicle for an Inspection Flight to Inspect an Object and Inspection Unmanned Aerial Vehicle
WO2021056144A1 (zh) 可移动平台的返航控制方法、装置及可移动平台
KR102467855B1 (ko) 자율항법지도를 설정하는 방법 및 무인비행체가 자율항법지도에 기초하여 자율 비행하는 방법 및 이를 구현하는 시스템
JP2022077942A (ja) 計器指示値読取方法及び管理サーバ、計器指示値読取システム、プログラム

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: 18940701

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2018940701

Country of ref document: EP

Effective date: 20210603