WO2020113447A1 - 无人机的喷洒作业方法和装置 - Google Patents

无人机的喷洒作业方法和装置 Download PDF

Info

Publication number
WO2020113447A1
WO2020113447A1 PCT/CN2018/119241 CN2018119241W WO2020113447A1 WO 2020113447 A1 WO2020113447 A1 WO 2020113447A1 CN 2018119241 W CN2018119241 W CN 2018119241W WO 2020113447 A1 WO2020113447 A1 WO 2020113447A1
Authority
WO
WIPO (PCT)
Prior art keywords
spraying
points
point
spray
route
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/CN2018/119241
Other languages
English (en)
French (fr)
Inventor
李劲松
闫光
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
SZ DJI Technology Co Ltd
Original Assignee
SZ DJI Technology Co Ltd
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 SZ DJI Technology Co Ltd filed Critical SZ DJI Technology Co Ltd
Priority to CN201880072279.0A priority Critical patent/CN111433701A/zh
Priority to PCT/CN2018/119241 priority patent/WO2020113447A1/zh
Publication of WO2020113447A1 publication Critical patent/WO2020113447A1/zh
Priority to US17/337,407 priority patent/US11853080B2/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B64AIRCRAFT; AVIATION; COSMONAUTICS
    • B64DEQUIPMENT FOR FITTING IN OR TO AIRCRAFT; FLIGHT SUITS; PARACHUTES; ARRANGEMENT OR MOUNTING OF POWER PLANTS OR PROPULSION TRANSMISSIONS IN AIRCRAFT
    • B64D1/00Dropping, ejecting, releasing or receiving articles, liquids, or the like, in flight
    • B64D1/16Dropping or releasing powdered, liquid, or gaseous matter, e.g. for fire-fighting
    • B64D1/18Dropping or releasing powdered, liquid, or gaseous matter, e.g. for fire-fighting by spraying, e.g. insecticides
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/04Control of altitude or depth
    • G05D1/042Control of altitude or depth specially adapted for aircraft
    • AHUMAN NECESSITIES
    • A01AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01MCATCHING, TRAPPING OR SCARING OF ANIMALS; APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS
    • A01M7/00Special adaptations or arrangements of liquid-spraying apparatus for purposes covered by this subclass
    • A01M7/0089Regulating or controlling systems
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/10Simultaneous control of position or course in three dimensions
    • G05D1/101Simultaneous control of position or course in three dimensions specially adapted for aircraft
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T19/00Manipulating three-dimensional [3D] models or images for computer graphics
    • G06T19/003Navigation within 3D models or images
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/70Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/10Terrestrial scenes
    • G06V20/17Terrestrial scenes taken from planes or by drones
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/10Terrestrial scenes
    • G06V20/188Vegetation
    • AHUMAN NECESSITIES
    • A01AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01CPLANTING; SOWING; FERTILISING
    • A01C7/00Sowing
    • A01C7/08Broadcast seeders; Seeders depositing seeds in rows
    • A01C7/085Broadcast seeders
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B64AIRCRAFT; AVIATION; COSMONAUTICS
    • B64UUNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U2101/00UAVs specially adapted for particular uses or applications
    • B64U2101/30UAVs specially adapted for particular uses or applications for imaging, photography or videography
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B64AIRCRAFT; AVIATION; COSMONAUTICS
    • B64UUNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U2101/00UAVs specially adapted for particular uses or applications
    • B64U2101/40UAVs specially adapted for particular uses or applications for agriculture or forestry operations
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B64AIRCRAFT; AVIATION; COSMONAUTICS
    • B64UUNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U2101/00UAVs specially adapted for particular uses or applications
    • B64U2101/45UAVs specially adapted for particular uses or applications for releasing liquids or powders in-flight, e.g. crop-dusting
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B64AIRCRAFT; AVIATION; COSMONAUTICS
    • B64UUNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U2201/00UAVs characterised by their flight controls
    • B64U2201/10UAVs characterised by their flight controls autonomous, i.e. by navigating independently from ground or air stations, e.g. by using inertial navigation systems [INS]
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B64AIRCRAFT; AVIATION; COSMONAUTICS
    • B64UUNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U2201/00UAVs characterised by their flight controls
    • B64U2201/20Remote controls
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10032Satellite or aerial image; Remote sensing
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20084Artificial neural networks [ANN]
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30181Earth observation
    • G06T2207/30188Vegetation; Agriculture

Definitions

  • the invention relates to the technical field of unmanned aerial vehicles, in particular to a spraying operation method and device of an unmanned aerial vehicle.
  • Agricultural drones have been widely used in the field of agricultural plant protection due to the advantages of simple operation and high work efficiency. For example, using agricultural drones can complete operations such as pesticide spraying and seeding.
  • the operation area in the designated plane can generate an operation waypoint that can cover the entire operation area through the coverage path planning algorithm, so that the designated area can be covered and sprayed.
  • the invention provides a spraying operation method and device for a drone, which improves the safety performance and spraying effect of the drone when performing the spraying operation.
  • the present invention provides a spraying operation method for a drone, including:
  • the operation route is used for drone spraying operations, and the operation route includes a plurality of waypoints, at least one of which has altitude information.
  • the operation route is used for drone spraying operation;
  • the operation route includes a spray point, and the spray point is used to start the spray operation or Close the spraying operation;
  • the drone is controlled to perform the spraying operation according to the operation route.
  • the present invention provides a spraying operation method for a drone, including:
  • the present invention provides a drone spraying operation device, including: a memory and a processor;
  • the processor is used to execute the instruction to realize:
  • the operation route is used for drone spraying operations, and the operation route includes a plurality of waypoints, at least one of which has altitude information.
  • the processor is used to execute the instruction to realize:
  • the operation route is used for drone spraying operation;
  • the operation route includes a spray point, and the spray point is used to start the spray operation or Close the spraying operation;
  • the drone is controlled to perform the spraying operation according to the operation route.
  • the present invention provides a drone spraying operation device, including: a memory and a processor;
  • the memory is used to store instructions
  • the processor is used to execute the instruction to realize:
  • the working route based on the two-dimensional position information and the three-dimensional model; wherein the working route is used for drone spraying operations, the working route includes a plurality of waypoints, at least one of the waypoints has a height Information, the plurality of waypoints also includes the spray point.
  • the present invention provides a storage medium, including: a readable storage medium and a computer program, where the computer program is used to implement the spraying operation method of the drone provided in any of the embodiments of the first aspect.
  • the present invention provides a program product including a computer program (ie, executing instructions), the computer program being stored in a readable storage medium.
  • the processor can read the computer program from the readable storage medium, and the processor executes the computer program for executing the spraying operation method of the drone provided in any of the embodiments of the first aspect.
  • the invention provides a spraying operation method and device for an unmanned aerial vehicle.
  • the operation route with altitude information is obtained according to the two-dimensional position information and the three-dimensional model.
  • the drone performs the spraying operation according to the operation route with high information, which improves the safety performance and spraying effect of the drone during the spraying operation.
  • FIG. 1 is an architectural diagram of a drone system to which an embodiment of the present invention is applicable;
  • FIG. 2 is a flowchart of a method for spraying an unmanned aerial vehicle according to Embodiment 1 of the present invention
  • FIG. 3A is a schematic diagram of an example of a working route provided by Embodiment 1 of the present invention.
  • 3B is a schematic diagram of the terrain corresponding to the operating route 101 in FIG. 3A;
  • 3C is a schematic diagram of the terrain corresponding to the operating route 102 in FIG. 3A;
  • Embodiment 4 is a schematic diagram of deleting candidate points on a planned route provided by Embodiment 1 of the present invention.
  • Embodiment 5 is a flowchart of a method for spraying a drone provided by Embodiment 2 of the present invention.
  • Embodiment 6 is a schematic diagram of a spraying area provided by Embodiment 2 of the present invention.
  • FIG. 7 is a schematic diagram of performing a point deletion operation on a point sequence composed of key points and spray points provided by Embodiment 2 of the present invention.
  • Embodiment 8 is a flowchart of a method for spraying a drone provided by Embodiment 3 of the present invention.
  • Embodiment 9 is a flowchart of a drone spraying method provided by Embodiment 4 of the present invention.
  • FIG. 10 is a schematic structural diagram of a drone spraying operation device provided in Embodiment 1 of the present invention.
  • FIG. 1 is an architectural diagram of an unmanned aerial vehicle system to which an embodiment of the present invention is applicable.
  • the drone system may include a drone 100 and a control device 200.
  • the UAV 100 and the control device 200 can communicate to transmit data and/or instructions.
  • the drone 100 may be an agricultural drone 100 for performing spraying operations.
  • the drone 100 may receive data and/or instructions sent by the control device 200, and complete the spraying operation according to the received data and/or instructions.
  • a shooting device can be set on the drone 100.
  • control device 200 may be a computer, a smart phone, a tablet computer, and so on.
  • a software program may be pre-installed on the control device 200 to implement data processing related to spraying operations.
  • control device 200 may include a display screen or be connected to an external display device to display data related to the spray operation of the drone 100.
  • the execution subject may be a spraying operation device for a drone.
  • the spraying operation method of the drone provided in this embodiment may include:
  • the two-dimensional position information of the area to be operated is used to identify the planar coverage of the area to be operated. This embodiment does not limit the implementation of two-dimensional position information.
  • the two-dimensional position information will be described below with examples. Assume that the area to be operated is a quadrilateral.
  • the two-dimensional position information of the area to be worked on may include the two-dimensional coordinates of the vertex of the area to be worked on.
  • the two-dimensional coordinates of the four vertices of the quadrilateral are specifically included.
  • the two-dimensional position information of the area to be operated may include two-dimensional information of the boundary line of the area to be operated.
  • the two-dimensional information of the four sides of the quadrilateral is specifically included.
  • this embodiment does not limit the manner of acquiring the three-dimensional model of the area to be operated.
  • the photogrammetry and three-dimensional reconstruction technology will be described below.
  • the operation route includes multiple waypoints, and at least one waypoint has altitude information.
  • the obtained operation route may have altitude information.
  • the operation route includes multiple waypoints. At least one of the waypoints has altitude information.
  • the drone can control the flying height according to the working route with altitude information. Raising the flying height of the drone in places with high terrain improves the safety of drone spraying operations. Reduce the flying height of unmanned aerial vehicles in places with low terrain. It is that the UAV is closer to the object to be sprayed, which improves the spraying effect of the drone for spraying operations.
  • FIG. 3A is a schematic diagram of an example of a working route provided by Embodiment 1 of the present invention
  • FIG. 3B is a schematic diagram of the terrain corresponding to the working route 101 in FIG. 3A
  • FIG. 3C is a schematic diagram of the terrain corresponding to the working route 102 in FIG. 3A.
  • P0 to P10 represent waypoints.
  • a working route 101 is defined between P0 and P6.
  • Another working route 102 is defined between P7 and P10. It should be noted that this embodiment does not limit the definition of the working route.
  • the operation routes 101 and 102 there are a total of 7 operation routes in the area to be operated shown in FIG. 3A.
  • P0 and P10 may be defined as only one operation route.
  • the working route 101 includes waypoints P0 to P6.
  • the terrain corresponding to the work route 101 has a structure that projects upward in the middle.
  • the waypoints P0 to P6 may all include altitude information. In this way, through the altitude information of waypoints P0 ⁇ P6, the UAV can control the raised altitude in the area protruding upward in the middle.
  • the working route 102 includes waypoints P7 to P10.
  • the terrain corresponding to the working route 102 is a structure that is depressed downward in the middle.
  • Waypoints P7, P9-P10 may include altitude information.
  • the waypoint P8 may not include altitude information. In this way, through the altitude information of waypoints P7, P9 to P10, the UAV can fly down at a lower altitude in the middle of the area.
  • the spraying operation method of the drone provided in this embodiment can obtain an operation route with height information according to the two-dimensional position information and the three-dimensional model of the area to be operated. Therefore, the drone performs spraying operations according to the operation route with altitude information, raises the flying height where the terrain is high, and reduces the flying height where the terrain is low. Compared with the existing route that only has two-dimensional information, the spraying operation method of the drone provided in this embodiment improves the safety performance and spraying effect of the drone during the spraying operation.
  • the drone spraying operation may include:
  • the drone is controlled to perform the spraying operation, so as to achieve the imitation flight.
  • the so-called flight simulation means that the flying operation height of the drone changes with the fluctuation of the ground.
  • the drone always maintains a certain distance from the ground. It should be noted that when there are objects on the ground, for example, obstacles, crops, fruit trees, etc. to be sprayed, the ground height includes the height of the object.
  • the drone can be controlled according to the operating route to achieve imitation flight.
  • the height between the drone and the ground can be a preset distance value or a distance value input by the user.
  • the specific value of the preset distance value or the distance value input by the user is not limited.
  • obtaining the operation route according to the two-dimensional position information and the three-dimensional model may include:
  • key points have altitude information
  • waypoints include key points.
  • the route determined based on the two-dimensional position information is called a planned route.
  • the route determined based on the two-dimensional position information and the three-dimensional model is called the operating route.
  • the planned route only has two-dimensional information.
  • the operating route also has altitude information.
  • the operating route is obtained based on the planned route.
  • the key points on each planned route are determined according to the three-dimensional model, and the key points have height information.
  • the waypoints included on the operating route include key points.
  • the following also uses FIG. 3A as an example to explain planned routes, operational routes, key points, and waypoints.
  • the algorithm for determining the planned route uses the full coverage path planning algorithm.
  • a series of waypoint sequences can be obtained, including: P0, P6, P11-P20, P7, P10.
  • a planned route is determined. Passing these waypoints in turn, and performing the switching action of the spray head, you can complete the spraying of the entire area to be operated.
  • P0 and P6 is defined as a planned route.
  • P11 and P12 is defined as another planned route.
  • the drone turns on the nozzle, and point P1, the drone turns off the nozzle.
  • the drone turns on the nozzle at P11, and the drone turns off at P12.
  • spraying of the entire area to be worked can be completed.
  • the key points on the planned route can be determined according to the three-dimensional model, for example, P0 to P6.
  • P0 ⁇ P6 already have height information.
  • the finally obtained work route 101 includes waypoints P0 to P6, and P0 to P6 are also key points.
  • determining key points on each planned route according to the three-dimensional model may include:
  • candidate points are automatically inserted on the planned route according to preset rules.
  • the candidate points manually inserted by the user in the planned route may be obtained. After that, you can add height information to the candidate points according to the three-dimensional model to obtain key points.
  • the difference between candidate points and key points is that the set of candidate points includes the set of key points.
  • the set of key points is the full set or a subset of the set of candidate points.
  • the spraying operation method of the drone provided in this embodiment may further include:
  • the slope between the two candidate points is determined according to the height information of the two candidate points.
  • the candidate points can also be sorted out. Delete unnecessary candidate points.
  • the candidate points that are finally retained are the key points.
  • the slope between two points is calculated for two adjacent candidate points. If the absolute value of the slope is less than the first preset value, it means that the terrain change is relatively smooth and does not require too many candidate points, so any one of the candidate points can be deleted. If the absolute value of the slope is greater than or equal to the first preset value, it means that the terrain change is steep, and the candidate points need to be kept as key points. Then continue to select the next two adjacent candidate points and repeat the above operation. It should be noted that the specific value of the first preset value is not limited in this embodiment.
  • the planned route 103 includes candidate points Q0 to Q10.
  • select candidate points Q0 and Q1 The absolute value of the slope between Q0 and Q1 is less than the first preset value, and Q1 is deleted.
  • select candidate points Q2 and Q3. The absolute value of the slope between Q2 and Q3 is less than the first preset value, and Q3 is deleted.
  • select candidate points Q4 and Q5. The absolute value of the slope between Q4 and Q5 is greater than the first preset value, and Q4 and Q5 are retained.
  • the key points include Q0, Q2, Q4-Q10.
  • FIG. 4 is only an example of “continue to perform operations on two adjacent candidate points”.
  • continuing to perform operations on two adjacent candidate points may include: selecting the two adjacent candidate points whose slope is not calculated after the candidate points whose slope calculation has been performed according to the order of the candidate points, Continue to calculate the slope and delete points.
  • continuing to perform operations on two adjacent candidate points may include: selecting the last candidate point among the candidate points whose slope calculation has been performed according to the order of the candidate points, and in Select the first candidate point among the candidate points without calculating the slope, and continue to perform the operations of calculating the slope and deleting points.
  • the spraying operation method of the drone provided in this embodiment may further include:
  • Each candidate point pair includes two adjacent candidate points.
  • Q4 to Q7 in the state (d) of FIG. 4 as an example for description.
  • the two feature point pairs are Q4 and Q5, Q6 and Q7, respectively. Due to the slope between Q4 and Q5, the difference between the slope between Q6 and Q7 is less than the preset value, then Q5 and Q6 are deleted. Similarly, for Q7 ⁇ Q10, Q8 and Q9 can be deleted. See Figure 4(e) for the key points finally obtained.
  • determining key points on each planned route according to the three-dimensional model may include:
  • Multiple planned routes and three-dimensional models are input into the first neural network model to obtain key points on each planned route.
  • the key points are obtained through the neural network algorithm, which improves the accuracy of obtaining key points.
  • the first neural network model is used to obtain key points, and this embodiment does not limit the training process and implementation manner of the first neural network model.
  • the planned route includes operating points, which are used to start spraying operations or close spraying operations.
  • the key points include operating points.
  • the number and position of the operating points are not limited.
  • the two end points of each planned route are two operating points, and the two operating points are used to start the spraying operation and close the spraying operation, respectively.
  • P0, P6, P11 to P20, P7, and P10 may be working points.
  • This embodiment provides a spraying operation method for an unmanned aerial vehicle, which includes: acquiring two-dimensional position information of a region to be operated and a three-dimensional model of the region to be operated, and acquiring an operation route according to the two-dimensional position information and the three-dimensional model.
  • the operating route is used for drone spraying operations.
  • the operation route includes multiple waypoints, and at least one waypoint has altitude information.
  • an operation route with altitude information can be obtained.
  • the drone performs the spraying operation according to the operation route with high information, which improves the safety performance and spraying effect of the drone during the spraying operation.
  • FIG. 5 is a flowchart of a drone spraying operation method provided by Embodiment 2 of the present invention.
  • the spraying operation method of the drone provided in this embodiment on the basis of the first embodiment shown in FIGS. 2 to 4, provides another implementation manner of the spraying operation method of the drone.
  • the spraying operation method of the drone provided in this embodiment, in S202, obtaining the operation route may further include:
  • the image of the area to be operated may be a two-dimensional plane image or a three-dimensional image.
  • the spray area in the area to be worked can be determined based on the image of the area to be worked.
  • S503. Determine the spray point on each planned route based on the spray area and multiple planned routes. Among them, the spray point is used to start the spray operation or close the spray operation, and the waypoint also includes the spray point.
  • the spray area 107 can be determined according to the image of the area to be worked.
  • the spray points on the planned route 104 can be determined as O1 and O2.
  • O2 is used to start the spraying operation
  • O1 is used to close the spraying operation.
  • the operating points P13 and P14 may not need to perform the operation of opening or closing the head.
  • the spray points on the planned route 105 can be determined as O3 and O4.
  • the spray points on the planned route 106 can be determined as O5 and O6.
  • the spraying operation method of the drone based on the three-dimensional model of the area to be operated so that the operation route has height information, can also determine the planned route according to different spraying scenarios according to the image of the area to be operated On the actual spray point. Therefore, the drone can use the actual spraying point to perform the spraying operation according to the actual spraying scene. Turn on the spray head in the area where spraying is required, and turn off the spray head in the area where spraying is not required. It further improves the spraying effect and flexibility of nozzle control when the drone is spraying.
  • determining the spray area in the area to be operated according to the image may include:
  • the spray area is obtained.
  • the second neural network model can directly obtain the spray area in the area to be operated, which improves the accuracy of determining the spray area.
  • classification information of different regions in the region to be operated is obtained.
  • the spray area can be determined according to whether the areas of different classifications need to be sprayed. Increased flexibility in determining spray areas.
  • the classification information may include: crops, fruit trees, pools, mountains, obstacles, and so on.
  • determining the spray points on each planned route may include:
  • the number of intersections on each planned route is not limited, and it varies according to the shape of the spray area and the direction of the planned route.
  • the spray area 107 has a relatively regular oval shape.
  • the spray area 107 and the planned routes 104-106 have two intersections. Then determine the intersection as the spraying point.
  • the spray point may have height information.
  • the spraying operation method of the drone provided in this embodiment may further include:
  • two adjacent points are obtained according to the order in which the points are arranged on the operation route.
  • the two points include at least one key point.
  • the spray points also have height information
  • unnecessary points with height information can be deleted, the number of points is reduced, and redundant height information is deleted. Conducive to drone spraying operations.
  • the specific value of the second preset value is not limited.
  • FIG. 7 is a schematic diagram of performing a point deletion operation on a point sequence composed of key points and spray points provided by Embodiment 2 of the present invention.
  • the key points are P1 to P7
  • the spray points are O1 to O4.
  • the key point P1 is deleted.
  • key points P2 and P3 can be deleted.
  • the key point P6 and P7 since the Euclidean distance between P6 and P7 is smaller than the second preset value, here, the key point P7 is deleted.
  • the points retained after the point deletion operation please refer to state (b) in FIG. 7.
  • the spray point may have height information.
  • the spraying operation method of the drone provided in this embodiment may further include:
  • two adjacent spray points are obtained according to the order in which the spray points are arranged on the operation route.
  • the two spraying points include the first spraying point arranged in front and the second spraying point arranged behind, and the distance between the first spraying point and the second spraying point is less than the third preset value, the two spraying points are reserved Or, delete the second spray point.
  • the two spraying points include the second spraying point arranged in front and the first spraying point arranged behind, and the distance between the first spraying point and the second spraying point is less than the fourth preset value, the two spraying points are deleted Or, delete the second spray point.
  • the first spraying point is used to start the spraying operation
  • the second spraying point is used to close the spraying operation.
  • the rear spraying point B is used to close the spraying operation, and the distance between A and B is very close. At this time, the subsequent spray point B can be deleted to reduce unnecessary operations to close the spray point. Of course, it is not necessary to delete the spray point.
  • the spraying point B For two adjacent spraying points, if the previous spraying point A is used to close the spraying operation, the rear spraying point B is used to start the spraying operation, and the distance between the two spraying points is very close. Since the spraying point B should be a spraying point C for closing the spraying operation, the spraying point A before the spraying point should also be a spraying point D for starting the spraying operation. Therefore, in this scenario, you can delete the spray points A, B, or delete the spray point A, so that from the spray point D to the spray point C, the sprinkler is always on, reducing unnecessary operations to close the spray point .
  • the spray point since the spray point also has altitude information, it is possible to delete the spray point without affecting the altitude information of the route. By deleting the points of the two adjacent spraying points, unnecessary operations of opening or closing the spraying points can be reduced, which is beneficial to the drone spraying operation.
  • the specific value of the third preset value is not limited.
  • the spraying operation method of the drone provided in this embodiment may further include:
  • the third spraying point is used to close the spraying operation
  • the fourth spraying point is the first spraying point after the third spraying point to start the spraying operation.
  • the third spraying point is used to close the spraying operation.
  • the fourth spraying point is the first spraying point to start the spraying operation. For each key point between the third spray point and the fourth spray point, if the height of the key point is less than the height of the third spray point, the key point may be deleted. In this way, when the drone does not perform the spraying operation, it is possible to avoid unnecessary flying that reduces the flying height, which is beneficial for the drone to perform the spraying operation.
  • This embodiment provides a spraying operation method for a drone, which further includes: acquiring an image of the area to be operated, determining the spraying area in the area to be operated according to the image, and determining each planned route based on the spraying area and multiple planned routes Spraying point.
  • the spray point is used to start the spray operation or close the spray operation, and the waypoint also includes the spray point.
  • the spraying operation method of the drone provided in this embodiment, based on the three-dimensional model of the area to be operated so that the operation route has height information, can also be based on the image of the area to be operated, according to different spraying scenarios to determine the actual route planning Spraying point. Therefore, the drone can use the actual spraying point to perform the spraying operation according to the actual spraying scene. It further improves the spraying effect and flexibility of nozzle control when the drone is spraying.
  • FIG. 8 is a flowchart of a drone spraying operation method provided in Embodiment 3 of the present invention.
  • the execution subject may be a spraying operation device for a drone.
  • the drone spraying operation method provided in this embodiment may include:
  • S803 Obtain the operation route according to the two-dimensional position information and the spray area.
  • the operating route is used for drone spraying operations.
  • the operation route includes spray points.
  • the spray points are used to start the spray operation or close the spray operation.
  • the spraying operation method of the drone provided in this embodiment may determine the actual spraying point on the planned route according to different spraying scenarios according to the image of the area to be operated. Therefore, the drone can use the actual spray point to perform the spraying operation according to the actual spraying scene, which improves the spraying effect and the flexibility of the nozzle control when the drone performs the spraying operation.
  • obtain the operation route based on the two-dimensional location information and spray area including:
  • the operating route including:
  • get the operation route which also includes:
  • the key points have height information, and also include key points on the operation route.
  • the drone can perform the spraying operation according to the operation route with altitude information, increase the flying height in places with high terrain, and reduce the flying height in places with low terrain. It further improves the safety performance and spraying effect of the drone during the spraying operation.
  • the key points on each planned route are determined based on multiple planned routes and three-dimensional models, including:
  • the slope between the two candidate points is determined according to the height information of the two candidate points.
  • the key points on each planned route are determined based on multiple planned routes and three-dimensional models, including:
  • Multiple planned routes and three-dimensional models are input into the first neural network model to obtain key points on each planned route.
  • the spray point has height information and also includes:
  • two adjacent points are obtained according to the order in which the points are arranged on the operation route.
  • the two points include at least one key point.
  • the spray point has height information and also includes:
  • two adjacent spray points are obtained according to the order in which the spray points are arranged on the operation route.
  • the two spraying points include the first spraying point arranged in front and the second spraying point arranged behind, and the distance between the first spraying point and the second spraying point is less than the third preset value, the two spraying points are reserved Or, delete the second spray point.
  • the two spraying points include the second spraying point arranged in front and the first spraying point arranged behind, and the distance between the first spraying point and the second spraying point is less than the fourth preset value, the two spraying points are deleted Or, delete the second spray point.
  • the first spraying point is used to start the spraying operation
  • the second spraying point is used to close the spraying operation.
  • Optional also includes:
  • the third spraying point is used to close the spraying operation
  • the fourth spraying point is the first spraying point after the third spraying point to start the spraying operation.
  • the drone can be controlled to spray according to the operation route, including:
  • the drone is controlled to perform the spraying operation, so as to achieve the imitation flight.
  • determine the spray area in the area to be operated according to the image including:
  • the spray area is obtained.
  • spraying operation method of the drone provided in this embodiment is similar to the spraying operation method of the drone provided in the embodiments shown in FIGS. 2 to 7, and the execution order of the specific steps involved is different. The technical principles and technical effects are similar, and will not be repeated here.
  • This embodiment provides a spraying operation method for a drone, which includes: acquiring two-dimensional position information of an area to be operated and an image of the area to be operated, determining the spraying area in the area to be operated according to the image, and according to the two-dimensional position information and spraying Regional access to operating routes.
  • the operating route is used for drone spraying operations.
  • the operation route includes spray points, which are used to start or close the spray operation.
  • the spraying operation method of the drone provided in this embodiment can determine the actual spraying point on the planned route according to different spraying scenarios according to the image of the area to be operated. Therefore, the drone can use the actual spray point to perform the spraying operation according to the actual spraying scene, which improves the spraying effect and the flexibility of the nozzle control when the drone performs the spraying operation.
  • the execution subject may be a spraying operation device for a drone.
  • the drone spraying operation method provided in this embodiment may include:
  • the operation route is used for drone spraying operations.
  • the operation route includes multiple waypoints, at least one waypoint has altitude information, and the multiple waypoints also include spray points.
  • the spraying operation method of the drone provided in this embodiment, on the one hand, can determine the actual spraying point on the planned route according to the image of the area to be operated and according to different spraying scenarios. Therefore, the drone can use the actual spray point to perform the spraying operation according to the actual spraying scene, which improves the spraying effect and the flexibility of the nozzle control when the drone performs the spraying operation.
  • the work route it is also possible to make the work route have altitude information according to the three-dimensional model of the area to be worked. Therefore, the drone can perform the spraying operation according to the operation route with altitude information, increase the flying height in places with high terrain, and reduce the flying height in places with low terrain. It further improves the safety performance and spraying effect of the drone during the spraying operation.
  • the execution order of S902 to S903 and S904 is not limited.
  • the spraying operation method of the drone provided in this embodiment is similar to the spraying operation method of the drone provided in the embodiments shown in FIG. 2 to FIG. 8, and the technical principles and technical effects are similar, which will not be repeated here.
  • the drone spraying operation device provided in this embodiment may include a processor 11 and a memory 12.
  • the memory 12 is used to store instructions.
  • the processor 11 is used to execute instructions stored in the memory, so that the drone spraying operation device executes the drone spraying operation method provided in any of the embodiments shown in FIGS. 2 to 9, specifically The implementation method is similar to the technical effect and will not be repeated here.
  • the spraying operation device of the drone may further include a transceiver, and the transceiver is used to communicate with other devices.

Landscapes

  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Remote Sensing (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Multimedia (AREA)
  • Software Systems (AREA)
  • Pest Control & Pesticides (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Automation & Control Theory (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Computer Graphics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Zoology (AREA)
  • Environmental Sciences (AREA)
  • Wood Science & Technology (AREA)
  • Insects & Arthropods (AREA)
  • Artificial Intelligence (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
  • Navigation (AREA)

Abstract

一种无人机的喷洒作业方法和装置。其中,无人机(100)的喷洒作业方法包括:获取待作业区域的二维位置信息和待作业区域的三维模型;根据二维位置信息和三维模型获取作业航线(101,102);作业航线用于无人机进行喷洒作业,作业航线上包括多个航点(P0-P10),至少一个航点具有高度信息。根据待作业区域的二维位置信息和三维模型,可以获得具有高度信息的作业航线。无人机根据具有高度信息的作业航线进行喷洒作业,提升了无人机进行喷洒作业时的安全性能和喷洒效果。

Description

无人机的喷洒作业方法和装置 技术领域
本发明涉及无人机技术领域,尤其涉及一种无人机的喷洒作业方法和装置。
背景技术
农业无人机由于操作简单、工作效率高等优点已经广泛的应用在农业植保领域。例如,使用农业无人机可以完成农药喷洒、播撒种子等操作。
传统技术中,指定平面中的作业区域,可以通过覆盖路径规划算法生成能够覆盖整个作业区域的作业航点,从而可以对该指定区域进行覆盖喷洒。
但是,传统技术中,基于平面中的作业区域进行路径规划,规划的航线只具有二维信息,包含的信息单一,影响了农业无人机的作业效果。
发明内容
本发明提供一种无人机的喷洒作业方法和装置,提升了无人机进行喷洒作业时的安全性能和喷洒效果。
第一方面,本发明提供一种无人机的喷洒作业方法,包括:
获取待作业区域的二维位置信息和所述待作业区域的三维模型;
根据所述二维位置信息和所述三维模型获取作业航线;所述作业航线用于无人机进行喷洒作业,所述作业航线上包括多个航点,至少一个所述航点具有高度信息。
第二方面,本发明提供一种无人机的喷洒作业方法,包括:
获取待作业区域的二维位置信息和所述待作业区域的图像;
根据所述图像确定所述待作业区域中的喷洒区域;
根据所述二维位置信息和所述喷洒区域获取作业航线;其中,所述作业航线用于无人机进行喷洒作业;所述作业航线上包括喷洒点,所述喷洒点用于开启喷洒作业或者关闭喷洒作业;
根据所述作业航线控制无人机进行喷洒作业。
第三方面,本发明提供一种无人机的喷洒作业方法,包括:
获取待作业区域的二维位置信息、三维模型和图像;
根据所述图像确定所述待作业区域中的喷洒区域;
根据所述二维位置信息和所述喷洒区域获取喷洒点,所述喷洒点用于开启喷洒作业或者关闭喷洒作业;
根据所述二维位置信息和所述三维模型获取作业航线;其中,所述作业航线用于无人机进行喷洒作业,所述作业航线上包括多个航点,至少一个所述航点具有高度信息,所述多个航点还包括所述喷洒点。
第四方面,本发明提供一种无人机的喷洒作业装置,包括:存储器和处理器;
所述存储器用于存储指令;
所述处理器用于运行所述指令以实现:
获取待作业区域的二维位置信息和所述待作业区域的三维模型;
根据所述二维位置信息和所述三维模型获取作业航线;所述作业航线用于无人机进行喷洒作业,所述作业航线上包括多个航点,至少一个所述航点具有高度信息。
第五方面,本发明提供一种无人机的喷洒作业装置,包括:存储器和处理器;
所述存储器用于存储指令;
所述处理器用于运行所述指令以实现:
获取待作业区域的二维位置信息和所述待作业区域的图像;
根据所述图像确定所述待作业区域中的喷洒区域;
根据所述二维位置信息和所述喷洒区域获取作业航线;其中,所述作业航线用于无人机进行喷洒作业;所述作业航线上包括喷洒点,所述喷洒点用于开启喷洒作业或者关闭喷洒作业;
根据所述作业航线控制无人机进行喷洒作业。
第六方面,本发明提供一种无人机的喷洒作业装置,包括:存储器和处理器;
所述存储器用于存储指令;
所述处理器用于运行所述指令以实现:
获取待作业区域的二维位置信息、三维模型和图像;
根据所述图像确定所述待作业区域中的喷洒区域;
根据所述二维位置信息和所述喷洒区域获取喷洒点,所述喷洒点用于开启喷洒作业或者关闭喷洒作业;
根据所述二维位置信息和所述三维模型获取作业航线;其中,所述作业航线用于无人机进行喷洒作业,所述作业航线上包括多个航点,至少一个所述航点具有高度信息,所述多个航点还包括所述喷洒点。
第七方面,本发明提供一种存储介质,包括:可读存储介质和计算机程序,所述计算机程序用于实现上述第一方面任一实施方式提供的无人机的喷洒作业方法。
第八方面,本发明提供一种程序产品,该程序产品包括计算机程序(即执行指令),该计算机程序存储在可读存储介质中。处理器可以从可读存储介质读取该计算机程序,处理器执行该计算机程序用于执行上述第一方面任一实施方式提供的无人机的喷洒作业方法。
本发明提供一种无人机的喷洒作业方法和装置,通过获取待作业区域的二维位置信息和待作业区域的三维模型,根据二维位置信息和三维模型获取具有高度信息的作业航线。无人机根据具有高度信息的作业航线进行喷洒作业,提升了无人机进行喷洒作业时的安全性能和喷洒效果。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍,显而易见地,下面描述中的附图是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1为本发明实施例适用的无人机系统的架构图;
图2为本发明实施例一提供的无人机的喷洒作业方法的流程图;
图3A为本发明实施例一提供的作业航线的一个示例的示意图;
图3B为图3A中作业航线101对应的地形的示意图;
图3C为图3A中作业航线102对应的地形的示意图;
图4为本发明实施例一提供的删除规划航线上候选点的示意图;
图5为本发明实施例二提供的无人机的喷洒作业方法的流程图;
图6为本发明实施例二提供的喷洒区域的示意图;
图7为本发明实施例二提供的对关键点和喷洒点组成的点序列执行删点操作的示意图;
图8为本发明实施例三提供的无人机的喷洒作业方法的流程图;
图9为本发明实施例四提供的无人机的喷洒作业方法的流程图;
图10为本发明实施例一提供的无人机的喷洒作业装置的结构示意图。
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、完整地描述,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。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。
图1为本发明实施例适用的无人机系统的架构图。如图1所示,无人机系统可以包括无人机100和控制设备200。无人机100与控制设备200之间可以进行通信,以传输数据和/或指令。可选的,无人机100可以为农业无人机100,用于执行喷洒作业。无人机100执行喷洒作业时,可以接收控制设备200发送的数据和/或指令,并根据接收到的数据和/或指令完成喷洒作业。
需要说明的是,本发明实施例对于无人机100的结构、型号不做限定。可选的,无人机100上可以设置拍摄设备。
需要说明的是,本发明实施例对于控制设备200的实现方式不做限定。例如,控制设备200可以为电脑、智能手机、平板电脑,等等。可选的,控制设备200上可以预先安装软件程序,以实现与喷洒作业相关的数据处理。可选的,控制设备200可以包括显示屏,或者与外部显示设备连接,以显示与无人机100喷洒作业相关的数据。
图2为本发明实施例一提供的无人机的喷洒作业方法的流程图。本实施例提供的无人机的喷洒作业方法,执行主体可以为无人机的喷洒作业装置。 如图2所示,本实施例提供的无人机的喷洒作业方法,可以包括:
S201、获取待作业区域的二维位置信息和待作业区域的三维模型。
其中,待作业区域的二维位置信息用于标识待作业区域的平面覆盖范围。本实施例对于二维位置信息的实现方式不做限定。
下面结合示例对二维位置信息进行说明。假设,待作业区域为四边形。
可选的,在一种实现方式中,待作业区域的二维位置信息可以包括待作业区域的顶点的二维坐标。在本示例中,具体包括四边形的四个顶点的二维坐标。
可选的,在另一种实现方式中,待作业区域的二维位置信息可以包括待作业区域的边界线的二维信息。在本示例中,具体包括四边形的四条边的二维信息。
其中,待作业区域的三维模型是指在三维坐标系中为待作业区域建立的具有三维位置信息的模型。通过三维模型,可以获取模型中每一点的高度。比如,待作业区域中的平地、山坡、甚至是山坡上的树木,都可以知道高度信息。可选的,待作业区域的三维模型还可以包括其他维度的信息。例如,颜色信息,等。
需要说明的是,本实施例对于待作业区域的三维模型的获取方式不做限定。下面对其中的摄影测量与三维重建技术进行说明。
首先,使用摄影测量技术,从多个角度覆盖拍摄地形的多张照片,并记录拍摄的位姿和全球定位系统(Global Positioning System,GPS)信息。比如,使用P4r等测绘飞行器。然后,使用三维重建技术(Structure from motion,SFM)就可以恢复出地形的三维模型。
S202、根据二维位置信息和三维模型获取作业航线。其中,作业航线用于无人机进行喷洒作业。作业航线上包括多个航点,至少一个航点具有高度信息。
具体的,根据可以标识出待作业区域的平面覆盖范围的二维位置信息和具有高度信息的三维模型,获得的作业航线可以具有高度信息。其中,作业航线上包括多个航点。其中的至少一个航点具有高度信息。无人机可以根据具有高度信息的作业航线控制飞行的高度。在地形较高的地方提高无人机的飞行高空,提升了无人机进行喷洒作业的安全性。在地形较低的地方降低无 人机的飞行高度,是的无人机更加贴近待喷洒的物体,提升了无人机进行喷洒作业的喷洒效果。
下面通过示例对作业航线、航点进行说明。
参见图3A~图3C。图3A为本发明实施例一提供的作业航线的一个示例的示意图,图3B为图3A中作业航线101对应的地形的示意图,图3C为图3A中作业航线102对应的地形的示意图。
如图3A所示,P0~P10表示航点。P0和P6之间定义为一条作业航线101。P7和P10之间定义为另一条作业航线102。需要说明的是,本实施例对于作业航线的定义不做限定。按照作业航线101、102的定义,图3A所示的待作业区域中,一共有7条作业航线。可选的,在一些应用场景中,P0和P10之间可以仅定义为一条作业航线。
如图3A和图3B所示,作业航线101上包括航点P0~P6。作业航线101对应的地形,为中间向上凸出的结构。航点P0~P6可以均包括高度信息。这样,通过航点P0~P6的高度信息,无人机可以在中间向上凸出的区域控制升高飞行高度。
如图3A和图3C所示,作业航线102上包括航点P7~P10。作业航线102对应的地形,为中间向下凹陷的结构。航点P7、P9~P10可以包括高度信息。航点P8不可以包括高度信息。这样,通过航点P7、P9~P10的高度信息,无人机可以在中间向下凹陷的区域降低高度飞行。
可见,本实施例提供的无人机的喷洒作业方法,根据待作业区域的二维位置信息和三维模型,可以获得具有高度信息的作业航线。从而,无人机根据具有高度信息的作业航线进行喷洒作业,在地形较高的地方升高飞行高度,在地形较低的地方降低飞行高度。相比于现有的航线只具有二维信息,本实施例提供的无人机的喷洒作业方法,提升了无人机进行喷洒作业时的安全性能和喷洒效果。
可选的,S202中,无人机进行喷洒作业,可以包括:
获取预设距离值或者用户输入的距离值。
根据预设距离值或者用户输入的距离值,以及作业航线控制无人机进行喷洒作业,以实现仿地飞行。
具体的,所谓仿地飞行,是指无人机的飞行作业高度随着地面起伏变化 而变化。无人机始终与地面高度保持一定的距离。需要说明的是,当地面上有物体时,例如,障碍物,需要喷洒的农作物、果树,等,地面高度包括所述物体的高度。
由于作业航线具有高度信息,因此,可以根据作业航线控制无人机实现仿地飞行。无人机与地面之间的高度可以为预设距离值或者是用户输入的距离值。
需要说明的是,本实施例对于预设距离值或者用户输入的距离值的具体取值不做限定。
可选的,S202中,根据二维位置信息和三维模型获取作业航线,可以包括:
根据二维位置信息确定多条规划航线。
根据三维模型确定每条规划航线上的关键点,获得作业航线。其中,关键点具有高度信息,航点包括关键点。
在本实施例中,根据二维位置信息确定的航线称为规划航线。根据二维位置信息和三维模型确定的航线称为作业航线。规划航线只具有二维信息。而作业航线除了具有二维信息之外,还具有高度信息。作业航线是基于规划航线获得的。具体的,根据三维模型确定每条规划航线上的关键点,关键点具有高度信息。最终,作业航线上包括的航点包括关键点。
需要说明的是,本实施例对于一条规划航线的定义,与一条作业航线的定义相同。
需要说明的是,本实施例对于如何根据二维位置信息确定多条规划航线的实现方式不做限定,采用现有的路径规划算法即可。
下面还以图3A为例,对规划航线、作业航线、关键点和航点进行说明。其中,确定规划航线的算法采用全覆盖路径规划算法。
如图3A所示,对于待作业区域,采用全覆盖路径规划算法,可以获得一系列的航点序列,包括:P0、P6、P11~P20、P7、P10。每两个相邻的航点,确定了一条规划航线。依次经过这些航点,并执行喷药头的开关动作,便可以完成整个待作业区域的喷洒。比如,P0和P6之间定义为一条规划航线。P11和P12之间定义为另一条规划航线。P0点无人机开启喷头,P1点无人机关闭喷头。P11点无人机开启喷头,P12点无人机关闭喷头。以此类推,可以 完成整个待作业区域的喷洒。对于航点P0和P6确定的规划航线来说,可以根据三维模型确定该规划航线上的关键点,例如,P0~P6。此时,P0~P6已经具有了高度信息。最终获得的作业航线101上包括航点P0~P6,而且,P0~P6也为关键点。
可选的,根据三维模型确定每条规划航线上的关键点,可以包括:
按照预设规则在规划航线上插入候选点,或者,获取用户针对规划航线输入的候选点。
根据三维模型获取候选点的高度信息,获得关键点。
具体的,在一种实现方式中,按照预设规则自动在规划航线上插入候选点。在另一种实现方式中,可以获取用户在规划航线中手动插入的候选点。之后,可以根据三维模型为候选点添加高度信息,获得关键点。
其中,候选点与关键点的区别在于,候选点组成的集合包括关键点组成的集合。或者说,关键点的集合为候选点的集合的全集或者子集。
需要说明的是,本实施例对于预设规则的具体实现方式不做限定。可选的,预设规则可以包括:按照预设间隔在规划航线上插入候选点。可选的,预设规则可以包括:按照预设的飞行时间间隔在规划航线上插入候选点。此时,无人机在相邻的两个候选点之间飞行的时间相同。
可选的,本实施例提供的无人机的喷洒作业方法,获得关键点之前,还可以包括:
获取相邻的两个候选点。
根据两个候选点的高度信息确定两个候选点之间的斜率。
若斜率的绝对值小于第一预设数值,则删除其中任意一个候选点,并继续执行对相邻的两个候选点的操作。
具体的,在规划航线上插入候选点之后,还可以对候选点进行整理。对不需要的候选点进行删除。最终保留下来的候选点即为关键点。在该种实现方式中,对于相邻的两个候选点计算两点之间的斜率。如果斜率的绝对值小于第一预设数值,说明地形变化较为平缓,不需要过多的候选点,因此可以删除其中的任意一个候选点。如果斜率的绝对值大于或者等于第一预设数值,说明地形变化较为陡峭,需要保留候选点为关键点。然后继续选取下两个相邻的候选点,重复执行上述操作。需要说明的是,本实施例对于第一预设数 值的具体取值不做限定。
通过计算两个相邻的候选点之间的斜率,可以删除不必要的候选点,减少了点的数量,删除了冗余的高度信息,有利于无人机进行喷洒作业。
下面通过示例进行说明。
图4为本发明实施例一提供的删除规划航线上候选点的示意图。如图4所示,在状态(a),规划航线103上包括候选点Q0~Q10。首先,选取候选点Q0和Q1。Q0和Q1之间的斜率的绝对值小于第一预设数值,删除Q1。然后,参见状态(b),选取候选点Q2和Q3。Q2和Q3之间的斜率的绝对值小于第一预设数值,删除Q3。然后,参见状态(c),选取候选点Q4和Q5。Q4和Q5之间的斜率的绝对值大于第一预设数值,保留Q4和Q5。最终,参见状态(d),关键点包括Q0、Q2、Q4~Q10。
需要说明的是,图4仅是对“继续执行对相邻的两个候选点的操作”的一个示例。在该示例中,继续执行对相邻的两个候选点的操作,可以包括:按照候选点的排列顺序,在已经进行斜率计算的候选点之后选取未计算斜率的相邻的两个候选点,继续执行计算斜率和删点的操作。
可选的,在另一个示例中,继续执行对相邻的两个候选点的操作,可以包括:按照候选点的排列顺序,在已经进行斜率计算的候选点中选取最后一个候选点,以及在未计算斜率的候选点中选取第一个候选点,继续执行计算斜率和删点的操作。
以图4中(a)为例进行说明。首先选取Q0和Q1。由于Q0和Q1之间的斜率的绝对值小于第一预设数值,删除Q1。之后,选取Q0和Q2。继续执行计算斜率和删点的操作。以此类推。
可选的,本实施例提供的无人机的喷洒作业方法,获得关键点之前,还可以包括:
获取相邻的四个候选点组成两个候选点对。其中,每个候选点对包括相邻的两个候选点。
分别获取两个候选点对中两个候选点之间的斜率。
若两个候选点对中两个候选点之间的斜率的差值小于预设值,则删除其中任意两个候选点,并继续执行对相邻的四个候选点的操作。
通过计算两个候选点对之间的斜率,可以删除不必要的候选点,减少了 点的数量,删除了冗余的高度信息,有利于无人机进行喷洒作业。
以图4状态(d)中Q4~Q7为例进行说明。两个特征点对分别为Q4和Q5、Q6和Q7。由于Q4和Q5之间的斜率,与Q6和Q7之间的斜率的差值小于预设值,则删除Q5和Q6。相似的,对于Q7~Q10,可以删除Q8和Q9。最终获得的关键点参见图4(e)。
需要说明的是,继续执行对相邻的四个候选点的操作,其中,相邻的四个候选点可以参见上述相邻的两个候选点的定义,原理相似,此处不再赘述。
可选的,根据三维模型确定每条规划航线上的关键点,可以包括:
将多条规划航线和三维模型输入第一神经网络模型,获得每条规划航线上的关键点。
在该种实现方式中,通过神经网络算法获得关键点,提升了获得关键点的准确性。其中,第一神经网络模型用于获取关键点,本实施例对于第一神经网络模型的训练过程和实现方式不做限定。
可选的,规划航线上包括作业点,作业点用于开启喷洒作业或者关闭喷洒作业。
关键点包括作业点。
其中,本实施例对于作业点的数量和位置不做限定。
可选的,每条规划航线的两个端点为两个作业点,两个作业点分别用于开启喷洒作业和关闭喷洒作业。
下面通过示例对作业点进行说明。如图4所示,P0、P6、P11~P20、P7、P10可以为作业点。
本实施例提供一种无人机的喷洒作业方法,包括:获取待作业区域的二维位置信息和待作业区域的三维模型,根据二维位置信息和三维模型获取作业航线。其中,作业航线用于无人机进行喷洒作业。作业航线上包括多个航点,至少一个航点具有高度信息。本实施例提供的无人机的喷洒作业方法,根据待作业区域的二维位置信息和三维模型,可以获得具有高度信息的作业航线。无人机根据具有高度信息的作业航线进行喷洒作业,提升了无人机进行喷洒作业时的安全性能和喷洒效果。
图5为本发明实施例二提供的无人机的喷洒作业方法的流程图。本实施 例提供的无人机的喷洒作业方法,在图2~图4所示实施例一的基础上,提供了无人机的喷洒作业方法的另一种实现方式。如图5所示,本实施例提供的无人机的喷洒作业方法,S202中,获得作业航线,还可以包括:
S501、获取待作业区域的图像。
其中,待作业区域的图像可以为二维平面图像或者三维图像。
S502、根据图像确定待作业区域中的喷洒区域。
具体的,对于整个待作业区域而言,例如一块农田,其中可能包括障碍物、水域等不需要喷洒的区域。因此,可以根据待作业区域的图像确定待作业区域中的喷洒区域。
S503、根据喷洒区域和多条规划航线,确定每条规划航线上的喷洒点。其中,喷洒点用于开启喷洒作业或者关闭喷洒作业,航点还包括喷洒点。
下面通过示例对喷洒区域、喷洒点进行说明。
图6为本发明实施例二提供的喷洒区域的示意图。如图6所示,根据待作业区域的图像可以确定喷洒区域107。对于规划航线104~106,均穿过喷洒区域107。根据喷洒区域107和规划航线104,可以确定规划航线104上的喷洒点为O1和O2。其中,O2用于开启喷洒作业,O1用于关闭喷洒作业。此时,作业点P13和P14可以不必执行开启或者关闭喷头的操作。相似的,根据喷洒区域107和规划航线105,可以确定规划航线105上的喷洒点为O3和O4。根据喷洒区域107和规划航线106,可以确定规划航线106上的喷洒点为O5和O6。
需要说明,为了方便将图6与图5进行比对,其他信息保持不变,可以参见关于图3A的描述。
需要说明的是,本实施例对于喷洒区域的数量不做限定。
可见,本实施例提供的无人机的喷洒作业方法,在根据待作业区域的三维模型使得作业航线具有高度信息的基础上,还可以根据待作业区域的图像,根据不同的喷洒场景确定规划航线上实际的喷洒点。从而,无人机可以根据实际的喷洒场景,利用实际的喷洒点进行喷洒作业。在需要喷洒的区域中开启喷头,在不需要喷洒的区域中关闭喷头。进一步提升了无人机进行喷洒作业时的喷洒效果和喷头控制的灵活性。
可选的,S502,根据图像确定待作业区域中的喷洒区域,可以包括:
将图像输入第二神经网络模型,获取喷洒区域。
或者,
将图像输入第三神经网络模型,获取每个单位图像对应的分类信息。
根据每个单位图像对应的分类信息,获取喷洒区域。
可选的,在一种实现方式中,通过第二神经网络模型,可以直接获得待作业区域中的喷洒区域,提升了确定喷洒区域的准确性。在另一种实现方式中,通过第三神经网络模型,首先获得待作业区域中不同区域的分类信息。进而,可以根据不同分类的区域是否需要喷洒确定喷洒区域。提升了确定喷洒区域的灵活性。例如,分类信息可以包括:农作物、果树、水池、山、障碍物,等等。
可选的,S503中,根据喷洒区域和多条规划航线,确定每条规划航线上的喷洒点,可以包括:
获取喷洒区域与每条规划航线的交叉点。
根据交叉点获取每条规划航线上的喷洒点。
需要说明的是,本实施例对于每条规划航线上交叉点的个数不做限定,根据喷洒区域的形状以及规划航线的方向而有所不同。
例如,在图6中,喷洒区域107为比较规则的椭圆形。喷洒区域107与规划航线104~106均有两个交叉点。则确定交叉点为喷洒点。
可选的,喷洒点可以具有高度信息。本实施例提供的无人机的喷洒作业方法,还可以包括:
针对每条作业航线上的关键点和喷洒点组成的点集合,按照点在该作业航线上的排列顺序,获取相邻的两个点。其中,两个点至少包括一个关键点。
若两个点之间的欧式距离小于第二预设数值,则删除其中任意一个关键点,并继续执行对相邻的两个点的操作。
由于喷洒点也具有高度信息,通过对距离较近的喷洒点和关键点进行删点处理,可以删除不必要的具有高度信息的点,减少了点的数量,删除了冗余的高度信息,有利于无人机进行喷洒作业。
其中,继续执行对相邻的两个点的操作中,关于相邻的两个点的定义,可以参见图4所示示例中的说明,此处不再赘述。
需要说明的是,本实施例对于第二预设数值的具体取值不做限定。
下面通过示例进行说明。
图7为本发明实施例二提供的对关键点和喷洒点组成的点序列执行删点操作的示意图。如图7中状态(a)所示,关键点为P1~P7,喷洒点为O1~O4。对于喷洒点O1和关键点P1,由于O1与P1之间的欧式距离小于第二预设数值,则删除关键点P1。相似的,可以删除关键点P2和P3。对于关键点P6和P7,由于P6和P7之间的欧式距离小于第二预设数值,此处,删除关键点P7。删点操作后保留的点可以参见如图7中状态(b)。
可选的,喷洒点可以具有高度信息。本实施例提供的无人机的喷洒作业方法,还可以包括:
针对每条作业航线上的喷洒点,按照喷洒点在该作业航线上的排列顺序,获取相邻的两个喷洒点。
若两个喷洒点包括排列在前的第一喷洒点和排列在后的第二喷洒点,且第一喷洒点与第二喷洒点之前的距离小于第三预设数值,则保留两个喷洒点,或者,删除第二喷洒点。
若两个喷洒点包括排列在前的第二喷洒点和排列在后的第一喷洒点,且第一喷洒点与第二喷洒点之前的距离小于第四预设数值,则删除两个喷洒点,或者,删除第二喷洒点。
其中,第一喷洒点用于开启喷洒作业,第二喷洒点用于关闭喷洒作业。
下面通过示例进行说明。
对于两个相邻的喷洒点,如果在前的喷洒点A用于开启喷洒作业,在后的喷洒点B用于关闭喷洒作业,且A、B之间距离很近。此时,可以删除后面的喷洒点B,以减少不必要的关闭喷洒点的操作。当然,也可以不删喷洒点。
对于两个相邻的喷洒点,如果在前的喷洒点A用于关闭喷洒作业,在后的喷洒点B用于开启喷洒作业,且这两个喷洒点的距离很近。由于喷洒点B之后还应该是一个用于关闭喷洒作业的喷洒点C,喷洒点A之前还应该是一个用于开启喷洒作业的喷洒点D。因此,在该场景中,可以删除喷洒点A、B,或者,删除喷洒点A,使得从喷洒点D开始直至喷洒点C为止,喷头一直处于打开状态,减少了不必要的关闭喷洒点的操作。
可见,由于喷洒点也具有高度信息,因此可以针对喷洒点进行删点操作 而不影响航线的高度信息。通过对相邻的两个喷洒点进行删点处理,可以减少不必要的打开或者关闭喷洒点的操作,有利于无人机进行喷洒作业。
需要说明的是,本实施例对于第三预设数值的具体取值不做限定。
可选的,本实施例提供的无人机的喷洒作业方法,还可以包括:
针对每条作业航线上的关键点和喷洒点组成的点集合,按照点在该作业航线上的排列顺序,若位于第三喷洒点与第四喷洒点之间的关键点的高度小于第三喷洒点的高度,则删除第三喷洒点与第四喷洒点之间的关键点。其中,第三喷洒点用于关闭喷洒作业,第四喷洒点为第三喷洒点之后的第一个用于开启喷洒作业的喷洒点。
具体的,第三喷洒点用于关闭喷洒作业。第四喷洒点为之后的第一个开启喷洒作业的喷洒点。对于位于第三喷洒点与第四喷洒点之间的每个关键点,如果关键点的高度小于第三喷洒点的高度,则可以删除该关键点。这样,当无人机没有执行喷洒操作时,可以避免不必要的降低飞行高度的飞行,有利于无人机进行喷洒作业。
本实施例提供一种无人机的喷洒作业方法,还包括:获取待作业区域的图像,根据图像确定待作业区域中的喷洒区域,根据喷洒区域和多条规划航线,确定每条规划航线上的喷洒点。其中,喷洒点用于开启喷洒作业或者关闭喷洒作业,航点还包括喷洒点。本实施例提供的无人机的喷洒作业方法,在根据待作业区域的三维模型使得作业航线具有高度信息的基础上,还可以根据待作业区域的图像,根据不同的喷洒场景确定规划航线上实际的喷洒点。从而,无人机可以根据实际的喷洒场景,利用实际的喷洒点进行喷洒作业。进一步提升了无人机进行喷洒作业时的喷洒效果和喷头控制的灵活性。
图8为本发明实施例三提供的无人机的喷洒作业方法的流程图。本实施例提供的无人机的喷洒作业方法,执行主体可以为无人机的喷洒作业装置。如图8所示,本实施例提供的无人机的喷洒作业方法,可以包括:
S801、获取待作业区域的二维位置信息和待作业区域的图像。
S802、根据图像确定待作业区域中的喷洒区域。
S803、根据二维位置信息和喷洒区域获取作业航线。其中,作业航线用于无人机进行喷洒作业。作业航线上包括喷洒点,喷洒点用于开启喷洒作业 或者关闭喷洒作业。
本实施例提供的无人机的喷洒作业方法,可以根据待作业区域的图像,根据不同的喷洒场景确定规划航线上实际的喷洒点。从而,无人机可以根据实际的喷洒场景,利用实际的喷洒点进行喷洒作业,提升了无人机进行喷洒作业时的喷洒效果和喷头控制的灵活性。
可选的,根据二维位置信息和喷洒区域获取作业航线,包括:
根据二维位置信息确定多条规划航线。
根据喷洒区域和多条规划航线,获取作业航线。
可选的,根据喷洒区域和多条规划航线,获取作业航线,包括:
获取喷洒区域与每条规划航线的交叉点。
根据交叉点获取每条规划航线上的喷洒点。
可选的,获取作业航线,还包括:
获取待作业区域的三维模型。
根据多条规划航线和三维模型确定每条规划航线上的关键点。其中,关键点具有高度信息,作业航线上还包括关键点。
具体的,在根据待作业区域的图像,根据不同的喷洒场景确定规划航线上实际的喷洒点的基础上,还可以根据待作业区域的三维模型使得作业航线具有高度信息。从而,无人机可以根据具有高度信息的作业航线进行喷洒作业,在地形较高的地方升高飞行高度,在地形较低的地方降低飞行高度。进一步提升了无人机进行喷洒作业时的安全性能和喷洒效果。
可选的,根据多条规划航线和三维模型确定每条规划航线上的关键点,包括:
按照预设规则在规划航线上插入候选点,或者,获取用户针对规划航线输入的候选点。
根据三维模型获取候选点的高度信息,获得关键点。
可选的,获得关键点之前,还包括:
获取相邻的两个候选点。
根据两个候选点的高度信息确定两个候选点之间的斜率。
若斜率的绝对值小于第一预设数值,则删除其中任意一个候选点,并继续执行对相邻的两个候选点的操作。
可选的,根据多条规划航线和三维模型确定每条规划航线上的关键点,包括:
将多条规划航线和三维模型输入第一神经网络模型,获得每条规划航线上的关键点。
可选的,喷洒点具有高度信息,还包括:
针对每条作业航线上的关键点和喷洒点组成的点集合,按照点在该作业航线上的排列顺序,获取相邻的两个点。其中,两个点至少包括一个关键点。
若两个点之间的欧式距离小于第二预设数值,则删除其中任意一个关键点,并继续执行对相邻的两个点的操作。
可选的,喷洒点具有高度信息,还包括:
针对每条作业航线上的喷洒点,按照喷洒点在该作业航线上的排列顺序,获取相邻的两个喷洒点。
若两个喷洒点包括排列在前的第一喷洒点和排列在后的第二喷洒点,且第一喷洒点与第二喷洒点之前的距离小于第三预设数值,则保留两个喷洒点,或者,删除第二喷洒点。
若两个喷洒点包括排列在前的第二喷洒点和排列在后的第一喷洒点,且第一喷洒点与第二喷洒点之前的距离小于第四预设数值,则删除两个喷洒点,或者,删除第二喷洒点。
其中,第一喷洒点用于开启喷洒作业,第二喷洒点用于关闭喷洒作业。
可选的,还包括:
针对每条作业航线上的关键点和喷洒点组成的点集合,按照点在该作业航线上的排列顺序,若位于第三喷洒点与第四喷洒点之间的关键点的高度小于第三喷洒点的高度,则删除第三喷洒点与第四喷洒点之间的关键点。其中,第三喷洒点用于关闭喷洒作业,第四喷洒点为第三喷洒点之后的第一个用于开启喷洒作业的喷洒点。
可选的,根据作业航线控制无人机进行喷洒作业,包括:
获取预设距离值或者用户输入的距离值。
根据预设距离值或者用户输入的距离值,以及作业航线控制无人机进行喷洒作业,以实现仿地飞行。
可选的,根据图像确定待作业区域中的喷洒区域,包括:
将图像输入第二神经网络模型,获取喷洒区域。
或者,
将图像输入第三神经网络模型,获取每个单位图像对应的分类信息。
根据每个单位图像对应的分类信息,获取喷洒区域。
需要说明的是,本实施例提供的无人机的喷洒作业方法,与图2~图7所示实施例提供的无人机的喷洒作业方法相似,涉及具体步骤的执行顺序不同。技术原理和技术效果相似,此处不再赘述。
本实施例提供一种无人机的喷洒作业方法,包括:获取待作业区域的二维位置信息和待作业区域的图像,根据图像确定待作业区域中的喷洒区域,根据二维位置信息和喷洒区域获取作业航线。其中,作业航线用于无人机进行喷洒作业。作业航线上包括喷洒点,喷洒点用于开启喷洒作业或者关闭喷洒作业。本实施例提供的无人机的喷洒作业方法,可以根据待作业区域的图像,根据不同的喷洒场景确定规划航线上实际的喷洒点。从而,无人机可以根据实际的喷洒场景,利用实际的喷洒点进行喷洒作业,提升了无人机进行喷洒作业时的喷洒效果和喷头控制的灵活性。
图9为本发明实施例四提供的无人机的喷洒作业方法的流程图。本实施例提供的无人机的喷洒作业方法,执行主体可以为无人机的喷洒作业装置。如图9所示,本实施例提供的无人机的喷洒作业方法,可以包括:
S901、获取待作业区域的二维位置信息、三维模型和图像。
S902、根据图像确定待作业区域中的喷洒区域。
S903、根据二维位置信息和喷洒区域获取喷洒点,喷洒点用于开启喷洒作业或者关闭喷洒作业。
S904、根据二维位置信息和三维模型获取作业航线。其中,作业航线用于无人机进行喷洒作业,作业航线上包括多个航点,至少一个航点具有高度信息,多个航点还包括喷洒点。
本实施例提供的无人机的喷洒作业方法,一方面,可以根据待作业区域的图像,根据不同的喷洒场景确定规划航线上实际的喷洒点。从而,无人机可以根据实际的喷洒场景,利用实际的喷洒点进行喷洒作业,提升了无人机进行喷洒作业时的喷洒效果和喷头控制的灵活性。另一方面,还可以根据待 作业区域的三维模型使得作业航线具有高度信息。从而,无人机可以根据具有高度信息的作业航线进行喷洒作业,在地形较高的地方升高飞行高度,在地形较低的地方降低飞行高度。进一步提升了无人机进行喷洒作业时的安全性能和喷洒效果。
需要说明的是,本实施例对于S902~S903与S904的执行顺序不做限定。本实施例提供的无人机的喷洒作业方法,与图2~图8所示实施例提供的无人机的喷洒作业方法相似,技术原理和技术效果相似,此处不再赘述。
图10为本发明实施例一提供的无人机的喷洒作业装置的结构示意图。如图10所示,本实施例提供的无人机的喷洒作业装置,可以包括:处理器11和存储器12。其中,所述存储器12用于存储指令。所述处理器11用于执行所述存储器中存储的指令,以使所述无人机的喷洒作业装置执行图2~图9所示任一实施例提供的无人机的喷洒作业方法,具体实现方式和技术效果类似,这里不再赘述。可选的,该无人机的喷洒作业装置还可以包括收发器,所述收发器用于和其他设备通信。
本领域普通技术人员可以理解:实现上述各方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成。前述的程序可以存储于一计算机可读取存储介质中。该程序在执行时,执行包括上述各方法实施例的步骤;而前述的存储介质包括:ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是:以上各实施例仅用以说明本发明实施例的技术方案,而非对其限制;尽管参照前述各实施例对本发明实施例进行了详细的说明,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,或者对其中部分或者全部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发明实施例技术方案的范围。

Claims (55)

  1. 一种无人机的喷洒作业方法,其特征在于,包括:
    获取待作业区域的二维位置信息和所述待作业区域的三维模型;
    根据所述二维位置信息和所述三维模型获取作业航线;所述作业航线用于无人机进行喷洒作业,所述作业航线上包括多个航点,至少一个所述航点具有高度信息。
  2. 根据权利要求1所述的方法,其特征在于,所述根据所述二维位置信息和所述三维模型获取作业航线,包括:
    根据所述二维位置信息确定多条规划航线;
    根据所述三维模型确定每条所述规划航线上的关键点,获得所述作业航线;其中,所述关键点具有高度信息,所述航点包括所述关键点。
  3. 根据权利要求2所述的方法,其特征在于,所述根据所述三维模型确定每条所述规划航线上的关键点,包括:
    按照预设规则在所述规划航线上插入候选点,或者,获取用户针对所述规划航线输入的候选点;
    根据所述三维模型获取所述候选点的高度信息,获得所述关键点。
  4. 根据权利要求3所述的方法,其特征在于,所述获得所述关键点之前,还包括:
    获取相邻的两个候选点;
    根据所述两个候选点的高度信息确定所述两个候选点之间的斜率;
    若所述斜率的绝对值小于第一预设数值,则删除其中任意一个候选点,并继续执行对相邻的两个候选点的操作。
  5. 根据权利要求2所述的方法,其特征在于,所述根据所述三维模型确定每条所述规划航线上的关键点,包括:
    将所述多条规划航线和所述三维模型输入第一神经网络模型,获得每条所述规划航线上的关键点。
  6. 根据权利要求2-5任一项所述的方法,其特征在于,所述规划航线上包括作业点,所述作业点用于开启喷洒作业或者关闭喷洒作业;
    所述关键点包括所述作业点。
  7. 根据权利要求6所述的方法,其特征在于,每条所述规划航线的两个端点为两个作业点,所述两个作业点分别用于开启喷洒作业和关闭喷洒作业。
  8. 根据权利要求2-5任一项所述的方法,其特征在于,所述获得所述作业航线,还包括:
    获取所述待作业区域的图像;
    根据所述图像确定所述待作业区域中的喷洒区域;
    根据所述喷洒区域和所述多条规划航线,确定每条所述规划航线上的喷洒点;其中,所述喷洒点用于开启喷洒作业或者关闭喷洒作业,所述航点还包括所述喷洒点。
  9. 根据权利要求8所述的方法,其特征在于,所述根据所述图像确定所述待作业区域中的喷洒区域,包括:
    将所述图像输入第二神经网络模型,获取所述喷洒区域;
    或者,
    将所述图像输入第三神经网络模型,获取每个单位图像对应的分类信息;
    根据所述每个单位图像对应的分类信息,获取所述所述喷洒区域。
  10. 根据权利要求8所述的方法,其特征在于,所述根据所述喷洒区域和所述多条规划航线,确定每条所述规划航线上的喷洒点,包括:
    获取所述喷洒区域与每条所述规划航线的交叉点;
    根据所述交叉点获取每条所述规划航线上的喷洒点。
  11. 根据权利要求8-10任一项所述的方法,其特征在于,所述喷洒点具有高度信息,还包括:
    针对每条所述作业航线上的关键点和喷洒点组成的点集合,按照点在该作业航线上的排列顺序,获取相邻的两个点;其中,所述两个点至少包括一个关键点;
    若所述两个点之间的欧式距离小于第二预设数值,则删除其中任意一个关键点,并继续执行对相邻的两个点的操作。
  12. 根据权利要求8-11任一项所述的方法,其特征在于,所述喷洒点具有高度信息,还包括:
    针对每条所述作业航线上的喷洒点,按照喷洒点在该作业航线上的排列顺序,获取相邻的两个喷洒点;
    若所述两个喷洒点包括排列在前的第一喷洒点和排列在后的第二喷洒点,且所述第一喷洒点与所述第二喷洒点之前的距离小于第三预设数值,则保留所述两个喷洒点,或者,删除所述第二喷洒点;
    若所述两个喷洒点包括排列在前的第二喷洒点和排列在后的第一喷洒点,且所述第一喷洒点与所述第二喷洒点之前的距离小于第四预设数值,则删除所述两个喷洒点,或者,删除所述第二喷洒点;
    其中,所述第一喷洒点用于开启喷洒作业,所述第二喷洒点用于关闭喷洒作业。
  13. 根据权利要求8-12任一项所述的方法,其特征在于,还包括:
    针对每条所述作业航线上的关键点和喷洒点组成的点集合,按照点在该作业航线上的排列顺序,若位于第三喷洒点与第四喷洒点之间的关键点的高度小于所述第三喷洒点的高度,则删除所述第三喷洒点与所述第四喷洒点之间的所述关键点;其中,所述第三喷洒点用于关闭喷洒作业,所述第四喷洒点为所述第三喷洒点之后的第一个用于开启喷洒作业的喷洒点。
  14. 根据权利要求1-13任一项所述的方法,其特征在于,所述无人机进行喷洒作业,包括:
    所述无人机根据预设距离值或者用户输入的距离值,以及所述作业航线进行喷洒作业,以实现仿地飞行。
  15. 一种无人机的喷洒作业方法,其特征在于,包括:
    获取待作业区域的二维位置信息和所述待作业区域的图像;
    根据所述图像确定所述待作业区域中的喷洒区域;
    根据所述二维位置信息和所述喷洒区域获取作业航线;其中,所述作业航线用于无人机进行喷洒作业;所述作业航线上包括喷洒点,所述喷洒点用于开启喷洒作业或者关闭喷洒作业;
    根据所述作业航线控制无人机进行喷洒作业。
  16. 根据权利要求15所述的方法,其特征在于,所述根据所述二维位置信息和所述喷洒区域获取作业航线,包括:
    根据所述二维位置信息确定多条规划航线;
    根据所述喷洒区域和所述多条规划航线,获取所述作业航线。
  17. 根据权利要求16所述的方法,其特征在于,所述根据所述喷洒区域和所述多条规划航线,获取所述作业航线,包括:
    获取所述喷洒区域与每条所述规划航线的交叉点;
    根据所述交叉点获取每条所述规划航线上的喷洒点。
  18. 根据权利要求16或17所述的方法,其特征在于,所述获取所述作业航线,还包括:
    获取所述待作业区域的三维模型;
    根据所述多条规划航线和所述三维模型确定每条所述规划航线上的关键点;其中,所述关键点具有高度信息,所述作业航线上还包括所述关键点。
  19. 根据权利要求18所述的方法,其特征在于,所述根据所述多条规划航线和所述三维模型确定每条所述规划航线上的关键点,包括:
    按照预设规则在所述规划航线上插入候选点,或者,获取用户针对所述规划航线输入的候选点;
    根据所述三维模型获取所述候选点的高度信息,获得所述关键点。
  20. 根据权利要求19所述的方法,其特征在于,所述获得所述关键点之前,还包括:
    获取相邻的两个候选点;
    根据所述两个候选点的高度信息确定所述两个候选点之间的斜率;
    若所述斜率的绝对值小于第一预设数值,则删除其中任意一个候选点,并继续执行对相邻的两个候选点的操作。
  21. 根据权利要求18所述的方法,其特征在于,所述根据所述多条规划航线和所述三维模型确定每条所述规划航线上的关键点,包括:
    将所述多条规划航线和所述三维模型输入第一神经网络模型,获得每条所述规划航线上的关键点。
  22. 根据权利要求18-21任一项所述的方法,其特征在于,所述喷洒点具有高度信息,还包括:
    针对每条所述作业航线上的关键点和喷洒点组成的点集合,按照点在该作业航线上的排列顺序,获取相邻的两个点;其中,所述两个点至少包括一个关键点;
    若所述两个点之间的欧式距离小于第二预设数值,则删除其中任意一个关键点,并继续执行对相邻的两个点的操作。
  23. 根据权利要求18-22任一项所述的方法,其特征在于,所述喷洒点具有高度信息,还包括:
    针对每条所述作业航线上的喷洒点,按照喷洒点在该作业航线上的排列顺序,获取相邻的两个喷洒点;
    若所述两个喷洒点包括排列在前的第一喷洒点和排列在后的第二喷洒点,且所述第一喷洒点与所述第二喷洒点之前的距离小于第三预设数值,则保留所述两个喷洒点,或者,删除所述第二喷洒点;
    若所述两个喷洒点包括排列在前的第二喷洒点和排列在后的第一喷洒点,且所述第一喷洒点与所述第二喷洒点之前的距离小于第四预设数值,则删除 所述两个喷洒点,或者,删除所述第二喷洒点;
    其中,所述第一喷洒点用于开启喷洒作业,所述第二喷洒点用于关闭喷洒作业。
  24. 根据权利要求18-23任一项所述的方法,其特征在于,还包括:
    针对每条所述作业航线上的关键点和喷洒点组成的点集合,按照点在该作业航线上的排列顺序,若位于第三喷洒点与第四喷洒点之间的关键点的高度小于所述第三喷洒点的高度,则删除所述第三喷洒点与所述第四喷洒点之间的所述关键点;其中,所述第三喷洒点用于关闭喷洒作业,所述第四喷洒点为所述第三喷洒点之后的第一个用于开启喷洒作业的喷洒点。
  25. 根据权利要求18-24任一项所述的方法,其特征在于,所述根据所述作业航线控制无人机进行喷洒作业,包括:
    获取预设距离值或者用户输入的距离值;
    根据所述预设距离值或者所述用户输入的距离值,以及所述作业航线控制所述无人机进行喷洒作业,以实现仿地飞行。
  26. 根据权利要求15-25任一项所述的方法,其特征在于,所述根据所述图像确定所述待作业区域中的喷洒区域,包括:
    将所述图像输入第二神经网络模型,获取所述喷洒区域;
    或者,
    将所述图像输入第三神经网络模型,获取每个单位图像对应的分类信息;
    根据所述每个单位图像对应的分类信息,获取所述所述喷洒区域。
  27. 一种无人机的喷洒作业方法,其特征在于,包括:
    获取待作业区域的二维位置信息、三维模型和图像;
    根据所述图像确定所述待作业区域中的喷洒区域;
    根据所述二维位置信息和所述喷洒区域获取喷洒点,所述喷洒点用于开启喷洒作业或者关闭喷洒作业;
    根据所述二维位置信息和所述三维模型获取作业航线;其中,所述作业 航线用于无人机进行喷洒作业,所述作业航线上包括多个航点,至少一个所述航点具有高度信息,所述多个航点还包括所述喷洒点。
  28. 一种无人机的喷洒作业装置,其特征在于,包括:存储器和处理器;
    所述存储器用于存储指令;
    所述处理器用于运行所述指令以实现:
    获取待作业区域的二维位置信息和所述待作业区域的三维模型;
    根据所述二维位置信息和所述三维模型获取作业航线;所述作业航线用于无人机进行喷洒作业,所述作业航线上包括多个航点,至少一个所述航点具有高度信息。
  29. 根据权利要求28所述的装置,其特征在于,所述处理器具体用于:
    根据所述二维位置信息确定多条规划航线;
    根据所述三维模型确定每条所述规划航线上的关键点,获得所述作业航线;其中,所述关键点具有高度信息,所述航点包括所述关键点。
  30. 根据权利要求29所述的装置,其特征在于,所述处理器具体用于:
    按照预设规则在所述规划航线上插入候选点,或者,获取用户针对所述规划航线输入的候选点;
    根据所述三维模型获取所述候选点的高度信息,获得所述关键点。
  31. 根据权利要求30所述的装置,其特征在于,所述处理器还用于:
    获取相邻的两个候选点;
    根据所述两个候选点的高度信息确定所述两个候选点之间的斜率;
    若所述斜率的绝对值小于第一预设数值,则删除其中任意一个候选点,并继续执行对相邻的两个候选点的操作。
  32. 根据权利要求29所述的装置,其特征在于,所述处理器具体用于:
    将所述多条规划航线和所述三维模型输入第一神经网络模型,获得每条所述规划航线上的关键点。
  33. 根据权利要求29-32任一项所述的装置,其特征在于,所述规划航线上包括作业点,所述作业点用于开启喷洒作业或者关闭喷洒作业;
    所述关键点包括所述作业点。
  34. 根据权利要求33所述的装置,其特征在于,每条所述规划航线的两个端点为两个作业点,所述两个作业点分别用于开启喷洒作业和关闭喷洒作业。
  35. 根据权利要求29-32任一项所述的装置,其特征在于,所述处理器还用于:
    获取所述待作业区域的图像;
    根据所述图像确定所述待作业区域中的喷洒区域;
    根据所述喷洒区域和所述多条规划航线,确定每条所述规划航线上的喷洒点;其中,所述喷洒点用于开启喷洒作业或者关闭喷洒作业,所述航点还包括所述喷洒点。
  36. 根据权利要求35所述的装置,其特征在于,所述处理器具体用于:
    将所述图像输入第二神经网络模型,获取所述喷洒区域;
    或者,
    将所述图像输入第三神经网络模型,获取每个单位图像对应的分类信息;
    根据所述每个单位图像对应的分类信息,获取所述所述喷洒区域。
  37. 根据权利要求35所述的装置,其特征在于,所述处理器具体用于:
    获取所述喷洒区域与每条所述规划航线的交叉点;
    根据所述交叉点获取每条所述规划航线上的喷洒点。
  38. 根据权利要求35-37任一项所述的装置,其特征在于,所述处理器还用于:
    针对每条所述作业航线上的关键点和喷洒点组成的点集合,按照点在该 作业航线上的排列顺序,获取相邻的两个点;其中,所述两个点至少包括一个关键点;
    若所述两个点之间的欧式距离小于第二预设数值,则删除其中任意一个关键点,并继续执行对相邻的两个点的操作。
  39. 根据权利要求35-38任一项所述的装置,其特征在于,所述喷洒点具有高度信息,所述处理器还用于:
    针对每条所述作业航线上的喷洒点,按照喷洒点在该作业航线上的排列顺序,获取相邻的两个喷洒点;
    若所述两个喷洒点包括排列在前的第一喷洒点和排列在后的第二喷洒点,且所述第一喷洒点与所述第二喷洒点之前的距离小于第三预设数值,则保留所述两个喷洒点,或者,删除所述第二喷洒点;
    若所述两个喷洒点包括排列在前的第二喷洒点和排列在后的第一喷洒点,且所述第一喷洒点与所述第二喷洒点之前的距离小于第四预设数值,则删除所述两个喷洒点,或者,删除所述第二喷洒点;
    其中,所述第一喷洒点用于开启喷洒作业,所述第二喷洒点用于关闭喷洒作业。
  40. 根据权利要求35-39任一项所述的装置,其特征在于,所述处理器还用于:
    针对每条所述作业航线上的关键点和喷洒点组成的点集合,按照点在该作业航线上的排列顺序,若位于第三喷洒点与第四喷洒点之间的关键点的高度小于所述第三喷洒点的高度,则删除所述第三喷洒点与所述第四喷洒点之间的所述关键点;其中,所述第三喷洒点用于关闭喷洒作业,所述第四喷洒点为所述第三喷洒点之后的第一个用于开启喷洒作业的喷洒点。
  41. 根据权利要求28-40任一项所述的装置,其特征在于,所述处理器具体用于:
    所述无人机根据预设距离值或者用户输入的距离值,以及所述作业航线进行喷洒作业,以实现仿地飞行。
  42. 一种无人机的喷洒作业装置,其特征在于,包括:存储器和处理器;
    所述存储器用于存储指令;
    所述处理器用于运行所述指令以实现:
    获取待作业区域的二维位置信息和所述待作业区域的图像;
    根据所述图像确定所述待作业区域中的喷洒区域;
    根据所述二维位置信息和所述喷洒区域获取作业航线;其中,所述作业航线用于无人机进行喷洒作业;所述作业航线上包括喷洒点,所述喷洒点用于开启喷洒作业或者关闭喷洒作业;
    根据所述作业航线控制无人机进行喷洒作业。
  43. 根据权利要求42所述的装置,其特征在于,所述处理器具体用于:
    根据所述二维位置信息确定多条规划航线;
    根据所述喷洒区域和所述多条规划航线,获取所述作业航线。
  44. 根据权利要求43所述的装置,其特征在于,所述处理器具体用于:
    获取所述喷洒区域与每条所述规划航线的交叉点;
    根据所述交叉点获取每条所述规划航线上的喷洒点。
  45. 根据权利要求43或44所述的装置,其特征在于,所述处理器还用于:
    获取所述待作业区域的三维模型;
    根据所述多条规划航线和所述三维模型确定每条所述规划航线上的关键点;其中,所述关键点具有高度信息,所述作业航线上还包括所述关键点。
  46. 根据权利要求45所述的装置,其特征在于,所述处理器具体用于:
    按照预设规则在所述规划航线上插入候选点,或者,获取用户针对所述规划航线输入的候选点;
    根据所述三维模型获取所述候选点的高度信息,获得所述关键点。
  47. 根据权利要求46所述的装置,其特征在于,所述处理器还用于:
    获取相邻的两个候选点;
    根据所述两个候选点的高度信息确定所述两个候选点之间的斜率;
    若所述斜率的绝对值小于第一预设数值,则删除其中任意一个候选点,并继续执行对相邻的两个候选点的操作。
  48. 根据权利要求45所述的装置,其特征在于,所述处理器具体用于:
    将所述多条规划航线和所述三维模型输入第一神经网络模型,获得每条所述规划航线上的关键点。
  49. 根据权利要求45-48任一项所述的装置,其特征在于,所述处理器还用于:
    针对每条所述作业航线上的关键点和喷洒点组成的点集合,按照点在该作业航线上的排列顺序,获取相邻的两个点;其中,所述两个点至少包括一个关键点;
    若所述两个点之间的欧式距离小于第二预设数值,则删除其中任意一个关键点,并继续执行对相邻的两个点的操作。
  50. 根据权利要求45-49任一项所述的装置,其特征在于,所述处理器还用于:
    针对每条所述作业航线上的喷洒点,按照喷洒点在该作业航线上的排列顺序,获取相邻的两个喷洒点;
    若所述两个喷洒点包括排列在前的第一喷洒点和排列在后的第二喷洒点,且所述第一喷洒点与所述第二喷洒点之前的距离小于第三预设数值,则保留所述两个喷洒点,或者,删除所述第二喷洒点;
    若所述两个喷洒点包括排列在前的第二喷洒点和排列在后的第一喷洒点,且所述第一喷洒点与所述第二喷洒点之前的距离小于第四预设数值,则删除所述两个喷洒点,或者,删除所述第二喷洒点;
    其中,所述第一喷洒点用于开启喷洒作业,所述第二喷洒点用于关闭喷洒作业。
  51. 根据权利要求45-50任一项所述的装置,其特征在于,所述处理器还用于:
    针对每条所述作业航线上的关键点和喷洒点组成的点集合,按照点在该作业航线上的排列顺序,若位于第三喷洒点与第四喷洒点之间的关键点的高度小于所述第三喷洒点的高度,则删除所述第三喷洒点与所述第四喷洒点之间的所述关键点;其中,所述第三喷洒点用于关闭喷洒作业,所述第四喷洒点为所述第三喷洒点之后的第一个用于开启喷洒作业的喷洒点。
  52. 根据权利要求45-51任一项所述的装置,其特征在于,所述处理器具体用于:
    获取预设距离值或者用户输入的距离值;
    根据所述预设距离值或者所述用户输入的距离值,以及所述作业航线控制所述无人机进行喷洒作业,以实现仿地飞行。
  53. 根据权利要求42-52任一项所述的装置,其特征在于,所述处理器具体用于:
    将所述图像输入第二神经网络模型,获取所述喷洒区域;
    或者,
    将所述图像输入第三神经网络模型,获取每个单位图像对应的分类信息;
    根据所述每个单位图像对应的分类信息,获取所述喷洒区域。
  54. 一种无人机的喷洒作业装置,其特征在于,包括:存储器和处理器;
    所述存储器用于存储指令;
    所述处理器用于运行所述指令以实现:
    获取待作业区域的二维位置信息、三维模型和图像;
    根据所述图像确定所述待作业区域中的喷洒区域;
    根据所述二维位置信息和所述喷洒区域获取喷洒点,所述喷洒点用于开启喷洒作业或者关闭喷洒作业;
    根据所述二维位置信息和所述三维模型获取作业航线;其中,所述作业 航线用于无人机进行喷洒作业,所述作业航线上包括多个航点,至少一个所述航点具有高度信息,所述多个航点还包括所述喷洒点。
  55. 一种存储介质,其特征在于,包括:可读存储介质和计算机程序,所述计算机程序用于实现如权利要求1-27中任一项所述的无人机的喷洒作业方法。
PCT/CN2018/119241 2018-12-04 2018-12-04 无人机的喷洒作业方法和装置 Ceased WO2020113447A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
CN201880072279.0A CN111433701A (zh) 2018-12-04 2018-12-04 无人机的喷洒作业方法和装置
PCT/CN2018/119241 WO2020113447A1 (zh) 2018-12-04 2018-12-04 无人机的喷洒作业方法和装置
US17/337,407 US11853080B2 (en) 2018-12-04 2021-06-02 Spray operation method and device for unmanned aerial vehicle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/119241 WO2020113447A1 (zh) 2018-12-04 2018-12-04 无人机的喷洒作业方法和装置

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/337,407 Continuation US11853080B2 (en) 2018-12-04 2021-06-02 Spray operation method and device for unmanned aerial vehicle

Publications (1)

Publication Number Publication Date
WO2020113447A1 true WO2020113447A1 (zh) 2020-06-11

Family

ID=70975245

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/119241 Ceased WO2020113447A1 (zh) 2018-12-04 2018-12-04 无人机的喷洒作业方法和装置

Country Status (3)

Country Link
US (1) US11853080B2 (zh)
CN (1) CN111433701A (zh)
WO (1) WO2020113447A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112506217A (zh) * 2020-11-19 2021-03-16 一飞(海南)科技有限公司 利用三维模型快速生成集群无人机表演立体画面的方法

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112528506A (zh) * 2020-12-15 2021-03-19 广州极飞科技有限公司 作业剂量的确定方法、装置、无人设备及存储介质
CN113325135A (zh) * 2021-05-27 2021-08-31 深圳市中博科创信息技术有限公司 无人机路径规划方法、装置、计算机设备
CN113826598A (zh) * 2021-09-10 2021-12-24 宁波权智科技有限公司 一种基于神经网络的无人机撒药方法及装置
CN114091896B (zh) * 2021-11-22 2022-04-29 中化现代农业有限公司 农机运行状态分析方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105116911A (zh) * 2015-07-20 2015-12-02 广州极飞电子科技有限公司 无人机喷药方法
CN105159319A (zh) * 2015-09-29 2015-12-16 广州极飞电子科技有限公司 一种无人机的喷药方法及无人机
KR20160082773A (ko) * 2014-12-29 2016-07-11 경운대학교 산학협력단 항공방제용 드론
CN107544548A (zh) * 2017-10-20 2018-01-05 广州极飞科技有限公司 控制无人机作业的方法、装置及无人机
CN108519775A (zh) * 2017-10-30 2018-09-11 北京博鹰通航科技有限公司 一种精准喷洒的无人机系统及其控制方法
CN108684282A (zh) * 2018-04-11 2018-10-23 北京麦飞科技有限公司 一种农业察打一体机系统及喷洒控制方法

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104808660B (zh) * 2015-03-04 2017-10-03 中南大学 凹凸混合复杂多边形农田无人机喷洒作业航迹规划方法
US9592912B1 (en) * 2016-03-08 2017-03-14 Unmanned Innovation, Inc. Ground control point assignment and determination system
US10353401B2 (en) * 2017-05-01 2019-07-16 EAVision Corporation Detecting and following terrain height autonomously along a flight path
CN107728642B (zh) * 2017-10-30 2021-03-09 北京博鹰通航科技有限公司 一种无人机飞行控制系统及其方法
US10991258B2 (en) * 2018-04-13 2021-04-27 Suzhou Eavision Robotic Technologies Co., Ltd. Real-time learning and detection of a border in a flight path
US11277956B2 (en) * 2018-07-26 2022-03-22 Bear Flag Robotics, Inc. Vehicle controllers for agricultural and industrial applications

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20160082773A (ko) * 2014-12-29 2016-07-11 경운대학교 산학협력단 항공방제용 드론
CN105116911A (zh) * 2015-07-20 2015-12-02 广州极飞电子科技有限公司 无人机喷药方法
CN105159319A (zh) * 2015-09-29 2015-12-16 广州极飞电子科技有限公司 一种无人机的喷药方法及无人机
CN107544548A (zh) * 2017-10-20 2018-01-05 广州极飞科技有限公司 控制无人机作业的方法、装置及无人机
CN108519775A (zh) * 2017-10-30 2018-09-11 北京博鹰通航科技有限公司 一种精准喷洒的无人机系统及其控制方法
CN108684282A (zh) * 2018-04-11 2018-10-23 北京麦飞科技有限公司 一种农业察打一体机系统及喷洒控制方法

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112506217A (zh) * 2020-11-19 2021-03-16 一飞(海南)科技有限公司 利用三维模型快速生成集群无人机表演立体画面的方法

Also Published As

Publication number Publication date
US11853080B2 (en) 2023-12-26
CN111433701A (zh) 2020-07-17
US20210286378A1 (en) 2021-09-16

Similar Documents

Publication Publication Date Title
US11853080B2 (en) Spray operation method and device for unmanned aerial vehicle
CN111142557B (zh) 无人机路径规划方法、系统、计算机设备及可读存储介质
JP2021111385A (ja) 協調的3dマップデータ融合プラットフォーム及びその仮想世界システムを可能にするシステム及び方法
WO2020164092A1 (zh) 图像处理方法、设备、可移动平台、无人机及存储介质
CN109845715A (zh) 农药喷洒控制方法、装置、设备以及存储介质
CN109682381A (zh) 基于全向视觉的大视场场景感知方法、系统、介质及设备
CN110568447A (zh) 视觉定位的方法、装置及计算机可读介质
US20240399249A1 (en) Data processing method based on voxel data, and server, medium and computer program product
JP7701932B2 (ja) 複数の特徴タイプに基づく効率的位置特定
WO2021051278A1 (zh) 地表特征识别方法、设备、无人机及计算机可读存储介质
WO2021081960A1 (zh) 一种航线规划方法、设备、系统及存储介质
CN111750857B (zh) 航线生成方法、装置、终端及存储介质
US20240161377A1 (en) Physics-based simulation of human characters in motion
CN114041097B (zh) 无人飞行器的航线平滑处理方法、装置及控制终端
CN118838383A (zh) 基于机器学习的无人机在工程施工中路径规划系统及方法
CN115053882A (zh) 航空施药方法、装置、电子设备及存储介质
Sun et al. UAV autonomous obstacle avoidance via causal reinforcement learning
Pan et al. Pheno-robot: An auto-digital modelling system for in-situ phenotyping in the field
CN113877210A (zh) 游戏场景的转换方法、系统、服务器及计算机可读存储介质
CN121007563B (zh) 一种用于未知森林区域的旋翼无人机视觉导航方法和系统
CN120121061B (zh) 一种基于人工智能的低空通航保障方法及系统
CN110749325A (zh) 航迹规划方法和装置
WO2021081896A1 (zh) 喷洒无人机的作业规划方法、系统和设备
CN118758318A (zh) 一种面向浓烟多雾环境下机器人的局部路径规划方法
CN117826867B (zh) 无人机集群路径规划方法、装置和存储介质

Legal Events

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

Ref document number: 18942379

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: 18942379

Country of ref document: EP

Kind code of ref document: A1