WO2021217375A1 - 无人机及其航点补充方法和装置、数据处理设备 - Google Patents
无人机及其航点补充方法和装置、数据处理设备 Download PDFInfo
- Publication number
- WO2021217375A1 WO2021217375A1 PCT/CN2020/087331 CN2020087331W WO2021217375A1 WO 2021217375 A1 WO2021217375 A1 WO 2021217375A1 CN 2020087331 W CN2020087331 W CN 2020087331W WO 2021217375 A1 WO2021217375 A1 WO 2021217375A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- waypoint
- waypoints
- flight
- supplementary
- flight controller
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
Definitions
- This application relates to the field of unmanned aerial vehicles, in particular to an unmanned aerial vehicle and its waypoint supplement method and device, and data processing equipment.
- the computing equipment of the UAV mainly includes the flight controller FC (flight control) and the data processing equipment AP (application processer).
- FC flight controller
- AP application processer
- the FC is used to complete flight control and other real-time flight control tasks, such as waypoint function (FC passes Perform the waypoint function and control the UAV to fly to the corresponding waypoint);
- FC passes Perform the waypoint function and control the UAV to fly to the corresponding waypoint);
- AP is used to undertake real-time tasks such as image processing with low computing power requirements.
- FC has good real-time performance but poor storage capacity. At present, FC supports up to 99 waypoints, but this order of magnitude is difficult to meet the long-distance and long-endurance operations such as pipeline inspections and power inspections in industrial applications.
- FC determines the waypoints it needs to supplement according to the local storage capacity and the consumption of the locally stored waypoints, and then sends a waypoint supplement request to the AP in real time , AP passively responds to FC's waypoint supplement request, dynamically pushes the supplementary waypoint to FC, and FC dynamically updates the local waypoint.
- This dynamic waypoint supplement method will increase the calculation of FC, greatly consumes FC's computing resources, and is not conducive to the execution of flight control tasks by FC; at the same time, this dynamic waypoint supplement method depends heavily on the communication bandwidth between FC and AP.
- This application provides an unmanned aerial vehicle and its waypoint supplement method and device, and data processing equipment.
- an embodiment of the present application provides a method for replenishing waypoints for a drone, where the drone includes a flight controller, and the method includes:
- the preset waypoint database stores multiple waypoints
- the waypoint supplement package carries the supplementary waypoints
- an embodiment of the present application provides a waypoint supplement device for a drone, the drone includes a flight controller, and the device includes:
- Storage device for storing program instructions
- One or more processors call program instructions stored in the storage device, and when the program instructions are executed, the one or more processors are individually or collectively configured to implement the following operations:
- the preset waypoint database stores multiple waypoints
- the waypoint supplement package carries the supplementary waypoints
- an embodiment of the present application provides a data processing device, and the data processing device includes:
- the waypoint supplementing device for the drone described in the second aspect of the embodiments of the present application is supported by the main body.
- an embodiment of the present application provides a method for replenishing waypoints for a drone.
- the drone includes a flight controller, and the method includes:
- the waypoint supplement package carries at least one supplementary waypoint
- the supplementary waypoint is the first number and forecast of the waypoint currently consumed by the drone predicted by the data processing device according to the data processing device. It is assumed that the waypoint database is determined, and the preset waypoint database stores multiple waypoints.
- an embodiment of the present application provides a waypoint supplement device for a drone, the drone includes a flight controller, and the device includes:
- Storage device for storing program instructions
- One or more processors call program instructions stored in the storage device, and when the program instructions are executed, the one or more processors are individually or collectively configured to implement the following operations:
- the waypoint supplement package carries at least one supplementary waypoint
- the supplementary waypoint is the first number and forecast of the waypoint currently consumed by the drone predicted by the data processing device according to the data processing device. It is assumed that the waypoint database is determined, and the preset waypoint database stores multiple waypoints.
- an embodiment of the present application provides a drone, and the drone includes:
- a flight controller located on the fuselage
- the waypoint supplement device of the drone described in the fifth aspect of the embodiments of the present application is supported by the fuselage.
- an embodiment of the present application provides an unmanned aerial vehicle system, including a fuselage, a flight controller provided on the fuselage, and a data processing device communicatively connected with the flight controller;
- the data processing device is used to predict the first number of waypoints currently consumed by the drone, and according to the first number, determine supplementary waypoints from a preset waypoint database, and send waypoint supplements Packaged to the flight controller, the preset waypoint database stores multiple waypoints, and the waypoint supplementary package carries the supplementary waypoints;
- the flight controller is configured to: receive the waypoint supplement package sent by the data processing device, and perform waypoint supplementation according to the waypoint supplement package.
- this application actively predicts the first number of waypoints currently consumed by the drone through the data processing device, and then determines supplementary waypoints from the preset waypoint database according to the predicted first number , And then send the waypoint supplementary package to the flight controller, which reduces the calculation of the flight controller, thereby ensuring the smoothness of the flight controller performing the waypoint function, and saving the calculation resources of the flight controller; at the same time, no flight controller is required
- the real-time request of the flight controller saves the link width between the flight controller and the data processing device, thereby reducing the communication bandwidth requirement between the flight controller and the data processing device.
- the dynamic waypoint supplement method in this application is suitable for long-distance and long-endurance operations such as pipeline inspections and power inspections in industrial applications.
- Fig. 1A is a schematic structural diagram of an unmanned aerial vehicle system in an embodiment of the present application
- FIG. 1B is a schematic structural diagram of the unmanned aerial vehicle system of the embodiment shown in FIG. 1A;
- FIG. 1C is another schematic structural diagram of the unmanned aerial vehicle system of the embodiment shown in FIG. 1A;
- FIG. 2 is a schematic flow chart of a method for replenishing waypoints of a drone in an embodiment of the present application
- Fig. 3 is a schematic diagram of a model for predicting the first number of waypoints currently consumed by a drone through an RBF neural network model in an embodiment of the present application;
- FIG. 4 is a schematic structural diagram of a waypoint supplement device for a drone in an embodiment of the present application
- FIG. 5 is a schematic flowchart of a method for replenishing waypoints of a drone in another embodiment of the present application
- Fig. 6 is a schematic structural diagram of a waypoint supplement device for an unmanned aerial vehicle in another embodiment of the present application.
- FC long-distance and long-endurance operations such as pipeline inspections and power inspections in industry applications
- FC the largest number of waypoints supported by FC is difficult to meet.
- the AP passively responds to FC's waypoint supplementary requests and dynamically pushes the supplementary waypoints to FC.
- FC dynamically updates local waypoints.
- This kind of waypoint supplement method of FC active request and AP passive response increases the calculation of FC, which greatly consumes FC's computing resources, which is not conducive to the execution of flight control tasks by FC. On the other hand, it affects the communication bandwidth between FC and AP. The requirements are higher.
- the embodiment of the present application actively predicts the first number of waypoints currently consumed by the drone through the data processing device, and then determines the supplementary waypoints from the preset waypoint database according to the predicted first number, and then sends the flight control
- the waypoint replenishment package is sent by the aircraft.
- the dynamic waypoint replenishment method of the embodiment of this application reduces the calculation of the flight controller, thereby ensuring the smoothness of the flight controller performing the waypoint function, and saving the calculation resources of the flight controller; at the same time; ,
- the dynamic waypoint supplement method in the embodiments of the present application does not require a real-time request from the flight controller, which saves the link width between the flight controller and the data processing device, thereby reducing the communication bandwidth between the flight controller and the data processing device need.
- the dynamic waypoint supplement method in the embodiment of this application is suitable for long-distance and long-endurance operations such as pipeline inspections and power inspections in industrial applications.
- the UAV system may include a UAV 100 and a data processing device 200, and the UAV 100 and the data processing device 200 are in communication connection.
- the drone 100 may include a fuselage 110 and a flight controller 120 provided on the fuselage 110, and the data processing device 200 may be communicatively connected with the flight controller 110.
- the data processing device 200 is provided on the fuselage 100, that is, the data processing device 200 is a part of the drone, and the data processing device 200 is in communication connection with the flight controller 120.
- the data processing device 200 is an image processing module of the drone 100; it should be understood that in addition to the flight controller 120, the data processing device 200 may also be other modules of the drone 100.
- the data processing module 200 may not be a part of the drone 100.
- the data processing device 200 is an external terminal remote from the drone 100.
- the external terminal may be a remote control of the drone 100, or other remote control terminals capable of controlling the drone 100, such as a mobile phone. , Tablet computers, smart bracelets, etc.
- executing the waypoint function through the flight controller means controlling the drone to fly to the corresponding waypoint through the flight controller.
- the embodiment of the application provides a method for replenishing the waypoint of a drone.
- the execution subject of the method for replenishing the waypoint of a drone in the embodiment of the application is a data processing device.
- the data processing device is a drone.
- the data processing device is the image processing module of the UAV; of course, in addition to the flight controller, the data processing device can also be other modules.
- the data processing equipment is a remote control terminal of a drone.
- the execution subject of the waypoint replenishment method of the drone is an example of the data processing device. It should be understood that when the execution subject of the waypoint replenishment method of the drone is other equipment, in the following embodiments Replace the data processing equipment with this equipment accordingly.
- FIG. 2 is a schematic flowchart of a method for replenishing waypoints of a drone in an embodiment of the present application; please refer to FIG. 2, the method for replenishing waypoints of a drone in an embodiment of the present application may include S201 to S203.
- a supplementary waypoint is determined from a preset waypoint database, where the preset waypoint database stores multiple waypoints;
- the waypoint supplementary package is sent to the flight controller, and the waypoint supplementary package carries supplementary waypoints.
- the waypoint currently consumed by the drone refers to the waypoint currently executed by the drone during the process of executing the waypoint function by the flight controller. Therefore, it is understandable that in the embodiment of this application, the data processing The device predicts the first number during the flight of the drone.
- the first number can be predicted through different strategies. For example, in some embodiments, the first number of waypoints currently consumed by the drone is predicted according to flight parameters. When the flight controller executes the waypoint function, the speed at which the UAV consumes waypoints is related to the flight parameters. Therefore, the first number is predicted based on the flight parameters with high accuracy.
- the speed at which the drone consumes waypoints may also be related to other factors.
- the second number of waypoints currently sent to the flight controller that is, the second number of waypoints currently sent to the flight controller by the data processing device
- the waypoint information of the waypoint predict the first number.
- the last actual waypoint received by the flight controller can be based on the supplementary waypoint and the actual UAV in the last waypoint supplement package (that is, the waypoint supplement package last sent by the data processing device to the flight controller).
- the third number of waypoints consumed is determined.
- the waypoint information may include at least one of the fourth number of waypoints actually received by the flight controller last time and the density of the waypoints actually received last time by the flight controller.
- the distance between points represents the distance between adjacent waypoints, the smaller the distance between adjacent waypoints, the higher the density of waypoints.
- the waypoint information includes the fourth number or the density of the waypoints actually received by the flight controller last time; for example, the waypoint information includes the fourth number and the density of the waypoints actually received by the flight controller last time. degree.
- the waypoint information is determined by the data processing device; optionally, the waypoint information is determined by the flight controller, and then the flight controller feeds back the waypoint information to the data processing device.
- the fourth number is determined by the flight controller, and the density of the waypoints actually received by the flight controller last time is determined by the data processing device and/or the flight controller.
- the method for determining the fourth quantity may include:
- the flight controller receives part of the supplementary waypoints in the waypoint supplementary package;
- the flight controller receives the waypoint supplementary pack. All supplementary waypoints in.
- the number of supplementary waypoints in the waypoint supplementary package is the first quantity. Therefore, when the third quantity is less than the first quantity, the fourth quantity is equal to the third quantity; when the third quantity is greater than the first quantity, the fourth quantity is equal to the first quantity.
- the fourth quantity can be fed back by the flight controller.
- the data processing device receives a response message returned by the flight controller for the waypoint supplementary package, and the response message carries the fourth quantity; It should be understood that the data processing device may also obtain the fourth quantity in other ways.
- the data processing device reads the third quantity from the flight controller after sending the waypoint supplement package to the flight controller; of course, the flight controller also The fourth quantity can be fed back to the data processing device in other ways, such as sending the fourth quantity to the data processing device separately.
- the data processing device may update the size of the second quantity according to the fourth quantity.
- the second number is equal to the number of the initial waypoints.
- the fourth number is Quantity; when the first quantity is not predicted for the first time, the second quantity is equal to the sum of the number of initial waypoints and the fourth quantity corresponding to each waypoint supplementary package.
- the calculation formula of the second quantity N2 can be as follows:
- N2 N1+N41+N42 (1)
- N2 is the second number
- N1 is the number of initial waypoints
- N41 is the waypoint sent by the data processing device for the first time, supplementary including the corresponding fourth number
- N42 is the waypoint sent by the data processing device for the second time The fourth quantity corresponding to the booster pack.
- the initial waypoint is the waypoint that the data processing device sends to the flight controller for the first time.
- the data processing module sends initialization information to the flight controller, and the initialization information carries the initial waypoint.
- the initial waypoint is the preset number of waypoints stored in the preset waypoint database, and the preset number is less than or equal to the maximum number of waypoints supported by the flight controller. For example, the preset The number is equal to the maximum number of waypoints supported by the flight controller.
- the data processing equipment can obtain the flight parameters before the UAV flight, and it can also obtain the flight parameters from the UAV in real time during the flight of the UAV.
- the type of flight parameters can be set as required.
- the flight parameters can include at least one of the flight speed of the drone and the distance between adjacent waypoints in the flight controller; of course, the type of flight parameters is not Limited to this.
- the flight parameters corresponding to the flight modes of different drones may be different.
- the flight parameters may include one of the flight speed and the distance between adjacent waypoints in the flight controller;
- the flight parameters may include the flight speed and the distance between adjacent waypoints in the flight controller.
- the flight speed of the drone is a dynamic speed (that is, the flight speed is a changing speed)
- the speed at which the drone consumes waypoints and the flight speed is a changing speed
- the first number can be predicted based on the flight speed and the distance between adjacent waypoints in the flight controller to improve the accuracy of the first number prediction; for example, the flight speed of the drone is constant
- the first number is only related to the distance between adjacent waypoints in the flight controller. Therefore, the first number is predicted only based on the distance between adjacent waypoints in the flight controller. A more accurate first quantity can also be obtained.
- the flight parameters corresponding to the flight modes of different drones may also be the same.
- the flight parameters include the flight speed and the adjacent flight in the flight controller. The distance between points.
- the first number is predicted based on the flight parameters and the preset model.
- the preset model is used to characterize the relationship between the flight parameters and the first quantity.
- the first quantity when predicting the first quantity according to the flight parameters, the second quantity, and the fourth quantity, the first quantity may be predicted through a preset model.
- the preset model is used to characterize the flight parameters, the second quantity, and the relationship between the fourth quantity and the first quantity.
- the preset model may include at least one of a neural network model and a function model, and may also include others, such as other deep learning models.
- the preset model is a neural network model
- the first number is predicted through an online learning method to improve the pre-accuracy.
- the input of the neural network model includes the flight parameters
- the output of the neural network model includes the first number; Parameters, the second quantity and the fourth quantity.
- the input of the neural network model includes the flight parameter, the second quantity and the fourth quantity
- the output of the neural network model includes the first quantity.
- the neural network model may include a radial basis RBF neural network (Radial Basis Function Neural Network) model, and may also include other neural network models.
- the neural network model is a radial basis RBF neural network model.
- y is the output of the RBF neural network model.
- n is a positive integer
- m is also a positive integer.
- the input of the RBF neural network model includes x1, x2, and x3, and the output includes y, where x1 is the flight parameter, x2 is the second quantity, and x3 is the first Four quantities, y is the first quantity.
- h1, h2, h3 and h4 are the hidden layer output of the RBF neural network model.
- sum means addition.
- the output of the jth neuron in the hidden layer can be expressed as:
- the error index approximated by the RBF neural network model is:
- the gradient descent method is used to adjust the weights of the RBF neural network model, as follows:
- w j (t) w j (t-1)+ ⁇ w j (t)+ ⁇ (w j (t-1)+ ⁇ w j (t-2)) (6);
- t is the prediction time
- ⁇ is the learning rate, ⁇ (0,1)
- ⁇ is the momentum factor, ⁇ (0,1).
- ⁇ 0.05
- ⁇ 0.5
- the initial value of the RBF neural network model takes a random value from 0 to 1.
- the preset model is a function model. For example, when predicting the first number of waypoints currently consumed by the drone based on the flight parameters, the function model takes the flight parameters as the independent variable, and the first number Is the dependent variable; for example, when predicting the first quantity based on the flight parameters, the second quantity, and the fourth quantity, the function model takes the flight parameters, the second quantity, and the fourth quantity as independent variables, and the first quantity is the dependent variable .
- the function model is a linear function of the flight parameters, and the expression between the flight parameter x and the first quantity y may be as follows:
- a and b are the coefficients corresponding to each order term.
- the function model is a quadratic function of the flight parameter, and the expression between the flight parameter x and the first quantity y may be as follows:
- a, b, and c are the coefficients corresponding to each order term.
- the function model may also be a cubic function, a quartic function, a quintic function, a hexadecimal function, or other functions of the flight parameters.
- the first number of waypoints in the storage order are obtained from the first waypoint in the preset waypoint database as supplementary waypoints, where the first waypoint is the preset waypoint database Waypoints marked as unsent in.
- the number of supplementary waypoints is the first number.
- the data processing equipment will mark the waypoints that have been successfully sent to the flight controller in the preset waypoint database (that is, the waypoints that the flight controller has received) as sent, but the waypoints that have not been sent to the flight controller and the waypoints that have not been sent to the flight controller.
- the waypoints successfully sent to the flight controller are marked as unsent.
- the waypoint corresponding to the waypoint in the waypoint supplement package last actually received by the flight controller in the preset waypoint database is marked as sent, so as to be timely Update the status of the waypoint in the preset waypoint database.
- the waypoint in the preset waypoint database can only be changed in status, and the waypoint itself will not be deleted.
- the status of the waypoints in the preset waypoint database are all marked as unsent.
- the preset waypoint database stores the waypoints in sequence according to the order in which the waypoints are to be executed, and the number of waypoints in the preset waypoint database is far greater than the maximum number of routes supported by the flight controller. The number of points.
- the preset waypoint database can be directly stored in the data processing device, or can be stored in an external storage device that communicates with the data processing device (not the flight controller).
- the drone may include a data processing device communicatively connected with the flight controller.
- the preset waypoint database is a waypoint database pre-stored in the data processing device;
- the preset waypoint database is a waypoint database pre-stored by an external storage device, and the external storage device is in communication connection with the data processing device.
- the external storage device may be an external storage device such as an external storage card directly plugged into the data processing device, or may be an external storage device connected to the data processing device through a signal line.
- the waypoint supplementary package is sent to the flight controller.
- the specific condition includes: the first number is greater than a preset threshold, so as to prevent the data processing device from frequently supplementing waypoints to the flight controller.
- the preset threshold can be set as needed.
- the preset threshold can be (the maximum number of waypoints supported by the flight controller-1), that is, when the first number is the maximum number of waypoints supported by the flight controller, send Waypoint supplement package to flight controller.
- the preset threshold may also be other.
- an embodiment of the present application also provides a waypoint supplement device for a drone.
- the waypoint supplement device of the drone in the embodiment of the present application may include a first storage device and one or more first processors.
- the first storage device is used to store program instructions.
- One or more first processors call program instructions stored in the first storage device, and when the program instructions are executed, the one or more first processors are individually or collectively configured to perform the following operations: prediction The first number of waypoints currently consumed by the drone; according to the first number, determine supplementary waypoints from the preset waypoint database; send waypoint supplementary packages to the flight controller; where, how many preset waypoint databases are stored There are supplementary waypoints in the waypoint supplement package.
- the first processor of this embodiment can implement the waypoint supplement method of the drone in the embodiment shown in FIG. 2 of the present application.
- the waypoint supplement device is explained.
- an embodiment of the present application also provides a data processing device.
- the data processing device may include a main body and the waypoint supplement device of the drone of the above embodiment, wherein the waypoint supplement device of the drone is composed of the main body part. support.
- FIG. 5 is a schematic diagram of a method flow chart of a waypoint supplement method for a drone in another embodiment of the present application; the execution subject of the waypoint supplement method for a drone in an embodiment of the present application is a drone, which is exemplary The execution subject of the method for supplementing waypoints of the drone in the embodiment of the present application is the flight controller of the drone.
- the waypoint supplement method of the drone in the embodiment of the present application may include S501 to S502.
- the first quantity is a prediction by the data processing device based on the flight parameters of the drone.
- the flight parameters include at least one of the flight speed of the drone and the distance between adjacent waypoints in the flight controller.
- different drone flight modes correspond to different flight parameters.
- the first number is a prediction by the data processing device based on the flight parameters, the second number of waypoints that the data processing device has currently sent to the flight controller, and the waypoint information of the waypoint actually received by the flight controller last time; where , The last actual waypoint received by the flight controller is determined according to the supplementary waypoints in the last waypoint supplement package and the third number of waypoints actually consumed by the drone.
- the waypoint information includes at least one of the fourth number of waypoints actually received by the flight controller last time and the density of the waypoints actually received last time by the flight controller.
- the fourth number is the number of initial waypoints; the initial waypoint is the waypoint sent by the data processing device first received by the flight controller.
- the fourth quantity is equal to the third quantity.
- the fourth quantity is equal to the number of supplementary waypoints in the waypoint supplementary pack.
- the first quantity is predicted by the data processing device based on the flight parameters and a preset model; wherein, the preset model is used to characterize the relationship between the flight parameters and the first quantity.
- the preset model includes at least one of a neural network model and a function model; wherein the input of the neural network model includes flight parameters, and the output of the neural network model includes a first quantity; the function model takes flight parameters as independent variables, The first quantity is the dependent variable.
- the neural network model includes a radial basis RBF neural network model.
- add waypoints to the flight controller according to the waypoint supplement package including: determining the third number of waypoints actually consumed by the drone during flight; according to the waypoint supplement package and the third quantity, The flight controller performs waypoint supplementation.
- the third number is increased by one. It should be noted that the initial value of the third number is 0, and the third number is reset to 0 after each waypoint replenishment by the flight controller.
- add waypoints to the flight controller according to the waypoint supplement package and the third quantity including: when the third quantity is less than the number of supplementary waypoints in the waypoint supplement package, determine what the flight controller actually receives The fourth number of waypoints is the third number; according to the fourth number and the waypoint supplementary package, determine the waypoint actually received by the flight controller.
- add waypoints to the flight controller based on the waypoint supplement package and the third quantity including: when the third quantity is greater than or equal to the number of supplementary waypoints in the waypoint supplement package, determining the actual flight controller
- the fourth number of waypoints received is the number of supplementary waypoints in the waypoint supplementary package; according to the fourth quantity and the waypoint supplementary package, the actual waypoints received by the flight controller are determined.
- the fourth number of supplementary waypoints in the storage order are taken from the waypoint supplementary package as the waypoints actually received by the flight controller.
- the method further includes: returning a response message to the data processing device, the response message carrying the fourth number of waypoints actually received by the flight controller.
- the method further includes: deleting the currently consumed waypoint from the flight controller, so as to clear the storage space occupied by the waypoint in the flight controller in time.
- the data processing equipment is a data processing equipment installed in the drone.
- the data processing device is an image processing module of the drone.
- the data processing device is an external terminal remote from the UAV, such as a remote control or other remote control terminals capable of controlling the UAV, such as a mobile phone, a tablet computer, a smart bracelet, etc.
- a remote control or other remote control terminals capable of controlling the UAV, such as a mobile phone, a tablet computer, a smart bracelet, etc.
- an embodiment of the present application also provides a device for replenishing waypoints for drones.
- the waypoint supplement device of the drone in the embodiment of the present application may include a second storage device and one or more second processors.
- the second storage device is used to store program instructions.
- One or more second processors call program instructions stored in the second storage device, and when the program instructions are executed, the one or more second processors are individually or collectively configured to perform the following operations: receiving The waypoint supplementary package sent to the data processing equipment; according to the waypoint supplementary package, the flight controller supplements the waypoints; among them, the waypoint supplementary package carries at least one supplementary waypoint, and the supplementary waypoint is the data processing equipment according to the data
- the first number of waypoints currently consumed by the UAV predicted by the processing device is determined with a preset waypoint database, and the preset waypoint database stores multiple waypoints.
- the second processor of this embodiment can implement the waypoint supplement method of a drone as shown in the embodiment shown in FIG.
- the waypoint supplement device of the aircraft is explained.
- the unmanned aerial vehicle 100 may include a fuselage 110, a flight controller 120, and an unmanned aerial vehicle described in Embodiment 2 of the present application.
- Waypoint supplementary device wherein, the flight controller 120 is provided on the fuselage 110, and the waypoint supplement device of the UAV is supported by the fuselage.
- the waypoint supplement device of the drone in this embodiment is the flight controller 120.
- the embodiment of the present application also provides an unmanned aerial vehicle system. Please refer to FIGS. 1A to 1C.
- the unmanned aerial vehicle system may include an unmanned aerial vehicle 100 and a data processing device 200.
- the drone 100 may include a fuselage 110 and a flight controller 120 provided on the fuselage 110, and the data processing device 200 is in communication connection with the flight controller 120.
- the data processing device 200 may be a part of the drone 100, or may not be a part of the drone 100.
- the data processing device 200 is used to predict the first number of waypoints currently consumed by the drone 100, and according to the first number, determine supplementary waypoints from the preset waypoint database, and send waypoint supplementary packages to flight control
- the preset waypoint database stores multiple waypoints
- the waypoint supplement package carries supplementary waypoints.
- the flight controller 120 is configured to: receive the waypoint supplement package sent by the data processing device 200, and perform waypoint supplementation according to the waypoint supplement package.
- the optional data processing device 200 is specifically used to obtain the flight parameters of the drone 100, and predict the first number of waypoints currently consumed by the drone 100 according to the flight parameters.
- the flight parameters include at least one of the flight speed of the drone 100 and the distance between adjacent waypoints in the flight controller 120.
- different flight modes of the UAV 100 correspond to different flight parameters.
- the data processing device 200 is specifically configured to: according to flight parameters, the second number of waypoints that the data processing device 200 has currently sent to the flight controller 120 and the waypoint of the waypoint actually received by the flight controller 120 last time Information, the first number is predicted; among them, the last waypoint actually received by the flight controller 120 is based on the supplementary waypoints in the waypoint supplement package last sent by the data processing device 200 and the first number of waypoints actually consumed by the drone 100 Three quantities are determined.
- the waypoint information includes at least one of the fourth number of waypoints actually received by the flight controller 120 last time and the density of the waypoints actually received by the flight controller 120 last time.
- the fourth number is the number of initial waypoints; the initial waypoint is the waypoint that the data processing device 200 sends to the flight controller 120 for the first time.
- the fourth quantity is equal to the third quantity.
- the fourth quantity is equal to the number of supplementary waypoints in the waypoint supplementary pack.
- the flight controller 120 is further configured to: after supplementing the waypoint according to the waypoint supplement package, return a response message to the data processing device 200, the response message carrying the fourth quantity.
- the data processing device 200 is further configured to: update the size of the second quantity according to the fourth quantity.
- the data processing device 200 is specifically used to predict the first number of waypoints currently consumed by the drone 100 based on the flight parameters and a preset model; wherein the preset model is used to characterize the flight parameters and the first number. Relationship between.
- the preset model includes at least one of a neural network model and a function model; wherein the input of the neural network model includes flight parameters, and the output of the neural network model includes a first quantity; the function model takes flight parameters as independent variables, The first quantity is the dependent variable.
- the neural network model includes a radial basis RBF neural network model.
- the data processing device 200 is specifically configured to: obtain the first number of waypoints in the storage order from the first waypoint in the preset waypoint database as the supplementary waypoint; the first waypoint is the preset waypoint Waypoints marked as unsent in the database.
- the data processing device 200 is specifically configured to: after sending the waypoint supplementary package to the flight controller 120, combine the waypoints in the waypoint supplementary package last actually received by the flight controller 120 in the preset waypoint database The corresponding waypoint is marked as sent.
- the drone 100 includes a data processing device 200 that is communicatively connected with the flight controller 120;
- the preset waypoint database is a waypoint database pre-stored in the data processing device 200; or,
- the preset waypoint database is a waypoint database pre-stored by an external storage device, and the external storage device is in communication connection with the data processing device 200.
- the data processing device 200 is configured to send a waypoint supplement package to the flight controller 120 when the first number is greater than a preset threshold.
- the flight controller 120 is specifically configured to: determine the third number of waypoints actually consumed by the drone 100 during the flight; and supplement waypoints according to the waypoint supplement package and the third number.
- the flight controller 120 is specifically configured to: when the third number is less than the number of supplementary waypoints in the waypoint supplementary package, determine that the fourth number of waypoints actually received by the flight controller 120 is the number of waypoints actually consumed Quantity: According to the fourth quantity and the waypoint supplementary package, it is determined that the flight controller 120 actually receives the waypoint.
- the flight controller 120 is specifically configured to: when the third number is greater than or equal to the number of supplementary waypoints in the waypoint supplementary package, determine that the fourth number of waypoints actually received by the flight controller 120 is the waypoint supplementary package According to the fourth number and the waypoint supplement package, it is determined that the flight controller 120 actually receives the waypoint.
- the flight controller 120 is also used to delete the currently consumed waypoints from the flight controller 120.
- the data processing device 200 includes a data processing device provided in the drone 100.
- the data processing device 200 is an image processing module of the drone 100.
- the data processing device 200 includes a remote control terminal that is the drone 100.
- the storage device in the first embodiment or the second embodiment stores the executable instruction computer program of the waypoint supplement method of the drone.
- the storage device may include at least one type of storage medium.
- the storage medium includes flash memory, hard disk, Multimedia card, card type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM) ), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc.
- the waypoint supplement device of the UAV can cooperate with a network storage device that performs the storage function of the memory through a network connection.
- the memory may be an internal storage unit of the waypoint supplement device of the drone, such as the hard disk or memory of the waypoint supplement device of the drone.
- the memory can also be the external storage device of the waypoint supplement device of the drone, such as the plug-in hard disk equipped on the waypoint supplement device of the drone, the smart memory card (Smart Media Card, SMC), and the secure digital (Secure Digital). ,SD) card, flash card (Flash Card), etc.
- the memory may also include both the internal storage unit of the waypoint supplement device of the drone and the external storage device.
- the memory is used to store computer programs and other programs and data required by the device.
- the memory can also be used to temporarily store data that has been output or will be output.
- the processor in Embodiment 1 or Embodiment 2 may be a central processing unit (Central Processing Unit, CPU), or other general-purpose processors, digital signal processors (Digital Signal Processors, DSPs), and application specific integrated circuits (Application Specific Integrated Circuits). Integrated Circuit, ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
- the general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.
- an embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, it implements the steps of the method for replenishing the waypoint of the drone in the first embodiment or the second embodiment.
- the computer-readable storage medium may be an internal storage unit of the drone system described in any of the foregoing embodiments, such as a hard disk or a memory.
- the computer-readable storage medium may also be an external storage device of the UAV system, such as a plug-in hard disk, a smart media card (SMC), an SD card, and a flash card (Flash Card) equipped on the device. )Wait.
- the computer-readable storage medium may also include both an internal storage unit of the drone system and an external storage device.
- the computer-readable storage medium is used to store the computer program and other programs and data required by the UAV system, and can also be used to temporarily store data that has been output or will be output.
- the program can be stored in a computer readable storage medium. During execution, it may include the procedures of the above-mentioned method embodiments.
- the storage medium can be a magnetic disk, an optical disc, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM), etc.
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
一种无人机及其航点补充方法和装置、数据处理设备,所述无人机包括飞行控制器,所述方法包括:预测所述无人机当前消耗的航点的第一数量;根据所述第一数量,从预设航点数据库中确定补充航点;发送航点补充包至所述飞行控制器;其中,所述预设航点数据库存储有多个航点,所述航点补充包携带有所述补充航点。本申请的动态航点补充方式减少了飞行控制器的计算,从而保证了飞行控制器执行航点功能的流畅性,并节约了飞行控器的计算资源;同时,无需飞行控制器的实时请求,节约了飞行控制器与数据处理设备之间的链路宽度,从而降低了飞行控制器与数据处理设备之间的通信带宽需求。
Description
本申请涉及无人机领域,尤其涉及一种无人机及其航点补充方法和装置、数据处理设备。
无人机的计算设备主要包括飞行控制器FC(flight control)和数据处理设备AP(application processer),FC用于完成飞行控制等实时性要求强的飞控控制任务,如航点功能(FC通过执行航点功能,控制无人机飞至相应的航点);AP用于承担图像处理等实时性要求低算力要求高的任务。FC实时性好、但存储能力差。目前,FC最多支持99个航点,但这个数量级难以满足行业应用中的管线巡检、电力巡查等远距离、长航时作业。
为解决上述问题,可将海量的航点存储在AP中,FC根据本地存储能力和本地存储的航点的消耗情况来确定其所需补充的航点,然后实时的向AP发送航点补充请求,AP被动地应答FC的航点补充请求,将补充航点动态推送给FC,FC动态更新本地航点。这种动态航点补充方式会增加FC的计算,大大消耗FC的计算资源,不利于FC执行飞控控制任务;同时,这种动态航点补充方式严重依赖于FC与AP之间的通信带宽。
发明内容
本申请提供一种无人机及其航点补充方法和装置、数据处理设备。
第一方面,本申请实施例提供一种无人机的航点补充方法,所述无人机包括飞行控制器,所述方法包括:
预测所述无人机当前消耗的航点的第一数量;
根据所述第一数量,从预设航点数据库中确定补充航点;
发送航点补充包至所述飞行控制器;
其中,所述预设航点数据库存储有多个航点,所述航点补充包携带有所述补充航点。
第二方面,本申请实施例提供一种无人机的航点补充装置,所述无人机包括飞行控制器,所述装置包括:
存储装置,用于存储程序指令;以及
一个或多个处理器,调用所述存储装置中存储的程序指令,当所述程序指令被执行时,所述一个或多个处理器单独地或共同地被配置成用于实施如下操作:
预测所述无人机当前消耗的航点的第一数量;
根据所述第一数量,从预设航点数据库中确定补充航点;
发送航点补充包至所述飞行控制器;
其中,所述预设航点数据库存储有多个航点,所述航点补充包携带有所述补充航点。
第三方面,本申请实施例提供一种数据处理设备,所述数据处理设备包括:
主体部;
本申请实施例第二方面所述的无人机的航点补充装置,由所述主体部支撑。
第四方面,本申请实施例提供一种无人机的航点补充方法,所述无人机包括飞行控制器,所述方法包括:
接收到数据处理设备发送的航点补充包;
根据所述航点补充包,向所述飞行控制器进行航点补充;
其中,所述航点补充包携带有至少一个补充航点,所述补充航点为所述数据处理设备根据该数据处理设备预测的所述无人机当前消耗的航点的第一数量和预设航点数据库确定,所述预设航点数据库存储有多个航点。
第五方面,本申请实施例提供一种无人机的航点补充装置,所述无人机包括飞行控制器,所述装置包括:
存储装置,用于存储程序指令;以及
一个或多个处理器,调用所述存储装置中存储的程序指令,当所述程序指令被执行时,所述一个或多个处理器单独地或共同地被配置成用于实施如下操作:
接收到数据处理设备发送的航点补充包;
根据所述航点补充包,向所述飞行控制器进行航点补充;
其中,所述航点补充包携带有至少一个补充航点,所述补充航点为所述数据处理设备根据该数据处理设备预测的所述无人机当前消耗的航点的第一数量和预设航点数据库确定,所述预设航点数据库存储有多个航点。
第六方面,本申请实施例提供一种无人机,所述无人机包括:
机身;
飞行控制器,设于所述机身;和
本申请实施例第五方面所述的无人机的航点补充装置,由所述机身支撑。
第七方面,本申请实施例提供一种无人机系统,包括机身、设于所述机身的飞行控制器和与所述飞行控制器通信连接的数据处理设备;
其中,所述数据处理设备用于:预测所述无人机当前消耗的航点的第一数量,并根据所述第一数量,从预设航点数据库中确定补充航点,发送航点补充包至所述飞行控制器,所述预设航点数据库存储有多个航点,所述航点补充包携带有所述补充航点;
所述飞行控制器用于:接收到数据处理设备发送的航点补充包,根据所述航点补充包进行航点补充。
根据本申请实施例提供的技术方案,本申请通过数据处理设备主动地预测无人机当前消耗的航点的第一数量,再根据预测的第一数量从预设航点数据库中确定补充航点,然后向飞行控制器发送航点补充包,减少了飞行控制器的计算,从而保证了飞行控制器执行航点功能的流畅性,并节约了飞行控器的计算资源;同时,无需飞行控制器的实时请求,节约了飞行控制器与数据处理设备之间的链路宽度,从而降低了飞行控制器与数据处理设备之间的通信带宽需求。本申请的动态航点补充方式适用于行业应用中的管线巡检、电力巡查等远距离、长航时作业。
为了更清楚地说明本申请实施例中的技术方案,下面将对实施例描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本申请的一些实施例,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1A是本申请一实施例中的一种无人机系统的结构示意图;
图1B是图1A所示实施例的无人机系统的一种结构示意图;
图1C是图1A所示实施例的无人机系统的另一种结构示意图;
图2是本申请一实施例中的一种无人机的航点补充方法的方法流程示意图;
图3是本申请一实施例中的一种通过RBF神经网络模型预测无人机当前消耗的航点的第一数量的模型示意图;
图4是本申请一实施例中的一种无人机的航点补充装置的结构示意图;
图5是本申请另一实施例中的一种无人机的航点补充方法的方法流程示意图;
图6是本申请另一实施例中的一种无人机的航点补充装置的结构示意图。
目前,为解决FC最多支持的航点的数量级难以满足行业应用中的管线巡检、电力巡查等远距离、长航时作业的问题,将海量的航点存储在AP中,FC根据本地存储能力和本地存储的航点的消耗情况来确定其所需补充的航点,然后实时的向AP发送航点补充请求,AP被动地应答FC的航点补充请求,将补充航点动态推送给FC,FC动态更新本地航点。这种FC主动请求、AP被动应答的航点补充方式一方面增加了FC的计算,大大消耗FC的计算资源,不利于FC执行飞控控制任务,另一方面对FC与AP之间的通信带宽的要求较高。
对于此,本申请实施例通过数据处理设备主动地预测无人机当前消耗的航点的第一数量,再根据预测的第一数量从预设航点数据库中确定补充航点,然后向飞行控制器发送航点补充包,本申请实施例的动态航点补充方式减少了飞行控制器的计算,从而保证了飞行控制器执行航点功能的流畅性,并节约了飞行控器的计算资源;同时,本申请实施例的动态航点补充方式无需飞行控制器的实时请求,节约了飞行控制器与数据处理设备之间的链路宽度,从而降低了飞行控制器与数据处理设备之间的通信带宽需求。本申请实施例的动态航点补充方式适用于行业应用中的管线巡检、电力巡查等远距离、长航时作业。
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、完整地描述,显然,所描述的实施例仅仅是本申请一部分实施例,而不是全部的实施例。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,在不冲突的情况下,下述的实施例及实施方式中的特征可以相互组合。
请参见图1A,无人机系统可包括无人机100和数据处理设备200,无人机100与数据处理设备200通信连接。请参见图1B和图1C,无人机100可包括机身110和设于机身110的飞行控制器120,数据处理设备200可与飞行控制器110通信连接。
示例性的,请参见图1B,数据处理设备200设于机身100,即数据处理设备200为无人机的一部分,数据处理设备200与飞行控制器120通信连接。示例性的,数据处理设备200为无人机100的图像处理模块;应当理解的,除飞行控制器120外,数据处理设备200也可以为无人机100的其他模块。当然,数据处理模块200也可以不作为无人机100的一部分。
示例性的,请参见图1C,数据处理设备200为远程于无人机100的外部终端,外部终端可以为无人机100的遥控器,或者其他能够控制无人机100的遥控终端,如手机、平板电脑、智能手环等。
需要说明的是,本申请实施例中,通过飞行控制器执行航点功能,即是指通过飞行控制器控制无人机飞行至相应的航点。
下面,将分别从无人机侧和数据处理侧,对无人机的航点补充方法进行阐述。
实施例一
本申请实施例提供一种无人机的航点补充方法,本申请实施例的无人机的航点补充方法的执行主体为数据处理设备,示例性的,数据处理设备为设于无人机的数据处理设备,可选的,该数据处理设备为无人机的图像处理模块;当然,除飞行控制器外,该数据处理设备也可以为其他模块。示例性的,数据处理设备为无人机的遥控终端。
本实施例以无人机的航点补充方法的执行主体为数据处理设备为例进行说明,应当理解的,当无人机的航点补充方法的执行主体为其他设备时,下述实施例中的数据处理设备相应替换成该设备。
图2是本申请一实施例中的一种无人机的航点补充方法的方法流程示意图;请参见图2,本申请实施例的无人机的航点补充方法可包括S201~S203。
其中,在S201中,预测无人机当前消耗的航点的第一数量;
在S202中,根据第一数量,从预设航点数据库中确定补充航点,其中,预设航点 数据库存储有多个航点;
在S203中,发送航点补充包至飞行控制器,航点补充包携带有补充航点。
本申请实施例中,无人机当前消耗的航点是指飞行控制器执行航点功能过程中,无人机当前已执行的航点,因此,可以理解的,本申请实施例中,数据处理设备是在无人机飞行过程中预测第一数量的。
可以通过不同的策略来预测第一数量,示例性的,在一些实施例中,根据飞行参数,预测无人机当前消耗的航点的第一数量。在飞行控制器执行航点功能过程中,无人机消耗航点的快慢与飞行参数相关,因此,根据飞行参数预测第一数量,准确性较高。
在另外一些实施例中,除飞行参数外,无人机消耗航点的快慢还可以与其他因素相关。示例性的,根据飞行参数、当前已发送给飞行控制器的航点的第二数量(即数据处理设备当前已发送给飞行控制器的航点的第二数量)以及飞行控制器最近一次实际接收的航点的航点信息,预测第一数量。其中,飞行控制器最近一次实际接收的航点可以根据最近一次发送的航点补充包(即数据处理设备最近一次发送给飞行控制器的航点补充包)中的补充航点和无人机实际消耗的航点的第三数量确定。
其中,航点信息可以包括飞行控制器最近一次实际接收的航点的第四数量和飞行控制器最近一次实际接收的航点的密集程度中的至少一个,航点的密集程度可以通过相邻航点之间的距离表征,相邻航点之间的距离越小,表示航点的密集程度越高。示例性的,航点信息包括第四数量或飞行控制器最近一次实际接收的航点的密集程度;示例性的,航点信息包括第四数量和飞行控制器最近一次实际接收的航点的密集程度。
可选的,通过数据处理设备确定航点信息;可选的,通过飞行控制器确定航点信息,再由飞行控制器将航点信息反馈给数据处理设备。示例性的,通过飞行控制器确定第四数量,通过数据处理设备和/或飞行控制器确定飞行控制器最近一次实际接收的航点的密集程度。
示例性的,第四数量的确定方式可以包括:
(1)、当第三数量小于航点补充包中的补充航点的数量时,第四数量与第三数量大小相等,此时,飞行控制器接收航点补充包中的部分补充航点;
(2)当第三数量大于航点补充包中的补充航点的数量时,第四数量与航点补充包中的补充航点的数量大小相等,此时,飞行控制器接收航点补充包中的全部补充航点。
应当理解的,本申请实施例中,航点补充包中的补充航点的数量即为第一数量。因此,当第三数量小于第一数量时,第四数量与第三数量相等;当第三数量大于第一数量时,第四数量与第一数量相等。
第四数量可由飞行控制器反馈,示例性的,数据处理设备在发送航点补充包至飞行控制器之后,接收飞行控制器针对航点补充包返回的应答消息,应答消息携带有第四数量;应当理解的,数据处理设备也可以通过其他方式获取第四数量,例如,数据处理设备在发送航点补充包至飞行控制器之后,从飞行控制器读取第三数量;当然,飞行控制器也可以通过其他方式反馈第四数量给数据处理设备,如单独发送第四数量给数据处理设备。
进一步可选的,数据处理设备可以根据第四数量,更新第二数量的大小。应当理解的,本申请实施例中,在首次预测第一数量时,第二数量与初始航点的数量相等,也可以理解为,在首次预测第一数量时,第四数量为初始航点的数量;在非首次预测第一数量时,第二数量与初始航点的数量和每个航点补充包对应的第四数量之和相等,示例性的,在数据处理设备第三次预测第一数量时,第二数量N2的计算公式可如下:
N2=N1+N41+N42 (1);
公式(1)中,N2为第二数量,N1为初始航点的数量,N41为数据处理设备首次发送的航点补充包括对应的第四数量,N42为数据处理设备第二次发送的航点补充包对应的第四数量。
其中,初始航点即为数据处理设备首次发送给飞行控制器的航点,示例性的,在无人机飞行前,数据处理模块向飞行控制器发送初始化信息,初始化信息携带初始航点。可以理解的,初始航点即为预设航点数据库中存储顺序靠前的预设数量个航点,预设数量小于或等于飞行控制器最多支持的航点的数量,示例性的,预设数量与飞行控制器最多支持的航点的数量相等。
数据处理设备可以在无人机飞行前获得飞行参数,也可以在无人机飞行过程中,实时地从无人机获得飞行参数。
飞行参数的类型可以根据需要设定,示例性的,飞行参数可以包括无人机的飞行速度和飞行控制器中相邻航点之间的距离中的至少一种;当然,飞行参数的类型不限于此。
在一些实施例中,不同的无人机的飞行模式对应飞行参数可不相同,例如,对于 一些飞行模式,飞行参数可以包括飞行速度和飞行控制器中相邻航点之间的距离中的一个;对于一些飞行模式,飞行参数可以包括飞行速度和飞行控制器中相邻航点之间的距离。示例性的,对于无人机的飞行速度为动态速度(即飞行速度为变化的速度)的飞行模式,无人机消耗航点的快慢与飞行速度、飞行控制器中相邻航点之间的距离均相关,因此,可以根据飞行速度和飞行控制器中相邻航点之间的距离预测第一数量,提高第一数量预测的准确性;示例性的,对于无人机的飞行速度为恒定速度的飞行模式,由于飞行速度恒定,第一数量仅与飞行控制器中相邻航点之间的距离相关,因此,仅根据飞行控制器中相邻航点之间的距离预测第一数量,也能获得较为准确的第一数量。
在另外一些实施例中,不同的无人机的飞行模式对应的飞行参数也可以相同,示例性的,对于无人机的不同飞行模式,飞行参数均包括飞行速度和飞行控制器中相邻航点之间的距离。
示例性的,在根据飞行参数,预测无人机当前消耗的航点的第一数量时,根据飞行参数和预设模型,预测第一数量。其中,预设模型用于表征飞行参数与第一数量之间的关系。
示例性的,在根据飞行参数、第二数量以及第四数量,预测第一数量时,可以通过预设模型,预测第一数量。其中,预设模型用于表征飞行参数、第二数量及第四数量与第一数量之间的关系。
预设模型可以包括神经网络模型和函数模型中的至少一种,也可以包括其他,如其他深度学习模型。
例如,在一些实施例中,预设模型为神经网络模型,通过在线学习方法预测第一数量,提高预准确性。示例性的,在根据飞行参数,预测无人机当前消耗的航点的第一数量时,神经网络模型的输入包括飞行参数,神经网络模型的输出包括第一数量;示例性的,在根据飞行参数、第二数量以及第四数量,预测第一数量时,神经网络模型的输入包括飞行参数、第二数量以及第四数量,神经网络模型的输出包括第一数量。
神经网络模型可以包括径向基RBF神经网络(Radial Basis Function Neural Network)模型,也可以包括其他神经网络模型。示例性的,神经网络模型为径向基RBF神经网络模型,示例性的,x=[x
1,...x
n]
T为RBF神经网络模型的输入,y为RBF神经网络模型的输出,h=[h
1,...h
m]
T为RBF神经网络模型的隐含层的输出, w=[w
1,...w
m]
T为RBF神经网络模型的权重。其中,n为正整数,m也为正整数。
可选的,y的计算公式可如下:
y=w
Th=w
1h
1+w
2h
2+...+w
mh
m (2);
示例性的,请参见图3,n=3,m=4,RBF神经网络模型的输入包括x1、x2和x3,输出包括y,其中,x1为飞行参数,x2为第二数量,x3为第四数量,y为第一数量。h1、h2、h3和h4为RBF神经网络模型的隐含层输出。图3中,sum即为相加。
公式(2)则为:y=w
1h
1+w
2h
2+w
3h
3+w
4h
4;
其中,隐含层第j个神经元的输出的可以表达为:
公式(3)中,c
j(j=1、2、3或4)为隐含层第j个神经元的高斯计函数中心点的坐标向量;b
j(j=1、2、3或4)为隐含层第j个神经元的高斯计函数的宽度。
RBF神经网络模型逼近的误差指标为:
公式(4)中,y
m=w
mh
m。
采用梯度下降法对RBF神经网络模型的权值进行调节,具体如下:
w
j(t)=w
j(t-1)+Δw
j(t)+α(w
j(t-1)+Δw
j(t-2)) (6);
其中,t为预测时刻,η为学习速率,η∈(0,1);α为动量因子,α∈(0,1)。
示例性的,α=0.05,η=0.5,RBF神经网络模型的初始取值取0到1的随机值。
在另外一些实施例中,预设模型为函数模型,示例性的,在根据飞行参数,预测无人机当前消耗的航点的第一数量时,函数模型以飞行参数为自变量,第一数量为因变量;示例性的,在根据飞行参数、第二数量以及第四数量,预测第一数量时,函数模型以飞行参数、第二数量以及第四数量为自变量,第一数量为因变量。
以函数模型以飞行参数为自变量,第一数量为因变量为例。示例性的,函数模型为飞行参数的一次函数,飞行参数x与第一数量y之间的表达式可如下:
y=f(x)=ax+b (7);
公式(7)中,a、b为各次项对应的系数.
示例性的,函数模型为飞行参数的二次函数,飞行参数x与第一数量y之间的表达式可如下:
y=f(x)=ax
2+bx+c (8);
公式(8)中,a、b、c为各次项对应的系数。
应当理解的,函数模型也可以为飞行参数的三次函数、四次函数、五次函数、六次函数或其他。
示例性的,在实现S202时,从预设航点数据库的第一航点中获取存储顺序靠前的第一数量个航点作为补充航点,其中,第一航点为预设航点数据库中标记为未发送状态的航点。本申请实施例中,补充航点的数量即为第一数量。数据处理设备会将预设航点数据库中已成功发送给飞行控制器的航点(即飞行控制器已接收的航点)标记为已发送状态,而未发送给飞行控制器的航点以及未成功发送给飞行控制器的航点均标记为未发送状态。
进一步的,发送航点补充包至飞行控制器之后,将预设航点数据库中与飞行控制器最近一次实际接收的航点补充包中的航点对应的航点标记为已发送状态,从而及时更新预设航点数据库中航点的状态。本申请实施例中,预设航点数据库中的航点仅是状态可以改变,航点本身不会被删除。在无人机本次飞行结束后,控制无人机再次飞行时,预设航点数据库中的航点的状态均标记为未发送状态。
需要说明的是,本申请实施例中,预设航点数据库根据航点待执行的顺序依次存储航点的,预设航点数据库中的航点的数量远远大于飞行控制器最多支持的航点的数量。
预设航点数据库可以直接存储在数据处理设备中,也可以存储在于数据处理设备通信的外部存储设备(非飞行控制器即可)。示例性的,无人机可包括与飞行控制器通信连接的数据处理设备,可选的,在一些实施例中,预设航点数据库为数据处理设备中预先存储的航点数据库;在另外一些实施例中,预设航点数据库为外部存储设备 预先存储的航点数据库,外部存储设备与数据处理设备通信连接。外部存储设备可以为直接插接在数据处理设备上的外部存储卡等外部存储设备,也可以为与数据处理设备通过信号线连接的外部存储设备。
进一步的,在一些实施例中,检测到满足特定条件时,发送航点补充包至飞行控制器。示例性的,特定条件包括:第一数量大于预设阈值,避免数据处理设备频繁的对飞行控制器补充航点。预设阈值可以根据需要设定,例如,预设阈值可以为(飞行控制器最多支持的航点的数量-1),即当第一数量为飞行控制器最多支持的航点的数量时,发送航点补充包至飞行控制器。当然,预设阈值也可以为其他。
对应于上述实施例的无人机的航点补充方法,本申请实施例还提供一种无人机的航点补充装置。请参见图4,本申请实施例的无人机的航点补充装置可以包括第一存储装置和一个或多个第一处理器。
其中,第一存储装置,用于存储程序指令。一个或多个第一处理器,调用第一存储装置中存储的程序指令,当程序指令被执行时,一个或多个第一处理器单独地或共同地被配置成用于实施如下操作:预测无人机当前消耗的航点的第一数量;根据第一数量,从预设航点数据库中确定补充航点;发送航点补充包至飞行控制器;其中,预设航点数据库存储有多个航点,航点补充包携带有补充航点。
本实施例的第一处理器可以实现如本申请图2所示实施例的无人机的航点补充方法,可参见上述实施例的无人机的航点补充方法对本实施例的无人机的航点补充装置进行说明。
进一步的,本申请实施例还提供一种数据处理设备,该数据处理设备可以包括主体部和上述实施例的无人机的航点补充装置,其中,无人机的航点补充装置由主体部支撑。
实施例二
图5是本申请另一实施例中的一种无人机的航点补充方法的方法流程示意图;本申请实施例的无人机的航点补充方法的执行主体为无人机,示例性的,本申请实施例的无人机的航点补充方法的执行主体为无人机的飞行控制器。
请参见图5,本申请实施例的无人机的航点补充方法可以包括S501~S502。
其中,在S501中,接收到数据处理设备发送的航点补充包;
在S502中,根据航点补充包,向飞行控制器进行航点补充,其中,航点补充包携带有至少一个补充航点,补充航点为数据处理设备根据该数据处理设备预测的无人机当前消耗的航点的第一数量和预设航点数据库确定,预设航点数据库存储有多个航点。
可选的,第一数量为数据处理设备根据无人机的飞行参数预测。
可选的,飞行参数包括无人机的飞行速度和飞行控制器中相邻航点之间的距离中的至少一种。
可选的,不同的无人机的飞行模式对应飞行参数不同。
可选的,第一数量为数据处理设备根据飞行参数、数据处理设备当前已发送给飞行控制器的航点的第二数量以及飞行控制器最近一次实际接收的航点的航点信息预测;其中,飞行控制器最近一次实际接收的航点根据最近一次发送的航点补充包中的补充航点和无人机实际消耗的航点的第三数量确定。
可选的,航点信息包括飞行控制器最近一次实际接收的航点的第四数量和飞行控制器最近一次实际接收的航点的密集程度中的至少一个。
可选的,在数据处理设备首次预测第一数量时,第四数量为初始航点的数量;初始航点为飞行控制器首次接收到的数据处理设备发送的航点。
可选的,当第三数量小于航点补充包中的补充航点的数量时,第四数量与第三数量大小相等。
可选的,当第三数量大于航点补充包中的补充航点的数量时,第四数量与航点补充包中的补充航点的数量大小相等。
可选的,第一数量为数据处理设备根据飞行参数和预设模型预测;其中,预设模型用于表征飞行参数与第一数量之间的关系。
可选的,预设模型包括神经网络模型和函数模型中的至少一种;其中,神经网络模型的输入包括飞行参数,神经网络模型的输出包括第一数量;函数模型以飞行参数为自变量,第一数量为因变量。
可选的,神经网络模型包括径向基RBF神经网络模型。
可选的,根据航点补充包,向飞行控制器进行航点补充,包括:确定无人机在飞行过程中实际消耗的航点的第三数量;根据航点补充包和第三数量,向飞行控制器进行航点补充。本申请实施例中,飞行控制器在控制无人机到达一个航点时,第三数量 即增加1个。需要说明的是,第三数量的初始值为0,飞行控制器在每次进行航点补充后,第三数量重新设置为0。
可选的,根据航点补充包和第三数量,向飞行控制器进行航点补充,包括:当第三数量小于航点补充包中的补充航点的数量时,确定飞行控制器实际接收的航点的第四数量为第三数量;根据第四数量和航点补充包,确定飞行控制器实际接收的航点。
可选的,根据航点补充包和第三数量,向飞行控制器进行航点补充,包括:当第三数量大于或等于航点补充包中的补充航点的数量时,确定飞行控制器实际接收的航点的第四数量为航点补充包中的补充航点的数量;根据第四数量和航点补充包,确定飞行控制器实际接收的航点。
本申请实施例中,从航点补充包中取存储顺序靠前的第四数量个补充航点作为飞行控制器实际接收的航点。
可选的,所述方法还包括:返回应答消息至数据处理设备,应答消息携带有飞行控制器实际接收的航点的第四数量。
可选的,所述方法还包括:将当前已消耗的航点从飞行控制器中删除,从而及时清空飞行控制器中被航点占用的存储空间。
可选的,数据处理设备为设于无人机的数据处理设备。
可选的,数据处理设备为无人机的图像处理模块。
可选的,数据处理设备为远程于无人机的外部终端,如遥控器或者其他能够控制无人机的遥控终端,如手机、平板电脑、智能手环等。
其余未展开的部分可以参见上述实施例一中相应部分的描述,此处不再赘述。
对应于上述实施例二的无人机的航点补充方法,本申请实施例还提供一种无人机的航点补充装置。请参见图6,本申请实施例的无人机的航点补充装置可以包括第二存储装置和一个或多个第二处理器。
其中,第二存储装置,用于存储程序指令。一个或多个第二处理器,调用第二存储装置中存储的程序指令,当程序指令被执行时,一个或多个第二处理器单独地或共同地被配置成用于实施如下操作:接收到数据处理设备发送的航点补充包;根据航点补充包,向飞行控制器进行航点补充;其中,航点补充包携带有至少一个补充航点,补充航点为数据处理设备根据该数据处理设备预测的无人机当前消耗的航点的第一数 量和预设航点数据库确定,预设航点数据库存储有多个航点。
本实施例的第二处理器可以实现如本申请图5所示实施例的无人机的航点补充方法,可参见上述实施例二的无人机的航点补充方法对本实施例的无人机的航点补充装置进行说明。
进一步的,本申请实施例还提供一种无人机,请参见图1B和1C,该无人机100可以包括机身110、飞行控制器120和本申请实施例二所述的无人机的航点补充装置。其中,飞行控制器120设于机身110,无人机的航点补充装置由机身支撑。
可选的,本实施例的无人机的航点补充装置为飞行控制器120。
实施例三
本申请实施例还提供一种无人机系统,请结合图1A至图1C,无人机系统可以包括无人机100和数据处理设备200。无人机100可包括机身110和设于机身110的飞行控制器120,数据处理设备200与飞行控制器120通信连接。本申请实施例中,数据处理设备200可以为无人机100的一部分,也可以不作为无人机100的一部分。
其中,数据处理设备200用于:预测无人机100当前消耗的航点的第一数量,并根据第一数量,从预设航点数据库中确定补充航点,发送航点补充包至飞行控制器120,预设航点数据库存储有多个航点,航点补充包携带有补充航点。
飞行控制器120用于:接收到数据处理设备200发送的航点补充包,根据航点补充包进行航点补充。
可选的数据处理设备200具体用于:获取无人机100的飞行参数,并根据飞行参数,预测无人机100当前消耗的航点的第一数量。
可选的,飞行参数包括无人机100的飞行速度和飞行控制器120中相邻航点之间的距离中的至少一种。
可选的,不同的无人机100的飞行模式对应飞行参数不同。
可选的,数据处理设备200具体用于:根据飞行参数、数据处理设备200当前已发送给飞行控制器120的航点的第二数量以及飞行控制器120最近一次实际接收的航点的航点信息,预测第一数量;其中,飞行控制器120最近一次实际接收的航点根据数据处理设备200最近一次发送的航点补充包中的补充航点和无人机100实际消耗的航点的第三数量确定。
可选的,航点信息包括飞行控制器120最近一次实际接收的航点的第四数量和飞行控制器120最近一次实际接收的航点的密集程度中的至少一个。
可选的,在数据处理设备200首次预测第一数量时,第四数量为初始航点的数量;初始航点为数据处理设备200首次发送给飞行控制器120的航点。
可选的,当第三数量小于航点补充包中的补充航点的数量时,第四数量与第三数量大小相等。
可选的,当第三数量大于航点补充包中的补充航点的数量时,第四数量与航点补充包中的补充航点的数量大小相等。
可选的,飞行控制器120还用于:在根据航点补充包进行航点补充之后,返回应答消息至数据处理设备200,应答消息携带有第四数量。
可选的,数据处理设备200还用于:根据第四数量,更新第二数量的大小。
可选的,数据处理设备200具体用于:根据飞行参数和预设模型,预测无人机100当前消耗的航点的第一数量;其中,预设模型用于表征飞行参数与第一数量之间的关系。
可选的,预设模型包括神经网络模型和函数模型中的至少一种;其中,神经网络模型的输入包括飞行参数,神经网络模型的输出包括第一数量;函数模型以飞行参数为自变量,第一数量为因变量。
可选的,神经网络模型包括径向基RBF神经网络模型。
可选的,数据处理设备200具体用于:从预设航点数据库的第一航点中获取存储顺序靠前的第一数量个航点作为补充航点;第一航点为预设航点数据库中标记为未发送状态的航点。
可选的,数据处理设备200具体用于:在发送航点补充包至飞行控制器120之后,将预设航点数据库中与飞行控制器120最近一次实际接收的航点补充包中的航点对应的航点标记为已发送状态。
可选的,无人机100包括与飞行控制器120通信连接的数据处理设备200;
预设航点数据库为数据处理设备200中预先存储的航点数据库;或者,
预设航点数据库为外部存储设备预先存储的航点数据库,外部存储设备与数据处理设备200通信连接。
可选的,数据处理设备200用于:在第一数量大于预设阈值时,发送航点补充包至飞行控制器120。
可选的,飞行控制器120具体用于:确定无人机100在飞行过程中实际消耗的航点的第三数量;根据航点补充包和第三数量进行航点补充。
可选的,飞行控制器120具体用于:在第三数量小于航点补充包中的补充航点的数量时,确定飞行控制器120实际接收航点的第四数量为实际消耗的航点的数量;根据第四数量和航点补充包,确定飞行控制器120实际接收航点。
可选的,飞行控制器120具体用于:在第三数量大于或等于航点补充包中的补充航点的数量时,确定飞行控制器120实际接收航点的第四数量为航点补充包中的补充航点的数量;根据第四数量和航点补充包,确定飞行控制器120实际接收航点。
可选的,飞行控制器120还用于:将当前已消耗的航点从飞行控制器120中删除。
可选的,数据处理设备200包括设于无人机100的数据处理设备。
可选的,数据处理设备200为无人机100的图像处理模块。
可选的,数据处理设备200包括为无人机100的遥控终端。
本实施例中未展开的部分可以参见上述实施例一和/或实施例二中相应部分的描述,此处不再赘述。
实施例一或实施例二中的存储装置存储所述无人机的航点补充方法的可执行指令计算机程序,所述存储装置可以包括至少一种类型的存储介质,存储介质包括闪存、硬盘、多媒体卡、卡型存储器(例如,SD或DX存储器等等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘等等。而且,所述无人机的航点补充装置可以与通过网络连接执行存储器的存储功能的网络存储装置协作。存储器可以是无人机的航点补充装置的内部存储单元,例如无人机的航点补充装置的硬盘或内存。存储器也可以是无人机的航点补充装置的外部存储设备,例如无人机的航点补充装置上配备的插接式硬盘,智能存储卡(Smart Media Card,SMC),安全数字(Secure Digital,SD)卡,闪存卡(Flash Card)等。进一步的,存储器还可以既包括无人机的航点补充装置的内部存储单元也包括外部存储设备。存储器用于存储计算机程序以及设备所需的其他程序和数据。存储器还可以用于暂时地存储已经输出或者将要输出的数据。
实施例一或实施例二中的处理器可以是中央处理单元(Central Processing Unit,CPU),还可以是其他通用处理器、数字信号处理器(Digital Signal Processor,DSP)、专用集成电路(Application Specific Integrated Circuit,ASIC)、现场可编程门阵列(Field-Programmable Gate Array,FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
此外,本申请实施例还提供一种计算机可读存储介质,其上存储有计算机程序,该程序被处理器执行时实现上述实施例一或实施例二无人机的航点补充方法的步骤。
所述计算机可读存储介质可以是前述任一实施例所述的无人机系统的内部存储单元,例如硬盘或内存。所述计算机可读存储介质也可以是无人机系统的外部存储设备,例如所述设备上配备的插接式硬盘、智能存储卡(Smart Media Card,SMC)、SD卡、闪存卡(Flash Card)等。进一步的,所述计算机可读存储介质还可以既包括无人机系统的内部存储单元也包括外部存储设备。所述计算机可读存储介质用于存储所述计算机程序以及所述无人机系统所需的其他程序和数据,还可以用于暂时地存储已经输出或者将要输出的数据。
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来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例的流程。其中,所述的存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory,ROM)或随机存储记忆体(Random Access Memory,RAM)等。
以上所揭露的仅为本申请部分实施例而已,当然不能以此来限定本申请之权利范围,因此依本申请权利要求所作的等同变化,仍属本申请所涵盖的范围。
Claims (111)
- 一种无人机的航点补充方法,其特征在于,所述无人机包括飞行控制器,所述方法包括:预测所述无人机当前消耗的航点的第一数量;根据所述第一数量,从预设航点数据库中确定补充航点;发送航点补充包至所述飞行控制器;其中,所述预设航点数据库存储有多个航点,所述航点补充包携带有所述补充航点。
- 根据权利要求1所述的方法,其特征在于,所述预测所述无人机当前消耗的航点的第一数量,包括:获取所述无人机的飞行参数;根据所述飞行参数,预测所述无人机当前消耗的航点的第一数量。
- 根据权利要求2所述的方法,其特征在于,所述飞行参数包括所述无人机的飞行速度和所述飞行控制器中相邻航点之间的距离中的至少一种。
- 根据权利要求2所述的方法,其特征在于,不同的所述无人机的飞行模式对应所述飞行参数不同。
- 根据权利要求2所述的方法,其特征在于,所述根据所述飞行参数,预测所述无人机当前消耗的航点的第一数量,具体包括:根据所述飞行参数、当前已发送给所述飞行控制器的航点的第二数量以及所述飞行控制器最近一次实际接收的航点的航点信息,预测所述第一数量;其中,所述飞行控制器最近一次实际接收的航点根据最近一次发送的所述航点补充包中的补充航点和所述无人机实际消耗的航点的第三数量确定。
- 根据权利要求5所述的方法,其特征在于,所述航点信息包括所述飞行控制器最近一次实际接收的航点的第四数量和所述飞行控制器最近一次实际接收的航点的密集程度中的至少一个。
- 根据权利要求6所述的方法,其特征在于,在首次预测所述第一数量时,所述第四数量为初始航点的数量;所述初始航点为首次发送给所述飞行控制器的航点。
- 根据权利要求6所述的方法,其特征在于,当所述第三数量小于所述航点补充包中的补充航点的数量时,所述第四数量与所述第三数量大小相等。
- 根据权利要求6所述的方法,其特征在于,当所述第三数量大于所述航点补充包中的补充航点的数量时,所述第四数量与所述航点补充包中的补充航点的数量大小相等。
- 根据权利要求6所述的方法,其特征在于,所述第四数量由所述飞行控制器反馈。
- 根据权利要求10所述的方法,其特征在于,所述发送航点补充包至所述飞行 控制器之后,还包括:接收所述飞行控制器针对所述航点补充包返回的应答消息,所述应答消息携带有所述第四数量。
- 根据权利要求11所述的方法,其特征在于,所述方法还包括:根据所述第四数量,更新所述第二数量的大小。
- 根据权利要求2所述的方法,其特征在于,所述根据所述飞行参数,预测所述无人机当前消耗的航点的第一数量,包括:根据所述飞行参数和预设模型,预测所述无人机当前消耗的航点的第一数量;其中,所述预设模型用于表征所述飞行参数与所述第一数量之间的关系。
- 根据权利要求13所述的方法,其特征在于,所述预设模型包括神经网络模型和函数模型中的至少一种;其中,所述神经网络模型的输入包括所述飞行参数,所述神经网络模型的输出包括所述第一数量;所述函数模型以所述飞行参数为自变量,所述第一数量为因变量。
- 根据权利要求14所述的方法,其特征在于,所述神经网络模型包括径向基RBF神经网络模型。
- 根据权利要求1所述的方法,其特征在于,所述根据所述第一数量,从预设航点数据库中确定补充航点,包括:从所述预设航点数据库的第一航点中获取存储顺序靠前的所述第一数量个航点作为所述补充航点;所述第一航点为所述预设航点数据库中标记为未发送状态的航点。
- 根据权利要求16所述的方法,其特征在于,所述发送航点补充包至所述飞行控制器之后,还包括:将所述预设航点数据库中与所述飞行控制器最近一次实际接收的所述航点补充包中的航点对应的航点标记为已发送状态。
- 根据权利要求16所述的方法,其特征在于,所述无人机包括与所述飞行控制器通信连接的数据处理设备;所述预设航点数据库为所述数据处理设备中预先存储的航点数据库;或者,所述预设航点数据库为外部存储设备预先存储的航点数据库,所述外部存储设备与所述数据处理设备通信连接。
- 根据权利要求1所述的方法,其特征在于,所述发送航点补充包至所述飞行控制器,包括:当所述第一数量大于预设阈值时,发送航点补充包至所述飞行控制器。
- 根据权利要求1所述的方法,其特征在于,所述方法的执行主体为设于无人机的数据处理设备。
- 根据权利要求20所述的方法,其特征在于,所述数据处理设备为图像处理模 块。
- 根据权利要求1所述的方法,其特征在于,所述方法的执行主体为所述无人机的遥控终端。
- 一种无人机的航点补充装置,其特征在于,所述无人机包括飞行控制器,所述装置包括:存储装置,用于存储程序指令;以及一个或多个处理器,调用所述存储装置中存储的程序指令,当所述程序指令被执行时,所述一个或多个处理器单独地或共同地被配置成用于实施如下操作:预测所述无人机当前消耗的航点的第一数量;根据所述第一数量,从预设航点数据库中确定补充航点;发送航点补充包至所述飞行控制器;其中,所述预设航点数据库存储有多个航点,所述航点补充包携带有所述补充航点。
- 根据权利要求23所述的装置,其特征在于,所述一个或多个处理器在预测所述无人机当前消耗的航点的第一数量时,单独地或共同地被进一步配置成用于实施如下操作:获取所述无人机的飞行参数;根据所述飞行参数,预测所述无人机当前消耗的航点的第一数量。
- 根据权利要求24所述的装置,其特征在于,所述飞行参数包括所述无人机的飞行速度和所述飞行控制器中相邻航点之间的距离中的至少一种。
- 根据权利要求24所述的装置,其特征在于,不同的所述无人机的飞行模式对应所述飞行参数不同。
- 根据权利要求24所述的装置,其特征在于,所述一个或多个处理器在根据所述飞行参数,预测所述无人机当前消耗的航点的第一数量时,单独地或共同地被进一步配置成用于实施如下操作:根据所述飞行参数、当前已发送给所述飞行控制器的航点的第二数量以及所述飞行控制器最近一次实际接收的航点的航点信息,预测所述第一数量;其中,所述飞行控制器最近一次实际接收的航点根据最近一次发送的所述航点补充包中的补充航点和所述无人机实际消耗的航点的第三数量确定。
- 根据权利要求27所述的装置,其特征在于,所述航点信息包括所述飞行控制器最近一次实际接收的航点的第四数量和所述飞行控制器最近一次实际接收的航点的密集程度中的至少一个。
- 根据权利要求28所述的装置,其特征在于,在首次预测所述第一数量时,所述第四数量为初始航点的数量;所述初始航点为首次发送给所述飞行控制器的航点。
- 根据权利要求28所述的装置,其特征在于,当所述第三数量小于所述航点补 充包中的补充航点的数量时,所述第四数量与所述第三数量大小相等。
- 根据权利要求28所述的装置,其特征在于,当所述第三数量大于所述航点补充包中的补充航点的数量时,所述第四数量与所述航点补充包中的补充航点的数量大小相等。
- 根据权利要求28所述的装置,其特征在于,所述第四数量由所述飞行控制器反馈。
- 根据权利要求32所述的装置,其特征在于,所述一个或多个处理器在发送航点补充包至所述飞行控制器之后,单独地或共同地还被配置成用于实施如下操作:接收所述飞行控制器针对所述航点补充包返回的应答消息,所述应答消息携带有所述第四数量。
- 根据权利要求33所述的装置,其特征在于,所述一个或多个处理器单独地或共同地还被配置成用于实施如下操作:根据所述第四数量,更新所述第二数量的大小。
- 根据权利要求24所述的装置,其特征在于,所述一个或多个处理器在根据所述飞行参数,预测所述无人机当前消耗的航点的第一数量时,单独地或共同地被进一步配置成用于实施如下操作:根据所述飞行参数和预设模型,预测所述无人机当前消耗的航点的第一数量;其中,所述预设模型用于表征所述飞行参数与所述第一数量之间的关系。
- 根据权利要求35所述的装置,其特征在于,所述预设模型包括神经网络模型和函数模型中的至少一种;其中,所述神经网络模型的输入包括所述飞行参数,所述神经网络模型的输出包括所述第一数量;所述函数模型以所述飞行参数为自变量,所述第一数量为因变量。
- 根据权利要求36所述的装置,其特征在于,所述神经网络模型包括径向基RBF神经网络模型。
- 根据权利要求23所述的装置,其特征在于,所述一个或多个处理器在根据所述第一数量,从预设航点数据库中确定补充航点时,单独地或共同地被进一步配置成用于实施如下操作:从所述预设航点数据库的第一航点中获取存储顺序靠前的所述第一数量个航点作为所述补充航点;所述第一航点为所述预设航点数据库中标记为未发送状态的航点。
- 根据权利要求38所述的装置,其特征在于,所述一个或多个处理器在发送航点补充包至所述飞行控制器之后,单独地或共同地还被配置成用于实施如下操作:将所述预设航点数据库中与所述飞行控制器最近一次实际接收的所述航点补充包中的航点对应的航点标记为已发送状态。
- 根据权利要求38所述的装置,其特征在于,所述无人机包括与所述飞行控制 器通信连接的数据处理设备;所述预设航点数据库为所述数据处理设备中预先存储的航点数据库;或者,所述预设航点数据库为外部存储设备预先存储的航点数据库,所述外部存储设备与所述数据处理设备通信连接。
- 根据权利要求23所述的装置,其特征在于,所述一个或多个处理器在发送航点补充包至所述飞行控制器时,单独地或共同地被进一步配置成用于实施如下操作:当所述第一数量大于预设阈值时,发送航点补充包至所述飞行控制器。
- 根据权利要求23所述的装置,其特征在于,所述无人机的航点补充装置为设于无人机的数据处理设备。
- 根据权利要求42所述的装置,其特征在于,所述数据处理设备为图像处理模块。
- 根据权利要求23所述的装置,其特征在于,所述无人机的航点补充装置为所述无人机的遥控终端。
- 一种数据处理设备,其特征在于,所述数据处理设备包括:主体部;权利要求23至44任一项所述的无人机的航点补充装置,由所述主体部支撑。
- 一种无人机的航点补充方法,其特征在于,所述无人机包括飞行控制器,所述方法包括:接收到数据处理设备发送的航点补充包;根据所述航点补充包,向所述飞行控制器进行航点补充;其中,所述航点补充包携带有至少一个补充航点,所述补充航点为所述数据处理设备根据该数据处理设备预测的所述无人机当前消耗的航点的第一数量和预设航点数据库确定,所述预设航点数据库存储有多个航点。
- 根据权利要求46所述的方法,其特征在于,所述第一数量为所述数据处理设备根据所述无人机的飞行参数预测。
- 根据权利要求47所述的方法,其特征在于,所述飞行参数包括所述无人机的飞行速度和所述飞行控制器中相邻航点之间的距离中的至少一种。
- 根据权利要求47所述的方法,其特征在于,不同的所述无人机的飞行模式对应所述飞行参数不同。
- 根据权利要求47所述的方法,其特征在于,所述第一数量为所述数据处理设备根据所述飞行参数、所述数据处理设备当前已发送给所述飞行控制器的航点的第二数量以及所述飞行控制器最近一次实际接收的航点的航点信息预测;其中,所述飞行控制器最近一次实际接收的航点根据最近一次发送的所述航点补充包中的补充航点和所述无人机实际消耗的航点的第三数量确定。
- 根据权利要求50所述的方法,其特征在于,所述航点信息包括所述飞行控制器最近一次实际接收的航点的第四数量和所述飞行控制器最近一次实际接收的航点的 密集程度中的至少一个。
- 根据权利要求51所述的方法,其特征在于,在所述数据处理设备首次预测所述第一数量时,所述第四数量为初始航点的数量;所述初始航点为所述飞行控制器首次接收到的所述数据处理设备发送的航点。
- 根据权利要求51所述的方法,其特征在于,当所述第三数量小于所述航点补充包中的补充航点的数量时,所述第四数量与所述第三数量大小相等。
- 根据权利要求51所述的方法,其特征在于,当所述第三数量大于所述航点补充包中的补充航点的数量时,所述第四数量与所述航点补充包中的补充航点的数量大小相等。
- 根据权利要求47所述的方法,其特征在于,所述第一数量为所述数据处理设备根据所述飞行参数和预设模型预测;其中,所述预设模型用于表征所述飞行参数与所述第一数量之间的关系。
- 根据权利要求55所述的方法,其特征在于,所述预设模型包括神经网络模型和函数模型中的至少一种;其中,所述神经网络模型的输入包括所述飞行参数,所述神经网络模型的输出包括所述第一数量;所述函数模型以所述飞行参数为自变量,所述第一数量为因变量。
- 根据权利要求56所述的方法,其特征在于,所述神经网络模型包括径向基RBF神经网络模型。
- 根据权利要求46所述的方法,其特征在于,所述根据所述航点补充包,向所述飞行控制器进行航点补充,包括:确定所述无人机在飞行过程中实际消耗的航点的第三数量;根据所述航点补充包和所述第三数量,向所述飞行控制器进行航点补充。
- 根据权利要求58所述的方法,其特征在于,所述根据所述航点补充包和所述第三数量,向所述飞行控制器进行航点补充,包括:当所述第三数量小于所述航点补充包中的补充航点的数量时,确定所述飞行控制器实际接收的航点的第四数量为所述第三数量;根据所述第四数量和所述航点补充包,确定所述飞行控制器实际接收的航点。
- 根据权利要求58所述的方法,其特征在于,所述根据所述航点补充包和所述第三数量,向所述飞行控制器进行航点补充,包括:当所述第三数量大于或等于所述航点补充包中的补充航点的数量时,确定所述飞行控制器实际接收的航点的第四数量为所述航点补充包中的补充航点的数量;根据所述第四数量和所述航点补充包,确定所述飞行控制器实际接收的航点。
- 根据权利要求46所述的方法,其特征在于,所述方法还包括:返回应答消息至所述数据处理设备,所述应答消息携带有所述飞行控制器实际接收的航点的第四数量。
- 根据权利要求46所述的方法,其特征在于,所述方法还包括:将当前已消耗的航点从所述飞行控制器中删除。
- 根据权利要求46所述的方法,其特征在于,所述数据处理设备为设于无人机的数据处理设备。
- 根据权利要求63所述的方法,其特征在于,所述数据处理设备为图像处理模块。
- 根据权利要求46所述的方法,其特征在于,所述数据处理设备为远程于无人机的外部终端。
- 一种无人机的航点补充装置,其特征在于,所述无人机包括飞行控制器,所述装置包括:存储装置,用于存储程序指令;以及一个或多个处理器,调用所述存储装置中存储的程序指令,当所述程序指令被执行时,所述一个或多个处理器单独地或共同地被配置成用于实施如下操作:接收到数据处理设备发送的航点补充包;根据所述航点补充包,向所述飞行控制器进行航点补充;其中,所述航点补充包携带有至少一个补充航点,所述补充航点为所述数据处理设备根据该数据处理设备预测的所述无人机当前消耗的航点的第一数量和预设航点数据库确定,所述预设航点数据库存储有多个航点。
- 根据权利要求66所述的装置,其特征在于,所述第一数量为所述数据处理设备根据所述无人机的飞行参数预测。
- 根据权利要求67所述的装置,其特征在于,所述飞行参数包括所述无人机的飞行速度和所述飞行控制器中相邻航点之间的距离中的至少一种。
- 根据权利要求67所述的装置,其特征在于,不同的所述无人机的飞行模式对应所述飞行参数不同。
- 根据权利要求67所述的装置,其特征在于,所述第一数量为所述数据处理设备根据所述飞行参数、所述数据处理设备当前已发送给所述飞行控制器的航点的第二数量以及所述飞行控制器最近一次实际接收的航点的航点信息预测;其中,所述飞行控制器最近一次实际接收的航点根据最近一次发送的所述航点补充包中的补充航点和所述无人机实际消耗的航点的第三数量确定。
- 根据权利要求70所述的装置,其特征在于,所述航点信息包括所述飞行控制器最近一次实际接收的航点的第四数量和所述飞行控制器最近一次实际接收的航点的密集程度中的至少一个。
- 根据权利要求71所述的装置,其特征在于,在所述数据处理设备首次预测所述第一数量时,所述第四数量为初始航点的数量;所述初始航点为所述飞行控制器首次接收到的所述数据处理设备发送的航点。
- 根据权利要求71所述的装置,其特征在于,当所述第三数量小于所述航点补 充包中的补充航点的数量时,所述第四数量与所述第三数量大小相等。
- 根据权利要求71所述的装置,其特征在于,当所述第三数量大于所述航点补充包中的补充航点的数量时,所述第四数量与所述航点补充包中的补充航点的数量大小相等。
- 根据权利要求67所述的装置,其特征在于,所述第一数量为所述数据处理设备根据所述飞行参数和预设模型预测;其中,所述预设模型用于表征所述飞行参数与所述第一数量之间的关系。
- 根据权利要求75所述的装置,其特征在于,所述预设模型包括神经网络模型和函数模型中的至少一种;其中,所述神经网络模型的输入包括所述飞行参数,所述神经网络模型的输出包括所述第一数量;所述函数模型以所述飞行参数为自变量,所述第一数量为因变量。
- 根据权利要求76所述的装置,其特征在于,所述神经网络模型包括径向基RBF神经网络模型。
- 根据权利要求66所述的装置,其特征在于,所述一个或多个处理器在根据所述航点补充包,向所述飞行控制器进行航点补充时,单独地或共同地被进一步配置成用于实施如下操作:确定所述无人机在飞行过程中实际消耗的航点的第三数量;根据所述航点补充包和所述第三数量,向所述飞行控制器进行航点补充。
- 根据权利要求78所述的装置,其特征在于,所述一个或多个处理器在根据所述航点补充包和所述第三数量,向所述飞行控制器进行航点补充时,单独地或共同地被进一步配置成用于实施如下操作:当所述第三数量小于所述航点补充包中的补充航点的数量时,确定所述飞行控制器实际接收的航点的第四数量为所述第三数量;根据所述第四数量和所述航点补充包,确定所述飞行控制器实际接收的航点。
- 根据权利要求78所述的装置,其特征在于,所述一个或多个处理器在根据所述航点补充包和所述第三数量,向所述飞行控制器进行航点补充时,单独地或共同地被进一步配置成用于实施如下操作:当所述第三数量大于或等于所述航点补充包中的补充航点的数量时,确定所述飞行控制器实际接收的航点的第四数量为所述航点补充包中的补充航点的数量;根据所述第四数量和所述航点补充包,确定所述飞行控制器实际接收的航点。
- 根据权利要求66所述的装置,其特征在于,所述一个或多个处理器单独地或共同地还被配置成用于实施如下操作:返回应答消息至所述数据处理设备,所述应答消息携带有所述飞行控制器实际接收的航点的第四数量。
- 根据权利要求66所述的装置,其特征在于,所述一个或多个处理器单独地或 共同地还被配置成用于实施如下操作:将当前已消耗的航点从所述飞行控制器中删除。
- 根据权利要求66所述的装置,其特征在于,所述数据处理设备为设于无人机的数据处理设备。
- 根据权利要求83所述的装置,其特征在于,所述数据处理设备为图像处理模块。
- 根据权利要求66所述的装置,其特征在于,所述数据处理设备为远程于无人机的外部终端。
- 一种无人机,其特征在于,所述无人机包括:机身;飞行控制器,设于所述机身;和权利要求66至75任一项所述的无人机的航点补充装置,由所述机身支撑。
- 一种无人机系统,其特征在于,包括机身、设于所述机身的飞行控制器和与所述飞行控制器通信连接的数据处理设备;其中,所述数据处理设备用于:预测所述无人机当前消耗的航点的第一数量,并根据所述第一数量,从预设航点数据库中确定补充航点,发送航点补充包至所述飞行控制器,所述预设航点数据库存储有多个航点,所述航点补充包携带有所述补充航点;所述飞行控制器用于:接收到数据处理设备发送的航点补充包,根据所述航点补充包进行航点补充。
- 根据权利要求87所述的系统,其特征在于,所述数据处理设备具体用于:获取所述无人机的飞行参数,并根据所述飞行参数,预测所述无人机当前消耗的航点的第一数量。
- 根据权利要求88所述的系统,其特征在于,所述飞行参数包括所述无人机的飞行速度和所述飞行控制器中相邻航点之间的距离中的至少一种。
- 根据权利要求88所述的系统,其特征在于,不同的所述无人机的飞行模式对应所述飞行参数不同。
- 根据权利要求88所述的系统,其特征在于,所述数据处理设备具体用于:根据所述飞行参数、所述数据处理设备当前已发送给所述飞行控制器的航点的第二数量以及所述飞行控制器最近一次实际接收的航点的航点信息,预测所述第一数量;其中,所述飞行控制器最近一次实际接收的航点根据所述数据处理设备最近一次发送的所述航点补充包中的补充航点和所述无人机实际消耗的航点的第三数量确定。
- 根据权利要求91所述的系统,其特征在于,所述航点信息包括所述飞行控制器最近一次实际接收的航点的第四数量和所述飞行控制器最近一次实际接收的航点的密集程度中的至少一个。
- 根据权利要求92所述的系统,其特征在于,在所述数据处理设备首次预测所述第一数量时,所述第四数量为初始航点的数量;所述初始航点为所述数据处理设备首次发送给所述飞行控制器的航点。
- 根据权利要求92所述的系统,其特征在于,当所述第三数量小于所述航点补充包中的补充航点的数量时,所述第四数量与所述第三数量大小相等。
- 根据权利要求92所述的系统,其特征在于,当所述第三数量大于所述航点补充包中的补充航点的数量时,所述第四数量与所述航点补充包中的补充航点的数量大小相等。
- 根据权利要求92所述的系统,其特征在于,所述飞行控制器还用于:在根据所述航点补充包进行航点补充之后,返回应答消息至所述数据处理设备,所述应答消息携带有所述第四数量。
- 根据权利要求96所述的系统,其特征在于,所述数据处理设备还用于:根据所述第四数量,更新所述第二数量的大小。
- 根据权利要求88所述的系统,其特征在于,所述数据处理设备具体用于:根据所述飞行参数和预设模型,预测所述无人机当前消耗的航点的第一数量;其中,所述预设模型用于表征所述飞行参数与所述第一数量之间的关系。
- 根据权利要求98所述的系统,其特征在于,所述预设模型包括神经网络模型和函数模型中的至少一种;其中,所述神经网络模型的输入包括所述飞行参数,所述神经网络模型的输出包括所述第一数量;所述函数模型以所述飞行参数为自变量,所述第一数量为因变量。
- 根据权利要求99所述的系统,其特征在于,所述神经网络模型包括径向基RBF神经网络模型。
- 根据权利要求87所述的系统,其特征在于,所述数据处理设备具体用于:从所述预设航点数据库的第一航点中获取存储顺序靠前的所述第一数量个航点作为所述补充航点;所述第一航点为所述预设航点数据库中标记为未发送状态的航点。
- 根据权利要求101所述的系统,其特征在于,所述数据处理设备具体用于:在发送航点补充包至所述飞行控制器之后,将所述预设航点数据库中与所述飞行控制器最近一次实际接收的所述航点补充包中的航点对应的航点标记为已发送状态。
- 根据权利要求101所述的系统,其特征在于,所述无人机包括与所述飞行控制器通信连接的数据处理设备;所述预设航点数据库为所述数据处理设备中预先存储的航点数据库;或者,所述预设航点数据库为外部存储设备预先存储的航点数据库,所述外部存储设备与所述数据处理设备通信连接。
- 根据权利要求87所述的系统,其特征在于,所述数据处理设备用于:在所述第一数量大于预设阈值时,发送航点补充包至所述飞行控制器。
- 根据权利要求87所述的系统,其特征在于,所述飞行控制器具体用于:确 定所述无人机在飞行过程中实际消耗的航点的第三数量;根据所述航点补充包和所述第三数量进行航点补充。
- 根据权利要求105所述的系统,其特征在于,所述飞行控制器具体用于:在所述第三数量小于所述航点补充包中的补充航点的数量时,确定所述飞行控制器实际接收航点的第四数量为所述实际消耗的航点的数量;根据所述第四数量和所述航点补充包,确定所述飞行控制器实际接收航点。
- 根据权利要求105所述的系统,其特征在于,所述飞行控制器具体用于:在所述第三数量大于或等于所述航点补充包中的补充航点的数量时,确定所述飞行控制器实际接收航点的第四数量为所述航点补充包中的补充航点的数量;根据所述第四数量和所述航点补充包,确定所述飞行控制器实际接收航点。
- 根据权利要求87所述的系统,其特征在于,所述飞行控制器还用于:将当前已消耗的航点从所述飞行控制器中删除。
- 根据权利要求87所述的系统,其特征在于,所述数据处理设备包括设于无人机的数据处理设备。
- 根据权利要求109所述的系统,其特征在于,所述数据处理设备为图像处理模块。
- 根据权利要求109所述的系统,其特征在于,所述数据处理设备包括为所述无人机的遥控终端。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2020/087331 WO2021217375A1 (zh) | 2020-04-27 | 2020-04-27 | 无人机及其航点补充方法和装置、数据处理设备 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2020/087331 WO2021217375A1 (zh) | 2020-04-27 | 2020-04-27 | 无人机及其航点补充方法和装置、数据处理设备 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021217375A1 true WO2021217375A1 (zh) | 2021-11-04 |
Family
ID=78373874
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2020/087331 WO2021217375A1 (zh) | 2020-04-27 | 2020-04-27 | 无人机及其航点补充方法和装置、数据处理设备 |
Country Status (1)
Country | Link |
---|---|
WO (1) | WO2021217375A1 (zh) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9115995B1 (en) * | 2006-09-28 | 2015-08-25 | Rockwell Collins, Inc. | Enhanced graphical flight planning for a flight management system |
CN108124471A (zh) * | 2017-12-11 | 2018-06-05 | 深圳市道通智能航空技术有限公司 | 无人飞行器返航方法、装置、存储介质和无人飞行器 |
CN110345945A (zh) * | 2019-05-29 | 2019-10-18 | 深圳市道通智能航空技术有限公司 | 一种参考航点数据的传输方法、装置及无人机 |
CN110570691A (zh) * | 2018-06-06 | 2019-12-13 | 杭州海康机器人技术有限公司 | 一种无人机航线确定方法及装置 |
-
2020
- 2020-04-27 WO PCT/CN2020/087331 patent/WO2021217375A1/zh active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9115995B1 (en) * | 2006-09-28 | 2015-08-25 | Rockwell Collins, Inc. | Enhanced graphical flight planning for a flight management system |
CN108124471A (zh) * | 2017-12-11 | 2018-06-05 | 深圳市道通智能航空技术有限公司 | 无人飞行器返航方法、装置、存储介质和无人飞行器 |
CN110570691A (zh) * | 2018-06-06 | 2019-12-13 | 杭州海康机器人技术有限公司 | 一种无人机航线确定方法及装置 |
CN110345945A (zh) * | 2019-05-29 | 2019-10-18 | 深圳市道通智能航空技术有限公司 | 一种参考航点数据的传输方法、装置及无人机 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113950066B (zh) | 移动边缘环境下单服务器部分计算卸载方法、系统、设备 | |
WO2020000700A1 (zh) | 一种无人机系统中的模块升级方法和无人机系统 | |
CN110531996B (zh) | 一种多微云环境下基于粒子群优化的计算任务卸载方法 | |
CN113032120A (zh) | 一种基于边缘计算的工业现场大数据任务协调度方法 | |
CN113645637B (zh) | 超密集网络任务卸载方法、装置、计算机设备和存储介质 | |
US11972184B2 (en) | Method and system for designing a robotic system architecture with optimized system latency | |
US20230139187A1 (en) | Method and apparatus for determining information, electronic device and storage medium | |
CN114327876A (zh) | 一种无人机辅助移动边缘计算的任务卸载方法和装置 | |
CN115145311A (zh) | 一种巡检路径规划方法、装置、设备和存储介质 | |
CN114691372A (zh) | 一种多媒体端边云系统的群体智能控制方法 | |
Mu et al. | Deep reinforcement learning based adaptive threshold multi-tasks offloading approach in mec | |
WO2021217375A1 (zh) | 无人机及其航点补充方法和装置、数据处理设备 | |
CN115456194B (zh) | 基于异步联邦学习的模型训练控制方法、装置及系统 | |
EP4401006A1 (en) | Data processing apparatus and method | |
CN115330058A (zh) | 对象选择模型的训练方法、对象选择方法及装置 | |
CN115269145A (zh) | 一种面向海上无人设备的高能效异构多核调度方法及装置 | |
CN113805578B (zh) | 无人车路径优化方法及相关设备 | |
CN113804208B (zh) | 无人车路径优化方法及相关设备 | |
Oh et al. | Energy-efficient task partitioning for CNN-based object detection in heterogeneous computing environment | |
Yang et al. | Blockchain-driven optimization in intelligent manufacturing | |
CN117553803B (zh) | 一种基于深度强化学习的多无人机智能路径规划方法 | |
US11989172B2 (en) | System and method for managing transition between inference models across multiple data processing systems | |
CN115512065B (zh) | 一种基于分块化的大规模场景下实时地图构建方法和装置 | |
US20230195531A1 (en) | Energy-aware task scheduling | |
CN113095537B (zh) | 路径规划的方法和装置 |
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: 20933564 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: 20933564 Country of ref document: EP Kind code of ref document: A1 |