Unmanned aerial vehicle return flight control method, device, equipment and medium
By obtaining environmental and flight parameters, using preset return inference models and LSTM neural networks to optimize the return decisions of drones, the problem of inaccurate return time in the existing technology is solved, and the task execution efficiency and safety is improved.
Patent Information
- Application Number
- CN202510522451.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-24
- Publication Date
- 2025-07-29
Smart Images
Figure CN120386384A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of unmanned aerial vehicle control, and particularly to a method, device, equipment and medium for controlling the return of an unmanned aerial vehicle. Background Art
[0002] Due to its efficient, flexible and multi-functional characteristics, unmanned aerial vehicles (UAVs) have a wide range of application scenarios in many fields. In related technologies, a UAV determines whether to return based on the remaining battery power or voltage. However, during the flight of the UAV, environmental parameters will have a certain impact on battery power consumption, and the mechanism of triggering the return by setting a fixed remaining current threshold may cause the UAV to return prematurely in a high-power consumption environment, wasting mission time; or return too late in a low-power consumption environment, posing a certain risk of crashing. Therefore, more accurately determining the return time of the UAV is an urgent problem to be solved currently. Summary of the Invention
[0003] In view of this, the present invention provides a method, device, equipment and medium for controlling the return of an unmanned aerial vehicle to solve the problem of inaccurate return control.
[0004] In a first aspect, the present invention provides a method for controlling the return of an unmanned aerial vehicle, the method comprising:
[0005] When the unmanned aerial vehicle executes a flight mission, obtain environmental parameters and flight parameters;
[0006] Based on a preset return inference model, the environmental parameters and the flight parameters, determine a first remaining available duration of the unmanned aerial vehicle;
[0007] Based on the flight parameters, determine a second remaining available duration, and compare the first remaining available duration and the second remaining available duration to determine a target remaining available duration according to a first comparison result;
[0008] Based on the environmental parameters and the duration required for return, determine a first duration, and compare the first duration and the target remaining available duration to determine a target return result according to a second comparison result, where the target return result indicates whether to control the unmanned aerial vehicle to return.
[0009] In an optional implementation manner, the determining the first remaining available duration of the unmanned aerial vehicle based on the preset return inference model, the environmental parameters and the flight parameters includes:
[0010] Input the environmental parameters and the flight parameters into the preset return inference model to determine the first remaining available duration of the unmanned aerial vehicle, where the environmental parameters at least include wind speed, temperature and humidity, and the flight parameters at least include the preset cruise duration of the unmanned aerial vehicle.
[0011] In an alternative embodiment, the flight parameters further include operating power and remaining battery power, and determining the second remaining available duration based on the flight parameters includes:
[0012] Determining the second remaining available duration based on the operating power and the remaining battery power.
[0013] In an alternative embodiment, comparing the first remaining available duration and the second remaining available duration to determine a target remaining available duration according to a first comparison result includes:
[0014] If the first remaining available duration is less than or equal to the second remaining available duration, determining the first remaining available duration as the target remaining available duration;
[0015] If the first remaining available duration is greater than the second remaining available duration, adjusting the preset return flight inference model based on the second remaining available duration, and determining a new first remaining available duration based on the optimized preset return flight inference model until the first remaining available duration is less than or equal to the second remaining available duration.
[0016] In an alternative embodiment, determining the first duration based on the environmental parameters and the required duration for returning includes:
[0017] Determining the required duration for returning based on the first remaining available duration and the return distance;
[0018] Determining a corresponding risk coefficient based on the environmental parameters, where there is a preset mapping relationship between the environmental parameters and the risk coefficient;
[0019] Calculating the sum of the risk coefficient and the required duration for returning to obtain the first duration.
[0020] In an alternative embodiment, comparing the first duration and the target remaining available duration to determine a target return result according to a second comparison result includes:
[0021] Calculating the difference between the target remaining available duration and the first duration;
[0022] Comparing the difference with a preset threshold to obtain a second comparison result;
[0023] If the difference is less than or equal to the preset threshold, controlling the UAV to return.
[0024] In an alternative embodiment, the method further includes:
[0025] The preset return flight inference model is trained based on training data, and the training data includes historical flight data.
[0026] In a second aspect, the present invention provides a drone return flight control device, and the device includes:
[0027] A parameter acquisition module, configured to acquire environmental parameters and flight parameters when the drone executes a flight mission;
[0028] A first duration determination module, configured to determine a first remaining available duration of the drone based on the preset return flight inference model, the environmental parameters, and the flight parameters;
[0029] A target duration determination module, configured to determine a second remaining available duration based on the flight parameters, and compare the first remaining available duration with the second remaining available duration, so as to determine a target remaining available duration according to a first comparison result;
[0030] A return flight control module, configured to determine a first duration based on the environmental parameters and the duration required for return flight, and compare the first duration with the target remaining available duration, so as to determine a target return flight result according to a second comparison result, where the target return flight result indicates whether to control the drone to return.
[0031] In a third aspect, the present invention provides a computer device, including: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the drone return flight control method according to the first aspect or any corresponding implementation manner thereof.
[0032] In a fourth aspect, the present invention provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to cause a computer to execute the drone return flight control method according to the first aspect or any corresponding implementation manner thereof.
[0033] The UAV return control method provided in this embodiment includes obtaining environmental parameters and flight parameters when the UAV is performing a flight mission; determining the first remaining available duration of the UAV based on a preset return reasoning model, environmental parameters, and flight parameters; determining a second remaining available duration based on the flight parameters, and comparing the first remaining available duration with the second remaining available duration to determine a target remaining available duration according to the first comparison result; determining a first duration based on the environmental parameters and the duration required for return, and comparing the first duration with the target remaining available duration to determine a target return result according to the second comparison result, where the target return result indicates whether to control the UAV to return. This method combines environmental parameters and the duration required for return to obtain the first duration as the threshold for whether to control return, taking into account the impact of environmental factors on flight, and can improve the execution efficiency of the flight mission as much as possible while ensuring safety. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.
[0035] Figure 1 is a schematic flowchart of the UAV return control method according to an embodiment of the present invention;
[0036] Figure 2 is a structural block diagram of the UAV return control device according to an embodiment of the present invention;
[0037] Figure 3 is a schematic hardware structure diagram of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0038] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
[0039] In related technologies, the return strategy of an unmanned aerial vehicle (UAV) is usually based on a fixed power or voltage threshold. For example, if the remaining power is 20%, the UAV is forced to return. However, during the flight of the UAV, the non-linear effects of environmental factors such as wind speed, temperature, and altitude on battery power consumption are not considered, resulting in a large error in the estimation of the remaining power. Due to the limitations of the static model, it relies on preset empirical values, making it impossible to dynamically learn the power consumption pattern in historical flight data. The mechanism of setting a fixed remaining current threshold to trigger the return may cause the UAV to return prematurely in a high-power consumption environment, wasting mission time; or return too late in a low-power consumption environment, posing a certain risk of crashing. Based on this, an embodiment of the present invention provides a method for controlling the return of a UAV.
[0040] According to an embodiment of the present invention, there is provided an embodiment of a method for controlling the return of a UAV. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.
[0041] In this embodiment, a method for controlling the return of a UAV is provided. Figure 1 It is a flowchart of a method for controlling the return of a UAV according to an embodiment of the present invention. As Figure 1 shown, the process includes the following steps:
[0042] Step S101, when the UAV is performing a flight mission, obtain environmental parameters and flight parameters.
[0043] The environmental parameters include meteorological data and geographical data. Specifically, the meteorological data may include parameters such as the air temperature, air pressure, wind speed, and humidity in the flight area where the UAV is performing the flight mission, and can be detected by devices such as a barometer, a temperature and humidity sensor, and an anemometer carried by the UAV. The geographical data includes parameters such as longitude, latitude, and altitude, and the geographical data is collected by GPS.
[0044] The flight parameters include the flight mission parameters, battery parameters, and airframe state of the UAV. The flight mission parameters include the planned cruise duration of the flight mission. The battery parameters include voltage, current, remaining battery power, and health status, etc. Specifically, the battery management system can monitor parameters such as voltage, current, and remaining power in real time. The parameters related to the airframe state during the flight of the UAV are measured by an IMU (Inertial Measurement Unit) provided on the UAV, specifically including flight speed, acceleration, attitude angle, etc.
[0045] Step S102, based on a preset return inference model, environmental parameters, and flight parameters, determine the first remaining available duration of the UAV.
[0046] The preset return flight inference model is used to infer the remaining available duration of the drone under the current task. The environmental parameters and flight parameters are used as the input of the preset return flight inference model. The preset return flight inference model processes the environmental parameters and flight parameters. First, it determines the battery power consumption rate, and then outputs the first remaining available duration according to the remaining battery power and the battery power consumption rate. The first remaining available duration is the inference result of the preset return flight inference model and is used to represent the remaining available duration of the drone's battery.
[0047] Before inputting the environmental parameters and flight parameters into the preset return flight inference model, it is also necessary to preprocess the data, including filtering and noise reduction, timestamp alignment, and outlier removal, etc.
[0048] In some optional embodiments, step S102 includes: inputting the environmental parameters and flight parameters into the preset return flight inference model to determine the first remaining available duration of the drone. Among them, the environmental parameters at least include wind speed, temperature, and humidity, and the flight parameters at least include the preset cruise duration of the drone.
[0049] Specifically, the wind speed will affect the flight speed and energy consumption of the drone. Flying against the wind will increase energy consumption and shorten the endurance time. The temperature affects the battery performance and air density. High temperature may cause the battery to overheat and reduce efficiency. Humidity may affect the performance of electronic devices and the discharge efficiency of the battery. The preset cruise duration is an important parameter in flight mission planning and directly affects the energy consumption distribution and return flight decision of the drone. The preset return flight inference model is obtained by the LSTM neural network learning the historical flight parameters and environmental parameters of the drone. The environmental parameters and flight parameters are used as the input of the preset return flight inference model. The model outputs the first remaining available duration. Before outputting the first remaining available duration, the model first predicts the battery power consumption rate and the remaining battery power based on the environmental parameters and flight parameters, and then calculates and outputs the first remaining available duration.
[0050] Step S103, determine the second remaining available duration based on the flight parameters, and compare the first remaining available duration with the second remaining available duration to determine the target remaining available duration according to the first comparison result.
[0051] Calculate the second remaining available duration based on the physical model and flight parameters. The physical model can calculate the theoretical cruise duration, that is, the second remaining available duration, based on parameters such as the operating power of the drone and the remaining battery power. When determining the second remaining available duration, environmental factors are not considered and it is only used as a theoretical value. The first remaining available duration is corrected by the second remaining available duration. Specifically, the magnitudes of the second remaining available duration and the first remaining available duration are compared. The first comparison result is used to represent the magnitude relationship between the first remaining available duration and the second remaining available duration.
[0052] The second remaining available duration is used as a theoretical value. Since environmental parameters are not considered, it can be used as the maximum available duration of the drone. However, the actual available duration may be less than the second remaining available duration. The first remaining available duration obtained by inferring through the preset return flight inference model should be less than the second remaining available duration. Based on the first comparison result, it is determined whether the first remaining available duration is available. If it is available, the first remaining available duration is used as the target remaining available duration.
[0053] In some alternative embodiments, step S103 includes: determining the second remaining available duration based on the operating power and the remaining battery power.
[0054] Specifically, the ratio of the remaining battery power to the operating power can be calculated to obtain the second remaining available duration, which is used as the theoretical remaining available duration of the drone.
[0055] Step S104, determining a first duration based on the environmental parameters and the duration required for return flight, and comparing the first duration with the target remaining available duration to determine the target return flight result according to the second comparison result.
[0056] Among them, the target return flight result indicates whether to control the drone to return. The duration required for return can be calculated based on the first remaining available duration and the return distance, and is used to represent the duration required for the drone to return to a specified location if necessary. The environmental parameters include wind speed, air pressure, temperature, etc. There is a corresponding relationship between the environmental parameters and the risk coefficient. Different ranges of environmental parameters correspond to different risk coefficients. It can be that the comprehensive environmental parameters directly correspond to the risk coefficient, or different environmental parameters respectively have corresponding coefficients, and all the coefficients are combined to obtain the target coefficient. Based on the target coefficient, the duration required for return is processed, and the first duration can be calculated by addition or multiplication. The first duration is a dynamic duration threshold calculated based on the environmental parameters and the duration required for return.
[0057] Compare the magnitude relationship between the first duration and the target remaining available duration. Specifically, it can be a simple comparison of their magnitudes, and then it is determined whether to control the drone to return based on the magnitude relationship. It can also be by calculating the difference between the two, and then it is determined whether to control the drone to return based on the difference.
[0058] In some alternative embodiments, if it is determined that the drone needs to be controlled to return, then it is determined whether the return battery power is sufficient. If it is not sufficient, it is necessary to search for the nearest drone hangar and perform path planning, so as to control the drone to fly to the nearest available drone hangar.
[0059] The UAV return control method provided in this embodiment includes obtaining environmental parameters and flight parameters when the UAV executes a flight mission; determining the first remaining available duration of the UAV based on a preset return reasoning model, environmental parameters, and flight parameters; determining a second remaining available duration based on the flight parameters, and comparing the first remaining available duration and the second remaining available duration to determine a target remaining available duration according to the first comparison result; determining a first duration based on the environmental parameters and the required duration for return, and comparing the first duration and the target remaining available duration to determine a target return result according to the second comparison result, where the target return result indicates whether to control the UAV to return. This method combines environmental parameters and the required duration for return to obtain the first duration as the threshold for determining whether to control the return, taking into account the impact of environmental factors on flight, and can improve the execution efficiency of the flight mission as much as possible while ensuring safety.
[0060] In some alternative embodiments, step S103 includes the following steps:
[0061] Step S201, if the first remaining available duration is less than or equal to the second remaining available duration, determine the first remaining available duration as the target remaining available duration.
[0062] The second remaining available duration is a theoretical value calculated without considering influencing factors such as environmental parameters and can be used as the maximum available duration of the UAV, but the actual available duration may be lower than the second remaining available duration. The first remaining available duration is calculated by the preset return reasoning model, which already includes the real-time impact of environmental parameters and flight parameters and reserves a safety margin (for example, 10%-15% of the battery power). If, after comparison, the first remaining available duration is less than or equal to the second remaining available duration, it indicates that the current model is conservative enough, and the first remaining available duration is used as the target remaining available duration.
[0063] Step S202, if the first remaining available duration is greater than the second remaining available duration, adjust the preset return reasoning model based on the second remaining available duration to determine a new first remaining available duration based on the optimized preset return reasoning model until the first remaining available duration is less than or equal to the second remaining available duration.
[0064] If the first remaining available duration is greater than the second remaining available duration, adjust the model parameters based on the difference between the second remaining available duration and the first remaining available duration. After adjusting the model, output a new first remaining available duration according to the latest environmental parameters and flight parameters until the first remaining available duration is less than or equal to the second remaining available duration, and terminate the iteration. Set an iteration threshold in this process to avoid over-adjustment.
[0065] In some alternative embodiments, step S104 includes:
[0066] Step S301: Determine the duration required for returning based on the first remaining available duration and the return distance.
[0067] The duration required for returning can be calculated based on the first remaining available duration and the return distance, and is used to represent the duration required for the UAV to return to a specified location. Calculate the ratio of the return distance to the first remaining available duration to obtain the duration required for returning.
[0068] Step S302: Determine the corresponding risk coefficient based on the environmental parameters.
[0069] Among them, there is a preset mapping relationship between the environmental parameters and the risk coefficient. The environmental parameters include wind speed, air pressure, temperature, etc. There is a corresponding relationship between the environmental parameters and the risk coefficient, and different ranges of environmental parameters correspond to different risk coefficients. It can be that the comprehensive environmental parameters directly correspond to the risk coefficient, or different environmental parameters have corresponding coefficients respectively, and all the coefficients are combined to obtain the target risk coefficient.
[0070] Step S303: Calculate the sum of the risk coefficient and the duration required for returning to obtain the first duration.
[0071] Step S304: Calculate the difference between the target remaining available duration and the first duration.
[0072] Step S305: Compare the difference with a preset threshold to obtain a second comparison result.
[0073] Step S306: If the difference is less than or equal to the preset threshold, control the UAV to return.
[0074] Specifically, let the first duration be Tthreshold, and the calculation method of the first duration is as follows:
[0075] Tthreshold = Treturn + k·σenv, where Tthreshold represents the duration required for returning, and k·σenv represents the risk coefficient corresponding to the environmental parameters.
[0076] Calculate the difference between the target remaining available duration and the first duration, and then compare the difference with the preset threshold. The preset threshold is a preset fixed duration threshold. If the difference is less than or equal to the preset threshold, control the UAV to return.
[0077] As an example: Let the target remaining available duration be Tremain = 18 minutes, the first duration be Tthreshold, the environmental risk coefficient k·σenv = 1.2·σenv = 1.2 (strong wind + low temperature), and the duration required for returning Treturn = 6 minutes. Then the first duration Tthreshold = 6 + 1.2 = 7.2 minutes.
[0078] Set the preset threshold to 5. Since 18 - 7.2 = 10.5 and 10.5 > 5, the drone is not controlled to return.
[0079] When the remaining available duration of the target is less than or equal to 12.2 minutes, control the drone to return.
[0080] In some alternative embodiments, the method further includes: training a preset return reasoning model based on training data, where the training data includes historical flight data.
[0081] The historical flight data includes flight record data during each flight of the drone, specifically including data such as flight mode, battery model, power consumption rate, return result, etc. Additionally, the historical flight data also includes environmental parameters. The parameters in the training data are all parameters that affect battery power consumption. Train a regression model with the input being environmental parameters and historical flight tasks. During the training process, a domain adversarial network can be introduced to make the model insensitive to the feature distributions of simulated data and real data, thereby improving the generalization ability. After training, a preset return reasoning model is obtained.
[0082] The drone return control method provided by the embodiments of the present invention integrates environmental factors and historical data to train a preset return reasoning model, can determine a risk coefficient based on real-time environmental risks, and then adaptively adjust the return threshold (the first duration), that is, the threshold can be adjusted according to real-time environmental risks (such as strong wind, low temperature), and return in advance in a harsh environment. The model can be adapted to multiple types of drones and supports cloud model iteration and local lightweight deployment.
[0083] In this embodiment, a drone return control device is further provided. This device is used to implement the above embodiments and preferred implementation manners, and those that have been described will not be repeated. As used hereinafter, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.
[0084] This embodiment provides a drone return control device, as Figure 2 shown, including:
[0085] A parameter acquisition module, configured to acquire environmental parameters and flight parameters when the drone executes a flight mission;
[0086] A first duration determination module, configured to determine the first remaining available duration of the drone based on the preset return reasoning model, the environmental parameters, and the flight parameters;
[0087] A target duration determination module, configured to determine a second remaining available duration based on the flight parameters, and compare the first remaining available duration with the second remaining available duration, so as to determine a target remaining available duration according to a first comparison result;
[0088] A return flight control module, configured to determine a first duration based on the environmental parameters and the duration required for return flight, and compare the first duration with the target remaining available duration, so as to determine a target return flight result according to a second comparison result, where the target return flight result indicates whether to control the UAV to return;
[0089] In some alternative embodiments, the first duration determination module includes:
[0090] A first duration determination unit, configured to input the environmental parameters and the flight parameters into the preset return flight inference model to determine the first remaining available duration of the UAV, where the environmental parameters at least include wind speed, temperature, and humidity, and the flight parameters at least include the preset cruise duration of the UAV.
[0091] In some alternative embodiments, the flight parameters further include operating power and remaining battery power, and the target duration determination module includes:
[0092] A second duration determination unit, configured to determine a second remaining available duration based on the operating power and the remaining battery power.
[0093] In some alternative embodiments, the target duration determination module includes:
[0094] A first determination unit, configured to determine the first remaining available duration as the target remaining available duration if the first remaining available duration is less than or equal to the second remaining available duration;
[0095] A second determination unit, configured to, if the first remaining available duration is greater than the second remaining available duration, adjust the preset return flight inference model based on the second remaining available duration, so as to determine a new first remaining available duration based on the optimized preset return flight inference model until the first remaining available duration is less than or equal to the second remaining available duration.
[0096] In some alternative embodiments, the return flight control module includes:
[0097] A return flight duration determination unit, configured to determine the duration required for return flight based on the first remaining available duration and the return flight distance;
[0098] A coefficient determination unit, configured to determine a corresponding risk coefficient based on the environmental parameters, where there is a preset mapping relationship between the environmental parameters and the risk coefficient;
[0099] The first duration determination unit is configured to calculate the sum of the risk coefficient and the duration required for returning, so as to obtain the first duration.
[0100] In some alternative embodiments, the return flight control module includes:
[0101] The difference determination unit is configured to calculate the difference between the target remaining available duration and the first duration;
[0102] The second result determination unit is configured to compare the difference with a preset threshold to obtain a second comparison result;
[0103] The drone control unit is configured to control the drone to return if the difference is less than or equal to the preset threshold.
[0104] In some alternative embodiments, the device further includes:
[0105] The training module is configured to train the preset return flight inference model based on training data, where the training data includes historical flight data.
[0106] The further function descriptions of the above-mentioned various modules and units are the same as those in the corresponding foregoing embodiments, and will not be elaborated herein.
[0107] The drone return flight control device in this embodiment is presented in the form of functional units. Here, the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and a memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.
[0108] This embodiment of the present invention further provides a computer device having the above Figure 2 shown drone return flight control device.
[0109] Please refer to Figure 3 , Figure 3 which is a schematic structural diagram of a computer device provided by an alternative embodiment of the present invention. As Figure 3As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting the components, including a high-speed interface and a low-speed interface. Each component communicates with each other using different buses and can be installed on a common motherboard or in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in the memory or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some alternative embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a set of blade servers, or a multi-processor system). Figure 3 In Figure 3 , a processor 10 is taken as an example.
[0110] The processor 10 can be a central processing unit, a network processor, or a combination thereof. Among them, the processor 10 can further include a hardware chip. The above hardware chip can be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The above programmable logic device can be a complex programmable logic device, a field programmable gate array, a generic array logic, or any combination thereof.
[0111] Among them, the memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiments.
[0112] The memory 20 can include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the computer device, etc. In addition, the memory 20 can include a high-speed random access memory, and can also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some alternative embodiments, the memory 20 can optionally include a memory remotely set relative to the processor 10, and these remote memories can be connected to the computer device through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and a combination thereof.
[0113] The memory 20 can include a volatile memory, such as a random access memory; the memory can also include a non-volatile memory, such as a flash memory, a hard disk, or a solid-state drive; the memory 20 can also include a combination of the above types of memories.
[0114] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or communication networks.
[0115] Embodiments of the present invention also provide a computer-readable storage medium. The method according to the embodiments of the present invention can be implemented in hardware, firmware, or can be implemented as computer code recorded on a storage medium, or can be implemented as computer code originally stored in a remote storage medium or a non-transitory machine-readable storage medium and downloaded through a network and to be stored in a local storage medium, so that the method described herein can be stored as such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid-state drive, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code, and when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method shown in the above embodiments is implemented.
[0116] A part of the present invention can be applied as a computer program product, for example, computer program instructions, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should be able to understand that the forms of computer program instructions existing in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways for computer program instructions to be executed by a computer include, but are not limited to: the computer directly executes the instructions, or the computer compiles the instructions and then executes the corresponding compiled program, or the computer reads and executes the instructions, or the computer reads and installs the instructions and then executes the corresponding installed program. Herein, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible by the computer.
[0117] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations all fall within the scope defined by the present invention.
Claims
1. A method for controlling the return of an unmanned aerial vehicle, characterized in that, The method includes: When the unmanned aerial vehicle (UAV) performs a flight mission, obtaining environmental parameters and flight parameters; Based on a preset return reasoning model, the environmental parameters, and the flight parameters, determining a first remaining available duration of the UAV; Determining a second remaining available duration based on the flight parameters, and comparing the first remaining available duration with the second remaining available duration to determine a target remaining available duration according to a first comparison result; Based on the environmental parameters and the duration required for return, determining a first duration, and comparing the first duration with the target remaining available duration to determine a target return result according to a second comparison result, where the target return result indicates whether to control the UAV to return; 2. The method according to claim 1, characterized in that The determining the first remaining available duration of the UAV based on a preset return reasoning model, the environmental parameters, and the flight parameters includes: Inputting the environmental parameters and the flight parameters into the preset return reasoning model to determine the first remaining available duration of the UAV, where the environmental parameters at least include wind speed, temperature, and humidity, and the flight parameters at least include a preset cruise duration of the UAV; 3. The method according to claim 1, characterized in that The flight parameters further include operating power and remaining battery power. The determining the second remaining available duration based on the flight parameters includes: Determining the second remaining available duration based on the operating power and the remaining battery power; 4. The method according to claim 1, wherein The comparing the first remaining available duration with the second remaining available duration to determine a target remaining available duration according to a first comparison result includes: If the first remaining available duration is less than or equal to the second remaining available duration, determining the first remaining available duration as the target remaining available duration; If the first remaining available duration is greater than the second remaining available duration, adjusting the preset return reasoning model based on the second remaining available duration, and determining a new first remaining available duration based on the optimized preset return reasoning model until the first remaining available duration is less than or equal to the second remaining available duration; 5. The method according to claim 1, wherein The determining the first duration based on the environmental parameters and the duration required for return includes: Based on the first remaining available duration and the return distance, determining the duration required for return; Determining a corresponding risk coefficient based on the environmental parameters, where there is a preset mapping relationship between the environmental parameters and the risk coefficient; Calculating the sum of the risk coefficient and the duration required for return to obtain the first duration; 6. The method according to claim 5, wherein The comparing the first duration with the target remaining available duration to determine a target return result according to a second comparison result includes: Calculating the difference between the target remaining available duration and the first duration; Comparing the difference with a preset threshold to obtain a second comparison result; If the difference is less than or equal to the preset threshold, controlling the UAV to return; 7. The method according to claim 1, characterized in that The method further includes: Training the preset return reasoning model based on training data, where the training data includes historical flight data; 8. An unmanned aerial vehicle return control device, characterized in that, The device includes: A parameter acquisition module, configured to obtain environmental parameters and flight parameters when the UAV performs a flight mission; The first duration determination module is configured to determine a first remaining available duration of the drone based on a preset return flight inference model, the environmental parameters, and the flight parameters; The target duration determination module is configured to determine a second remaining available duration based on the flight parameters, and compare the first remaining available duration with the second remaining available duration, so as to determine a target remaining available duration according to a first comparison result; The return flight control module is configured to determine a first duration based on the environmental parameters and the duration required for return flight, and compare the first duration with the target remaining available duration, so as to determine a target return flight result according to a second comparison result, where the target return flight result indicates whether to control the drone to return.
9. A computer device, characterized in that, It includes: A memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to execute the drone return flight control method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, Computer instructions are stored on the computer-readable storage medium, and the computer instructions are used to cause a computer to execute the drone return flight control method according to any one of claims 1 to 7.