Unmanned aerial vehicle cooperative operation method and device and electronic equipment

Abstract

The invention discloses an unmanned aerial vehicle cooperative operation method and device and electronic equipment. The method comprises the steps that a preset flight route of the unmanned aerial vehicle is acquired, and the preset flight route is determined through a plurality of discrete waypoints; determining a preset junction point and a preset landing airport of the unmanned aerial vehicle according to the preset flight route; using a neural network model to predict the remaining endurance time of the unmanned aerial vehicle to obtain the predicted remaining endurance time, and adjusting the preset junction point and the preset landing airport according to the predicted remaining endurance time to obtain a target junction point and a target landing airport; and the cooperative operation of the multiple unmanned aerial vehicles is executed according to the target handover point and the target landing airport, the previous unmanned aerial vehicle lands at the target landing airport, and the next unmanned aerial vehicle continues to execute the operation at the target handover point. The technical problems of low resource utilization rate, poor task continuity and difficulty in coping with large-range task requirements of an unmanned aerial vehicle inspection mode in related technologies are solved.

Description

Technical Field

[0001] The present application relates to the field of drones, and more specifically, to a method, device, and electronic equipment for collaborative operation of drones. Background Art

[0002] In low-altitude inspection scenarios, such as those for power lines and pipelines, where economical low-altitude inspections are widely used, integrated automated platforms combining drones and airports are often used to achieve full-time unmanned operations. To ensure the safe return of drones, the actual operating radius of a single drone is often limited to less than half of its maximum range, significantly reducing the drone's inspection range and impacting operational efficiency. Furthermore, the industry generally adopts an inefficient "single-machine, single-task" model, where a single drone only completes tasks within its operating radius. This results in low resource utilization, poor mission continuity, and difficulty meeting the demands of large-scale missions.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0004] The embodiments of the present application provide a method, device and electronic equipment for collaborative operation of drones, so as to at least solve the technical problems in the related art of drone inspection methods, such as low resource utilization, poor task continuity, and difficulty in coping with large-scale task requirements.

[0005] According to one aspect of an embodiment of the present application, a method for collaborative operation of drones is provided, including: obtaining a preset flight route of a drone, wherein the preset flight route is determined by multiple discrete waypoints; determining a preset handover point and a preset landing airport of the drone based on the preset flight route; using a neural network model to predict the remaining flight time of the drone to obtain a predicted remaining flight time, and adjusting the preset handover point and the preset landing airport based on the predicted remaining flight time to obtain a target handover point and a target landing airport; performing collaborative operation of multiple drones based on the target handover point and the target landing airport, wherein the previous drone lands at the target landing airport, and the operation is continued by the next drone at the target handover point.

[0006] Optionally, determining a preset handover point and a preset landing airport of the UAV based on a preset flight route includes: obtaining the starting point of the route in the preset flight route; determining a first airport closest to the starting point of the route from a set of available airports, wherein each airport in the set of available airports contains a first UAV that meets the preset flight conditions; determining the flight power of the first UAV from the starting point of the route to other waypoints in the preset flight route, and determining the remaining battery capacity required for the first UAV from each waypoint in the preset flight route to the landing airport; determining the farthest waypoint that the first UAV can reach if the remaining battery capacity allows as the preset handover point based on the flight power of the first UAV; and determining the available airport closest to the preset handover point as the preset landing airport.

[0007] Optionally, determining the flight power of the first UAV from the starting point of the route to other waypoints in the preset flight route includes: obtaining a power set corresponding to the first UAV, wherein the power set includes induced power, type resistance power, waste resistance power, and the power of the first UAV communication and the carried payload; determining the flight power of the first UAV based on the induced power, type resistance power, waste resistance power, the power of the first UAV communication and the carried payload, and the energy efficiency coefficient.

[0008] Optionally, the power set is determined in the following manner: obtaining the induced power of the first UAV when hovering, the ground speed of the first UAV and the average rotor induced speed of the first UAV when hovering; determining the induced power of the first UAV based on the induced power of the first UAV, the ground speed of the first UAV and the average rotor induced speed when hovering; obtaining the form drag power of the first UAV and the rotor tip speed of the first UAV when hovering; determining the form drag power of the first UAV based on the form drag power of the first UAV, the ground speed of the first UAV and the rotor tip speed of the first UAV when hovering; obtaining the fuselage drag ratio, air density, rotor solidity of the first UAV and rotor disc area of ​​the first UAV; obtaining the fuselage drag ratio, air density, rotor solidity and rotor disc area of ​​the first UAV; determining the power set corresponding to the first UAV based on the induced power of the first UAV, the form drag power of the first UAV, the waste drag power of the first UAV and the power of the first UAV communication and the carried payload.

[0009] Optionally, the ground speed of the first UAV is determined by: obtaining the airspeed and flight direction of the first UAV, and obtaining the wind speed and wind direction; and determining the ground speed of the first UAV based on the airspeed, flight direction, wind speed and wind direction.

[0010] Optionally, the induced power of the first UAV when hovering is determined by: obtaining the aircraft weight and incremental correction coefficient of the first UAV; and determining the induced power of the first UAV when hovering based on the aircraft weight, incremental correction coefficient, air density, and rotor disc area.

[0011] Optionally, the drag power of the first UAV when hovering is determined by: obtaining the drag coefficient, the rotor angular velocity and the rotor radius of the first UAV; and determining the drag power of the first UAV when hovering based on the drag coefficient, air density, rotor solidity, rotor disc area, rotor angular velocity and rotor radius.

[0012] Optionally, determining the remaining battery capacity required for the first UAV to travel from each waypoint in a preset flight route to a landable airport includes: obtaining a first remaining battery capacity, full charge voltage, nominal battery capacity, and a slope of a linear curve of voltage drop of the first UAV at a previous waypoint, wherein the slope is determined by the full charge voltage, nominal battery capacity, standard voltage, and nominal battery discharge coefficient; determining the voltage of the first UAV at a next waypoint based on the full charge voltage, the slope, the nominal battery capacity, and the first remaining battery capacity; determining the current of the first UAV at the next waypoint based on the flight power of the first UAV and the voltage of the first UAV at the next waypoint; determining a second remaining battery capacity of the first UAV at the next waypoint based on the current, rated discharge time, nominal battery capacity, and time step of the first UAV at the next waypoint, wherein the time step is the number of waypoints flown by the first UAV, and stopping iteration when the second remaining battery capacity meets a preset battery capacity condition, and the preset battery capacity condition is determined by the nominal battery capacity and the nominal battery discharge coefficient.

[0013] Optionally, the neural network model is trained in the following manner: obtaining sample data, wherein the sample data includes multi-dimensional feature data of the UAV, and the multi-dimensional feature data includes battery status data, flight status data, environmental data, and mission payload data; using an initial neural network model to process the sample data to obtain sample predicted remaining flight time, wherein the initial neural network model includes a first model for processing time series data and a second model for processing spatial data; determining a fusion loss function based on the sample predicted remaining flight time and the actual remaining flight time, and adjusting the parameters of the initial neural network model based on the loss value of the fusion loss function, and stopping the iteration until the adjusted loss value meets the preset conditions to obtain the neural network model.

[0014] Optionally, the fusion loss function is determined in the following manner: determining the mean square error function of the sample predicted remaining flight time and the actual remaining flight time, and determining the mean square error function as the main loss; determining the asymmetric loss based on the first penalty coefficient, the second penalty coefficient, the sample predicted remaining flight time and the actual remaining flight time; determining the multi-task learning loss based on the weight coefficients of multiple auxiliary tasks and the corresponding mean square error loss function, wherein the multiple auxiliary tasks include voltage auxiliary prediction and flight status prediction; determining the fusion loss function based on the main loss, the asymmetric loss and the multi-task learning loss.

[0015] Optionally, the preset handover point and the preset landing airport are adjusted based on the predicted remaining flight time to obtain the target handover point and the target landing airport, including: obtaining a reference time required for the UAV to reach the preset handover point; when the predicted remaining flight time is less than the reference time, determining that the preset handover point needs to be adjusted; determining the waypoint closest to the UAV in the set of available waypoints as the target handover point; and determining the target landing airport closest to the target handover point from the set of available airports.

[0016] According to another aspect of an embodiment of the present application, a drone collaborative operation device is also provided, including: an acquisition module for acquiring a preset flight route of a drone, wherein the preset flight route is determined by multiple discrete waypoints; a determination module for determining a preset handover point and a preset landing airport of the drone based on the preset flight route; a prediction module for predicting the remaining flight time of the drone using a neural network model to obtain the predicted remaining flight time, and adjusting the preset handover point and the preset landing airport based on the predicted remaining flight time to obtain a target handover point and a target landing airport; an execution module for executing collaborative operations of multiple drones based on the target handover point and the target landing airport, wherein the previous drone lands at the target landing airport, and the next drone continues to perform the operation at the target handover point.

[0017] According to another aspect of the embodiments of the present application, an electronic device is also provided, including: a memory for storing program instructions; a processor, connected to the memory, for executing program instructions to implement the following functions: obtaining a preset flight route of a drone, wherein the preset flight route is determined by multiple discrete waypoints; determining a preset handover point and a preset landing airport of the drone based on the preset flight route; using a neural network model to predict the remaining flight time of the drone to obtain the predicted remaining flight time, and adjusting the preset handover point and the preset landing airport based on the predicted remaining flight time to obtain a target handover point and a target landing airport; performing collaborative operations of multiple drones based on the target handover point and the target landing airport, wherein the previous drone lands at the target landing airport, and the next drone continues to perform the operation at the target handover point.

[0018] According to another aspect of an embodiment of the present application, a non-volatile storage medium is further provided, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the above-mentioned drone collaborative operation method by running the computer program.

[0019] According to another aspect of the embodiments of the present application, a computer program product is also provided, including computer instructions, which implement the above-mentioned drone collaborative operation method when executed by a processor.

[0020] In an embodiment of the present application, a preset flight route of a UAV is obtained, wherein the preset flight route is determined by a plurality of discrete waypoints; a preset handover point and a preset landing airport of the UAV are determined based on the preset flight route; a neural network model is used to predict the remaining flight time of the UAV to obtain the predicted remaining flight time, and the preset handover point and the preset landing airport are adjusted based on the predicted remaining flight time to obtain the target handover point and the target landing airport; multiple UAVs are performed in collaboration based on the target handover point and the target landing airport, wherein the previous UAV lands at the target landing airport, and the operation is continued by the next UAV at the target handover point, thereby achieving the purpose of expanding the effective operation range of the UAV and optimizing resource allocation, thereby realizing the technical effect of improving resource utilization, and further solving the technical problems of the UAV inspection method in the related technology, such as low resource utilization, poor task continuity, and difficulty in coping with large-scale task requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0022] Figure 1 This is a hardware structure block diagram of a computer terminal for implementing a method for cooperative operation of drones according to an embodiment of the present application;

[0023] Figure 2 is a flow chart of a method for cooperative operation of drones according to an embodiment of the present application;

[0024] Figure 3 This is a simulation diagram of a static pre-planning stage according to an embodiment of the present application;

[0025] Figure 4 is a loss function curve diagram according to an embodiment of the present application;

[0026] Figure 5 This is a structural diagram of a UAV collaborative operation device according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] The information collected in the embodiments of the present application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or reject the automated decision results; if the user chooses to reject, the expert decision-making process will be entered.

[0030] First, some nouns or terms that appear in the process of explaining the embodiments of this application are subject to the following explanations:

[0031] Unmanned Aerial Vehicle (UAV): An unmanned aerial vehicle (UAV) is an aircraft capable of flying without a human pilot. UAVs can be remotely operated by a ground control station or autonomously flown according to pre-programmed procedures to complete various missions.

[0032] Induced Power (IP) refers to the energy consumed by an aircraft (especially a helicopter or rotary-wing drone) to generate lift during flight. When an aircraft hovers or flies forward, the rotors or propellers push the air downward, generating an upward reaction force, known as lift, that helps the aircraft remain airborne against gravity. Induced Power is the energy required to maintain this lift.

[0033] Blade Profile Power (BPP): Blade Profile Power (BPP) refers to the power consumed by friction between the rotor blades and the air during flight of a rotary-wing drone or helicopter. It is related to the blade shape and flight speed. As the rotor blades cut through the air, they create drag. To overcome this drag and maintain flight speed, the engine must output additional energy, known as blade profile power. In rotary-wing aircraft, blade profile power is typically closely related to the drone's flight speed and rotor characteristics (such as blade shape and solidity). As speed increases, so does blade profile power.

[0034] Parasite Power (PP): Parasite power refers to the additional energy consumption of an aircraft due to non-lift related factors during flight, such as the friction resistance between the fuselage, rotor, landing gear and the air, as well as the energy consumption generated by the operation of electronic equipment and communication systems.

[0035] Long Short-Term Memory (LSTM): LSTM is a specialized recurrent neural network (RNN) designed specifically for processing and predicting time series data. By introducing a "gating" mechanism, it selectively remembers and forgets information, effectively overcoming the vanishing or exploding gradient problems of traditional RNNs when processing long sequences of data. LSTM maintains a "cell state" within the network, controlling the inflow, outflow, and forgetting of information through input, forget, and output gates, enabling the network to remember dependencies over longer periods of time.

[0036] Convolutional Neural Networks (CNN): A CNN is a deep learning network architecture that excels at processing grid-structured input data, such as images and videos. Through a structure consisting of convolutional, pooling, and fully connected layers, it can automatically detect multiple layers of features in the input data.

[0037] Mean-Square Error (MSE): MSE is a commonly used loss function used to evaluate the difference between predicted values ​​and true values. It is the average of the squared prediction errors of all observations.

[0038] In related technologies, to overcome the limitations of single-machine flight range, there are two automation solutions in the industry. The first is the single-drone and multi-airport solution, in which a single drone uses the jump-pod function to perform flight missions in segments between multiple airports. However, airport facility costs are high, the airport utilization rate of a single drone is low, and the cumulative charging waiting time caused by the serial operation of a single drone significantly extends the mission cycle. The second is the multi-drone and multi-airport solution, which breaks down the flight mission into multiple drones, all of which take off simultaneously to perform segmented missions and land at the next airport. However, the single-machine operating radius under this method is still less than half of the maximum flight range, and in the event of an abnormal situation, the drone cannot reach the next airport, resulting in mission interruption.

[0039] Currently, the commonly used drone networking solutions in the industry cannot solve the problem of the small operating radius of a single aircraft, and have not deeply integrated high-precision, real-time prediction of remaining flight time into multi-aircraft collaborative decision-making. There is a lack of an effective mechanism for adjusting tasks and routes based on dynamic flight time status, resulting in poor multi-aircraft collaborative flight time, low reliability, and poor efficiency.

[0040] In order to solve the problems existing in the related art, the embodiment of the present application provides a method for cooperative operation of drones. Figure 1 In the computer terminal shown, the computer terminal is explained below.

[0041] The drone collaborative operation method embodiment provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The following is a hardware block diagram of a computer terminal for implementing a method for cooperative operation of unmanned aerial vehicles. Figure 1 As shown, the computer terminal 10 may include one or more processors (illustrated as 102a, 102b, ..., 102n in the figure) (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission module 106 for communication functions via a wired and / or wireless network connection. In addition, it may also include: a display, a keyboard, a cursor control device, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, and a BUS bus. Those skilled in the art will understand that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0042] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry." The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuitry may be a single, independent processing module, or may be fully or partially integrated into any of the other components of the computer terminal 10. As discussed in the embodiments of the present application, the data processing circuitry functions as a processor control (e.g., the selection of a variable resistor terminal path connected to an interface).

[0043] Memory 104 can be used to store software programs and modules for application software, such as the program instructions / data storage device corresponding to the drone collaborative operation method in the embodiments of the present application. The processor executes the software programs and modules stored in memory 104 to perform various functional applications and data processing, thereby implementing the drone collaborative operation method described above. Memory 104 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 104 may further include memory located remotely from the processor, which can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0044] The transmission module 106 is configured to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by the communications provider of the computer terminal 10. In one embodiment, the transmission module 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission module 106 may be a radio frequency (RF) module, which is configured to communicate with the Internet wirelessly.

[0045] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 .

[0046] It should be noted that, in some optional embodiments, the above Figure 1 The computer terminal shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of hardware elements and software elements. Figure 1 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the computer terminal described above.

[0047] In the above-mentioned operating environment, an embodiment of the present application provides an embodiment of a method for collaborative operation of drones. 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 a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0048] Figure 2 is a flow chart of a method for cooperative operation of drones according to an embodiment of the present application. Figure 2 As shown, the method includes the following steps:

[0049] Step S202: obtaining a preset flight route of the UAV, wherein the preset flight route is determined by a plurality of discrete waypoints.

[0050] In the above step S202, in the drone mission planning, the preset flight route refers to one or more flight paths pre-set before the mission begins based on the mission requirements and flight area conditions. These paths are composed of a series of discrete waypoints, each waypoint represents a specific location that the drone needs to pass through on the flight path. The drone will fly in the order of these waypoints to complete the set goals.

[0051] In step S204, a preset handover point and a preset landing airport of the UAV are determined according to the preset flight route.

[0052] In step S204, in the multi-UAV relay flight mode, the preset handover point is the specific location where the preceding and succeeding UAVs hand over their missions. Upon reaching the preset handover point, the preceding UAV will hand over its unfinished mission to the succeeding UAV and then proceed to the nearest landing airport (i.e., the preset landing airport) for recharging or maintenance. Before the mission begins, the theoretical energy consumption curves of the UAVs are calculated using a physical energy consumption model to estimate their endurance. The preset handover point and landing airport are then determined accordingly.

[0053] In step S206, a neural network model is used to predict the remaining flight time of the UAV to obtain the predicted remaining flight time, and the preset handover point and the preset landing airport are adjusted according to the predicted remaining flight time to obtain the target handover point and the target landing airport.

[0054] In the above step S206, during the actual flight process, the remaining flight time of the UAV is predicted in real time through the neural network model. If the predicted remaining flight time cannot reach the preset handover point or the preset landing airport, adjustments will be made to determine the target handover point and the target landing airport to ensure the continuity of the mission and the safety of the UAV.

[0055] In step S208, multiple drones perform collaborative operations based on the target handover point and the target landing airport, wherein the previous drone lands at the target landing airport, and the next drone continues to perform the operation at the target handover point.

[0056] Through the above steps S202 to S208, the purpose of expanding the effective operating range of the drone and optimizing resource allocation can be achieved, thereby achieving the technical effect of improving resource utilization, thereby solving the technical problems of the related art drone inspection method such as low resource utilization, poor task continuity, and difficulty in meeting large-scale task requirements. The following is an explanation.

[0057] In step S204 of the above-mentioned UAV collaborative operation method, a preset handover point and a preset landing airport of the UAV are determined based on the preset flight route, including: obtaining the route starting point in the preset flight route; determining the first airport closest to the route starting point from the set of available airports, wherein each airport in the set of available airports contains the first UAV that meets the preset flight conditions; determining the first UAV flight power of the first UAV from the route starting point to other waypoints in the preset flight route, and determining the remaining battery capacity required for the first UAV to reach the landing airport from each waypoint in the preset flight route; determining the farthest waypoint that the first UAV can reach if the remaining battery capacity allows as the preset handover point based on the flight power of the first UAV; and determining the available airport closest to the preset handover point as the preset landing airport.

[0058] In some embodiments of the present application, the route origin is the location where the drone mission begins, i.e., the first waypoint in a preset flight route. From all airports, airports meeting preset flight conditions are screened to obtain a set of available airports. Preset flight conditions include the airport being in working order and having idle drones with sufficient battery power. The airport closest to the route origin in the set of available airports is determined as the first airport (containing the first drone). Based on the first drone's physical characteristics and external environmental factors, a physical energy consumption model is used to calculate the flight power of the first drone at each waypoint. Flight power reflects the drone's energy consumption at that point and affects the drone's endurance. The remaining battery capacity required to reach a landing airport from each waypoint is also calculated. Based on the first drone's flight power, the farthest waypoint that the first drone can reach, while remaining battery capacity allows, is determined as the preset landing point. The preset landing airport is selected based on proximity to the preset landing point, but the remaining battery capacity must allow the first drone to safely reach the preset landing airport.

[0059] The following is an explanation with specific examples:

[0060] Traditional drones, when taking off and landing at the same airport, are inevitably limited to operating at half their maximum range. This embodiment of the application utilizes a multi-drone, multi-airport collaboration approach, utilizing multiple drones to complete the overall mission through handover. Drones no longer need to return to their takeoff cabins, landing at the nearest cabin, significantly increasing the operating radius of a single drone. Before takeoff, the drones obtain a preset flight path from the flight control platform and use a physical energy consumption model to predict static range and handover points.

[0061] Let the route starting point be , first find the distance Nearest available drone airport (i.e. the first airport mentioned above). “Available” here is defined as: 1. The airport itself is available (e.g., capable of takeoff and landing, no maintenance, open airspace, etc.); 2. There is an idle area within the airport with sufficient power. 95% of drones (i.e. the first drone mentioned above), to ensure that it can perform subsequent missions. From all available airports that meet the above conditions, Calculate the distance from each airport to Actual flight distance , select the airport with the smallest comprehensive distance according to the following formula:

[0062]

[0063] In the selected back, Take off to , along the preset flight route at a constant speed Fly and perform missions. In this process, the core lies in the remaining endurance prediction. Based on the physical energy consumption model, it can be calculated The cumulative energy consumption along the route (determined by the flight power of the first drone) and the remaining battery capacity (also referred to as power) at any position on the route ,according to Determine the next An airport that can be safely flown to and landed. The embodiment of the present application predicts that a certain airport that can be landed near the route from the current location Required battery capacity (subject to airport availability) Considering the safety power threshold , the prediction goal is to find a set of waypoints that meet the following power conditions :

[0064] +

[0065] in, From the waypoint Departure, under the conditions of availability, the preset landing airport with the shortest actual flight distance (the selection logic is the same as ).from Select the waypoint closest to the preset landing airport As a preset junction point, Arrive at the destination End the mission and fly to Landing. Arrive at the destination forward, drones Taken off and flew to point, from Points take over along the preset flight path Perform subsequent tasks due to Earlier than arrive point, so the two drones will not meet.

[0066] right The following process is repeated for the following drones: The energy consumption at the time of departure (i.e. the new starting point) is used to predict the energy consumption along the remaining route and the new preset handover point that can be reached using the physical energy consumption model. And corresponding to the new default landing airport The flight endurance prediction and handover decision of different UAVs are logically independent of each other.

[0067] In the above steps, determining the flight power of the first UAV from the starting point of the route to other waypoints in the preset flight route includes: obtaining a power set corresponding to the first UAV, wherein the power set includes induced power, type resistance power, waste resistance power, and the power of the first UAV communication and the carried payload; determining the flight power of the first UAV based on the induced power, type resistance power, waste resistance power, the power of the first UAV communication and the carried payload, and the energy efficiency coefficient.

[0068] In some embodiments of the present application, the first UAV flight power The calculation formula is as follows:

[0069]

[0070] in, represents the induced power, Indicates the type of resistance power, Indicates the waste resistance power, Indicates the power consumed by the first drone communication and the payload, that is, the power consumed by the drone communication system and the mission equipment carried (such as cameras, sensors, etc.), while taking into account the health of the battery, that is, the number of charge and discharge cycles. Indicates the energy efficiency coefficient. To better predict the battery life, it is necessary to study the characteristics of the battery's effective capacity. The Peukert law shows the effect of the battery discharge rate on the battery's effective capacity. The actual available capacity of the battery as follows:

[0071]

[0072] in, is the nominal battery capacity, is the rated discharge time, I is the discharge current of the battery, is the Peukert coefficient, Represents the voltage of the battery at point b. When the discharge power is constant, the voltage of the lithium battery decreases linearly and is proportional to the remaining power. There is the following functional relationship:

[0073]

[0074] in, is the full charge voltage, and m is the slope of the linear curve of the voltage drop. Reduce to standard voltage When m is given by the following formula, is the nominal battery discharge coefficient:

[0075]

[0076] In the above steps, the power set is determined by: obtaining the induced power of the first UAV when hovering, the ground speed of the first UAV and the average rotor induced speed of the first UAV when hovering; determining the induced power of the first UAV based on the induced power of the first UAV, the ground speed of the first UAV and the average rotor induced speed when hovering; obtaining the form drag power of the first UAV and the rotor tip speed of the first UAV when hovering; determining the form drag power of the first UAV based on the form drag power of the first UAV, the ground speed of the first UAV and the rotor tip speed of the first UAV when hovering; obtaining the fuselage drag ratio, air density, rotor solidity of the first UAV and rotor disc area of ​​the first UAV; obtaining the fuselage drag ratio, air density, rotor solidity and rotor disc area of ​​the first UAV; determining the power set corresponding to the first UAV based on the induced power of the first UAV, the form drag power of the first UAV, the waste drag power of the first UAV and the power of communication and carried payloads of the first UAV.

[0077] In some embodiments of the present application, (first) the energy consumption of the UAV during flight mainly includes induced power , resistance power and waste resistance power , the specific calculation formula is as follows:

[0078]

[0079]

[0080]

[0081] in, and They are the drag power and induced power of the first UAV when hovering; represents the ground speed of the first UAV; is the average rotor induced speed of the first UAV when hovering; is the rotor tip speed of the first UAV; and They are the fuselage drag ratio and rotor solidity of the first UAV, and are the air density and the rotor disk area of ​​the first UAV, respectively.

[0082] In the above steps, the ground speed of the first UAV is determined by: obtaining the airspeed and flight direction of the first UAV, and obtaining the wind speed and wind direction; and determining the ground speed of the first UAV based on the airspeed, flight direction, wind speed, and wind direction.

[0083] In some embodiments of the present application, the first UAV mainly flies at a constant speed, and the acceleration and deceleration flight accounts for a small proportion that can be ignored. Therefore, the present application does not consider the energy consumption caused by the acceleration and deceleration of the first UAV. Considering the impact of wind on the energy consumption of the first UAV, it is decomposed into wind speed and wind direction , the first UAV ground speed It can be expressed as:

[0084]

[0085] in, and are the airspeed and flight direction of the first UAV respectively.

[0086] In the above steps, the induced power of the first UAV when hovering is determined by: obtaining the aircraft weight and incremental correction coefficient of the first UAV; and determining the induced power of the first UAV when hovering based on the aircraft weight, incremental correction coefficient, air density, and rotor disc area.

[0087] In some embodiments of the present application, the induced power of the first UAV when hovering The calculation formula is as follows:

[0088]

[0089] in, is the aircraft weight of the first UAV, is the incremental correction factor.

[0090] In the above steps, the drag power of the first UAV when hovering is determined by: obtaining the drag coefficient, the rotor angular velocity and the rotor radius of the first UAV; and determining the drag power of the first UAV when hovering based on the drag coefficient, air density, rotor solidity, rotor disc area, rotor angular velocity and rotor radius.

[0091] In some embodiments of the present application, the drag power of the first drone when hovering is The calculation formula is as follows:

[0092]

[0093] in, is the drag coefficient, is the rotor angular velocity of the first UAV, is the rotor radius.

[0094] In the above steps, determining the remaining battery capacity required for the first UAV to travel from each waypoint in the preset flight route to the landing airport includes: obtaining a first remaining battery capacity, a full charge voltage, a nominal battery capacity, and a slope of a linear curve of voltage drop of the first UAV at the previous waypoint, wherein the slope is determined by the full charge voltage, the nominal battery capacity, the standard voltage, and the nominal battery discharge coefficient; determining the voltage of the first UAV at the next waypoint based on the full charge voltage, the slope, the nominal battery capacity, and the first remaining battery capacity; determining the current of the first UAV at the next waypoint based on the flight power of the first UAV and the voltage of the first UAV at the next waypoint; determining a second remaining battery capacity of the first UAV at the next waypoint based on the current, the rated discharge time, the nominal battery capacity, and the time step of the first UAV at the next waypoint, wherein the time step is the number of waypoints flown by the first UAV, and stopping iteration when the second remaining battery capacity meets a preset battery capacity condition, which is determined by the nominal battery capacity and the nominal battery discharge coefficient.

[0095] In some embodiments of the present application, since the voltage, current and effective capacity change dynamically with the remaining battery capacity, the remaining battery capacity is predicted based on an iterative method. Let the time step be , which is equivalent to the first UAV flying at a constant speed on the route Time, Step 1 The iteration time is Assume that the speed of the first drone is , the preset flight route can be converted into an interval of Each iteration represents the first UAV flying over a route point. The formulas for the voltage, current, and remaining (usable) battery capacity for the iteration are as follows:

[0096]

[0097]

[0098]

[0099] in, represents the remaining battery capacity of the first UAV at the i-th iteration, i.e., the first remaining battery capacity mentioned above, represents the voltage of the first UAV at the i+1th iteration, i.e., the voltage of the first UAV at the next waypoint. represents the current of the first UAV at the i+1th iteration, that is, the current of the first UAV at the next waypoint. represents the current of the first UAV at the next waypoint considering Peukert's law, represents the rated discharge time taking into account Peukert's law, represents the nominal battery capacity taking into account Peukert's law, It represents the remaining battery capacity of the first UAV at the i+1th iteration, that is, the second remaining battery capacity of the first UAV at the next waypoint.

[0100] The second remaining battery capacity is calculated iteratively until the following equation is satisfied:

[0101]

[0102] in, Indicates preset battery capacity conditions.

[0103] This is equivalent to the predicted remaining flight time of the first drone. The above iterations can also be considered as predictions of the actual waypoints the first drone can reach. Each iteration simultaneously calculates whether the first drone can fly from the current waypoint and land at the next available airport. The calculation logic is consistent with the iterative process: based on the battery capacity of the current waypoint, the first drone is predicted to have enough time to reach the designated landing airport. If it is reachable, the waypoint is added to the set of available waypoints. Finally, the available waypoint closest to the designated landing airport is selected from this set as the designated handover point. Figure 3This is a simulation diagram from the static pre-planning phase. Blue dots represent discrete route points, blue boxes represent selected drone airports, red boxes represent other airports, and green triangles represent calculated drone handover points. When the current drone (e.g., the first drone) approaches the handover point, the replacement drone at the blue airport takes off to the handover point and continues along the route. The current drone then arrives at the handover point and lands at the blue airport.

[0104] In the above-mentioned UAV collaborative operation method, the neural network model is trained in the following manner: obtaining sample data, wherein the sample data includes multi-dimensional feature data of the UAV, and the multi-dimensional feature data includes battery status data, flight status data, environmental data, and mission payload data; using the initial neural network model to process the sample data to obtain the sample predicted remaining flight time, wherein the initial neural network model includes a first model for processing time series data and a second model for processing spatial data; determining a fusion loss function based on the sample predicted remaining flight time and the actual remaining flight time, and adjusting the parameters of the initial neural network model based on the loss value of the fusion loss function, and stopping the iteration until the adjusted loss value meets the preset conditions to obtain the neural network model.

[0105] In some embodiments of this application, due to the numerous uncertainties associated with drone flight, multi-dimensional features such as battery status, environmental changes, and flight status all affect the remaining flight time prediction. Static planning cannot comprehensively consider these environmental and flight factors and can only provide a baseline reference. This embodiment of the application dynamically adjusts the static planning using an artificial intelligence (AI) neural network model after static pre-planning, using multi-dimensional feature data to modify the static planning and predict the remaining flight time in real time. The neural network model is described below.

[0106] As a commonly used time series prediction model, LSTM can handle long-term dependencies in time series data, but is not suitable for processing spatial data; CNN, as a commonly used spatial data processing model, can process spatial features in data, but is not suitable for processing time series data. Since the energy consumption of drones is affected by environmental spatial fields such as flight altitude, flight terrain elevation, and airspace restrictions, the state of drones (position, posture, battery status, etc.) changes continuously over time. Therefore, the embodiment of the present application uses ConvLSTM that combines LSTM (i.e., the first model mentioned above) and CNN (i.e., the second model mentioned above) architectures to predict the real-time endurance of drones. The spatial features that affect the energy consumption of drones are extracted through convolution operations, and the gated recursive mechanism is used to model the long-term impact of drone state sequences and their cumulative effects on energy consumption. Among them, the input gate , Forget Gate , output gate The data processing process is as follows:

[0107]

[0108]

[0109]

[0110] in, is the activation function, Is the convolution kernel, different subscripts represent different convolution kernels, is the bias vector, different subscripts represent different bias vectors, is the hidden state at the previous moment, is the current input.

[0111] During training, the neural network model uses more than 20 feature types as sample data, including battery status data (voltage, current, remaining power, temperature, battery health), flight status data (altitude, speed, attitude angle, flight mode), environmental data (wind speed, temperature), mission payload data (UAV weight, mount power consumption, mount weight), etc. The sample data is processed by the initial neural network model to obtain the sample predicted remaining endurance time. According to the difference between the sample predicted endurance time and the actual remaining endurance time, the loss value of the fusion loss function is calculated, and then backpropagation is performed to adjust the parameters of the neural network model to reduce the loss value. The above process is repeated until the adjusted model parameters make the loss value meet the preset conditions (such as the loss value reaches the minimum or the change range is lower than the threshold). The training process stops, and the above neural network model is obtained. After about 25 rounds of iterative training, it is obtained. Figure 4 As shown in the loss function curve, the battery life prediction error within 1 minute accounts for 93.5%.

[0112] In the above steps, the fusion loss function is determined by: determining the mean square error function of the sample predicted remaining flight time and the actual remaining flight time, and determining the mean square error function as the main loss; determining the asymmetric loss based on the first penalty coefficient, the second penalty coefficient, the sample predicted remaining flight time and the actual remaining flight time; determining the multi-task learning loss based on the weight coefficients of multiple auxiliary tasks and the corresponding mean square error loss function, wherein the multiple auxiliary tasks include voltage auxiliary prediction and flight status prediction; determining the fusion loss function based on the main loss, the asymmetric loss and the multi-task learning loss.

[0113] In some embodiments of the present application, in order to improve the prediction accuracy of the model, the present application embodiment defines the main loss , asymmetric loss and multi-task learning loss The fusion loss function is as follows:

[0114]

[0115]

[0116]

[0117]

[0118] in, is the sample size, Is the actual remaining battery life, Is the remaining time of the sample prediction. The main loss in the loss function is the mean square error function, and the asymmetric loss introduces a penalty coefficient and ( ),in, is the first penalty coefficient, is the second penalty coefficient, which increases the penalty when the sample predicted remaining battery life is greater than the actual remaining battery life (overestimated). is the sigmoid function, The smaller the remaining flight time of the sample prediction, that is, the lower the battery power, the heavier the penalty for asymmetric loss, thereby improving the prediction accuracy at low battery levels. Multi-task learning (or multi-auxiliary tasks) includes voltage auxiliary prediction and flight status prediction. and are the weight coefficients and MSE (mean square error) loss functions of different auxiliary tasks.

[0119] During flight, the neural network model dynamically predicts the remaining flight time based on real-time and historical flight status. It also determines the validity of the preset handover points generated during the pre-planning phase. If the neural network model repeatedly determines that a handover point has failed, a new handover point is selected from the set of available waypoints. By combining static planning with dynamic correction, the system can perceive changes in the flight environment in real time and automatically adjust the pre-planned solution, ensuring the dynamic feasibility and safety of handover point selection.

[0120] In step S206 of the above-mentioned UAV collaborative operation method, the preset handover point and the preset landing airport are adjusted according to the predicted remaining flight time to obtain the target handover point and the target landing airport, including: obtaining the reference time required for the UAV to reach the preset handover point; when the predicted remaining flight time is less than the reference time, determining that the preset handover point needs to be adjusted; determining the waypoint closest to the UAV in the available waypoint set as the target handover point; and determining the target landing airport closest to the target handover point from the available airport set.

[0121] In some embodiments of the present application, the reference time refers to the time required for the drone to reach the preset handover point from its current position, calculated in advance based on theoretical calculations or historical data in the static planning phase. The predicted remaining flight time is compared with the reference time to reach the preset handover point. If the predicted remaining flight time is less than the reference time, it indicates that the drone may not be able to reach the preset handover point as originally planned, and the strategy needs to be adjusted immediately. The waypoint closest to the drone's current position is selected from the set of available waypoints as the new target handover point, thereby ensuring that the drone completes the handover within a safe range of battery power, and the airport closest to the target handover point is selected as the target landing airport.

[0122] The drone collaborative operation method provided in the embodiment of the present application, under a multi-machine network, adopts a multi-machine different cabin take-off and landing method to break through the endurance limit, which can release an additional 30% to 40% of the drone's endurance. Through precise endurance perception and relay mechanism, it can reliably and continuously complete long-distance and long-time tasks, avoid task interruption due to power problems, and solve the problems of low infrastructure utilization, long task cycle, and poor flexibility in traditional multi-machine collaborative solutions. In addition, in the static pre-planning stage, this method predicts the remaining endurance based on the physical energy consumption model according to the independence between different drone flights, decomposes the global task into multiple sub-tasks, and comprehensively considers various energy consumptions such as induced power, type resistance power, waste resistance power, as well as wind speed, battery health and other factors, thereby optimizing the utilization of the overall endurance resources of the fleet. In the dynamic AI adjustment stage, the fusion loss function is modeled according to the drone flight scenario, and the mean square error (main loss), asymmetric loss, and multi-task learning loss are introduced into the spatiotemporal neural network to reduce the impact of sudden interference. At the same time, the system utilizes a wealth of real-time flight-related status (such as wind speed and attitude) to enable it to perceive and respond to changes in flight conditions in real time, automatically correct pre-planning plans, and achieve an endurance prediction error of 93.5% within 1 minute, ensuring the dynamic safety and feasibility of relay point selection, thereby greatly enhancing the system's adaptability and robustness in uncertain environments.

[0123] Figure 5 This is a structural diagram of a UAV cooperative operation device according to an embodiment of the present application. Figure 5 As shown, the device includes:

[0124] an acquisition module 40 for acquiring a preset flight route of the UAV, wherein the preset flight route is determined by a plurality of discrete waypoints;

[0125] A determination module 42 is used to determine a preset handover point and a preset landing airport of the UAV according to a preset flight route;

[0126] The prediction module 44 is configured to use a neural network model to predict the remaining flight time of the UAV to obtain the predicted remaining flight time, and adjust the preset handover point and the preset landing airport based on the predicted remaining flight time to obtain the target handover point and the target landing airport;

[0127] The execution module 46 is used to execute a collaborative operation of multiple drones based on the target handover point and the target landing airport, wherein the previous drone lands at the target landing airport and the next drone continues to perform the operation at the target handover point.

[0128] Through the acquisition module, determination module, prediction module and execution module in the above-mentioned UAV collaborative operation device, the purpose of expanding the effective operation range of the UAV and optimizing resource allocation is achieved, thereby achieving the technical effect of improving resource utilization, and further solving the technical problems of low resource utilization, poor task continuity and difficulty in coping with large-scale task requirements in the related technology of UAV inspection methods.

[0129] In the determination module in the above-mentioned UAV collaborative operation device, the determination module is also used to obtain the starting point of the route in the preset flight route; determine the first airport closest to the starting point of the route from the set of available airports, wherein each airport in the set of available airports contains a first UAV that meets the preset flight conditions; determine the first UAV flight power of the first UAV from the route starting point to other waypoints in the preset flight route, and determine the remaining battery capacity required for the first UAV from each waypoint in the preset flight route to the landing airport; based on the flight power of the first UAV, determine the farthest waypoint that the first UAV can reach if the remaining battery capacity allows as the preset handover point; and determine the available airport closest to the preset handover point as the preset landing airport.

[0130] In the determination module in the above-mentioned UAV collaborative operation device, the determination module is also used to obtain the power set corresponding to the first UAV, wherein the power set includes induced power, type resistance power, waste resistance power and the power of the first UAV communication and the carried payload; based on the induced power, type resistance power, waste resistance power, the power of the first UAV communication and the carried payload and the energy efficiency coefficient, the flight power of the first UAV is determined.

[0131] In the determination module in the above-mentioned UAV collaborative operation device, the determination module is also used to determine a power set. Specifically, the power set is determined in the following manner: obtaining the induced power of the first UAV when hovering, the ground speed of the first UAV, and the average rotor induced speed of the first UAV when hovering; determining the induced power of the first UAV based on the induced power of the first UAV, the ground speed of the first UAV, and the average rotor induced speed when hovering; obtaining the form drag power of the first UAV and the rotor tip speed of the first UAV when hovering; determining the form drag power of the first UAV based on the form drag power of the first UAV, the ground speed of the first UAV, and the rotor tip speed of the first UAV when hovering; obtaining the fuselage drag ratio, air density, rotor solidity of the first UAV, and rotor disc area of ​​the first UAV; obtaining the fuselage drag ratio, air density, rotor solidity, and rotor disc area of ​​the first UAV; determining the power set corresponding to the first UAV based on the induced power of the first UAV, the form drag power of the first UAV, the waste drag power of the first UAV, and the power of the first UAV's communication and carried payloads.

[0132] In the determination module in the above-mentioned UAV collaborative operation device, the determination module is also used to determine the ground speed of the first UAV. Specifically, the ground speed of the first UAV is determined by: obtaining the airspeed and flight direction of the first UAV, and obtaining the wind speed and wind direction; determining the ground speed of the first UAV based on the airspeed, flight direction, wind speed and wind direction.

[0133] In the determination module in the above-mentioned UAV collaborative operation device, the determination module is also used to determine the induced power of the first UAV when hovering. Specifically, the induced power of the first UAV when hovering is determined by: obtaining the aircraft weight and incremental correction coefficient of the first UAV; determining the induced power of the first UAV when hovering based on the aircraft weight, incremental correction coefficient, air density and rotor disc area.

[0134] In the determination module in the above-mentioned UAV collaborative operation device, the determination module is also used to determine the drag power of the first UAV when hovering. Specifically, the drag power of the first UAV when hovering is determined by the following method: obtaining the drag coefficient, the rotor angular velocity and rotor radius of the first UAV; determining the drag power of the first UAV when hovering based on the drag coefficient, air density, rotor solidity, rotor disc area, rotor angular velocity and rotor radius.

[0135] In the determination module in the above-mentioned drone collaborative operation device, the determination module is further used to obtain the first remaining battery capacity, full charge voltage, nominal battery capacity and voltage drop linear curve of the first drone at the previous waypoint, wherein the slope is determined by the full charge voltage, nominal battery capacity, standard voltage and nominal battery discharge coefficient; determine the voltage of the first drone at the next waypoint based on the full charge voltage, slope, nominal battery capacity and first remaining battery capacity; determine the current of the first drone at the next waypoint based on the flight power of the first drone and the voltage of the first drone at the next waypoint; determine the second remaining battery capacity of the first drone at the next waypoint based on the current, rated discharge time, nominal battery capacity and time step of the first drone at the next waypoint, wherein the time step is the number of waypoints flown by the first drone, and stop iteration when the second remaining battery capacity meets a preset battery capacity condition, and the preset battery capacity condition is determined by the nominal battery capacity and the nominal battery discharge coefficient.

[0136] The above-mentioned UAV collaborative operation device also includes a training module 48, which is used to train the neural network model. Specifically, the neural network model is trained in the following manner: obtaining sample data, wherein the sample data includes multi-dimensional feature data of the UAV, and the multi-dimensional feature data includes battery status data, flight status data, environmental data, and mission payload data; using an initial neural network model to process the sample data to obtain the sample predicted remaining flight time, wherein the initial neural network model includes a first model for processing time series data and a second model for processing spatial data; determining a fusion loss function based on the sample predicted remaining flight time and the actual remaining flight time, and adjusting the parameters of the initial neural network model based on the loss value of the fusion loss function, and stopping the iteration until the adjusted loss value meets the preset conditions to obtain the neural network model.

[0137] In the training module in the above-mentioned UAV collaborative operation device, the training module is also used to determine the fusion loss function. Specifically, the fusion loss function is determined in the following manner: determining the mean square error function of the sample predicted remaining flight time and the actual remaining flight time, and determining the mean square error function as the main loss; determining the asymmetric loss based on the first penalty coefficient, the second penalty coefficient, the sample predicted remaining flight time and the actual remaining flight time; determining the multi-task learning loss based on the weight coefficients of multiple auxiliary tasks and the corresponding mean square error loss function, wherein the multiple auxiliary tasks include voltage auxiliary prediction and flight state prediction; determining the fusion loss function based on the main loss, the asymmetric loss and the multi-task learning loss.

[0138] In the prediction module in the above-mentioned UAV collaborative operation device, the prediction module is also used to obtain the reference time required for the UAV to reach the preset handover point; when the predicted remaining flight time is less than the reference time, it is determined that the preset handover point needs to be adjusted; the waypoint closest to the UAV in the available waypoint set is determined as the target handover point; and the target landing airport closest to the target handover point is determined from the available airport set.

[0139] It should be noted that Figure 5 The UAV cooperative operation device shown is used to perform Figure 2 The drone collaborative operation method shown in the figure, therefore the relevant explanations in the above drone collaborative operation method are also applicable to the drone collaborative operation device, and will not be repeated here.

[0140] An embodiment of the present application also provides an electronic device, which includes a memory and a processor, wherein the memory is used to store program instructions; the processor is connected to the memory and is used to execute program instructions to implement the following functions: obtaining a preset flight route of a drone, wherein the preset flight route is determined by multiple discrete waypoints; determining a preset handover point and a preset landing airport of the drone based on the preset flight route; using a neural network model to predict the remaining flight time of the drone to obtain a predicted remaining flight time, and adjusting the preset handover point and the preset landing airport based on the predicted remaining flight time to obtain a target handover point and a target landing airport; performing collaborative operations of multiple drones based on the target handover point and the target landing airport, wherein the previous drone lands at the target landing airport, and the next drone continues to perform the operation at the target handover point.

[0141] It should be noted that the above electronic equipment is used to perform Figure 2 The drone collaborative operation method shown in the figure, therefore the relevant explanations and instructions in the above drone collaborative operation method are also applicable to the electronic device and will not be repeated here.

[0142] An embodiment of the present application also provides a non-volatile storage medium, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the following drone collaborative operation method by running the computer program: obtaining a preset flight route of the drone, wherein the preset flight route is determined by multiple discrete waypoints; determining a preset handover point and a preset landing airport of the drone based on the preset flight route; using a neural network model to predict the remaining flight time of the drone to obtain the predicted remaining flight time, and adjusting the preset handover point and the preset landing airport based on the predicted remaining flight time to obtain a target handover point and a target landing airport; performing multiple drone collaborative operations based on the target handover point and the target landing airport, wherein the previous drone lands at the target landing airport, and the next drone continues to perform the operation at the target handover point.

[0143] It should be noted that the above non-volatile storage medium is used to execute Figure 2 The drone collaborative operation method shown in the figure, therefore the relevant explanations in the above drone collaborative operation method are also applicable to the non-volatile storage medium, and will not be repeated here.

[0144] An embodiment of the present application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the drone collaborative operation method in each embodiment of the present application.

[0145] An embodiment of the present application also provides a computer program, which, when executed by a processor, implements the steps of the drone collaborative operation method in each embodiment of the present application.

[0146] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0147] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0148] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0149] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0150] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0151] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the existing technology, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program code.

[0152] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A UAV collaborative operation method, characterized in that: include: Obtaining a preset flight route of the UAV, wherein the preset flight route is determined by a plurality of discrete waypoints; Determining a preset handover point and a preset landing airport for the UAV based on the preset flight route; Using a neural network model to predict the remaining flight time of the UAV to obtain a predicted remaining flight time, and adjusting the preset handover point and the preset landing airport according to the predicted remaining flight time to obtain a target handover point and a target landing airport; Multiple drones perform collaborative operations based on the target handover point and the target landing airport, wherein the previous drone lands at the target landing airport and the next drone continues to perform the operation at the target handover point.

2. The method according to claim 1, characterized in that Determining a preset handover point and a preset landing airport for the drone based on the preset flight route includes: Obtaining a starting point of the preset flight route; Determining a first airport closest to the starting point of the route from a set of available airports, wherein each airport in the set of available airports contains a first drone that meets preset flight conditions; determining a first drone flight power for the first drone from the route starting point to other waypoints in the preset flight route, and determining a remaining battery capacity required for the first drone to reach a landing airport from each waypoint in the preset flight route; Determining, based on the flight power of the first UAV, the farthest waypoint that the first UAV can reach within the scope of the remaining battery capacity as the preset handover point; The available airport closest to the preset handover point is determined as the preset landing airport.

3. The method according to claim 2, characterized in that Determining the flight power of the first UAV from the route starting point to other waypoints in the preset flight route includes: Obtain a power set corresponding to the first UAV, where the power set includes induced power, form resistance power, waste resistance power, and power required for communication with the first UAV and its payloads; The flight power of the first UAV is determined according to the induced power, the form resistance power, the waste resistance power, the power of the first UAV communication and the carried payload, and the energy efficiency coefficient.

4. The method according to claim 3, characterized in that The power set is determined by: Obtaining the induced power of the first UAV when hovering, the ground speed of the first UAV, and the average induced rotor speed of the first UAV when hovering; determining the induced power of the first UAV based on the induced power of the first UAV when hovering, the ground speed of the first UAV, and the average induced rotor speed; Obtaining the drag power of the first UAV and the rotor tip speed of the first UAV when the UAV is hovering; Determining the form drag power of the first UAV based on the form drag power of the first UAV when hovering, the ground speed of the first UAV, and the rotor tip speed of the first UAV; Obtaining a fuselage drag ratio of the first UAV, air density, rotor solidity of the first UAV, and rotor disc area of ​​the first UAV; determining the waste drag power of the first UAV based on the fuselage drag ratio, the air density, the rotor solidity, the rotor disc area, and the ground speed of the first UAV; A power set corresponding to the first UAV is determined according to the induced power of the first UAV, the form resistance power of the first UAV, the waste resistance power of the first UAV, and the power of the first UAV communication and the carried payload.

5. The method according to claim 4, characterized in that The ground speed of the first UAV is determined by: Obtaining the airspeed and flight direction of the first UAV, and obtaining the wind speed and wind direction; Determine the ground speed of the first UAV based on the airspeed, the flight direction, the wind speed, and the wind direction.

6. The method according to claim 4, characterized in that The induced power of the first UAV during hovering is determined by: Obtaining the aircraft weight and incremental correction coefficient of the first UAV; The induced power of the first UAV during hovering is determined based on the aircraft weight, the incremental correction coefficient, the air density, and the rotor disc area.

7. The method according to claim 4, characterized in that The drag power of the first UAV when hovering is determined by the following method: Obtaining a drag coefficient, a rotor angular velocity, and a rotor radius of the first UAV; The drag power of the first UAV when hovering is determined based on the drag coefficient, the air density, the rotor solidity, the rotor disc area, the rotor angular velocity, and the rotor radius.

8. The method according to claim 2, characterized in that Determining the remaining battery capacity required for the first UAV to travel from each waypoint in the preset flight route to a landing airport includes: Obtaining a slope of a linear curve of a first remaining battery capacity, a full charge voltage, a nominal battery capacity, and a voltage drop of the first UAV at a previous waypoint, wherein the slope is determined by the full charge voltage, the nominal battery capacity, the standard voltage, and the nominal battery discharge coefficient; determining a voltage of the first drone at a next waypoint based on the full charge voltage, the slope, the nominal battery capacity, and the first remaining battery capacity; determining a current of the first drone at the next waypoint based on the flight power of the first drone and the voltage of the first drone at the next waypoint; Determine a second remaining battery capacity of the first drone at the next waypoint based on the current, rated discharge time, the nominal battery capacity, and a time step of the first drone at the next waypoint, where the time step is the number of waypoints flown by the first drone. Stop iteration when the second remaining battery capacity satisfies a preset battery capacity condition, where the preset battery capacity condition is determined by the nominal battery capacity and the nominal battery discharge coefficient.

9. The method according to claim 1, characterized in that The neural network model is trained in the following way: Acquire sample data, wherein the sample data includes multi-dimensional feature data of the UAV, and the multi-dimensional feature data includes battery status data, flight status data, environmental data, and mission payload data; Processing the sample data using an initial neural network model to obtain a sample predicted remaining battery life, wherein the initial neural network model includes a first model for processing time series data and a second model for processing spatial data; A fusion loss function is determined based on the sample predicted remaining battery life and the actual remaining battery life, and the parameters of the initial neural network model are adjusted according to the loss value of the fusion loss function. The iteration is stopped until the adjusted loss value meets the preset conditions to obtain the neural network model.

10. The method according to claim 9, characterized in that The fusion loss function is determined by: Determine a mean square error function between the sample predicted remaining endurance time and the actual remaining endurance time, and determine the mean square error function as a main loss; Determining an asymmetric loss based on the first penalty coefficient, the second penalty coefficient, the sample predicted remaining battery life, and the actual remaining battery life; Determining a multi-task learning loss based on weight coefficients of multiple auxiliary tasks and corresponding mean square error loss functions, wherein the multiple auxiliary tasks include voltage auxiliary prediction and flight state prediction; The fusion loss function is determined based on the main loss, the asymmetric loss, and the multi-task learning loss.

11. The method according to claim 1, wherein Adjusting the preset handover point and the preset landing airport according to the predicted remaining flight time to obtain a target handover point and a target landing airport includes: Obtaining the reference time required for the UAV to reach the preset handover point; When the predicted remaining endurance time is less than the reference time, determining that the preset handover point needs to be adjusted; Determine the closest waypoint to the UAV in the available waypoint set as the target handover point; A target landing airport closest to the target handover point is determined from the set of available airports.

12. A UAV cooperative operation device, characterized in that: include: An acquisition module, configured to acquire a preset flight route of the UAV, wherein the preset flight route is determined by a plurality of discrete waypoints; a determination module, configured to determine a preset handover point and a preset landing airport of the UAV according to the preset flight route; a prediction module, configured to predict the remaining flight time of the UAV using a neural network model to obtain the predicted remaining flight time, and adjust the preset handover point and the preset landing airport based on the predicted remaining flight time to obtain a target handover point and a target landing airport; An execution module is used to execute a collaborative operation of multiple drones based on the target handover point and the target landing airport, wherein the previous drone lands at the target landing airport and the next drone continues to perform the operation at the target handover point.

13. An electronic device, characterized in that: include: a memory for storing program instructions; A processor is connected to the memory and is used to execute program instructions that implement the following functions: obtaining a preset flight route of the drone, wherein the preset flight route is determined by multiple discrete waypoints; determining a preset handover point and a preset landing airport of the drone based on the preset flight route; using a neural network model to predict the remaining flight time of the drone to obtain a predicted remaining flight time, and adjusting the preset handover point and the preset landing airport based on the predicted remaining flight time to obtain a target handover point and a target landing airport; performing a collaborative operation of multiple drones based on the target handover point and the target landing airport, wherein the previous drone lands at the target landing airport, and the operation is continued by the next drone at the target handover point.

14. A non-volatile storage medium, characterized in that: The non-volatile storage medium includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the drone collaborative operation method described in any one of claims 1 to 11 by running the computer program.

15. A computer program product comprising computer instructions, characterized in that When the computer instructions are executed by the processor, the drone collaborative operation method described in any one of claims 1 to 11 is implemented.

Images