Simulation unmanned aerial vehicle scheduling method and device, electronic equipment and storage medium

Abstract

The invention provides a simulation unmanned aerial vehicle scheduling method and device, electronic equipment and a storage medium, and the method comprises the steps: constructing a simulation virtual scene for a target region based on a simulation platform, the simulation virtual scene comprises a simulation geographical environment and at least one simulation unmanned aerial vehicle, and each simulation unmanned aerial vehicle has simulation remaining electric quantity information; the simulation residual electric quantity information of each simulation unmanned aerial vehicle is sent to a server; receiving a target flight instruction sent by the server, wherein the target flight instruction carries identification information of the target simulation unmanned aerial vehicle and flight target position information; the target simulation unmanned aerial vehicle is screened from at least one simulation unmanned aerial vehicle by the server based on the simulation residual electric quantity information of each simulation unmanned aerial vehicle; and controlling the target simulation unmanned aerial vehicle to execute the target flight task according to the flight target position information. The simulation unmanned aerial vehicle has the simulation electric quantity information, so that the matching between simulation scheduling and real scheduling of the simulation unmanned aerial vehicle can be improved, and the verification effect can be improved.

Description

Technical Field

[0001] This application relates to the field of UAV control technology, and in particular, to a scheduling method, device, electronic device, and storage medium for a simulated UAV. Background Art

[0002] With the rapid popularization of UAV technology in fields such as power inspection, disaster relief, and geographical mapping, the technical limitations of simulation verification, as a key link before actual deployment, have become increasingly prominent. For example, for the scheduling of a simulated UAV cluster, the simulated UAVs that need to execute tasks are usually determined according to the shortest path first or round-robin allocation method. However, there are many factors that need to be considered for the scheduling of real UAVs, resulting in a deviation of the UAV scheduling algorithm between the simulation scenario and the real scenario, which affects the verification effect. Summary of the Invention

[0003] In view of this, this application provides a scheduling method, device, equipment, and storage medium for a simulated UAV, which can improve the matching between the simulated scheduling and the real scheduling of the simulated UAV and is beneficial to improving the verification effect.

[0004] According to the first aspect of this application, a scheduling method for a simulated UAV is provided, which is applied to a terminal device. The method includes: Construct a simulated virtual scene for a target area based on a simulation platform. The simulated virtual scene includes a simulated geographical environment and at least one simulated UAV, and each simulated UAV has simulated remaining battery information; Send the simulated remaining battery information of each simulated UAV to the server; Receive a target flight instruction sent by the server. The target flight instruction carries the identification information of the target simulated UAV and the flight target position information. The target simulated UAV is selected by the server from the at least one simulated UAV based on the user flight instruction and the simulated remaining battery information of each simulated UAV; Control the target simulated UAV to execute a target flight task according to the flight target position information.

[0005] According to the second aspect of this application, a scheduling method for a simulated UAV is provided, which is applied to a server. The method includes: Obtain a user flight instruction, and receive the simulated remaining battery information of at least one simulated UAV and the identification information of each simulated UAV sent by the terminal device; Determine a target simulated UAV from the at least one simulated UAV according to the simulated remaining battery information of each simulated UAV and the user flight instruction; Generate a target flight instruction based on the identification information of the target simulated UAV and the user flight instruction; Send the target flight instruction to the terminal device; the target flight instruction is used to instruct the target simulation UAV to perform a target flight mission.

[0006] According to a third aspect of the present application, there is provided a scheduling device for a simulation UAV, the device includes: A scenario construction module, configured to construct a simulation virtual scenario for a target area based on a simulation platform, where the simulation virtual scenario includes a simulation geographical environment and at least one simulation UAV, and each simulation UAV has simulation remaining power information; An information sending module, configured to send the simulation remaining power information of each simulation UAV to a server; An instruction receiving module, configured to receive a target flight instruction sent by the server, where the target flight instruction carries identification information of a target simulation UAV and flight target position information; the target simulation UAV is screened by the server from the at least one simulation UAV based on the simulation remaining power information of each simulation UAV and a user flight instruction; A flight control module, configured to control the target simulation UAV to perform a target flight mission according to the flight target position information.

[0007] According to a fourth aspect of the present application, there is provided a scheduling device for a simulation UAV, the device includes: An information receiving module, configured to obtain a user flight instruction and receive the simulation remaining power information of at least one simulation UAV sent by a terminal device; A UAV screening module, configured to determine a target simulation UAV from the at least one simulation UAV according to the simulation remaining power information of each simulation UAV and the user flight instruction; An instruction generation module, configured to generate a target flight instruction based on the identification information of the target simulation UAV and the user flight instruction; An instruction sending module, configured to send the target flight instruction to the terminal device, where the target flight instruction is used to instruct the target simulation UAV to perform a target flight mission.

[0008] According to a fifth aspect of the present application, there is provided an electronic device, including: a processor, a memory, and a bus, where the memory stores machine-readable instructions executable by the processor, and when the electronic device runs, the processor communicates with the memory through the bus, and when the machine-readable instructions are executed by the processor, the scheduling method for a simulation UAV described in the first aspect or the second aspect is executed.

[0009] According to a sixth aspect of the present application, there is provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is run by a processor, it executes the scheduling method of the simulated unmanned aerial vehicle described in the first aspect or the second aspect above.

[0010] For the scheduling method, device, electronic device and storage medium of the simulated unmanned aerial vehicle provided by the present application, since each simulated unmanned aerial vehicle has simulated remaining battery information, and the simulated remaining battery information of each simulated unmanned aerial vehicle is sent to the server, the server can make a task decision according to the user flight instruction and the simulated remaining battery information, so as to screen out the optimal target simulated unmanned aerial vehicle capable of executing the target flight task from at least one simulated unmanned aerial vehicle. In this way, since the screening of the target simulated unmanned aerial vehicle is based not only on the user flight instruction but also on the simulated remaining battery information of each simulated unmanned aerial vehicle, the simulation result can be made more matching with the real scenario, which is beneficial to improving the simulation verification effect.

[0011] To make the above objects, features and advantages of the present disclosure more obvious and understandable, the following specific preferred embodiments are given, and in conjunction with the accompanying drawings, the detailed description is as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following will briefly introduce the drawings required for use in the embodiments. The drawings here are incorporated into the specification and form a part of this specification. These drawings show embodiments that conform to the present disclosure and are used together with the specification to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only show some embodiments of the present disclosure, and thus should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0013] Figure 1 is a schematic diagram of the architecture of a scheduling system of a simulated unmanned aerial vehicle shown in an exemplary embodiment of the present application; Figure 2 is a flowchart of a scheduling method of a simulated unmanned aerial vehicle shown in an exemplary embodiment of the present application; Figure 3 is a flowchart of a method for constructing a simulated virtual scene shown in an exemplary embodiment of the present application; Figure 4 is a flowchart of another scheduling method of a simulated unmanned aerial vehicle shown in an exemplary embodiment of the present application; Figure 5 is a schematic diagram of the interaction process of a scheduling method of a simulated unmanned aerial vehicle shown in an exemplary embodiment of the present application; Figure 6It is a functional module diagram of a simulation unmanned aerial vehicle scheduling device shown in an exemplary embodiment of the present application; Figure 7 It is a functional module diagram of another simulation unmanned aerial vehicle scheduling device shown in an exemplary embodiment of the present application; Figure 8 It is a schematic structural diagram of an electronic device shown in an exemplary embodiment of the present application. Detailed implementation manners

[0014] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0015] The terms used in the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. The singular forms "a", "the", and "said" used in the present application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0016] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to determining".

[0017] The term "and / or" herein merely describes an association relationship and indicates that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" herein represents any one of a plurality or any combination of at least two of a plurality. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set composed of A, B, and C.

[0018] See Figure 1 As shown, it is a schematic architecture diagram of a scheduling system for a simulation unmanned aerial vehicle provided by an embodiment of the present application. As Figure 1As shown, the simulation UAV scheduling system may include a terminal device 100 and a server 200 capable of communicating with the terminal device 100. Among them, the terminal device 100 may include mobile devices, user terminals, in-vehicle devices, computing devices, wearable devices, etc. For example, the terminal device 100 may include tablet computers, mobile phones, laptop computers, ultra-mobile personal computers (UMPCs), netbooks, etc.

[0019] The server 200 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, big data, and artificial intelligence platforms, which is not limited herein.

[0020] Exemplarily, the terminal device 100 may be installed with a simulation platform. The simulation platform may, based on mathematical models and algorithms, use computer simulation technology to simulate behaviors and rules in the real world. A large language model may be deployed on the server 200. Among them, the large language model is an artificial intelligence system based on deep learning. Through learning from a large amount of text data, it can understand and generate natural language and complete various complex tasks.

[0021] See Figure 2 As shown, it is a flowchart of a scheduling method for a simulation UAV provided by an embodiment of the present application. This method is applied to the terminal device 100, and the method includes the following S101 - S104: S101, construct a simulation virtual scene for a target area based on the simulation platform. The simulation virtual scene includes a simulation geographical environment and at least one simulation UAV, and each simulation UAV has simulation remaining battery information.

[0022] Among them, the interface of the simulation platform is consistent with the interface of the real UAV. The algorithms verified on the simulation UAV can be deployed on the real UAV to perform corresponding control on the real UAV.

[0023] In some embodiments, each simulation UAV is integrated with a battery simulation model, and the method further includes: for each simulation UAV, use the battery simulation model to determine the simulation remaining battery information of the simulation UAV according to the preset discharge interval parameter.

[0024] Exemplarily, the battery simulation model can be implemented through battery simulator code. The preset discharge interval parameter can be obtained based on multiple experiments, and specific details are not limited. In this way, determining the simulated remaining battery power information of the simulated UAV according to the preset discharge interval parameter can cause the simulated remaining battery power of the simulated UAV to decay over time, which is beneficial to improving the simulation accuracy of the simulated remaining battery power.

[0025] In some embodiments, the method may further include the following (a) to (b): (a) For any simulated UAV, generate a battery fault simulation instruction using the battery simulation model; (b) In response to the battery fault simulation instruction, set the simulated remaining battery power information of the simulated UAV to zero.

[0026] Exemplarily, the voltage or current of the battery simulation model can be detected, and when it is determined that the simulated battery is abnormal, an alarm prompt message can be generated and the simulated remaining battery power can be set to zero (cleared). In this way, the simulated UAV with zero simulated remaining battery power will not participate in scheduling. Among them, the form of the alarm prompt message is not limited, for example, it can be a buzzer alarm or a voice alarm.

[0027] In this embodiment, using the battery simulation model can not only simulate the simulated remaining battery power, but also simulate battery faults, making the simulation environment more compatible with the real scenario.

[0028] In some embodiments, each simulated UAV has a virtual port and an instance identifier. The virtual ports of different simulated UAVs are different, and the instance identifiers are also different. Here, by setting different ports in the simulation environment, port conflicts can be avoided. In addition, by configuring different instance identifiers for each simulated UAV, it can be ensured that after the system is started each time, the corresponding simulated UAV is started, and the attitude of the restarted simulated UAV matches the previous attitude. For example, after the attitude of each simulated UAV is configured, it will still maintain the original attitude after the system is restarted. Another example is that if the simulated battery power of simulated UAV A is 80% before startup, then after the system is restarted again, the simulated battery power of simulated UAV A is still 80% and does not need to be reconfigured.

[0029] S102, Send the simulated remaining battery power information of each of the simulated UAVs to the server.

[0030] Exemplarily, the terminal device 100 will send the simulated remaining battery power information of each of the simulated UAVs to the server 200, and the identifier information of the simulated UAV is also carried when sending the simulated remaining battery power information.

[0031] S103. Receive the target flight instruction sent by the server. The target flight instruction carries the identification information of the target simulation UAV and the flight target position information. The target simulation UAV is selected by the server from the at least one simulation UAVs based on the user flight instruction and the remaining simulation power information of each simulation UAV.

[0032] Understandably, after receiving the remaining simulation power information of each simulation UAV, the server 200 can determine the target simulation UAV for executing the target task from the at least one simulation UAVs according to the user flight instruction and the remaining simulation power information of each simulation UAV. The specific determination process will be elaborated in detail later. In addition, after determining the target simulation UAV, the server 200 also generates a target flight instruction for instructing the target simulation UAV to execute the target task, and sends the target flight instruction to the terminal device 100.

[0033] S104. Control the target simulation UAV to execute the target flight task according to the flight target position information.

[0034] After receiving the target flight instruction sent by the server 200, the terminal device 100 can control the target simulation UAV to execute the target flight task according to the flight target position information. For example, the target flight task may include flying from a first target position (such as the current position) to a second target position indicated by the target position information.

[0035] In the scheduling method of the simulation UAV provided by the embodiments of the present application, since each simulation UAV has remaining simulation power information, and the remaining simulation power information of each simulation UAV is sent to the server 200. The server 200 can make a task decision according to the user flight instruction and the remaining simulation power information to select the optimal target simulation UAV that can execute the target flight task from at least one simulation UAVs. In this way, since the selection of the target simulation UAV is not only based on the user flight instruction but also combined with the remaining simulation power information of each simulation UAV, the simulation result can be more matched with the real scene, which is beneficial to improving the simulation verification effect.

[0036] See Figure 3 As shown, in some embodiments, for the above step S101, when constructing a simulation virtual scene for the target area based on the simulation platform, it may specifically include the following S1011 to S1013: S1011. Obtain satellite image data, elevation data, and vector maps for the target area, and fuse the satellite image data, the elevation data, and the vector maps to generate three-dimensional fusion map data for the target area.

[0037] Here, by fusing satellite image data (3D), elevation data, and vector maps (2D) of the target area, 3D fused map data can be obtained, which can improve the accuracy of 3D map data. Among them, elevation data can provide information about the height of points on the Earth's surface relative to a specific vertical reference (usually sea level). Further, semantic recognition can be performed on key geographical features in the 3D fused map data to obtain semantic labels for these geographical features. For example, key geographical features can be identified based on the semantic labels of OpenStreetMap (OSM). Exemplarily, key geographical features can include mountains, rivers, paths, etc.

[0038] S1012, using the simulation platform to perform simulation processing on the 3D fused map data to obtain the simulated geographical environment, and using the simulation platform to perform simulation processing on at least one called drone model to obtain the at least one simulated drone.

[0039] Here, when generating a simulated drone, a designed drone model can be called for simulation processing, which can improve the simulation efficiency.

[0040] Specifically, when using the simulation platform to perform simulation processing on the 3D fused map data to obtain the simulated geographical environment, it may include: adjusting the 3D fused map data to obtain target map data, and using the simulation platform to perform simulation processing on the target map data to obtain the simulated geographical environment; where the adjustment includes at least one of element path adjustment, scale ratio adjustment, and coordinate system adjustment.

[0041] Exemplarily, when importing the 3D fused map data into the simulation platform, the element models in the 3D fused map data can be adjusted so that the path length in the simulation platform is consistent with the path length in the real map. For example, the flight path and position coordinates of the simulated drone in the simulated geographical environment need to be consistent with the flight path and position coordinates of the real drone on the real map. Also, for example, if the position path between elements (models) in the 3D fused map data changes, the path of the model needs to be adjusted so that the paths between various elements in the simulation environment are consistent with the corresponding paths between elements in the real map.

[0042] And through scale ratio adjustment, the simulated geographical environment can be made consistent with the real geographical environment at a certain ratio, for example, 1:1 restoration. For example, if the 3D fused map data (captured map) is small, the scale needs to be enlarged in the simulation platform to make the simulated environment map consistent with the real geographical environment. Figure 1 :1 restoration. For example, if the 3D fused map data (captured map) is small, the scale needs to be enlarged in the simulation platform to make the simulated environment map and the real geographical environment consistent. Figure 1 consistent.

[0043] In addition, a preset software or algorithm can be used to achieve automatic conversion between geographical coordinates and local coordinates of the simulation platform.

[0044] It should be noted that the above adjustment of the three-dimensional fusion map data can be achieved through manual adjustment or automatic adjustment, and the specific method is not limited.

[0045] S1013, construct the simulation virtual scene based on the simulation geographical environment and the at least one simulation unmanned aerial vehicle.

[0046] In the simulation virtual scene of the embodiment of the present application, in addition to including the simulation geographical environment and the at least one simulation unmanned aerial vehicle, other factors can also be included, such as simulation airflow, simulation lighting, and sensor noise. In this way, it is beneficial to improve the scene restoration degree and make the simulation environment more matched with the real environment.

[0047] In some embodiments, in order to further improve the accuracy of the three-dimensional fusion map data, after generating the three-dimensional fusion map data for the target area, the method further includes: performing parametric modeling on the target elements in the three-dimensional fusion map data to generate a three-dimensional model corresponding to the target elements, and embedding real physical attribute information into the three-dimensional model to obtain a target three-dimensional model; the target three-dimensional model has semantic labels. Among them, the target elements may include infrastructure that needs to be identified or avoided during cruising. For example, the infrastructure may include utility poles, and according to different cruising scenarios, the infrastructure may be different.

[0048] Exemplarily, parametric modeling can be performed on key infrastructure (such as transmission utility poles) to generate a three-dimensional model with millimeter-level accuracy, embed real physical attributes, and embed semantic labels when exporting the model to enhance the semantic recognition ability of the model. For example, the real physical attributes may include a 5-cm redundant buffer layer for the collision volume, material stiffness (elastic modulus of steel is 200 GPa), and friction coefficient (0.6 for the concrete surface).

[0049] In the embodiment of the present application, by performing parametric modeling on the target elements in the three-dimensional fusion map data and embedding real physical attribute information, the accuracy of the simulation results can be improved. Taking power line inspection as an example, in the related art, since utility poles in the simulation are usually simplified as cylinder models, and their collision detection parameters do not match the real physical characteristics, the misjudgment rate of the UAV obstacle avoidance algorithm in the real scene is as high as 25%. However, by adopting this solution, the misjudgment rate of the UAV obstacle avoidance algorithm in the real scene can be greatly reduced.

[0050] In some embodiments, when the target area includes multiple sub-areas, when fusing the satellite image data, the elevation data, and the vector map to generate three-dimensional fusion map data for the target area, the following steps may be included: For any sub-area, fuse the satellite image data, elevation data, and vector map corresponding to the sub-area to obtain sub-three-dimensional fusion map data for the sub-area; Using the least squares method, splice the sub-three-dimensional fusion map data respectively corresponding to each sub-area to generate three-dimensional fusion map data for the target area.

[0051] In this way, when splicing multiple sub-maps and combining the least squares fitting, the stitching error of multi-source data can be eliminated, which is beneficial to improving the accuracy of the three-dimensional fusion map data. For example, the root mean square average (RMS) of the positioning accuracy can be achieved to be less than 0.3 meters.

[0052] In some embodiments, during the process of the target simulation UAV executing the target flight mission, it is also possible to obtain the environmental image of the environment where the target simulation UAV is located when executing the target flight mission, perform target detection on the environmental image to obtain a target detection result, and send the target detection result to the server. Exemplarily, a target detection model can be used to perform target detection on the environmental image to obtain a target detection result, and the target detection result may include vehicles, flying birds, etc. In this way, the server can adjust the flight instruction according to the target detection result. For example, change to hovering or descending, etc.

[0053] In other embodiments, in order to provide more information to improve the decision-making accuracy of the server, it is also possible to call a multi-modal large language model to perform scene analysis on the target detection result to generate scene description information for the target detection result. For example, if the target detection result is detecting a vehicle, corresponding scene description information "This is a white vehicle with a damaged tire" can be generated based on this target detection result. Optionally, the target detection result and the scene description information corresponding to the target detection result are also sent to the server. In this way, the server can judge whether it is necessary to change the flight instruction for the target simulation UAV according to the target detection result and the scene description information.

[0054] Therefore, in some embodiments, the method further includes: calling a multi-modal large language model to perform scene analysis on the target detection result to generate scene description information for the target detection result; The step of sending the target detection result to the server includes: Sending the target detection result and the description information corresponding to the target detection result to the server.

[0055] It should be noted that during the process of the target simulation UAV executing the target flight mission, in addition to feeding back the target detection result and the picture description information for the target detection result to the server, the simulation UAV can also perform three-dimensional trajectory replanning based on the target detection result for obstacle avoidance.

[0056] See Figure 4 As shown, it is a flowchart of a scheduling method for a simulation UAV provided by another embodiment of the present application. This method is applied to the server 200, and the method includes the following S201 - S204: S201, obtain the user flight instruction, and receive the remaining simulation power information of at least one simulation UAV and the identification information of each simulation UAV sent by the terminal device.

[0057] Among them, the identification information of each simulation UAV is the identity information of each simulation UAV, which is used to distinguish different simulation UAVs.

[0058] Exemplarily, the user flight instruction can be obtained through the user interaction interface, and this user flight instruction is the flight instruction issued by the user. Of course, this user flight instruction can also be obtained through voice input. For example, the obtained user flight instruction can be "Dispatch the UAV with a remaining power greater than 60% near 31.2° north latitude", or it can also be "Dispatch the UAV with a remaining power greater than 70% near 31.2° north latitude to cruise to the XX target point". In the embodiments of the present application, this user flight instruction is a natural language instruction.

[0059] S202, determine the target simulation UAV from the at least one simulation UAV according to the remaining simulation power information of each simulation UAV and the user flight instruction.

[0060] Exemplarily, a large language model is deployed on the server 200, and the large language model can be used to determine the target simulation UAV from the at least one simulation UAV according to the remaining simulation power information of each simulation UAV and the user flight instruction.

[0061] In some embodiments, when determining the target simulation UAV from the at least one simulation UAV according to the remaining simulation power information of each simulation UAV and the user flight instruction, the following steps (I) - (III) can be included: (I), based on the user flight instruction, determine the target task range corresponding to the user flight instruction.

[0062] Specifically, after obtaining the user's flight instruction, the target task range corresponding to the user's flight instruction can be obtained. For example, the task range can be cruising from 31.2°N to 33.2°N, which can be determined according to the actual situation.

[0063] (II) For each simulated drone, based on the simulated remaining power information of the simulated drone, determine the maximum flight task range that the simulated drone can execute.

[0064] Exemplarily, equation modeling can be used to determine the maximum task range of the simulated drone. For example, it can be achieved through the following formula (1): R = R0×(1 - ) (1) Where, R represents the maximum task radius corresponding to the current simulated remaining power of the simulated drone, R0 represents the task radius corresponding to the simulated drone when it is fully charged, and ΔSOC represents the change amount between the current simulated remaining power and the fully charged state of the simulated drone. For example, if the current simulated remaining power of the simulated drone is 80%, then ΔSOC is 20%. It can be seen from the above formula (1) that when SOC drops from 80% to 70%, the inspection distance automatically shrinks by 48%.

[0065] (III) Determine the simulated drones with a maximum flight task range greater than the target task range as candidate simulated drones, and determine the target simulated drone from at least one of the candidate simulated drones.

[0066] Exemplarily, after determining the maximum task range that each simulated drone can fly, the simulated drones with a maximum flight task range greater than the target task range can be determined as candidate simulated drones, and then the target simulated drone can be determined from at least one of the candidate simulated drones.

[0067] In some embodiments, when determining the target simulated drone from at least one of the candidate simulated drones, it may include the following: For each candidate simulated drone, based on the maximum flight task range, power consumption information, urgency information, and the weights corresponding to the maximum flight task range, the power consumption information, and the urgency information respectively, determine the evaluation index information of the candidate simulated drone; where, the maximum flight task range corresponds to the first weight, the power consumption information corresponds to the second weight, and the urgency information corresponds to the third weight; Based on the evaluation index information of at least one of the candidate simulated drones, determine the target simulated drone from at least one of the candidate simulated drones.

[0068] Among them, the power consumption information refers to the power that the candidate simulated unmanned aerial vehicle (UAV) has consumed currently. For example, if the remaining power of the candidate simulated UAV is 80% currently, the power consumption information is 20%. The urgency information is used to characterize the urgency of the flight mission.

[0069] Specifically, the candidate simulated UAV with the optimal evaluation index information can be determined as the target simulated UAV.

[0070] Here, the evaluation index information of each candidate simulated UAV can be determined by the following formula (2): M = α × maximum flight mission range + β × power consumption information + γ × urgency information (2) Among them, M represents the evaluation index information of the candidate simulated UAV, α represents the first weight, β represents the second weight, and γ represents the third weight. When the value of M is the smallest, it means that the evaluation index information is the best.

[0071] Optionally, there is a real-time simulated wind speed in the simulated virtual scene. The first weight, the second weight, and the third weight are determined based on the real-time simulated wind speed. Furthermore, each weight can be dynamically adjusted according to the simulation environment, which is beneficial to improving the determination accuracy of the target simulated UAV.

[0072] In some other embodiments, the user flight instruction includes a delay time. When determining the maximum flight mission range that each simulated UAV can execute based on the simulated remaining power information of the simulated UAV, it may include: for each simulated UAV, determining the maximum flight mission range that the simulated UAV can execute based on the simulated remaining power information of the simulated UAV after the delay time.

[0073] For example, if the user flight instruction is "Dispatch the simulated UAV near 31.2° north latitude to cruise to the XX target point after 3 hours", it is necessary to consider the behaviors of each simulated UAV within 3 hours at this time. For example, if some simulated UAVs have less remaining power currently but will be charged after 1 hour, they may be fully charged after 3 hours. Therefore, they can be listed as candidate simulated UAVs for executing the target mission. In this way, by realizing delayed takeoff through the timing function, the flexibility of decision-making can be improved.

[0074] S203, generating a target flight instruction based on the identification information of the target simulated UAV and the user flight instruction.

[0075] Exemplarily, a large language model is deployed on the server 200. When generating a target flight instruction based on the identification information of the target simulated UAV and the user flight instruction, it may include the following: Convert the user flight instruction using the large language model to obtain a flight instruction in the target format; Generate the target flight instruction based on the identification information of the target simulation UAV and the flight target position information indicated by the flight instruction in the target format.

[0076] Here, the large language model can be used to convert the user flight instruction to obtain a flight instruction in the target format (such as JSON object format) to achieve the parsing of natural language instructions; then, based on the identification information of the target simulation UAV and the flight target position information indicated by the flight instruction in the target format, the target flight instruction is generated. In this way, the generated target flight instruction can carry the identification information of the target simulation UAV and the flight target position information (also known as waypoint parameters).

[0077] For example, for the user flight instruction of "Dispatch a UAV for inspection at 31.2° north latitude", after the large language model parses the user flight instruction, structured constraint conditions (JSON format) can be dynamically generated, and the optimal UAV can be selected in real time, reducing the response time. Specifically, when the large language model uses the attention mechanism to parse the user flight instruction, it can also perform a 1-kilometer radius expansion on the geographical fuzzy description. For example, convert the latitude 31.2° to a rectangular geographical fence of 31.195° - 31.205°, which can improve the accuracy of target task determination.

[0078] S204, send the target flight instruction to the terminal device; the target flight instruction is used to instruct the target simulation UAV to perform the target flight task.

[0079] After generating the target flight instruction, the target flight instruction can be sent to the terminal device to control the target simulation UAV to perform the target flight task.

[0080] In some embodiments, the method further includes the following: Receive the target detection result sent by the terminal device, where the target detection result is obtained by the target simulation UAV performing target detection based on the acquired environmental image during the execution of the target flight task; Generate a flight adjustment instruction based on the target detection result and send the flight adjustment instruction to the terminal device.

[0081] Here, when the simulated drone is performing a task, it can acquire environmental images and perform object detection on the environmental images to obtain object detection results. After the server 200 receives the object detection results, it can determine whether the target point indicated by the target flight position information is found according to the object detection results. Exemplarily, the target point indicated by the target flight position information can be a fixed location or a non-fixed target (such as a moving white vehicle).

[0082] Optionally, in order to improve the accuracy of the judgment, the method further includes: receiving picture description information, which is obtained based on the object detection results. Here, when generating a flight adjustment instruction based on the object detection results, it may include: generating the flight adjustment instruction based on the object detection results and the picture description information. For example, if the target flight instruction is to make the target simulated drone fly above a white sedan with a damaged tire, the server 200 can determine whether the target point is found according to the detection results and the picture description information, and send an adjustment instruction after determining that the target point is found, for example, hovering above the target point.

[0083] In addition, after the remaining simulated power of the target simulated drone is cleared due to a battery failure, another simulated drone can be replaced to continue executing the target flight task. Specifically, starting from the failure point of the currently executing simulated drone, a target simulated drone can be re-screened according to the above screening strategy.

[0084] Next, the interaction process of the scheduling method of the simulated drone provided in this application will be described.

[0085] See Figure 5As shown, the terminal device 100 first executes step S101 to construct a simulation virtual scene for the target area based on the simulation platform. The simulation virtual scene includes a simulation geographical environment and at least one simulation drone, and each simulation drone has simulation remaining battery information. Then it executes step S102 to send the simulation remaining battery information of each simulation drone to the server. Next, the server 200 sequentially executes step S201 to obtain a user flight instruction and receive the simulation remaining battery information of at least one simulation drone and the identification information of each simulation drone sent by the terminal device; step S202 to determine a target simulation drone from the at least one simulation drone according to the simulation remaining battery information of each simulation drone and the user flight instruction; and step S203 to generate a target flight instruction based on the identification information of the target simulation drone and the user flight instruction; and then execute step S204 to send the target flight instruction to the terminal device. Finally, the terminal device 100 executes step S103 to receive the target flight instruction sent by the server; and step S104 to control the target simulation drone to execute the target flight task according to the flight target position information.

[0086] Experiments show that by using the scheduling method of this application, the following technical effects can be achieved, as shown in Table 1 specifically.

[0087] Table 1

[0088] Among them, the instruction response delay refers to the response delay time of the interaction instructions between the terminal device 100 and the server 200, and the edge inference energy efficiency ratio refers to the energy consumed for processing a preset number of frames of images.

[0089] In the scheduling method of the simulation drone provided by the embodiment of this application, the server 200 can receive the simulation remaining battery information of each simulation drone, and make a task decision according to the user flight instruction and the simulation remaining battery information, so as to screen and obtain the optimal target simulation drone that can execute the target flight task from at least one simulation drone. In this way, since the screening of the target simulation drone is based not only on the user flight instruction but also on the simulation remaining battery information of each simulation drone, the simulation result can be made more matching with the real scene, which is beneficial to improving the simulation verification effect.

[0090] Those skilled in the art can understand that in the above method of the specific embodiment, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined according to its function and possible internal logic.

[0091] Based on the same inventive concept, an embodiment of the present disclosure further provides a scheduling device for a simulation unmanned aerial vehicle (UAV) corresponding to the scheduling method of the simulation UAV. Since the principle of problem-solving of the device in the embodiment of the present disclosure is similar to that of the above-mentioned scheduling method of the simulation UAV in the embodiment of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be elaborated.

[0092] Referring Figure 6 As shown in the figure, it is a schematic diagram of a scheduling device for a simulation UAV provided by an embodiment of the present disclosure. The scheduling device 300 for the simulation UAV includes: A scenario construction module 301, configured to construct a simulation virtual scenario for a target area based on a simulation platform. The simulation virtual scenario includes a simulation geographical environment and at least one simulation UAV, and each simulation UAV has simulation remaining power information; An information sending module 302, configured to send the simulation remaining power information of each simulation UAV to a server; An instruction receiving module 303, configured to receive a target flight instruction sent by the server. The target flight instruction carries identification information of a target simulation UAV and flight target position information; the target simulation UAV is selected by the server from the at least one simulation UAV based on the simulation remaining power information of each simulation UAV and a user flight instruction; A flight control module 304, configured to control the target simulation UAV to execute a target flight task according to the flight target position information.

[0093] In some embodiments, each simulation UAV integrates a battery simulation model, and the scenario construction module 301 is further configured to: For each simulation UAV, use the battery simulation model to determine the simulation remaining power information of the simulation UAV according to a preset discharge interval parameter.

[0094] In some embodiments, the scenario construction module 301 is further configured to: For any simulation UAV, generate a battery fault simulation instruction using the battery simulation model; In response to the battery fault simulation instruction, set the simulation remaining power information of the simulation UAV to zero.

[0095] In some embodiments, each simulation UAV has a virtual port and an instance identifier, and the virtual ports and instance identifiers of different simulation UAVs are different.

[0096] In some embodiments, when the scenario construction module 301 constructs a simulation virtual scenario for a target area based on a simulation platform, it is specifically configured to: Obtain satellite image data, elevation data, and vector maps for the target area, and fuse the satellite image data, the elevation data, and the vector maps to generate three-dimensional fused map data for the target area; Use the simulation platform to perform simulation processing on the three-dimensional fused map data to obtain the simulated geographical environment, and use the simulation platform to perform simulation processing on at least one called drone model to obtain the at least one simulated drone; Based on the simulated geographical environment and the at least one simulated drone, construct the simulated virtual scene.

[0097] In some embodiments, the scene construction module 301 is further specifically configured to: Perform parametric modeling on the target elements in the three-dimensional fused map data to generate a three-dimensional model corresponding to the target elements, and embed real physical attribute information into the three-dimensional model to obtain a target three-dimensional model; the target three-dimensional model has semantic labels.

[0098] In some embodiments, the scene construction module 301 is further specifically configured to: Adjust the three-dimensional fused map data to obtain target map data, where the adjustment includes at least one of element path adjustment, scale adjustment, and coordinate system adjustment; Use the simulation platform to perform simulation processing on the target map data to obtain the simulated geographical environment.

[0099] In some embodiments, the flight control module 304 is further configured to: Obtain an environmental image of the environment where the target simulated drone is located when performing the target flight mission; Perform target detection on the environmental image to obtain a target detection result, and send the target detection result to the server.

[0100] In some embodiments, the flight control module 304 is further configured to: Call a multimodal large language model to perform picture analysis on the target detection result to generate picture description information for the target detection result; Send the target detection result and the picture description information corresponding to the target detection result to the server.

[0101] Refer to Figure 7 As shown, it is a schematic diagram of another simulation drone scheduling device provided by an embodiment of the present disclosure. The simulation drone scheduling device 400 includes: An information receiving module 401, configured to obtain a user flight instruction and receive the remaining simulation power information of at least one simulation drone sent by the terminal device; The UAV screening module 402 is configured to determine a target simulated UAV from the at least one simulated UAV according to the simulated remaining power information of each simulated UAV and the user flight instruction; The instruction generation module 403 is configured to generate a target flight instruction based on the identification information of the target simulated UAV and the user flight instruction; The instruction sending module 404 is configured to send the target flight instruction to the terminal device, and the target flight instruction is used to instruct the target simulated UAV to execute a target flight mission.

[0102] In some embodiments, the UAV screening module 402 is specifically configured to: Determine a target task range corresponding to the user flight instruction based on the user flight instruction; For each simulated UAV, determine the maximum flight task range that the simulated UAV can execute based on the simulated remaining power information of the simulated UAV; Determine the simulated UAV with the maximum flight task range greater than the target task range as a candidate simulated UAV, and determine the target simulated UAV from at least one of the candidate simulated UAVs.

[0103] In some embodiments, the UAV screening module 402 is specifically configured to: For each candidate simulated UAV, determine the evaluation index information of the candidate simulated UAV based on the maximum flight task range, power consumption information, urgency information, and the weights corresponding to the maximum flight task range, the power consumption information, and the urgency information respectively; wherein, the maximum flight task range corresponds to a first weight, the power consumption information corresponds to a second weight, and the urgency information corresponds to a third weight; Determine the target simulated UAV from at least one of the candidate simulated UAVs based on the evaluation index information of at least one of the candidate simulated UAVs.

[0104] In some embodiments, there is a real-time simulated wind speed in the simulated virtual scene; the first weight, the second weight, and the third weight are determined based on the real-time simulated wind speed.

[0105] In some embodiments, the user flight instruction includes a delay time; the UAV screening module 402 is specifically configured to: For each simulated UAV, determine the maximum flight task range that the simulated UAV can execute based on the simulated remaining power information of the simulated UAV after the delay time.

[0106] In some embodiments, a large language model is deployed on the server, and the drone screening module 402 is specifically configured to: Using the large language model, determine a target simulation drone from the at least one simulation drone according to the remaining simulated power information of each simulation drone and the user flight instruction.

[0107] In some embodiments, a large language model is deployed on the server, and the drone screening module 402 is specifically configured to: Use the large language model to perform format conversion on the user flight instruction to obtain a flight instruction in a target format; Based on the identification information of the target simulation drone and the flight target position information indicated by the flight instruction in the target format, generate the target flight instruction.

[0108] In some embodiments, the information receiving module 401 is further configured to: Receive a target detection result sent by a terminal device, where the target detection result is obtained by performing target detection on the acquired environmental image when the target simulation drone executes the target flight mission; The instruction generation module 403 is further configured to: generate a flight adjustment instruction based on the target detection result; The instruction sending module 404 is further configured to: send the flight adjustment instruction to the terminal device.

[0109] In some embodiments, the information receiving module 401 is further configured to: Receive picture description information, where the picture description information is obtained based on the target detection result; The instruction generation module 403 is further configured to: Generate the flight adjustment instruction based on the target detection result and the picture description information.

[0110] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this application. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0111] Based on the same technical concept, an embodiment of the present disclosure further provides an electronic device. Refer to Figure 8As shown in the figure, it is a schematic structural diagram of an electronic device 500 provided by an embodiment of the present disclosure, including a processor 501, a memory 502, and a bus 503. Among them, the memory 502 is used to store execution instructions, including an internal memory 5021 and an external memory 5022; the internal memory 5021 here is also called the main memory, which is used to temporarily store the operation data in the processor 501 and the data exchanged with the external memory 5022 such as a hard disk. The processor 501 exchanges data with the external memory 5022 through the internal memory 5021.

[0112] In an embodiment of the present application, the memory 502 is specifically used to store the application program code for executing the solution of the present application, and is controlled by the processor 501 for execution. That is, when the electronic device 500 runs, the processor 501 communicates with the memory 502 through the bus 503, so that the processor 501 executes the application program code stored in the memory 502, and further executes the method described in any of the foregoing embodiments.

[0113] Among them, the memory 502 may be, but is not limited to, a random access memory (Random Access Memory, RAM), a read only memory (Read Only Memory, ROM), a programmable read only memory (Programmable Read-Only Memory, PROM), an erasable programmable read only memory (Erasable Programmable Read-Only Memory, EPROM), an electrically erasable programmable read only memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc.

[0114] The processor 501 may be an integrated circuit chip with signal processing capabilities. The above-mentioned processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; it may also be a digital signal processor (Digital Signal Processing, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0115] It can be understood that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on the electronic device 500. In other embodiments of the present application, the electronic device 500 may include more or fewer components than those illustrated, or combine certain components, or split certain components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0116] Embodiments of the present disclosure also provide a computer-readable storage medium having a computer program stored thereon, and when the computer program is run by a processor, it executes the steps of the scheduling method of the simulation robot in the above method embodiments. Wherein, the storage medium may be a volatile or non-volatile computer-readable storage medium.

[0117] Embodiments of the present disclosure also provide a computer program product carrying program code, and the instructions included in the program code can be used to execute the steps of the scheduling method of the simulation robot in the above method embodiments. For details, reference can be made to the above method embodiments, which will not be elaborated herein.

[0118] Among them, the above computer program product can be specifically implemented in the form of hardware, software, or a combination thereof. In an alternative embodiment, the computer program product is specifically embodied as a computer storage medium. In another alternative embodiment, the computer program product is specifically embodied as a software product, such as a Software Development Kit (SDK), etc.

[0119] In addition, the embodiments of the subject matter and functional operations described in this specification can be implemented in the following: digital electronic circuits, tangible computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or a combination of one or more of them. The embodiments of the subject matter described in this specification can be implemented as one or more computer programs, that is, one or more modules in computer program instructions encoded on a tangible non-transitory program carrier for execution by a data processing apparatus or to control the operation of the data processing apparatus. Alternatively or additionally, the program instructions can be encoded on an artificially generated propagated signal, such as a machine-generated electrical, optical, or electromagnetic signal, which is generated to encode information and transmit it to a suitable receiver device for execution by the data processing apparatus. The computer storage medium can be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.

[0120] The processes and logical flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform the corresponding functions by operating on input data and generating output. The processes and logical flows can also be performed by, for example, FPGA (Field Programmable Gate Array) or ASIC (Application Specific Integrated Circuit) of special logic circuits, and the apparatus can also be implemented as special logic circuits.

[0121] Computers suitable for executing computer programs include, for example, general and / or special microprocessors, or any other type of central processing unit. Generally, the central processing unit will receive instructions and data from a read-only memory and / or a random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include one or more mass storage devices for storing data, such as magnetic disks, magneto-optical disks, or optical disks, etc., or the computer will be operatively coupled to such mass storage devices to receive data therefrom or transfer data thereto, or both. However, a computer is not necessarily required to have such devices. In addition, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name just a few.

[0122] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as including semiconductor memory devices (such as EPROM, EEPROM, and flash memory devices), magnetic disks (such as internal hard disks or removable disks), magneto-optical disks, and CD ROM and DVD-ROM disks. The processor and the memory can be supplemented by, or incorporated in, special logic circuits.

[0123] Although this specification contains many specific implementation details, these should not be construed as limiting the scope of any invention or the scope of what is claimed, but rather as mainly describing the features of specific embodiments of a particular invention. Certain features described in multiple embodiments in this specification can also be implemented in combination in a single embodiment. On the other hand, the various features described in a single embodiment can also be implemented separately in multiple embodiments or in any suitable sub-combination. In addition, although features can operate in certain combinations as described above and are even initially claimed as such, one or more features from the claimed combination can in some cases be removed from the combination, and the claimed combination can be directed to a sub-combination or a variation of the sub-combination.

[0124] Similarly, although the operations are depicted in the drawings in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or sequentially, or that all illustrated operations be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Additionally, the separation of various system modules and components in the above-described embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the program components and systems described can generally be integrated together in a single software product or packaged into multiple software products.

[0125] Thus, particular embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the acts recited in the claims can be performed in a different order and still achieve the desired result. Additionally, the processes depicted in the figures are not necessarily in the particular order or sequential order shown to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0126] The foregoing is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the scope of protection of the present application.

Claims

1. A scheduling method for a simulated unmanned aerial vehicle, characterized in that, Applied to a terminal device, the method includes: Constructing a simulation virtual scene for a target area based on a simulation platform, where the simulation virtual scene includes a simulated geographical environment and at least one simulated drone, and each simulated drone has simulated remaining battery information; Sending the simulated remaining battery information of each simulated drone to a server; Receiving a target flight instruction sent by the server, where the target flight instruction carries identification information of a target simulated drone and flight target location information; the target simulated drone is selected by the server from the at least one simulated drone based on a user flight instruction and the simulated remaining battery information of each simulated drone; Controlling the target simulated drone to perform a target flight task according to the flight target location information.

2. The method according to claim 1, characterized in that Each simulated drone is integrated with a battery simulation model, and the method further includes: For each simulated drone, using the battery simulation model and according to a preset discharge interval parameter, determining the simulated remaining battery information of the simulated drone.

3. The method according to claim 2, wherein The method further includes: For any simulated drone, using the battery simulation model to generate a battery fault simulation instruction; In response to the battery fault simulation instruction, setting the simulated remaining battery information of the simulated drone to zero.

4. The method according to claim 1, wherein Each simulated drone has a virtual port and an instance identifier, and the virtual ports and instance identifiers of different simulated drones are different.

5. The method according to claim 1, characterized in that, The constructing a simulation virtual scene for a target area based on a simulation platform includes: Obtaining satellite image data, elevation data, and vector maps for the target area, and fusing the satellite image data, the elevation data, and the vector maps to generate three-dimensional fused map data for the target area; Using the simulation platform to perform simulation processing on the three-dimensional fused map data to obtain the simulated geographical environment, and using the simulation platform to perform simulation processing on at least one drone model called to obtain the at least one simulated drone; Constructing the simulation virtual scene based on the simulated geographical environment and the at least one simulated drone.

6. The method according to claim 5, wherein After generating the three-dimensional fused map data for the target area, the method further includes: Performing parametric modeling on target elements in the three-dimensional fused map data to generate a three-dimensional model corresponding to the target elements, and embedding real physical attribute information into the three-dimensional model to obtain a target three-dimensional model; the target three-dimensional model has semantic tags.

7. The method according to claim 5, wherein The using the simulation platform to perform simulation processing on the three-dimensional fused map data to obtain the simulated geographical environment includes: Adjusting the three-dimensional fused map data to obtain target map data, where the adjustment includes at least one of element path adjustment, scale adjustment, and coordinate system adjustment; Using the simulation platform to perform simulation processing on the target map data to obtain the simulated geographical environment.

8. The method according to claim 1, characterized in that The method further includes: Obtaining an environmental image of the environment where the target simulated drone is located when performing the target flight task. Perform object detection on the environmental image to obtain an object detection result, and send the object detection result to the server.

9. The method according to claim 8, wherein The method further includes: Invoke a multimodal large language model to perform scene analysis on the object detection result and generate scene description information for the object detection result; The step of sending the object detection result to the server includes: Send the object detection result and the corresponding scene description information to the server.

10. A scheduling method for a simulated unmanned aerial vehicle, characterized in that, When applied to a server, the method includes: Obtain a user flight instruction, and receive the remaining simulation power information of at least one simulated drone and the identification information of each simulated drone sent by the terminal device; Determine a target simulated drone from the at least one simulated drone according to the remaining simulation power information of each simulated drone and the user flight instruction; Generate a target flight instruction based on the identification information of the target simulated drone and the user flight instruction; Send the target flight instruction to the terminal device; the target flight instruction is used to instruct the target simulated drone to perform a target flight task.

11. The method according to claim 10, characterized in that, The step of determining a target simulated drone from the at least one simulated drone according to the remaining simulation power information of each simulated drone and the user flight instruction includes: Based on the user flight instruction, determine a target task range corresponding to the user flight instruction; For each simulated drone, based on the remaining simulation power information of the simulated drone, determine the maximum flight task range that the simulated drone can execute; Determine the simulated drones with a maximum flight task range greater than the target task range as candidate simulated drones, and determine the target simulated drone from at least one of the candidate simulated drones.

12. The method according to claim 11, wherein The step of determining the target simulated drone from at least one of the candidate simulated drones includes: For each candidate simulated drone, based on the maximum flight task range, power consumption information, urgency information, and the weights corresponding to the maximum flight task range, power consumption information, and urgency information respectively, determine the evaluation index information of the candidate simulated drone; wherein, the maximum flight task range corresponds to a first weight, the power consumption information corresponds to a second weight, and the urgency information corresponds to a third weight; Determine the target simulated drone from at least one of the candidate simulated drones based on the evaluation index information of at least one of the candidate simulated drones.

13. The method according to claim 12, wherein There is a real-time simulation wind speed in the simulation virtual scene; the first weight, the second weight, and the third weight are determined based on the real-time simulation wind speed.

14. The method according to claim 11, wherein The user flight instruction includes a delay time; The step of, for each simulated drone, based on the remaining simulation power information of the simulated drone, determining the maximum flight task range that the simulated drone can execute includes: For each simulated drone, based on the remaining simulation power information of the simulated drone after the delay time, determine the maximum flight task range that the simulated drone can execute.

15. The method according to claim 10, characterized in that, The server deploys a large language model. Determining a target simulation UAV from the at least one simulation UAV according to the simulation remaining power information of each simulation UAV and the user flight instruction includes: Using the large language model, determining a target simulation UAV from the at least one simulation UAV according to the simulation remaining power information of each simulation UAV and the user flight instruction.

16. The method according to claim 10, wherein The server deploys a large language model. Generating a target flight instruction based on the identification information of the target simulation UAV and the user flight instruction includes: Using the large language model to perform format conversion on the user flight instruction to obtain a flight instruction in a target format; Based on the identification information of the target simulation UAV and the flight target position information indicated by the flight instruction in the target format, generating the target flight instruction.

17. The method according to claim 10, wherein The method further includes: Receiving a target detection result sent by a terminal device, where the target detection result is obtained by the target simulation UAV performing target detection based on the acquired environmental images when executing the target flight task; Based on the target detection result, generating a flight adjustment instruction and sending the flight adjustment instruction to the terminal device.

18. The method according to claim 17, characterized in that The method further includes: Receiving picture description information obtained based on the target detection result; Based on the target detection result, generating a flight adjustment instruction includes: Based on the target detection result and the picture description information, generating the flight adjustment instruction.

19. A scheduling device for a simulation unmanned aerial vehicle, characterized in that, The device includes: A scene construction module, configured to construct a simulation virtual scene for a target area based on a simulation platform. The simulation virtual scene includes a simulation geographical environment and at least one simulation UAV, and each simulation UAV has simulation remaining power information; An information sending module, configured to send the simulation remaining power information of each simulation UAV to the server; An instruction receiving module, configured to receive the target flight instruction sent by the server. The target flight instruction carries the identification information of the target simulation UAV and the flight target position information. The target simulation UAV is screened by the server from the at least one simulation UAV according to the simulation remaining power information of each simulation UAV and the user flight instruction; A flight control module, configured to control the target simulation UAV to execute the target flight task according to the flight target position information.

20. A scheduling device for a simulated unmanned aerial vehicle, characterized in that, The device includes: An information receiving module, configured to obtain a user flight instruction and receive the simulation remaining power information of at least one simulation UAV sent by a terminal device; A UAV screening module, configured to determine a target simulation UAV from the at least one simulation UAV according to the simulation remaining power information of each simulation UAV and the user flight instruction; An instruction generation module, configured to generate a target flight instruction based on the identification information of the target simulation UAV and the user flight instruction; An instruction sending module, configured to send the target flight instruction to the terminal device, and the target flight instruction is used to instruct the target simulation UAV to execute the target flight task.

21. An electronic device, characterized in that, Includes: A processor, a memory, and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device runs, the processor communicates with the memory via the bus, and when the machine-readable instructions are executed by the processor, the scheduling method of the simulated unmanned aerial vehicle according to any one of claims 1-18 is executed.

22. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is run by a processor, the scheduling method of the simulated unmanned aerial vehicle according to any one of claims 1-18 is executed.

Images