Unmanned aerial vehicle scheduling method and system, and readable storage medium

Abstract

The application provides a UAV scheduling method, system and readable storage medium, the method comprising: predicting whether the target UAV has insufficient power when performing an unfinished task according to the current power; if the target UAV has insufficient power, constructing a spatial constraint condition; obtaining a candidate UAV set and a candidate task handover point set, combining any candidate UAV with a candidate task handover point to determine whether the combination result satisfies the spatial constraint condition; obtaining a first candidate set according to the determination result, the first candidate set comprising at least one selected UAV and at least one selected task handover point corresponding to each selected UAV, and constructing a linear scheduling function to screen a first replacement UAV and a first handover point corresponding to the first replacement UAV from the first candidate set according to the linear scheduling function. The application greatly improves the stability, safety and efficiency of UAV task execution by predicting the power, reasonably screening and optimizing the task scheduling.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicle scheduling, and in particular to an unmanned aerial vehicle scheduling method, system and readable storage medium. BACKGROUND

[0002] At present, unmanned aerial vehicles are widely used in many fields to undertake various complex tasks, such as long-distance power transmission lines, remote mountainous areas oil and gas pipelines, and border monitoring. During the execution of these tasks, the power management of the unmanned aerial vehicle becomes a key problem. Due to the limited endurance of the unmanned aerial vehicle, it may not be able to complete the intended task due to insufficient power during task execution, which not only affects the overall progress and effect of the task, but also may cause the unmanned aerial vehicle to crash due to power depletion during the return journey, resulting in equipment loss and safety hazards.

[0003] At present, the traditional unmanned aerial vehicle scheduling method mostly only considers the initial power of the unmanned aerial vehicle and simple task allocation, lacks dynamic prediction of power changes during the execution of the task by the unmanned aerial vehicle, and is difficult to discover the risk of insufficient power in advance and make reasonable scheduling arrangements in time. At the same time, the existing unmanned aerial vehicle scheduling strategy often lacks a systematic solution when facing insufficient power. On the one hand, there is a lack of scientific and effective judgment basis and optimization method for how to accurately select suitable replacement unmanned aerial vehicles from numerous candidate unmanned aerial vehicles and determine reasonable task handover points, resulting in low scheduling efficiency and failing to meet the requirements of timeliness and accuracy of actual tasks. On the other hand, when the replacement unmanned aerial vehicle also has the risk of insufficient power, there is no perfect task segmentation and relay scheduling mechanism, making it difficult to ensure that the entire task can be completed smoothly and efficiently. SUMMARY

[0004] The purpose of the present application is to provide an unmanned aerial vehicle scheduling method, system and readable storage medium, which aims to solve the problem of scheduling efficiency existing in the traditional technology.

[0005] In a first aspect, the present application provides an unmanned aerial vehicle scheduling method, which comprises:

[0006] obtaining the current power of the target unmanned aerial vehicle, and predicting whether the target unmanned aerial vehicle has insufficient power when executing the unfinished task according to the current power;

[0007] if the target unmanned aerial vehicle has insufficient power, constructing a spatial constraint condition;

[0008] obtaining a candidate unmanned aerial vehicle set and a candidate task handover point set, the candidate unmanned aerial vehicle set comprising all candidate unmanned aerial vehicles, the candidate task handover point set comprising all candidate task handover points, and combining any candidate unmanned aerial vehicle with a candidate task handover point to determine whether the combination result satisfies the spatial constraint condition;

[0009] According to the judgment result, a first candidate set is obtained, the first candidate set including at least one candidate unmanned aerial vehicle and at least one candidate task handover point corresponding to each candidate unmanned aerial vehicle, and a linear scheduling function is constructed to screen a first replacement unmanned aerial vehicle and a first handover point corresponding to the first replacement unmanned aerial vehicle from the first candidate set according to the linear scheduling function.

[0010] In some embodiments, the step of obtaining the current power of the target unmanned aerial vehicle and predicting whether the target unmanned aerial vehicle will be insufficient in power when performing the unfinished task according to the current power includes:

[0011] The power prediction formula is constructed according to the following formula:

[0012] ;

[0013] wherein, the current power of the unmanned aerial vehicle, the power consumption per unit time of the unmanned aerial vehicle, the remaining time of the task, and the safety return power threshold;

[0014] It is judged whether the unmanned aerial vehicle satisfies the power prediction formula;

[0015] If the power prediction formula is satisfied, it is determined that the target unmanned aerial vehicle or the replacement unmanned aerial vehicle will not be insufficient in power when performing the unfinished task;

[0016] If the power prediction formula is not satisfied, it is determined that the target unmanned aerial vehicle or the replacement unmanned aerial vehicle will be insufficient in power when performing the unfinished task.

[0017] In some embodiments, if the target unmanned aerial vehicle is insufficient in power, the step of constructing a space constraint condition includes:

[0018] The space constraint condition is constructed according to the following formula:

[0019] ;

[0020] Expressions of the obtained candidate unmanned aerial vehicle set and candidate task handover point set are as follows:

[0021] ;

[0022] wherein, , , , the current position coordinates of the first candidate unmanned aerial vehicle, the second candidate unmanned aerial vehicle, the i-th candidate unmanned aerial vehicle, and the N-th candidate unmanned aerial vehicle in the candidate unmanned aerial vehicle set, the Euclidean space distance function, is a first preset distance threshold, N is a total number of candidate UAVs in the candidate UAV set, is a candidate UAV set, is a candidate task handover point set, , , , are position coordinates of the first, second, Kth, and jth task handover points respectively, and K is a total number of task handover points in the candidate task handover point set.

[0023] In some embodiments, the step of constructing a linear scheduling function to screen out a first replacement UAV and a first handover point corresponding to the first replacement UAV from the first candidate set according to the linear scheduling function comprises:

[0024] The linear scheduling function is constructed according to the following formula:

[0025] ;

[0026] wherein, is a scheduling priority coefficient, is a current position of the target UAV, is a jth candidate task handover point corresponding to the ith candidate UAV, is a current position of the ith candidate UAV, is a current power of the ith candidate UAV, is a unit time power consumption of the ith candidate UAV, is an estimated task time of the ith replacement UAV from the handover point to a task end point, , , are scheduling cost weights respectively;

[0027] The linear scheduling function is solved with the objective of minimizing the linear scheduling function, and a replacement UAV and a first handover point corresponding to the first replacement UAV are obtained according to a solution result.

[0028] In some embodiments, the step of screening out a replacement UAV and a first handover point corresponding to the first replacement UAV from the first candidate set according to the linear scheduling function further comprises:

[0029] predicting whether the first replacement UAV has insufficient power when performing an unfinished task;

[0030] if the first replacement UAV does not have insufficient power, completing scheduling relay of the first replacement UAV and the target UAV according to the first handover point.

[0031] In some embodiments, the step of predicting whether the first replacement drone has insufficient power when performing the unfinished task further comprises:

[0032] If the first replacement drone has insufficient power, the maximum executable distance is obtained according to the battery power of the first replacement drone, the task trajectory is segmented into at least two sub-tasks according to the maximum executable distance, and a new relay drone is matched for each sub-task in turn, specifically as follows:

[0033] The maximum executable distance calculation formula is:

[0034] ;

[0035] Wherein, is the maximum flight distance of the i-th first replacement drone, is the current drone power of the i-th first replacement drone, is the unit time power consumption of the i-th first replacement drone, is the flight speed of the i-th first replacement drone;

[0036] The first distance between the current position of the replacement drone and the current position of the replaced drone, and the second distance between the current position of the replaced drone and the end point of the sub-task are obtained with the current position of the replaced drone as the handover point, and the position of the end point of the sub-task is solved according to the following formula:

[0037] ;

[0038] Wherein, is the current position of the first replacement drone, is the current position of the target drone, is the end point of the sub-task of the first replacement drone;

[0039] The second replacement drone is repeatedly obtained with the first replacement drone as the target drone, and it is repeatedly judged whether the second replacement drone has insufficient power. If the power is insufficient, the end point of the sub-task of the second replacement drone is obtained, and the cycle is continuously repeated until the entire task is performed.

[0040] In some embodiments, the step of if the target drone has insufficient power further comprises:

[0041] The spatial Euclidean distance between the target drone and all available residence points is calculated, and the smallest spatial Euclidean distance is selected from all spatial Euclidean distances;

[0042] The residence point corresponding to the smallest spatial Euclidean distance is selected as the power supplement point of the target drone;

[0043] When multiple UAVs simultaneously perform power compensation at the same residence point, power distribution is performed according to the following formula:

[0044] ;

[0045] wherein, is the i-th UAV performing power compensation, is the maximum output power of the residence point, and n is the total number of UAVs that need to perform power compensation at the same residence point.

[0046] In a second aspect, the present application provides a UAV scheduling system, the system comprising:

[0047] a power prediction module configured to obtain the current power of a target UAV and predict whether the target UAV will run out of power when performing an unfinished task according to the current power;

[0048] a constraint condition construction module configured to construct a spatial constraint condition if the target UAV runs out of power;

[0049] a candidate UAV screening module configured to obtain a candidate UAV set and a candidate task handover point set, the candidate UAV set comprising all candidate UAVs, the candidate task handover point set comprising all candidate task handover points, and combine any candidate UAV with a candidate task handover point to determine whether the combination result satisfies the spatial constraint condition;

[0050] a scheduling function construction module configured to obtain a first candidate set according to the determination result, the first candidate set comprising at least one candidate UAV and at least one candidate task handover point corresponding to each candidate UAV, and construct a linear scheduling function to screen a first replacement UAV and a first handover point corresponding to the first replacement UAV from the first candidate set according to the linear scheduling function.

[0051] In a third aspect, the present application provides a readable storage medium storing one or more programs, which are executed by a processor to implement the above-mentioned UAV scheduling method.

[0052] In a fourth aspect, the present application provides an electronic device comprising a memory and a processor, wherein:

[0053] the memory is configured to store a computer program;

[0054] the processor is configured to execute the computer program stored on the memory to implement the above-mentioned UAV scheduling method.

[0055] Compared with the prior art, the present application has the following advantages:

[0056] This invention establishes a complete, efficient, and flexible drone scheduling system by predicting battery power, rationally selecting drones, and optimizing task scheduling, significantly improving the stability, safety, and efficiency of drone mission execution. Specifically, it first accurately obtains the target drone's current battery level and scientifically predicts the battery status when an unfinished task is completed, proactively mitigating risks such as mission interruptions and drone crashes due to insufficient battery power. When insufficient battery power is present, spatial constraints are constructed to clearly define the set of candidate drones and task handover points. A linear scheduling function is then used for scientific selection, forming a rational scheduling framework. After selecting replacement drones and handover points, the battery power of the replacement drones is further evaluated. If insufficient, the task trajectory is segmented and a new relay drone is matched, constructing a flexible task relay mechanism to ensure mission execution. Attached Figure Description

[0057] Figure 1 This is a flowchart of a drone scheduling method proposed in an embodiment of the present invention;

[0058] Figure 2 This is a schematic diagram of the structure of an unmanned aerial vehicle (UAV) scheduling system proposed in an embodiment of the present invention.

[0059] The following detailed description, in conjunction with the accompanying drawings, will further illustrate the present invention. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Unless otherwise defined, the technical or scientific terms used herein should have the ordinary meaning understood by those skilled in the art. The terms "comprising" and similar expressions used herein mean that the element or object preceding the word covers the element or object listed after the word and its equivalents, but does not exclude other elements or objects.

[0061] like Figure 1 As shown, an embodiment of the present invention proposes a drone scheduling method, which includes steps S101 to S104, wherein:

[0062] Step S101: Obtain the current battery level of the target drone and predict whether the target drone will run out of power when performing unfinished tasks based on the current battery level;

[0063] It should be noted that the detailed process for predicting whether the target drone has insufficient battery power in this step is as follows:

[0064] First, the power prediction formula is constructed according to the following formula:

[0065]

[0066] Wherein, is the current power of the UAV, is the power consumption per unit time of the UAV, is the remaining time of the task, and is the safe return power threshold;

[0067] Then, it is judged whether the UAV satisfies the power prediction formula;

[0068] If the power prediction formula is satisfied, it is determined that the target UAV or the replacement UAV does not have insufficient power when performing the unfinished task.

[0069] If the power prediction formula is not satisfied, it is determined that the target UAV or the replacement UAV has insufficient power when performing the unfinished task.

[0070] For the formula of the termination of the task in the traditional UAV task execution process, it should be pointed out that the existing method usually only makes a static determination based on the power threshold, without dynamically estimating the energy demand in combination with the power consumption and the remaining task time. In the case of high task density or strong power fluctuation, this method may terminate the task that can still be completed in advance, or delay the withdrawal to cause power consumption in the middle, thereby affecting the continuity of the inspection and the safety of the task. The product of the unit power consumption and the remaining task time is introduced to estimate the energy consumption demand, in combination with the current remaining power of the UAV and the safe threshold, to realize the real-time evaluation of the task feasibility. Compared with the traditional fixed threshold judgment, this method can adapt to the dynamic changes of energy consumption in different flight states. In addition, since the power consumption of the UAV in complex terrain and different wind conditions is significantly different, dynamic power prediction can more truly reflect the task continuity, and provide a stable and reliable basis for the triggering of the subsequent relay mechanism. This mechanism improves the adaptability and prediction ability of the system to complex task states, and reduces inefficient behaviors such as false stopping and early withdrawal.

[0071] Step S102: If the target UAV has insufficient power, a space constraint condition is constructed;

[0072] It should be noted that the space constraint condition is constructed according to the following formula:

[0073]

[0074] The expressions of the obtained candidate UAV set and candidate task handover point set are as follows:

[0075]

[0076] Wherein,​​​ 、 、 、 is the current position coordinates of the first, second, i-th, N-th candidate UAV in the candidate UAV set, is the Euclidean space distance function, is the first preset distance threshold, N is the total number of candidate UAVs in the candidate UAV set, is the candidate UAV set, is the candidate task handover point set, 、 、 、 are the position coordinates of the first, second, K-th, j-th task handover point, respectively, K is the total number of task handover points in the candidate task handover point set. The candidate task handover point set is a plurality of handover points selected from the task trajectory. Generally, the task trajectory is evenly divided into a plurality of segments, and then a plurality of task handover points are obtained to form the candidate task handover point set.

[0077] In summary, for the task handover problem in the above unmanned aerial vehicle scheduling process, it should be pointed out that the traditional method usually uses a single unmanned aerial vehicle to independently complete the entire inspection task, and lacks a relay mechanism. In long-distance or long-time operation, due to the limitation of battery capacity and flight range, it often leads to task interruption, frequent return, and difficulty in guaranteeing the continuity and completeness of the task. The present application first introduces a task relay mechanism between unmanned aerial vehicles. When the unmanned aerial vehicle currently performing the task predicts that it cannot complete the remaining task, the system automatically selects a relay node from the standby or energy-replenished unmanned aerial vehicles (candidate UAV set) to realize seamless handover and ensure the response efficiency of the relay.

[0078] Step S103: obtaining a candidate UAV set and a candidate task handover point set, the candidate UAV set including all candidate UAVs, and the candidate task handover point set including all candidate task handover points, combining any candidate UAV with a candidate task handover point to determine whether the combination result meets the spatial constraint condition;

[0079] Step S104: obtaining a first candidate set according to the determination result, the first candidate set including at least one standby UAV and at least one standby task handover point corresponding to each standby UAV, and constructing a linear scheduling function to select a first replacement UAV and a first handover point corresponding to the first replacement UAV from the first candidate set according to the linear scheduling function.

[0080] It should be pointed out that the linear scheduling function is constructed according to the following formula:

[0081] ;

[0082] wherein, is a scheduling priority coefficient, is a current position of the target UAV, is a jth candidate task handover point corresponding to the ith candidate UAV, is a current position of the ith candidate UAV, is a current power of the ith candidate UAV, is a unit time power consumption of the ith candidate UAV, is an expected task time of the ith substitute UAV from the handover point to the task end point, , , respectively are scheduling cost weights;

[0083] Then, a linear scheduling function is minimized to obtain a substitute UAV and a first handover point corresponding to the first substitute UAV according to a solving result. Further, the first substitute UAV and the first handover point are scheduled.

[0084] In summary, when a traditional UAV performs a task, the task is often completed by one UAV. Once the power is insufficient during the task, the UAV needs to return, and the task must be rescheduled, which leads to repeated coverage, time waste, and even task interruption. Based on this, the present application proposes a linear scheduling function. In a candidate relay node set, a UAV with the minimum total cost is selected as a relay node by sorting through spatial constraints and a cost function.

[0085] In addition, after the first substitute UAV goes to the first handover point and completes the task handover with the target UAV, the power may also be insufficient. Based on this, in some embodiments, after the substitute UAV and the first handover point corresponding to the first substitute UAV are screened from the first candidate set according to the linear scheduling function, it is further needed to predict whether the first substitute UAV has insufficient power when performing an unfinished task. If the first substitute UAV does not have insufficient power, the scheduling relay of the first substitute UAV and the target UAV is completed according to the first handover point.

[0086] If the first substitute UAV has insufficient power, the maximum executable distance is obtained according to the battery power of the first substitute UAV, the task trajectory is segmented by the maximum executable distance to form at least two subtasks, and a new relay UAV is matched for each subtask in turn, specifically as follows:

[0087] The maximum executable distance calculation formula is:

[0088] ;

[0089] wherein, a maximum flight distance of the ith first substitute UAV, a current UAV power of the ith first substitute UAV, a unit time power consumption of the ith first substitute UAV, a flight speed of the ith first substitute UAV;

[0090] a first distance between the current position of the substitute UAV and the current position of the replaced UAV, a second distance between the current position of the replaced UAV and the end point of the subtask, and the end point of the subtask is solved according to the following formula:

[0091] ;

[0092] wherein, a current position of the first substitute UAV, a current position of the target UAV, an end point of the subtask of the first substitute UAV;

[0093] the first substitute UAV is taken as the target UAV, the second substitute UAV is repeatedly obtained, and it is repeatedly judged whether the second substitute UAV is insufficient in power. If the second substitute UAV is insufficient in power, the end point of the subtask of the second substitute UAV is obtained, and the cycle is continuously repeated until the entire task is executed. Thus, the UAV relay of the entire task is completed.

[0094] In addition, in some embodiments, if it is detected that the target UAV is insufficient in power, the spatial Euclidean distances between the target UAV and all available residence points are calculated, and the smallest spatial Euclidean distance is selected from all the spatial Euclidean distances. Then, the residence point corresponding to the smallest spatial Euclidean distance is selected as the power supplement point of the target UAV. When multiple UAVs simultaneously supplement power at the same residence point, the power is allocated according to the following formula:

[0095] ;

[0096] wherein, the ith UAV for power supplement, a maximum output power of the residence point, and n is the total number of UAVs for power supplement at the same residence point.

[0097] In the scenario of multiple UAVs simultaneously residing in the energy supplement field, the traditional system often adopts a static allocation mode of fixed power output or first-come-first-serve, which fails to dynamically balance the energy demand between multiple nodes, and is prone to cause power waste, energy supplement delay, or the phenomenon of fighting for residence resources among UAVs. Based on this, by ensuring the balanced allocation of the output power of the residence point, the overall energy supplement fairness and utilization efficiency are improved, the coordinated and efficient energy supplement among multiple UAVs is realized, and the power supply adaptability of the system in the high-density state of the task is enhanced.

[0098] In summary, according to the UAV scheduling method described above, a complete, efficient and flexible UAV scheduling system is formed by predicting the power, reasonably selecting and optimizing the task scheduling, which greatly improves the stability, safety and efficiency of UAV task execution. Specifically, first, the current power of the target UAV is accurately obtained, and the power condition when the uncompleted task is executed is scientifically predicted, so as to avoid risks such as task interruption and UAV out-of-control crash caused by insufficient power in advance. When there is insufficient power, the spatial constraint condition is constructed to clearly define the candidate UAV and the task handover point set, and the linear scheduling function is combined to realize scientific selection and form a reasonable scheduling framework. After selecting the replacement UAV and the handover point, the power of the replacement UAV is further evaluated, and if it is insufficient, the task trajectory is segmented and a new relay UAV is matched to build a flexible task relay mechanism to ensure task execution.

[0099] As shown in Figure 2 An embodiment of the present application also provides a UAV scheduling system, which comprises:

[0100] The power prediction module 10 is configured to obtain the current power of the target UAV, and predict whether the target UAV has insufficient power when executing the uncompleted task according to the current power.

[0101] The constraint condition construction module 20 is configured to construct a spatial constraint condition if the target UAV has insufficient power.

[0102] The candidate UAV screening module 30 is configured to obtain a candidate UAV set and a candidate task handover point set, the candidate UAV set comprising all candidate UAVs, and the candidate task handover point set comprising all candidate task handover points, and to combine any candidate UAV and candidate task handover point to determine whether the combination result satisfies the spatial constraint condition.

[0103] The scheduling function construction module 40 is configured to obtain a first candidate set according to the determination result, the first candidate set comprising at least one candidate UAV and at least one candidate task handover point corresponding to each candidate UAV, and to construct a linear scheduling function to screen a first replacement UAV and a first handover point corresponding to the first replacement UAV from the first candidate set according to the linear scheduling function.

[0104] Further, in some embodiments, the system further comprises:

[0105] The relay screening module is configured to, if the first replacement UAV has insufficient power, acquire a maximum executable distance according to the battery power of the first replacement UAV, segment the task trajectory according to the maximum executable distance to form at least two sub-tasks, and sequentially match a new relay UAV for each sub-task, specifically as follows:

[0106] The maximum executable distance calculation formula is:

[0107] ;

[0108] Wherein, is the maximum flight distance of the i-th first replacement UAV, is the current UAV power of the i-th first replacement UAV, is the unit time power consumption of the i-th first replacement UAV, is the flight speed of the i-th first replacement UAV;

[0109] The first distance between the current position of the replacement UAV and the current position of the replaced UAV, and the second distance between the current position of the replaced UAV and the end point of the sub-task are acquired with the current position of the replaced UAV as the handover point, and the position of the end point of the sub-task is solved according to the following formula:

[0110] ;

[0111] Wherein, is the current position of the first replacement UAV, is the current position of the target UAV, is the end point of the sub-task of the first replacement UAV;

[0112] The second replacement UAV is repeatedly acquired with the first replacement UAV as the target UAV, and it is repeatedly judged whether the second replacement UAV has insufficient power. If the power is insufficient, the end point of the sub-task of the second replacement UAV is acquired, and the cycle is continuously repeated until the entire task is executed.

[0113] Further, in some embodiments, the system further comprises:

[0114] The Euclidean distance calculation module is configured to calculate the spatial Euclidean distance between the target UAV and all available residence points, and screen the minimum spatial Euclidean distance from all spatial Euclidean distances;

[0115] The residence point corresponding to the minimum spatial Euclidean distance is selected as the power compensation point of the target UAV;

[0116] When multiple UAVs simultaneously perform energy replenishment at the same residence point, power distribution is performed according to the following formula:

[0117] ;

[0118] wherein, is the ith UAV performing energy replenishment, is the maximum output power of the residence point, and n is the total number of UAVs performing energy replenishment at the same residence point.

[0119] Another aspect of the present application further provides a readable storage medium having one or more programs stored thereon, which programs, when executed by a processor, implement the above-described UAV scheduling method.

[0120] Another aspect of the present application further provides an electronic device comprising a memory and a processor, wherein the memory is configured to store a computer program, and the processor is configured to execute the computer program stored in the memory to implement the above-described UAV scheduling method.

[0121] Those skilled in the art can understand that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a list of executable instructions for implementing the logic function, which can be embodied in any computer readable medium for use by or in conjunction with an instruction execution system, apparatus or device, such as a computer-based system, a system including a processor or other system that can fetch and execute instructions from the instruction execution system, apparatus or device. For the purpose of the present description, the "computer readable medium" can be any device that can contain a storage, communication, propagation or transmission of a program for use by or in conjunction with an instruction execution system, apparatus or device, or in conjunction with these instruction execution systems, apparatus or devices.

[0122] More specific examples (non-exhaustive list) of the computer readable medium include the following: an electrical connection having one or more wires (electrical devices), a portable computer diskette (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CD ROM). In addition, the computer readable medium can even be paper or other suitable medium on which the program can be printed, as the program can be electronically obtained, for example, by optical scanning of the paper or other medium, followed by electronic conversion, interpretation or processing, if necessary, in other suitable manner, and then stored in a computer memory.

[0123] It should be understood that aspects of the application can be implemented in hardware, software, firmware or a combination of them. In the above embodiments, various steps or methods can be implemented in software or firmware which is stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any of the following technologies, known in the art, or a combination thereof, can be used: a discrete logic circuit having logic gates for implementing logic functions upon an data signals, an application specific integrated circuit having appropriate combinational logic gates, a programmable gate array (PGA), a field programmable gate array (FPGA), and / or the like.

[0124] While the embodiments of the application have been illustrated and described in detail, it will be readily apparent to those skilled in the art that various modifications and changes can be made to the embodiments without departing from the scope and spirit of the application as described in the claims. Moreover, the application described is not limited to the particular embodiments described herein but extends to other embodiments and variations thereof.

Claims

1. A method for scheduling unmanned aerial vehicles (UAVs), characterized in that, The method comprises: obtaining the current power of the target UAV and predicting whether the target UAV has insufficient power when performing the unfinished task according to the current power; if the target UAV has insufficient power, constructing a space constraint condition; obtaining a candidate UAV set and a candidate task handover point set, the candidate UAV set comprising all candidate UAVs, the candidate task handover point set comprising all candidate task handover points, combining any candidate UAV with a candidate task handover point to determine whether the combination result satisfies the space constraint condition; obtaining a first candidate set according to the determination result, the first candidate set comprising at least one selected UAV and at least one selected task handover point corresponding to each selected UAV, and constructing a linear scheduling function to screen a first replacement UAV and a first handover point corresponding to the first replacement UAV from the first candidate set according to the linear scheduling function. 2.The method of Claim 1, wherein, The step of obtaining the current power of the target UAV and predicting whether the target UAV has insufficient power when performing the unfinished task according to the current power comprises: constructing a power prediction formula according to the following formula: ； wherein, is the current power of the UAV, is the power consumption per unit time of the UAV, is the remaining time of the task, and is the safe return power threshold. determining whether the UAV satisfies the power prediction formula; if the power prediction formula is satisfied, determining that the target UAV or the replacement UAV does not have insufficient power when performing the unfinished task; if the power prediction formula is not satisfied, determining that the target UAV or the replacement UAV has insufficient power when performing the unfinished task. 3.The UAV dispatching method of claim 2, wherein, The step of constructing a space constraint condition if the target UAV has insufficient power comprises: constructing a space constraint condition according to the following formula: ； The expressions of the obtained candidate UAV set and the candidate task handover point set are as follows: ； wherein, , , , are the current position coordinates of the first, second, i-th, and N-th candidate UAV in the candidate UAV set, is a Euclidean space distance function, is a first preset distance threshold, and N is the total number of candidate UAVs in the candidate UAV set, is the candidate UAV set, is the candidate task handover point set, , , , are the position coordinates of the first, second, K-th, and j-th task handover point, respectively, and K is the total number of task handover points in the candidate task handover point set.

4. The method of claim 3, wherein, The step of constructing a linear scheduling function to screen a first replacement UAV and a first handover point corresponding to the first replacement UAV from the first candidate set according to the linear scheduling function comprises: constructing a linear scheduling function according to the following formula: ； wherein, is a scheduling priority coefficient, is a current position of the target UAV, is a jth candidate task handover point corresponding to the ith candidate UAV, is a current position of the ith candidate UAV, is a current power of the ith candidate UAV, is a unit time power consumption of the ith candidate UAV, is an estimated task time of the ith substitute UAV from the handover point to the task end point, , , are scheduling cost weights, respectively. solving the linear scheduling function with the goal of minimizing the linear scheduling function, and obtaining a replacement UAV and a first handover point corresponding to the first replacement UAV according to the solving result.

5. The method of claim 4, wherein, The step of screening a replacement UAV and a first handover point corresponding to the first replacement UAV from the first candidate set according to the linear scheduling function further comprises: predicting whether the first replacement UAV has insufficient power when performing the unfinished task; if the first replacement UAV does not have insufficient power, completing the scheduling relay of the first replacement UAV and the target UAV according to the first handover point. 6.The UAV dispatching method of claim 5, wherein, The step of predicting whether the first replacement UAV has insufficient power when performing the unfinished task further comprises: if the first replacement UAV has insufficient power, obtaining a maximum executable distance according to the battery power of the first replacement UAV, segmenting the task trajectory according to the maximum executable distance to form at least two sub-tasks, and sequentially matching a new relay UAV for each sub-task, specifically as follows: The maximum executable distance calculation formula is: ； wherein, is a maximum flight distance of the i-th first replacement drone, is a current drone power of the i-th first replacement drone, is a power consumption per unit time of the i-th first replacement drone, is a flight speed of the i-th first replacement drone; The first distance between the current position of the replacement UAV and the current position of the replaced UAV, and the second distance between the current position of the replaced UAV and the sub-task end point are obtained, and the position of the sub-task end point is solved according to the following formula: ； wherein, is a current position of the first replacement drone, is a current position of the target drone, is a sub-task end point of the first replacement drone; The first replacement UAV is taken as a target UAV, the second replacement UAV is repeatedly obtained, and it is repeatedly judged whether the second replacement UAV has insufficient power. If the second replacement UAV has insufficient power, the sub-task end point of the second replacement UAV is obtained, and the cycle is continuously repeated until the entire task is completed.

7. The UAV dispatching method of claim 6, wherein, The step of determining whether the target UAV has insufficient power further comprises: calculating the spatial Euclidean distance between the target UAV and all available residence points, and screening the minimum spatial Euclidean distance from all spatial Euclidean distances; selecting the residence point corresponding to the minimum spatial Euclidean distance as the power compensation point of the target UAV; When multiple UAVs simultaneously compensate power at the same residence point, power allocation is performed according to the following formula: ； wherein, is the ith drone that needs to be re-energized, is the maximum output power of the residence point, and n is the total number of drones that need to be re-energized at the same residence point.

8. A drone dispatch system, comprising: The system comprises: a power prediction module configured to obtain the current power of the target UAV, and predict whether the target UAV has insufficient power when performing the unfinished task according to the current power; a constraint condition construction module configured to construct a spatial constraint condition if the target UAV has insufficient power; a candidate UAV screening module configured to obtain a candidate UAV set and a candidate task handover point set, the candidate UAV set comprising all candidate UAVs, and the candidate task handover point set comprising all candidate task handover points, and to combine any candidate UAV and a candidate task handover point to determine whether the combination result satisfies the spatial constraint condition; a scheduling function construction module configured to obtain a first candidate set according to the determination result, the first candidate set comprising at least one selected UAV and at least one selected task handover point corresponding to each selected UAV, and to construct a linear scheduling function to screen a first replacement UAV and a first handover point corresponding to the first replacement UAV from the first candidate set according to the linear scheduling function.

9. A readable storage medium, characterized by, The readable storage medium stores one or more programs, which are executed by the processor to implement the UAV scheduling method according to any one of claims 1-7.

10. An electronic device, comprising: The electronic device comprises a memory and a processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer programs stored on the memory to implement the UAV scheduling method according to any one of claims 1-7. The electronic device comprises a memory and a processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer programs stored on the memory to implement the UAV scheduling method according to any one of claims 1-7.

Images