An unmanned aerial vehicle adaptive scheduling method, system, device and storage medium

Abstract

This application discloses an adaptive scheduling method, system, device, and storage medium for unmanned aerial vehicles (UAVs). The method includes: acquiring task type, task execution time, target task weight set, environmental parameters, and historical success rate factor; inputting the environmental parameters into a preset function to obtain an environmental safety factor; performing an execution suitability assessment based on the corresponding weight values ​​in the target task weight set, the environmental safety factor, and the historical success rate factor to obtain a suitability assessment value; and scheduling the UAV based on the flight path corresponding to the task execution time and task type when the suitability assessment value meets preset task execution conditions. This improves the accuracy of the suitability assessment and fully ensures the effectiveness of the UAV in executing tasks.

Description

Technical Field

[0001] This application relates to the field of non-electrical variable control, and more particularly to an adaptive scheduling method, system, device, and storage medium for unmanned aerial vehicles (UAVs). Background Technology

[0002] With the deep integration and rapid iteration of the Internet of Things, artificial intelligence, avionics, and communication technologies, drone technology has entered a stage of explosive development in industrial and sectoral applications. Leveraging its core advantages of mobility, ease of deployment, cost control, and the ability to overcome the limitations of human labor, its application boundaries continue to expand. It has widely penetrated diverse industrial fields such as photovoltaic inspection, power line inspection, surveying and exploration, disaster relief, agricultural plant protection, urban security, logistics and distribution, and environmental monitoring, becoming a key piece of equipment for driving digital transformation across industries, improving operational efficiency, and reducing operational risks.

[0003] In related technologies, during drone scheduling, users typically pre-set fixed task execution times. The system issues the task at each scheduled execution time, or it collects a single environmental parameter and compares it with a corresponding preset threshold. For example, it collects the current wind speed and compares it with a preset wind speed threshold. If the current wind speed exceeds the threshold, an error is reported; if the current wind speed is less than the threshold, drone scheduling is initiated immediately. However, scheduling drones through environmental parameter comparison or setting fixed task execution times cannot guarantee the effectiveness of drone flight missions. Summary of the Invention

[0004] This application provides an adaptive scheduling method, system, device, and storage medium for unmanned aerial vehicles (UAVs). It addresses the problem that existing methods of comparing environmental parameters or setting fixed task execution times cannot guarantee the effectiveness of UAV flight missions. The method utilizes environmental parameters, the weight values ​​of various types of parameters within the environmental parameters, and historical success rate factors to jointly assess suitability. By comprehensively considering the impact of different factors on suitability assessment, the accuracy of suitability assessment is improved. Based on the suitability assessment value, it determines whether the estimated task execution time can effectively complete the UAV flight mission. If the suitability meets the preset task execution conditions, the UAV is scheduled at the task execution time, ensuring it operates on the corresponding route on time, thus fully guaranteeing the effectiveness of the UAV flight mission.

[0005] In a first aspect, embodiments of this application provide an adaptive scheduling method for unmanned aerial vehicles (UAVs), comprising:

[0006] Obtain the task type, task execution time, target task weight set, environmental parameters, and historical success rate factor; input the environmental parameters into a preset function to obtain the environmental safety factor.

[0007] An execution suitability assessment is performed based on the corresponding weight values ​​in the target task weight set, the environmental safety factor, and the historical success rate factor to obtain a suitability assessment value.

[0008] If the suitability assessment value meets the preset task execution conditions, the UAV is scheduled based on the task execution time and the flight route corresponding to the task type.

[0009] Optionally, the preset functions include wind speed safety factor function, rainfall safety factor function, visibility safety factor function, temperature safety factor function, light intensity factor function, environmental clarity factor function, and shadow penalty factor function. The environmental parameters include wind speed, rainfall, visibility, temperature, solar radiation intensity, cloud cover, air quality index, and solar altitude angle.

[0010] Optionally, the step of inputting the environmental parameters into a preset function to obtain the environmental safety factor includes:

[0011] The wind speed is input into the wind speed safety factor function to obtain the wind speed safety factor; the rainfall is input into the rainfall safety factor function to obtain the rainfall safety factor; the visibility is input into the visibility safety factor function to obtain the visibility safety factor; and the temperature is input into the temperature safety factor function to obtain the temperature safety factor.

[0012] The solar radiation intensity and cloud cover are input into the light intensity factor function to obtain the light intensity factor. The visibility and air quality index are input into the environmental clarity factor function to obtain the environmental clarity factor. The solar altitude angle is input into the shadow penalty factor function to obtain the shadow penalty factor.

[0013] Optionally, the execution suitability assessment based on the corresponding weight values ​​in the target task weight set, the environmental safety factor, and the historical success rate factor includes:

[0014] The flight safety probability is calculated based on the wind speed safety factor, the rainfall safety factor, the visibility safety factor, and the temperature safety factor.

[0015] The expected data quality value is calculated based on the light intensity factor, the environmental clarity factor, the shadow penalty factor, and the corresponding weight values ​​in the target task weight set;

[0016] The data quality weight value and the expected data quality value in the target task weight set are weighted to obtain a first weighted result. The historical success rate weight value and the success rate factor in the target task weight set are weighted to obtain a second weighted result. An execution suitability assessment is performed based on the flight safety probability, the first weighted result, and the second weighted result.

[0017] Optionally, after obtaining the suitability assessment value, the method further includes:

[0018] If the suitability assessment value does not meet the preset task execution conditions, the time range consisting of the task execution time and the preset re-flight time threshold is determined as the target time range, which includes multiple time windows.

[0019] The target time window for each time window is determined based on a preset supplementary flight prediction function, and the UAV is scheduled based on the target time window and the flight path corresponding to the task type.

[0020] Optionally, the supplementary flight prediction function includes a suitability function, a delay penalty function, a resource conflict cost function, and a time window filtering function;

[0021] Accordingly, determining the target time window for each time window based on the preset supplementary flight prediction function includes:

[0022] The future suitability value of each time window is calculated based on the suitability function, the delay penalty value of each time window is determined based on the delay penalty function, and the resource conflict value of each time window is determined based on the resource conflict cost function.

[0023] The target suitability value for the corresponding time window is determined based on the future suitability value, the delay penalty value, and the resource conflict value.

[0024] The target suitability values ​​corresponding to each time window are compared based on the time window filtering function. The maximum target suitability value is determined based on the comparison results, and the target time window corresponding to the maximum target suitability value is output.

[0025] Optionally, after scheduling the drone, the method further includes:

[0026] Monitor the mission execution status of the UAV; if the mission execution status is in a failed state, obtain an initial mission weight set; and adjust the corresponding weight values ​​in the initial mission weight set in reverse according to the target mission weight set.

[0027] If the task execution status is successful, an initial task weight set is obtained, and the corresponding weight values ​​in the initial task weight set are positively adjusted according to the target task weight set.

[0028] In a second aspect, embodiments of this application provide an adaptive scheduling system for unmanned aerial vehicles (UAVs), comprising:

[0029] The data acquisition module is used to acquire task type, task execution time, target task weight set, environmental parameters, and historical success rate factors.

[0030] An environmental safety factor determination module is used to input the environmental parameters into a preset function to obtain the environmental safety factor;

[0031] The suitability assessment module is used to perform an execution suitability assessment based on the corresponding weight values ​​in the target task weight set, the environmental safety factor, and the historical success rate factor, and obtain a suitability assessment value.

[0032] The drone scheduling module is used to schedule the drone based on the task execution time and the flight route corresponding to the task type, provided that the suitability assessment value meets the preset task execution conditions.

[0033] In a third aspect, embodiments of this application provide an electronic device, the device comprising: one or more processors; and a storage device configured to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the UAV adaptive scheduling method described in the first aspect.

[0034] In a fourth aspect, embodiments of this application provide a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the UAV adaptive scheduling method as described in the first aspect.

[0035] This application embodiment obtains the task type, task execution time, target task weight set, environmental parameters, and historical success rate factor. The environmental parameters are input into a preset function to obtain an environmental safety factor. Based on the corresponding weight values ​​in the target task weight set, the environmental safety factor, and the historical success rate factor, an execution suitability assessment is performed to obtain a suitability assessment value. If the suitability assessment value meets the preset task execution conditions, the UAV is scheduled based on the task execution time and the flight path corresponding to the task type. In the above scheme, suitability assessment is performed jointly using environmental parameters, the weight values ​​corresponding to each type of parameter in the environmental parameters, and the historical success rate factor. This comprehensively considers the impact of different factors on the suitability assessment, improving the accuracy of the suitability assessment. Based on the suitability assessment value, it is determined whether the expected task execution time can effectively complete the UAV's flight mission. If the suitability meets the preset task execution conditions, the UAV is scheduled during the task execution time, ensuring it operates on the corresponding flight path on time, thus fully guaranteeing the effectiveness of the UAV flight mission. Attached Figure Description

[0036] Figure 1 This is a flowchart of an adaptive scheduling method for unmanned aerial vehicles (UAVs) provided in an embodiment of this application;

[0037] Figure 2 This is a flowchart of an environmental safety factor calculation method provided in an embodiment of this application;

[0038] Figure 3 This is a flowchart of an execution suitability assessment method provided in an embodiment of this application;

[0039] Figure 4 This is a flowchart of another UAV adaptive scheduling method provided in the embodiments of this application;

[0040] Figure 5 This is a flowchart of a method for determining a target time window provided in an embodiment of this application;

[0041] Figure 6 This is a flowchart of an initial task weight set adjustment method provided in an embodiment of this application;

[0042] Figure 7 This is a schematic diagram of the structure of an adaptive scheduling system for unmanned aerial vehicles (UAVs) provided in an embodiment of this application;

[0043] Figure 8 This is a schematic diagram of the structure of an adaptive scheduling device for unmanned aerial vehicles provided in an embodiment of this application. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of this application clearer, specific embodiments of this application will be described in further detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely for explaining this application and not for limiting it. It should also be noted that, for ease of description, only the parts relevant to this application are shown in the drawings, not all of them. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe operations (or steps) as sequential processes, many of these operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but may also have additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0045] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0046] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0047] The following description, in conjunction with the accompanying drawings, details the UAV adaptive scheduling method, system, device, and medium provided in this application through specific embodiments and application scenarios.

[0048] The UAV adaptive scheduling method provided in this application is used in scenarios where UAVs are used for inspection. Based on the above application scenario, it can be understood that the executing entity of each step can be a computer device. This computer device refers to any electronic device with data computing, processing, and storage capabilities, such as mobile phones, PCs (Personal Computers), tablet computers, and other terminal devices, or it can be a server or other devices. This application does not limit the scope of the method.

[0049] Figure 1 This is a flowchart of an adaptive scheduling method for unmanned aerial vehicles (UAVs) provided in an embodiment of this application, such as... Figure 1 As shown, it includes:

[0050] Step S101: Obtain the task type, task execution time, target task weight set, environmental parameters, and historical success rate factor. Input the environmental parameters into a preset function to obtain the environmental safety factor.

[0051] The task type refers to the specific type of operation the drone needs to perform, and is the core basis for determining the scheduling strategy, flight path planning, and parameter weight configuration. This task type can include: photovoltaic inspection, power line inspection, surveying and mapping, disaster relief, agricultural plant protection, etc. The task execution time refers to the pre-planned specific time point or time interval for the drone to start its operation. The target task weight set refers to a parameter matrix set for a specific task type that reflects the importance of various influencing factors, such as... Environmental parameters can refer to various environmental data that affect the flight safety and mission execution effectiveness of UAVs. Historical success rate factors can refer to the statistically derived mission success probability value based on historical execution records of this mission type under similar time and environmental conditions. Preset functions can refer to a set of defined mathematical models used to convert environmental parameters into standardized evaluation indicators. Environmental safety factors can refer to a set of standardized, quantifiable environmental adaptability evaluation indicators obtained by inputting various environmental parameters into corresponding preset functions.

[0052] In one embodiment, the system receives the user's input of the task type and task execution time in real time. Based on a pre-set mapping relationship between task types and influencing factor weight sets, it determines the target task weight set corresponding to that task type. Simultaneously, it collects environmental parameters corresponding to the task execution time and the latest historical success rate factor from historical records via a data acquisition module. If the time difference between the task execution time and the current time is small, the environmental parameters corresponding to the current time can be directly collected via the data acquisition module. After obtaining the environmental parameters, they are input into a preset function to calculate the corresponding environmental safety factor.

[0053] Optionally, the preset functions include wind speed safety factor function, rainfall safety factor function, visibility safety factor function, temperature safety factor function, light intensity factor function, environmental clarity factor function, and shadow penalty factor function. Environmental parameters include wind speed, rainfall, visibility, temperature, solar radiation intensity, cloud cover, air quality index, and solar altitude angle.

[0054] Among them, the wind speed safety factor function refers to a mathematical model used to quantify the impact of wind speed on UAV flight safety. The rainfall safety factor function refers to a mathematical model used to quantify the impact of rainfall on UAV flight safety. The visibility safety factor function refers to a mathematical model used to quantify the impact of visibility on UAV flight safety. The temperature safety factor function refers to a mathematical model used to quantify the impact of ambient temperature on UAV flight safety. The light intensity factor function refers to a mathematical model used to quantify the impact of lighting conditions on the effectiveness of mission data acquisition. The environmental clarity factor function refers to a mathematical model used to quantify the impact of air cleanliness and visibility on the clarity of data acquisition. The shadow penalty factor function refers to a mathematical model used to quantify the impact of shadows caused by the solar altitude angle on the effectiveness of data acquisition. Wind speed refers to the speed of air movement. Rainfall refers to the depth of rainwater falling to the ground within a certain period of time. Visibility refers to the maximum horizontal distance at which a target can be clearly seen by the human eye under the given weather conditions. Solar radiation intensity refers to the solar radiation energy vertically projected onto a unit area per unit time. Cloud cover refers to the proportion of the sky obscured by clouds. The Air Quality Index (AQI) is a dimensionless index used to quantitatively describe air quality, ranging from 0 to 500. A higher AQI indicates more severe air pollution. Solar altitude angle refers to the angle between sunlight and the horizon (ranging from -90° to 90°, with the angle being largest at noon and smallest at dawn / dusk).

[0055] Step S102: Based on the corresponding weight values ​​in the target task weight set, environmental safety factors, and historical success rate factors, conduct an execution suitability assessment to obtain a suitability assessment value.

[0056] Among them, the execution suitability assessment value can be a core dynamic indicator used to quantitatively determine whether the task execution time is suitable for executing the target task.

[0057] In one embodiment, both the environmental safety factor in the current environment and the historical success rate factor in similar historical environments affect the task execution suitability assessment result. However, the degree of influence of the environmental safety factor and the historical success rate factor on the assessment result differs. Therefore, firstly, a first weight value representing the degree of influence of the safety factor on the suitability assessment value and a second weight value representing the degree of influence of the historical success rate factor on the suitability assessment value are determined in the target task weight set. The environmental safety factor and the historical success rate factor are then weighted and calculated based on the first and second assessment values ​​to obtain the suitability assessment value.

[0058] Step S103: If the suitability assessment value meets the preset task execution conditions, the UAV is scheduled based on the task execution time and the flight route corresponding to the task type.

[0059] Among them, the preset task execution conditions can refer to the pre-set rules or threshold standards used to determine whether the task can be executed as originally planned. The flight path can refer to the UAV flight path pre-planned based on factors such as the requirements of the task type, the geographical environment of the operation area, and the location of the task target.

[0060] In one embodiment, the suitability assessment value is compared with a preset standard threshold for executable tasks. If the suitability assessment value is greater than or equal to the preset standard threshold for executable tasks, the preset task execution conditions are met. Based on the preset mapping relationship between task types and flight routes, the flight route corresponding to the current task type is determined, and the UAV is initiated at the task execution time. The flight path of the UAV is controlled based on the flight route.

[0061] In this embodiment, suitability assessment can be performed by combining environmental parameters, the weight values ​​of each type of parameter in the environmental parameters, and the historical success rate factor. By comprehensively considering the impact of different factors on suitability assessment, the accuracy of suitability assessment is improved. Based on the suitability assessment value, it is determined whether the expected task execution time can effectively complete the UAV flight mission. If the suitability meets the preset task execution conditions, the UAV is scheduled during the task execution time so that it can work on time according to the corresponding route, thus fully ensuring the effectiveness of the UAV flight mission.

[0062] Figure 2 This is a flowchart of an environmental safety factor calculation method provided in an embodiment of this application, such as... Figure 2 As shown, it includes:

[0063] Step S1011: Input the wind speed into the wind speed safety factor function to obtain the wind speed safety factor; input the rainfall into the rainfall safety factor function to obtain the rainfall safety factor; input the visibility into the visibility safety factor function to obtain the visibility safety factor; input the temperature into the temperature safety factor function to obtain the temperature safety factor.

[0064] Among them, the wind speed safety factor refers to a standardized assessment indicator (range 0-1) used to quantify the impact of actual wind speed on drone flight safety. The rainfall safety factor refers to a standardized assessment indicator (range 0-1) used to quantify the impact of actual rainfall on drone flight safety. The visibility safety factor refers to a standardized assessment indicator (range 0-1) used to quantify the impact of actual visibility on drone flight safety, its influence on obstacle avoidance and visual navigation. The temperature safety factor refers to a standardized assessment indicator (range 0-1) used to quantify the impact of ambient temperature on the operational safety of drone equipment, affecting drone battery temperature.

[0065] In one embodiment, the wind speed is input into a wind speed safety factor function to obtain the wind speed safety factor, wherein the wind speed safety factor function... for:

[0066]

[0067] in, To ensure the maximum wind speed resistance of the drone, The wind speed collected by the data acquisition module, when Approaching hour, Approaching 0.5, far exceeding hour, Approaching 0.

[0068] The rainfall amount is input into the rainfall safety factor function to obtain the rainfall safety factor, where the rainfall safety factor function... for:

[0069]

[0070] in, The maximum tolerable rainfall intensity is represented by r, where r is the rainfall amount collected by the data acquisition module.

[0071] The visibility is input into the visibility safety factor function to obtain the visibility safety factor, where the visibility safety factor function... for:

[0072]

[0073] in, The minimum visibility required for the mission. This refers to the visibility data collected by the data acquisition module.

[0074] The temperature is input into the temperature safety factor function to obtain the temperature safety factor, where the temperature safety factor function... for:

[0075]

[0076] in, and These are the highest and lowest temperatures that the drone can withstand. This is the median temperature value; the closer the temperature is to the extreme temperature, the better. The closer it gets to 0.

[0077] Step S1012: Input solar radiation intensity and cloud cover into the light intensity factor function to obtain the light intensity factor; input visibility and air quality index into the environmental clarity factor function to obtain the environmental clarity factor; input solar altitude angle into the shadow penalty factor function to obtain the shadow penalty factor.

[0078] Among them, the light intensity factor refers to a standardized evaluation index (range 0-1) used to quantify the impact of current lighting conditions on the effectiveness of mission data acquisition. The environmental clarity factor refers to a standardized evaluation index (range 0-1) used to quantify the impact of air cleanliness and visibility on the clarity of mission data acquisition. The shadow penalty factor refers to a standardized evaluation index (range 0-1) used to quantify the impact of shadows caused by the solar altitude angle on the effectiveness of mission data acquisition.

[0079] In one embodiment, solar radiation intensity and cloud cover are input into a light intensity factor function to obtain a light intensity factor, wherein the light intensity factor function... for:

[0080]

[0081] in, Let be the actual solar radiation intensity at time t (unit: W / m²). The cloud cover at time t (unit: percentage, value range 0-10). The maximum effective solar radiation intensity corresponding to the mission type. This is a geographical correction factor for the mission execution location (range: 0.8-1.2).

[0082] Visibility and air quality index are input into the environmental clarity factor function to obtain the environmental clarity factor. The environmental clarity factor function... for:

[0083]

[0084] in, To control the quality index, This is the visibility safety factor.

[0085] Inputting the solar altitude angle into the shadow penalty factor function yields the shadow penalty factor, where the shadow penalty factor function... for:

[0086]

[0087] Among them, solar altitude angle A penalty is incurred when the sun's altitude angle is too low (such as in the early morning or evening).

[0088] In this embodiment, a scientific and reasonable mathematical model and weight allocation mechanism can be used to achieve accurate quantitative evaluation of multi-dimensional environmental parameters, providing reliable data support for UAV adaptive scheduling. It can also improve task execution efficiency while providing strong protection for the safety and stability of UAVs in diverse application scenarios.

[0089] Figure 3 This is a flowchart of an implementation suitability assessment method provided in an embodiment of this application, such as... Figure 3 As shown, it includes:

[0090] Step S1021: Calculate the flight safety probability based on wind speed safety factor, rainfall safety factor, visibility safety factor and temperature safety factor.

[0091] Among them, flight safety probability can refer to the core probability index (with a value range of 0-1) used to quantify the safety of UAV flight under current environmental conditions.

[0092] In one embodiment, the wind speed safety factor, rainfall safety factor, visibility safety factor, and temperature safety factor can be cumulatively calculated to obtain the flight safety probability. For example, the formula for calculating the flight safety probability is:

[0093]

[0094] Step S1022: Calculate the expected data quality value based on the light intensity factor, environmental clarity factor, shadow penalty factor, and the corresponding weight values ​​in the target task weight set.

[0095] The expected data quality value refers to the core evaluation indicator used to quantify the effectiveness and reliability of task data acquisition under current environmental conditions. It is primarily affected by light intensity and environmental clarity. If the task type is identified as i and the target task execution time is t, then the expected data quality value can be expressed as: .

[0096] In one embodiment, the light intensity factor, ambient clarity factor, and shadow penalty factor are weighted and calculated based on the light intensity weight, ambient clarity weight, and shadow penalty weight in the target task weight set to obtain the expected data quality value. The formula for calculating the expected data quality value is as follows:

[0097]

[0098] in, The light intensity factor is derived from the coordinates of the execution location of task i, the solar radiation intensity at time t, and the cloud cover. Environmental clarity factor, along with visibility and air quality index (AQI). (Negative correlation) This is a shadow penalty factor that incurs a penalty when the sun's altitude angle is too low, such as in the early morning or evening. Indicates the weight of light intensity. Indicates the environmental clarity weight. This indicates the shadow penalty weight.

[0099] Step S1023: Perform a weighted calculation on the data quality weight value and the expected data quality value in the target task weight set to obtain a first weighted result; perform a weighted calculation on the historical success rate weight value and the historical success rate factor in the target task weight set to obtain a second weighted result; and conduct an execution suitability assessment based on the flight safety probability, the first weighted result, and the second weighted result.

[0100] The first weighted result can be an indicator that quantifies the contribution of data quality to the suitability assessment. The second weighted result can be an indicator that quantifies the contribution of historical execution experience to the suitability assessment. The data quality weight value can be a parameter used to quantify the importance of the data quality dimension in the overall suitability assessment. The historical success rate weight value can be a parameter used to quantify the importance of historical execution experience in the overall suitability assessment.

[0101] In one embodiment, the product of the data quality weight value and the expected data quality value is determined as the first weighted result, and the product of the historical success rate weight value and the historical success rate factor is determined as the second weighted result. The first and second weighted results are then summed, and the product of this summation and the calculated flight safety probability is determined as the execution fitness assessment value. When mission type i performs a flight mission within time window t, the formula for calculating the execution fitness assessment value is:

[0102]

[0103] in, This represents the flight safety probability when mission type i performs a flight mission within a time window t. This represents the data quality weight value. This represents the expected data quality value for mission type i when performing a flight mission within time window t. This represents the weighted value of historical success rate. This represents the historical success rate factor when historical mission type i performs a flight mission within the time window t.

[0104] In this embodiment, by comprehensively considering the impact of flight safety probability, expected data quality, and historical success rate factors on suitability assessment, a comprehensive evaluation of the suitability of UAV mission execution is achieved. This effectively enhances the adaptability of UAVs in complex environments, ensuring the efficiency and safety of mission execution.

[0105] Figure 4 This is a flowchart of another UAV adaptive scheduling method provided in the embodiments of this application, such as... Figure 4 As shown, it includes:

[0106] Step S201: Obtain the task type, task execution time, target task weight set, environmental parameters, and historical success rate factor. Input the environmental parameters into a preset function to obtain the environmental safety factor.

[0107] Step S202: Based on the corresponding weight values ​​in the target task weight set, environmental safety factors, and historical success rate factors, conduct an execution suitability assessment to obtain a suitability assessment value.

[0108] Step S203: If the suitability assessment value does not meet the preset task execution conditions, the time range consisting of the task execution time and the preset supplementary flight time threshold is determined as the target time range, which includes multiple time windows.

[0109] The preset re-flight time threshold refers to a pre-defined time boundary value, which can be used to limit the maximum re-flight interval, such as 120 minutes. The target time range refers to the search interval for the UAV's re-flight time, providing a clear range for selecting the optimal re-flight window. The task execution time and the preset re-flight time threshold are the two boundaries of the target time range, where the task execution time is less than the preset re-flight time threshold. A time window can refer to a discrete time segment with a fixed duration within the target time range, such as 15 minutes per segment.

[0110] In one embodiment, when the suitability assessment value is less than a preset standard threshold for executable tasks, the time range consisting of the task execution time and a preset replacement flight time threshold is determined as the target time range, and this target time range is divided into multiple time segments according to a preset fixed duration. For example, the target time range is 10:00-13:00, which can be divided into 15-minute segments to obtain multiple time windows such as 10:00-10:15, 10:15-10:30...12:45-13:00, each window serving as an independent candidate for replacement flight.

[0111] Step S204: Determine the target time window for each time window based on the preset supplementary flight prediction function, and schedule the UAV based on the target time window and the flight route corresponding to the task type.

[0112] The supplementary flight prediction function refers to the core algorithm set in the UAV adaptive scheduling supplementary flight decision-making stage. It is used to perform multi-dimensional evaluation of each time window within the target time range and ultimately select the optimal supplementary flight timing. The target time window can refer to the optimal supplementary flight execution timing selected from multiple discrete time windows within the target time range.

[0113] In one embodiment, environmental parameters corresponding to each time window are obtained, and the corresponding environmental safety factor, historical success rate factor, and various parameters in the task weight set corresponding to similar historical time windows and similar environments are calculated. The suitability score corresponding to each determined time window is predicted using the same method as the steps described above. The time window with the highest suitability score is determined as the target time window. The UAV is started at the start time of the target time window, and the flight path of the UAV is controlled based on the flight route corresponding to the task type.

[0114] In this embodiment, by introducing a flight completion prediction function and a dynamic time window partitioning mechanism, the problem of mission execution failure caused by environmental changes or unforeseen circumstances is effectively solved, providing a reliable guarantee for the flexible scheduling of UAVs in diverse scenarios. It can minimize the waste of time and resources while ensuring mission completion quality, improving the overall operating efficiency of the UAV system and increasing the flexibility of UAV scheduling time.

[0115] Optionally, the flight prediction function may include a suitability function, a delay penalty function, a resource conflict cost function, and a time window filtering function.

[0116] The suitability function can be defined as follows: The suitability function is the basic prediction function used to calculate the future suitability value for each time window within the target time range. The delay penalty function is the function used to quantify the delay cost of the make-up flight time relative to the original mission execution time, outputting a "delay penalty value". The resource conflict cost function is the function used to detect resource occupancy and route conflicts in each make-up flight time window, outputting a "resource conflict value". The time window selection function is the final decision function used to integrate the outputs of the above three functions.

[0117] Figure 5 This is a flowchart of a method for determining a target time window provided in an embodiment of this application, such as... Figure 5 As shown, it includes:

[0118] Step S2041: Calculate the future fitness value for each time window based on the fitness function, determine the delay penalty value for each time window based on the delay penalty function, and determine the resource conflict value for each time window based on the resource conflict cost function.

[0119] Step S2042: Determine the target suitability value for the corresponding time window based on the future suitability value, the delay penalty value, and the resource conflict value.

[0120] Step S2043: Compare the target suitability values ​​corresponding to each time window based on the time window filtering function, determine the maximum target suitability value based on the comparison results, and output the target time window corresponding to the maximum target suitability value.

[0121] Among these, the future suitability value refers to a core quantitative indicator used to predict the suitability of performing a supplementary flight mission within a specific time window within the target time range. The delay penalty value refers to a core indicator used to quantify the cost of delay in supplementary flight time relative to the original mission execution time. The resource conflict value refers to a core indicator used to quantify the degree of conflict between the supplementary flight time window and existing resources, such as drone conflicts, airspace conflicts, and mission priority conflicts. The target suitability value can be considered a core quantitative indicator used to quantify the suitability of performing supplementary flight missions within each time window within the target time range.

[0122] In one embodiment, the future fitness value for each time window is calculated based on a fitness function, which can be expressed as: Where i represents the task type and t' represents the corresponding time window. The delay penalty value for each time window is determined based on the delay penalty function, which can be expressed as: ,in, This represents the time difference between each corresponding time window and the task execution time. The larger the time difference, the longer the task is delayed, and the more severe the corresponding penalty. The resource conflict value for each time window is determined based on the resource conflict cost function, which can be expressed as: ,in, This indicates the corresponding time window; if other high-priority tasks are already in progress at time t', The value tends towards infinity. Based on the future suitability value, the delay penalty value, and the resource conflict value, the target suitability value for the corresponding time window is determined. For example, the formula for calculating the target suitability value for each time window is:

[0123] Target suitability value =

[0124] The target suitability values ​​corresponding to each time window are compared based on the time window filtering function. The maximum target suitability value is determined based on the comparison results, and the target time window corresponding to the maximum target suitability value is output. Optionally, the above suitability function, delay penalty function, resource conflict cost function, and time window filtering function can be integrated into a complete target time window determination function, which can be expressed as:

[0125]

[0126] in, This is a preset refresh flight time threshold.

[0127] In this embodiment, a comprehensive target time window determination mechanism is formed by integrating the suitability function, delay penalty function, resource conflict cost function, and time window filtering function. This mechanism enables intelligent scheduling of UAV re-flight missions and can dynamically select the optimal re-flight time window based on multi-dimensional evaluation. This effectively addresses the task scheduling needs in complex environments and improves the flexibility of task execution.

[0128] Figure 6 This is a flowchart of an initial task weight set adjustment method provided in an embodiment of this application, such as... Figure 6 As shown, it includes:

[0129] Step S301: Monitor the mission execution status of the UAV. If the mission execution status is in failure, obtain the initial mission weight set and adjust the corresponding weight values ​​in the initial mission weight set in reverse according to the target mission weight set.

[0130] Step S302: When the task execution status is successful, obtain the initial task weight set, and make positive adjustments to the corresponding weight values ​​in the initial task weight set according to the target task weight set.

[0131] Among them, the mission execution status can refer to the core status identifier used to describe the actual operation of the UAV throughout the entire mission execution process. The initial mission weight set can refer to a pre-defined set of basic weight parameters for various mission types, containing all factors affecting scheduling decisions. This initial mission weight set can be represented as:

[0132]

[0133] Where n is the task type identifier. , , , , , and These are the influence weight coefficients corresponding to the various factors influencing the suitability assessment value.

[0134] In one embodiment, after task Ti completes, if the task execution fails or the execution result is poor, then according to W... Ti (a) The weights W(a) of task class a in the weight matrix are adjusted in reverse to obtain the adjusted set of task weights:

[0135]

[0136] Otherwise, a positive adjustment is performed, resulting in the adjusted set of task weights:

[0137]

[0138] in, It is the learning rate, which controls the impact of a single task on the overall weight, enabling continuous adaptive learning of the scheduling strategy.

[0139] This application embodiment achieves continuous optimization of UAV scheduling strategies by dynamically adjusting the task weight set. In the event of task execution failure or unsatisfactory results, it can automatically identify key factors affecting task execution and adjust the corresponding weights in reverse to reduce the probability of similar problems occurring in future tasks. In the event of successful task execution, positive adjustments to the weights strengthen the learning and consolidation of successful experiences, thereby continuously improving the accuracy and efficiency of overall scheduling decisions.

[0140] Figure 7 This is a schematic diagram of the structure of an adaptive scheduling system for unmanned aerial vehicles (UAVs) provided in an embodiment of this application, as shown below. Figure 7 As shown, it includes:

[0141] Data acquisition module 41 is used to acquire task type, task execution time, target task weight set, environmental parameters, and historical success rate factor;

[0142] The environmental safety factor determination module 42 is used to input the environmental parameters into a preset function to obtain the environmental safety factor;

[0143] The suitability assessment module 43 is used to perform an execution suitability assessment based on the corresponding weight values ​​in the target task weight set, the environmental safety factor, and the historical success rate factor, and to obtain a suitability assessment value.

[0144] The UAV scheduling module 44 is used to schedule the UAV based on the task execution time and the flight route corresponding to the task type, provided that the suitability assessment value meets the preset task execution conditions.

[0145] In this embodiment, suitability assessment can be performed by combining environmental parameters, the weight values ​​of each type of parameter in the environmental parameters, and the historical success rate factor. By comprehensively considering the impact of different factors on suitability assessment, the accuracy of suitability assessment is improved. Based on the suitability assessment value, it is determined whether the expected task execution time can effectively complete the UAV flight mission. If the suitability meets the preset task execution conditions, the UAV is scheduled during the task execution time so that it can work on time according to the corresponding route, thus fully ensuring the effectiveness of the UAV flight mission.

[0146] In one possible embodiment, the preset functions include a wind speed safety factor function, a rainfall safety factor function, a visibility safety factor function, a temperature safety factor function, a light intensity factor function, an environmental clarity factor function, and a shadow penalty factor function. The environmental parameters include wind speed, rainfall, visibility, temperature, solar radiation intensity, cloud cover, air quality index, and solar altitude angle.

[0147] In one possible embodiment, the environmental safety factor determination module 42 is specifically used for:

[0148] The wind speed is input into the wind speed safety factor function to obtain the wind speed safety factor; the rainfall is input into the rainfall safety factor function to obtain the rainfall safety factor; the visibility is input into the visibility safety factor function to obtain the visibility safety factor; and the temperature is input into the temperature safety factor function to obtain the temperature safety factor.

[0149] The solar radiation intensity and cloud cover are input into the light intensity factor function to obtain the light intensity factor. The visibility and air quality index are input into the environmental clarity factor function to obtain the environmental clarity factor. The solar altitude angle is input into the shadow penalty factor function to obtain the shadow penalty factor.

[0150] In one possible embodiment, the fitness assessment module 43 is specifically used for:

[0151] The flight safety probability is calculated based on the wind speed safety factor, the rainfall safety factor, the visibility safety factor, and the temperature safety factor.

[0152] The expected data quality value is calculated based on the light intensity factor, the environmental clarity factor, the shadow penalty factor, and the corresponding weight values ​​in the target task weight set;

[0153] The data quality weight value and the expected data quality value in the target task weight set are weighted to obtain a first weighted result. The historical success rate weight value and the pre-calculated success rate factor in the target task weight set are weighted to obtain a second weighted result. An execution suitability assessment is performed based on the flight safety probability, the first weighted result, and the second weighted result.

[0154] In one possible embodiment, a target time window determination module is further included, the target time window determination module being used to:

[0155] If the suitability assessment value does not meet the preset task execution conditions, the time range consisting of the task execution time and the preset re-flight time threshold is determined as the target time range, which includes multiple time windows.

[0156] The target time window for each time window is determined based on a preset supplementary flight prediction function;

[0157] The UAV scheduling module 44 is used to schedule the UAV based on the target time window and the flight route corresponding to the task type.

[0158] In one possible embodiment, the flight prediction function includes a suitability function, a delay penalty function, a resource conflict cost function, and a time window filtering function;

[0159] Accordingly, the target time window determination module is specifically used for:

[0160] The future suitability value of each time window is calculated based on the suitability function, the delay penalty value of each time window is determined based on the delay penalty function, and the resource conflict value of each time window is determined based on the resource conflict cost function.

[0161] The target suitability value for the corresponding time window is determined based on the future suitability value, the target delay penalty value, and the target resource conflict value.

[0162] The target suitability values ​​corresponding to each time window are compared based on the time window filtering function. The maximum target suitability value is determined based on the comparison results, and the target time window corresponding to the maximum target suitability value is output.

[0163] In one possible embodiment, a task weight set adjustment module is further included, which is specifically used for:

[0164] Monitor the mission execution status of the UAV; if the mission execution status is in a failed state, obtain an initial mission weight set; and adjust the corresponding weight values ​​in the initial mission weight set in reverse according to the target mission weight set.

[0165] If the task execution status is successful, an initial task weight set is obtained, and the corresponding weight values ​​in the initial task weight set are positively adjusted according to the target task weight set.

[0166] This application also provides an electronic device that can integrate an adaptive drone scheduling system provided in this application. Figure 8 This is a schematic diagram of the structure of an adaptive scheduling device for unmanned aerial vehicles (UAVs) provided in an embodiment of this application. (Refer to...) Figure 8The UAV adaptive scheduling device includes: an input device 53, an output device 54, a memory 52, and one or more processors 51; the memory 52 is used to store one or more programs; when one or more programs are executed by one or more processors 51, the one or more processors 51 implement the UAV adaptive scheduling method provided in the above embodiments. The input device 53, output device 54, memory 52, and processors 51 can be connected via a bus or other means. Figure 8 Taking the example of a connection between China and Israel via a bus.

[0167] The memory 52, as a computing device readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the UAV adaptive scheduling method provided in any embodiment of this application. The memory 52 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function; the data storage area may store data created based on the use of the device. Furthermore, the memory 52 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 52 may further include memory remotely located relative to the processor 51, and these remote memories can be connected to the device via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0168] Input device 53 can be used to receive input digital or character information, and to generate key signal inputs related to user settings and function control of the device. Output device 54 may include display devices such as a display screen.

[0169] The processor 51 executes various functional applications and data processing of the device by running software programs, instructions and modules stored in the memory 52, thereby realizing the above-mentioned UAV adaptive scheduling method.

[0170] The UAV adaptive scheduling system, device, and computer provided above can be used to execute the UAV adaptive scheduling method provided in any of the above embodiments, and have corresponding functions and beneficial effects.

[0171] This application embodiment also provides a storage medium for storing computer-executable instructions. When executed by a computer processor, the computer-executable instructions are used to execute the UAV adaptive scheduling method provided in the above embodiment. The UAV adaptive scheduling method includes: obtaining a task type, task execution time, target task weight set, environmental parameters, and historical success rate factor; inputting the environmental parameters into a preset function to obtain an environmental safety factor; performing an execution suitability assessment based on the corresponding weight value in the target task weight set, the environmental safety factor, and the historical success rate factor to obtain a suitability assessment value; and scheduling the UAV based on the task execution time and the flight path corresponding to the task type when the suitability assessment value meets preset task execution conditions.

[0172] Storage medium – any type of memory device or storage device. The term “storage medium” is intended to include: mounting media, such as CD-ROMs, floppy disks, or magnetic tape devices; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (e.g., hard disks or optical storage); registers or other similar types of memory elements, etc. Storage medium may also include other types of memory or combinations thereof. Furthermore, storage medium may reside in a first computer system in which the program is executed, or it may reside in a different second computer system connected to the first computer system via a network (such as the Internet). The second computer system can provide program instructions to the first computer for execution. The term “storage medium” can include two or more storage media that may reside in different locations (e.g., in different computer systems connected via a network). Storage medium may store program instructions (e.g., specifically implemented as a computer program) executable by one or more processors.

[0173] Of course, the computer-executable instructions provided in the embodiments of this application are not limited to the UAV adaptive scheduling method described above, but can also execute related operations in the UAV adaptive scheduling method provided in any embodiment of this application.

[0174] The UAV adaptive scheduling system, device and storage medium provided in the above embodiments can execute the UAV adaptive scheduling method provided in any embodiment of this application. For technical details not described in detail in the above embodiments, please refer to the UAV adaptive scheduling method provided in any embodiment of this application.

[0175] The above description is merely a preferred embodiment and the technical principles employed in this application. This application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions that can be made by those skilled in the art will not depart from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of this application, the scope of which is determined by the scope of the claims.

Claims

1. An adaptive scheduling method for unmanned aerial vehicles (UAVs), characterized in that, include: Obtain the task type, task execution time, target task weight set, environmental parameters, and historical success rate factor; input the environmental parameters into a preset function to obtain the environmental safety factor. An execution suitability assessment is performed based on the corresponding weight values ​​in the target task weight set, the environmental safety factor, and the historical success rate factor to obtain a suitability assessment value. If the suitability assessment value does not meet the preset task execution conditions, the time range consisting of the task execution time and the preset supplementary flight time threshold is determined as the target time range. The target time range includes multiple time windows. The target time window of each time window is determined based on the preset supplementary flight prediction function. The UAV is scheduled based on the target time window and the flight route corresponding to the task type. If the suitability assessment value meets the preset task execution conditions, the UAV is scheduled based on the task execution time and the flight route corresponding to the task type.

2. The UAV adaptive scheduling method according to claim 1, characterized in that, The preset functions include wind speed safety factor function, rainfall safety factor function, visibility safety factor function, temperature safety factor function, light intensity factor function, environmental clarity factor function, and shadow penalty factor function. The environmental parameters include wind speed, rainfall, visibility, temperature, solar radiation intensity, cloud cover, air quality index, and solar altitude angle.

3. The UAV adaptive scheduling method according to claim 2, characterized in that, The step of inputting the environmental parameters into a preset function to obtain the environmental safety factor includes: The wind speed is input into the wind speed safety factor function to obtain the wind speed safety factor; the rainfall is input into the rainfall safety factor function to obtain the rainfall safety factor; the visibility is input into the visibility safety factor function to obtain the visibility safety factor; and the temperature is input into the temperature safety factor function to obtain the temperature safety factor. The solar radiation intensity and cloud cover are input into the light intensity factor function to obtain the light intensity factor. The visibility and air quality index are input into the environmental clarity factor function to obtain the environmental clarity factor. The solar altitude angle is input into the shadow penalty factor function to obtain the shadow penalty factor.

4. The UAV adaptive scheduling method according to claim 2, characterized in that, The execution suitability assessment based on the corresponding weight values ​​in the target task weight set, the environmental safety factor, and the historical success rate factor includes: The flight safety probability is calculated based on the wind speed safety factor, the rainfall safety factor, the visibility safety factor, and the temperature safety factor. The expected data quality value is calculated based on the light intensity factor, the environmental clarity factor, the shadow penalty factor, and the corresponding weight values ​​in the target task weight set; The data quality weight value and the expected data quality value in the target task weight set are weighted to obtain a first weighted result. The historical success rate weight value and the historical success rate factor in the target task weight set are weighted to obtain a second weighted result. An execution suitability assessment is performed based on the flight safety probability, the first weighted result, and the second weighted result.

5. The UAV adaptive scheduling method according to claim 1, characterized in that, The supplementary flight prediction function includes a suitability function, a delay penalty function, a resource conflict cost function, and a time window filtering function; Accordingly, determining the target time window for each time window based on the preset supplementary flight prediction function includes: The future suitability value of each time window is calculated based on the suitability function, the delay penalty value of each time window is determined based on the delay penalty function, and the resource conflict value of each time window is determined based on the resource conflict cost function. The target suitability value for the corresponding time window is determined based on the future suitability value, the delay penalty value, and the resource conflict value. The target suitability values ​​corresponding to each time window are compared based on the time window filtering function. The maximum target suitability value is determined based on the comparison results, and the target time window corresponding to the maximum target suitability value is output.

6. The UAV adaptive scheduling method according to any one of claims 1-5, characterized in that, After scheduling the drone, the process also includes: Monitor the mission execution status of the UAV; if the mission execution status is in a failed state, obtain an initial mission weight set; and adjust the corresponding weight values ​​in the initial mission weight set in reverse according to the target mission weight set. If the task execution status is successful, an initial task weight set is obtained, and the corresponding weight values ​​in the initial task weight set are positively adjusted according to the target task weight set.

7. An adaptive scheduling system for unmanned aerial vehicles (UAVs), characterized in that, include: The data acquisition module is used to acquire task type, task execution time, target task weight set, environmental parameters, and historical success rate factors. An environmental safety factor determination module is used to input the environmental parameters into a preset function to obtain the environmental safety factor; The suitability assessment module is used to perform an execution suitability assessment based on the corresponding weight values ​​in the target task weight set, the environmental safety factor, and the historical success rate factor, and obtain a suitability assessment value. The target time window determination module is used to determine the time range consisting of the task execution time and the preset supplementary flight time threshold as the target time range when the suitability assessment value does not meet the preset task execution conditions. The target time range includes multiple time windows. The target time window of each time window is determined based on the preset supplementary flight prediction function. The UAV is scheduled based on the target time window and the flight route corresponding to the task type. The drone scheduling module is used to schedule the drone based on the task execution time and the flight route corresponding to the task type, provided that the suitability assessment value meets the preset task execution conditions.

8. An electronic device, characterized in that, The device includes: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement the UAV adaptive scheduling method as described in any one of claims 1-6.

9. A storage medium for storing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the UAV adaptive scheduling method as described in any one of claims 1-6.

Images