A low-altitude operation unmanned aerial vehicle cluster cooperative scheduling system

Abstract

The present application relates to the field of scheduling analysis, and more particularly to a low-altitude operation UAV cluster cooperative scheduling system, the present application identifies the operation resource characteristics of the UAV group through instruction execution data, evaluates the mutual interference representation value of the UAV group based on the operation resource characteristics, and marks the UAV group; based on the marking result, the UAV group is analyzed and predicted; the flight trajectory of the UAV group at the time node is determined, the number of UAVs in the wind shear frequent area and the relative position density are obtained, the involved representation parameters of the UAV group are evaluated, and the interference degree category of the UAV group is determined; based on the interference degree category, the UAV group is adaptively scheduled and adjusted, the present application helps the UAV group to flexibly face the interference risk on the basis of ensuring the safety and stability of the UAV group flight, improves the overall operation efficiency and cooperative operation ability of the UAV group, and reduces the possibility of operation failure caused by interference.

Description

Technical Field

[0001] This invention relates to the field of scheduling analysis, and in particular to a collaborative scheduling system for low-altitude drone swarms. Background Technology

[0002] With the continuous advancement of technology, drones are increasingly widely used in low-altitude operations. For example, in agriculture, drones can be used for sowing, fertilizing, and plant protection, improving agricultural production efficiency and quality. In surveying and mapping, they can perform topographic surveying and cadastral surveying, quickly acquiring high-precision geographic information data. A large number of application scenarios have placed higher demands on the collaborative operation capabilities and scheduling and detection of drones.

[0003] During collaborative operations, a large number of drones need to transmit data and exchange commands via wireless communication. However, limited resources can easily lead to communication interference, affecting the information transmission between drones and thus the effectiveness of collaborative operations.

[0004] Meanwhile, the low-altitude operation environment is complex and changeable, with various terrain features and meteorological conditions. Meteorological factors such as wind shear and airflow turbulence, as well as terrain features such as buildings and trees, can all affect the flight safety and trajectory control of UAVs.

[0005] Therefore, when drone swarms operate collaboratively, it is necessary to assess the operational status of the drone swarm and make appropriate and reasonable planning interventions to avoid mutual interference between drones in changing environments and improve operational efficiency.

[0006] Chinese Patent Application Publication No. CN118966719A discloses a management platform for low-altitude unmanned aerial vehicles (UAVs). To address the issues of insufficient effectiveness of terrain data monitoring and difficulty in ensuring flight safety of low-altitude UAVs in existing technologies, this invention includes a flight path management module to optimize the flight path of the low-altitude UAV, a terrain feature monitoring module to identify terrain features, a dynamic obstacle identification module to identify and avoid dynamic obstacles in the survey area in real time, an environment adaptation module to dynamically adjust the flight parameters of the low-altitude UAV, a task switching module to manage and switch the terrain information that the low-altitude UAV is currently executing or has not yet executed, and a data integration module to integrate the terrain.

[0007] However, the following problems still exist in the existing technology.

[0008] Faced with complex and changing flight operation environments, the inability to pre-intervene in the collaborative operations among a large number of drones and the untimely scheduling and adjustment reduce the safety and stability of drone swarm collaborative operations. Summary of the Invention

[0009] To address this, the present invention provides a low-altitude drone swarm collaborative scheduling system to overcome the problems in the prior art where, in the face of complex and changing flight operation environments, it is impossible to pre-intervene in the collaborative operations among a large number of drones, and the scheduling adjustments are not timely, resulting in reduced safety and stability of drone swarm collaborative operations.

[0010] To achieve the above objectives, the present invention provides a collaborative scheduling system for low-altitude unmanned aerial vehicle (UAV) swarms, comprising:

[0011] The job storage module includes a trajectory storage unit for storing flight trajectory data of the UAV swarm, an instruction storage unit for storing instruction execution data of each UAV, and an image storage unit for storing image data of the flight operation.

[0012] The analysis and labeling module identifies the operational resource characteristics of the UAV swarm based on the instruction execution data, evaluates the mutual interference characterization value of the UAV swarm based on the operational resource characteristics, and labels the UAV swarm.

[0013] The prediction module is adjusted to analyze and predict the drone swarm based on the labeling results of the analysis and labeling module, including:

[0014] The detection frequency for the UAV swarm is adjusted based on the mutual interference characterization value to obtain the environmental variation characteristics of each flight coverage area. Based on the environmental variation characteristics, the wind shear frequent area is determined, and the time node of the UAV swarm arriving at the wind shear frequent area is predicted.

[0015] The interference assessment module is used to determine the flight trajectory of the UAV swarm at the specified time point, obtain the number of UAVs and their relative positional density in the area with frequent wind shear, and assess the involved characterization parameters of the UAV swarm to determine the interference level category of the UAV swarm.

[0016] The involved scheduling module is used to adjust the scheduling of the drone swarm based on the category of interference level, including:

[0017] The flight trajectory of the drone swarm is determined based on the involved features.

[0018] Alternatively, reduce the execution speed of the drone swarm.

[0019] Furthermore, the analysis and labeling module is used to evaluate the mutual interference characterization value of the UAV swarm based on the operational resource characteristics, including,

[0020] Used to obtain operational resource characteristics, including the same spectrum utilization and the same frequency band signal communication density;

[0021] The ratio of the same spectrum utilization rate to the utilization rate threshold is used as the first mutual interference feature;

[0022] The ratio of the communication density of signals in the same frequency band to the communication density threshold is used as the second mutual interference feature;

[0023] The sum of the first mutual interference feature and the second mutual interference feature is used to determine the mutual interference characterization value.

[0024] Furthermore, the analysis and labeling module is used to label the drone swarm, including,

[0025] If the mutual interference characterization value of the UAV swarm is greater than or equal to the mutual interference characterization threshold, the analysis labeling module sets a cooperative disorder label for the UAV swarm.

[0026] Furthermore, the adjustment prediction module is used to analyze and predict the drone swarm based on the labeling results of the analysis and labeling module, including:

[0027] If a drone swarm is tagged with a cooperative disorder, then the drone swarm is analyzed and predicted.

[0028] Furthermore, the adjustment prediction module is used to determine areas with frequent wind shear based on the environmental variation characteristics, including:

[0029] Used to retrieve the environmental features of each flight coverage area, including the maximum height difference of ground objects and the average distance to adjacent ground objects;

[0030] If any flight coverage area does not meet the environmental variation conditions, then the flight coverage area is determined as the area with frequent wind shear.

[0031] The environmental staggered conditions include the maximum height difference between ground objects being less than the maximum height difference threshold and the average distance between adjacent ground objects being greater than the average distance threshold.

[0032] Furthermore, the adjustment prediction module is used to predict the time point at which the drone swarm arrives in the area with frequent wind shear, including,

[0033] Used to extract the execution time and corresponding flight distance of several instructions based on instruction execution data;

[0034] Used to obtain the currently executing instruction and determine the sequence of subsequent instructions following the currently executing instruction;

[0035] This is used to determine the region execution command corresponding to the edge of the area with frequent wind shear based on the flight distance of each executed command in the subsequent command sequence;

[0036] Used to determine, based on the subsequent instruction sequence, a number of intermediate instructions included in the current instruction to the region instruction;

[0037] Used to calculate the total execution time of each of the intermediate execution instructions;

[0038] This is used to sum the execution time up to the current moment as the time node.

[0039] Furthermore, the interference assessment module is used to assess the involved characterization parameters of the UAV swarm, including,

[0040] The ratio of the number of drones to a threshold number of drones is used as the first interference feature;

[0041] The ratio of relative position density to density threshold is used as the second interference feature;

[0042] The sum of the first interfered feature and the second interfered feature is used to determine the involved characterization parameter.

[0043] Furthermore, the interference assessment module is used to determine the category of interference level of the drone swarm, including,

[0044] If the involved characterization parameter of the drone swarm is greater than or equal to the involved characterization parameter threshold, then the interference level of the drone swarm is determined to be a strong interference category.

[0045] If the interference characterization parameter of the drone swarm is less than the threshold of the interference characterization parameter, then the interference level of the drone swarm is determined to be weak interference.

[0046] Furthermore, the involved scheduling module is used to adjust the scheduling of the drone swarm based on the category of interference level, including,

[0047] If the interference level of the drone swarm is classified as strong interference, then the flight trajectory of the drone swarm should be changed based on the involved characteristics.

[0048] If the interference level of the drone swarm is classified as weak interference, then the execution speed of the drone swarm will be reduced.

[0049] Furthermore, the involved scheduling module is used to determine whether to change the flight trajectory of the UAV swarm based on involved features, including:

[0050] Used to obtain relevant features based on command execution data, including the number of drones connected to areas with frequent wind shear and the corresponding complexity of command switching differences;

[0051] If the number of connected drones outside the area with frequent wind shear exceeds the threshold for the number of connected drones or / and the complexity of command switching differences exceeds the complexity threshold, then the flight trajectory of the drone swarm will be changed.

[0052] Compared with existing technologies, this invention sets up a task storage module, which includes a trajectory storage unit for storing flight trajectory data of the UAV swarm, an instruction storage unit for storing instruction execution data of each UAV, and an image storage unit for storing image data of the flight operation; an analysis and marking module, which identifies the task resource characteristics of the UAV swarm based on the instruction execution data, evaluates the mutual interference characterization value of the UAV swarm based on the task resource characteristics, and marks the UAV swarm; an adjustment and prediction module, which analyzes and predicts the UAV swarm based on the marking results of the analysis and marking module; an interference assessment module, which determines the flight trajectory of the UAV swarm at a time node, obtains the number and relative position density of UAVs in areas with frequent wind shear, evaluates the involved characterization parameters of the UAV swarm, and determines the interference level category of the UAV swarm; and an involved scheduling module, which schedules and adjusts the UAV swarm based on the interference level category. This invention, while ensuring the safety and stability of UAV swarm flight, helps the UAV swarm flexibly cope with interference risks, improves the overall operating efficiency and collaborative operation capability of the UAV swarm, and reduces the possibility of task failure due to interference.

[0053] In particular, this invention includes an analysis and marking module that considers resource contention and conflict during collaborative operations by UAV swarms. When the utilization rate of the same spectrum is high or the signal communication density of the same frequency band is high, the possibility of mutual interference between UAVs increases, thereby increasing the difficulty of collaborative operations and reducing their efficiency. Therefore, this invention evaluates the mutual interference characterization value of the UAV swarm through operational resource characteristics to characterize the degree of mutual interference between UAVs due to resource contention, providing data support for subsequent marking of the UAV swarm. While ensuring the safety and stability of UAV swarm flight, this invention helps UAV swarms flexibly cope with interference risks, improves the overall operational efficiency and collaborative operation capabilities of the UAV swarm, and reduces the possibility of operation failure due to interference.

[0054] In particular, this invention includes an adjustment and prediction module that pre-adjusts the detection frequency for drone swarms with high levels of mutual interference and disordered coordination. This allows for more timely detection of potential problems and enables the analysis and evaluation of the environmental conditions in the area covered by the drone swarm's collaborative operations. This identifies areas with frequent wind shear and predicts the arrival time of the drone swarm in these areas, allowing for early intervention in the collaborative operations and ensuring the smooth progress of the overall operation. While ensuring the safety and stability of drone swarm flight, this invention helps drone swarms flexibly cope with interference risks, improves the overall operational efficiency and collaborative operation capabilities of the drone swarm, and reduces the possibility of operation failure due to interference.

[0055] In particular, this invention includes an interference assessment module that considers the degree of interference aggravation among several drones operating in areas with frequent wind shear, taking into account the impact of wind shear itself on the operation of the drone swarm. This allows for a more accurate assessment of the risk level of the drone swarm operating in the corresponding areas with frequent wind shear, enabling advance adjustments and ensuring stable operation of the drone swarm. Therefore, this invention assesses the involved characterization parameters of the drone swarm by evaluating the number of drones and their relative positional density in areas with frequent wind shear, thus characterizing the degree of abnormal aggravation of the distribution of the drone swarm under the influence of wind shear. This provides data support for subsequent determination of the interference level of the drone swarm. While ensuring the safety and stability of drone swarm flight, this invention helps the drone swarm flexibly cope with interference risks, improves the overall operational efficiency and collaborative operation capabilities of the drone swarm, and reduces the possibility of operation failure due to interference. Attached Figure Description

[0056] Figure 1 A functional block diagram of a low-altitude unmanned aerial vehicle (UAV) swarm collaborative scheduling system according to an embodiment of the invention;

[0057] Figure 2 This is a logic diagram for marking a swarm of drones according to an embodiment of the invention;

[0058] Figure 3 A logic decision diagram for determining the region of frequent wind shear in the embodiments of the invention;

[0059] Figure 4 This is a logic diagram for determining the interference level category of a drone swarm in an embodiment of the invention. Detailed Implementation

[0060] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0061] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0062] It should be noted that in the description of this invention, the terms "upper," "lower," "inner," "outer," etc., which indicate the direction or positional relationship, are based on the direction or positional relationship shown in the drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0063] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the term "connection" should be interpreted broadly. For example, it can refer to a fixed connection, a detachable connection, or an integral connection; it can refer to a mechanical connection or an electrical connection. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0064] Please see Figure 1 The diagram shown is a functional block diagram of a low-altitude unmanned aerial vehicle (UAV) swarm collaborative scheduling system according to an embodiment of the present invention. The low-altitude unmanned aerial vehicle (UAV) swarm collaborative scheduling system according to an embodiment of the present invention includes:

[0065] The job storage module includes a trajectory storage unit for storing flight trajectory data of the UAV swarm, an instruction storage unit for storing instruction execution data of each UAV, and an image storage unit for storing image data of the flight operation.

[0066] An analysis and labeling module, connected to the job storage module, identifies the operational resource characteristics of the UAV swarm based on the instruction execution data, and evaluates the mutual interference characterization value of the UAV swarm based on the operational resource characteristics in order to label the UAV swarm.

[0067] The prediction module is adjusted and connected to the analysis and labeling module to perform analysis and prediction on the UAV swarm based on the labeling results of the analysis and labeling module, including:

[0068] The detection frequency for the UAV swarm is adjusted based on the mutual interference characterization value to obtain the environmental variation characteristics of each flight coverage area. Based on the environmental variation characteristics, the wind shear frequent area is determined, and the time node of the UAV swarm arriving at the wind shear frequent area is predicted.

[0069] Interference assessment module, connected to the adjustment prediction module, is used to determine the flight trajectory of the UAV swarm at the time node, obtain the number of UAVs and their relative position density in the area of ​​frequent wind shear, and assess the involved characterization parameters of the UAV swarm to determine the interference level category of the UAV swarm.

[0070] The involved scheduling module, connected to the interference assessment module, is used to adjust the scheduling of the UAV swarm based on the category of interference level, including:

[0071] The flight trajectory of the drone swarm is determined based on the involved features.

[0072] Alternatively, reduce the execution speed of the drone swarm.

[0073] Specifically, the flight trajectory data includes flight trajectories, etc.; the command execution data includes operational resource characteristics, involved characteristics, execution time of several commands, and corresponding flight distances, etc.; the image data includes environmental features of each flight coverage area, the number of drones in each flight coverage area, and relative position density, etc.

[0074] It is understandable that during collaborative operations, drone swarms will use different frequency bands for communication and interaction based on different task requirements, environmental conditions, and communication requirements. Therefore, there is no specific limitation on the method of collecting and acquiring operational resource characteristics. A lightweight spectrum sensor can be mounted on the drone to determine the channel occupancy rate of the spectrum (the ratio of the time the channel is occupied to the observation duration). The channel occupancy rate is used as the spectrum utilization rate. To balance real-time performance and data stability, the observation duration is set to 5 seconds.

[0075] The lightweight spectrum sensor detects the signal power spectral density of several frequency bands, and the corresponding signals are used as the signal communication density of the same frequency band.

[0076] In this embodiment, relevant data such as flight trajectory, execution time of several commands, and corresponding flight distance are stored in a relevant database in advance for subsequent retrieval and retrieval.

[0077] Specifically, there are no specific limitations on the method of obtaining environmental features. A drone equipped with LiDAR can scan the ground features in each flight coverage area to obtain high-density point clouds. Based on the point cloud classification algorithm, the types of ground features such as ground, buildings, and vegetation can be distinguished.

[0078] Understandably, point clouds based on ground features can determine the height of the features and the center coordinates of the features, thereby determining the height difference between the features and the distance between adjacent features.

[0079] Specifically, by extracting the point clouds of the highest and lowest ground features within the flight coverage area, the vertical distances from the top points of the highest and lowest ground features to the ground are calculated respectively, and the difference between the vertical distances corresponding to the highest and lowest ground features is taken as the maximum height difference of the ground features.

[0080] The shortest distance between ground features and the remaining ground features is determined as the distance between adjacent ground features, and then the average distance between adjacent ground features within the flight coverage area is determined.

[0081] In practice, the number of drones and their relative density in each flight coverage area can be captured by the high-definition camera carried by the drone. This is existing technology and will not be elaborated further.

[0082] Specifically, there are no restrictions on the specific structure of the job storage module, analysis and marking module, adjustment and prediction module, interference evaluation module, and involved scheduling module. Each module or its units can be composed of logic components or combinations of logic components. Logic components include field-programmable processors, computers, or microprocessors in computers.

[0083] In this embodiment, through close collaboration among the modules, the entire process of managing the UAV swarm, from data storage and analysis to risk prediction, interference assessment, and scheduling adjustment, is achieved. This helps improve the overall performance of the UAV swarm, enabling it to operate more stably and efficiently under complex environments and task requirements, and providing reliable support for relevant application scenarios such as logistics delivery, surveying, and inspection.

[0084] Specifically, the analysis and labeling module is used to evaluate the mutual interference characterization value of the UAV swarm based on the operational resource characteristics, including,

[0085] Used to obtain operational resource characteristics, including the same spectrum utilization and the same frequency band signal communication density;

[0086] The ratio of the same spectrum utilization rate to the utilization rate threshold is used as the first mutual interference feature;

[0087] The ratio of the communication density of signals in the same frequency band to the communication density threshold is used as the second mutual interference feature;

[0088] The sum of the first mutual interference feature and the second mutual interference feature is used to determine the mutual interference characterization value.

[0089] In this embodiment, the purpose of setting the utilization rate threshold and the communication density threshold is to characterize the situation where the UAV swarm is severely affected by interference due to resource contention and conflict. By acquiring historical data of several times when the UAV swarms cooperated to perform the same operation, calling historical data of the same spectrum utilization rate and historical data of the same frequency band signal communication density, the average utilization rate and the average communication density are calculated and used as the benchmark quantities under normal conditions. Based on the purpose of setting the above two thresholds, the utilization rate threshold is determined as the product of the average utilization rate and the utilization deviation coefficient, and the communication density threshold is determined as the product of the average communication density and the density deviation coefficient. The utilization deviation coefficient is selected in the interval [1.2, 1.3], preferably 1.2 in practice, and the density deviation coefficient is selected in the interval [1.15, 1.2], preferably 1.15 in practice.

[0090] Specifically, please refer to Figure 2 As shown, this is a logic decision diagram for marking a drone swarm according to an embodiment of the present invention. The analysis and marking module is used to mark the drone swarm, including...

[0091] If the mutual interference characterization value of the UAV swarm is greater than or equal to the mutual interference characterization threshold, the analysis labeling module sets a cooperative disorder label for the UAV swarm.

[0092] If the mutual interference characterization value of the drone swarm is less than the mutual interference characterization threshold, then there is no need to set a cooperative disorder label for the drone swarm.

[0093] The mutual interference characterization threshold is predetermined. The mutual interference characterization value calculated under the conditions that the same spectrum utilization rate is equal to the utilization rate threshold and the same frequency band signal communication density is equal to the communication density threshold is determined as the mutual interference characterization threshold.

[0094] Specifically, this invention includes an analysis and marking module that considers resource contention and conflict during collaborative operations by a drone swarm. When the utilization rate of the same spectrum is high or the signal communication density in the same frequency band is high, the possibility of mutual interference between drones increases. For example, if the utilization rate of the same spectrum is too high, it means that multiple drones are sending and receiving signals on the same frequency, which may lead to mutual interference, degrading the quality of the signals received by the drones, and causing signal distortion and increased bit error rate. If too much data generated by too many signals is transmitted in the same frequency band, the frequency band will become congested, and signals will "collide" with each other, affecting the drones' accurate interpretation of signals, thus increasing the difficulty and efficiency of collaborative operations. Therefore, this invention evaluates the mutual interference characteristics of the drone swarm through operational resource features to characterize the degree of mutual interference among drones due to resource contention, providing data support for subsequent marking of the drone swarm. This invention, while ensuring the safety and stability of drone swarm flight, helps the drone swarm flexibly cope with interference risks, improves the overall operational efficiency and collaborative operation capabilities of the drone swarm, and reduces the possibility of operational failures due to interference.

[0095] Specifically, the adjustment prediction module is used to analyze and predict the drone swarm based on the labeling results of the analysis and labeling module, including:

[0096] If a drone swarm is tagged with a cooperative disorder, then the drone swarm is analyzed and predicted.

[0097] Specifically, the adjustment prediction module is used to adjust the detection frequency for the UAV swarm based on the mutual interference characterization value, including:

[0098] The detection frequency for drone swarms is increased, and the increase in detection frequency is positively correlated with the mutual interference characterization value.

[0099] In this embodiment, optionally,

[0100] The mutual interference characterization value is compared with the preset first mutual interference characterization comparison threshold and the second mutual interference characterization comparison threshold.

[0101] When the mutual interference characterization value is greater than the second mutual interference characterization comparison threshold, the increase in detection frequency is determined to be the first increase, which is set to 0.5 times the current detection frequency.

[0102] When the mutual interference characterization value is greater than or equal to the first mutual interference characterization comparison threshold and less than or equal to the second mutual interference characterization comparison threshold, the increase in detection frequency is determined to be the second increase, which is set to 0.35 times the current detection frequency.

[0103] When the mutual interference characterization value is less than the first mutual interference characterization comparison threshold, the increase in detection frequency is determined to be the third increase, which is set to be 0.2 times the current detection frequency.

[0104] Among them, the first mutual interference characterization comparison threshold is 1.1 times the mutual interference characterization threshold, and the second mutual interference characterization comparison threshold is 1.3 times the mutual interference characterization threshold;

[0105] Specifically, please refer to Figure 3 As shown, this is a logic decision diagram for determining areas with frequent wind shear according to an embodiment of the present invention. The adjustment prediction module is used to determine areas with frequent wind shear based on the environmental features, including:

[0106] Used to retrieve the environmental features of each flight coverage area, including the maximum height difference of ground objects and the average distance to adjacent ground objects;

[0107] If any flight coverage area does not meet the environmental variation conditions, then the flight coverage area is determined as the area with frequent wind shear.

[0108] The environmental staggered conditions include the maximum height difference between ground objects being less than the maximum height difference threshold and the average distance between adjacent ground objects being greater than the average distance threshold.

[0109] In this embodiment, the purpose of setting the maximum height difference threshold and the average distance threshold is to characterize the situation where environmental factors in the coverage area of ​​the UAV swarm flight have a serious degree of abnormal interference with the collaborative operation under the environmental conditions of frequent wind shear. By acquiring historical data of several UAV swarms performing the same operation collaboratively, calling historical data of the maximum height difference of ground objects and historical data of the average distance of adjacent ground objects, the average value of the maximum height difference and the average value of the average distance are calculated and used as the benchmark quantity under normal conditions. Based on the purpose of setting the above two thresholds, the maximum height difference threshold is determined as the product of the average value of the maximum height difference and the height deviation coefficient, and the average distance threshold is determined as the product of the average value of the average distance and the distance deviation coefficient. The height deviation coefficient is selected in the interval [1.3, 1.5], preferably 1.3 in the implementation, and the distance deviation coefficient is selected in the interval [1.1, 1.2], preferably 1.1 in the implementation.

[0110] Specifically, land features refer to all kinds of natural and man-made objects that exist on the Earth's surface, including forests, buildings, etc.

[0111] Specifically, this invention includes an adjustment and prediction module. For drone swarms with high levels of mutual interference and disordered coordination, the detection frequency for the drone swarm is adjusted in advance to detect potential problems more promptly. This allows for the analysis and evaluation of the environmental conditions of the area covered by the drone swarm's collaborative operations. For example, considering the maximum height difference of ground features, in areas with large height differences, the degree to which airflow is obstructed and affected by terrain is more complex, making wind shear more likely. Simultaneously, considering the average distance to adjacent ground features, in areas with a smaller average distance, i.e., areas with dense ground feature distribution, airflow is more easily disturbed, leading to wind shear. Under the combined influence of these characteristics, wind shear is more frequent and concentrated. This allows for the identification of areas with frequent wind shear, and the prediction of the drone swarm's arrival time in these areas. This enables early intervention in the drone swarm's collaborative operations, ensuring the overall smooth progress of the operation. This invention, while ensuring the safety and stability of drone swarm flight, helps drone swarms flexibly cope with interference risks, improves the overall operational efficiency and collaborative operation capabilities of the drone swarm, and reduces the possibility of operation failure due to interference.

[0112] Specifically, the adjustment prediction module is used to predict the time point at which the drone swarm arrives in the area with frequent wind shear, including,

[0113] Used to extract the execution time and corresponding flight distance of several instructions based on instruction execution data;

[0114] Used to obtain the currently executing instruction and determine the sequence of subsequent instructions following the currently executing instruction;

[0115] This is used to determine the region execution command corresponding to the edge of the area with frequent wind shear based on the flight distance of each executed command in the subsequent command sequence;

[0116] Used to determine, based on the subsequent instruction sequence, a number of intermediate instructions included in the current instruction to the region instruction;

[0117] Used to calculate the total execution time of each of the intermediate execution instructions;

[0118] This is used to sum the execution time up to the current moment as the time node.

[0119] Specifically, the interference assessment module is used to assess the involved characterization parameters of the UAV swarm, including,

[0120] The ratio of the number of drones to a threshold number of drones is used as the first interference feature;

[0121] The ratio of relative position density to density threshold is used as the second interference feature;

[0122] The sum of the first interfered feature and the second interfered feature is used to determine the involved characterization parameter.

[0123] In this embodiment, the purpose of setting the drone quantity threshold and density threshold is to characterize the situation where the scale distribution of drone swarms in areas with frequent wind shear significantly exacerbates the interference with collaborative operations. By acquiring historical data of several drone swarms collaboratively performing the same operation, and calling historical data of drone quantity and relative position density, the mean drone quantity and mean density are calculated and used as the benchmark quantities under normal conditions. Based on the purpose of setting the above two thresholds, the drone quantity threshold is determined as the product of the mean drone quantity and the quantity difference coefficient, and the density threshold is determined as the product of the mean density and the density offset coefficient. The quantity difference coefficient is selected within the interval [1.3, 1.5], preferably 1.3 in practice, and the density offset coefficient is selected within the interval [1.1, 1.2], preferably 1.1 in practice.

[0124] Specifically, the relative position density refers to the distance between adjacent drones in the vertical and horizontal directions in the spatial dimension, which will not be elaborated further.

[0125] Specifically, this invention includes an interference assessment module that, considering the impact of wind shear on the operation of a drone swarm, assesses the degree of interference aggravation among several drones operating in areas with frequent wind shear. This allows for a more accurate assessment of the risk level of a drone swarm operating in a corresponding area with frequent wind shear. For example, wind shear causes changes in wind speed and direction for drones. The more drones in an area, the greater the likelihood of being affected by wind shear airflows of different directions and intensities. These effects can also be superimposed, increasing the overall operational chaos of the drone swarm. Furthermore, if the drones are relatively densely packed within an area, it means that the distance between them is small. When wind shear causes changes in the drones' flight attitude, it may exceed the limits of their own capabilities. To ensure the stable operation of a drone swarm, this invention assesses the interference characteristics of a drone swarm by evaluating the number of drones and their relative density in areas with frequent wind shear. This parameter characterizes the degree to which the distribution of the drone swarm aggravates the impact of wind shear on the stable operation of the drone swarm, providing data support for subsequent determination of the interference level of the drone swarm. While ensuring the safety and stability of drone swarm flight, this invention helps drone swarms flexibly cope with interference risks, improves the overall operational efficiency and collaborative operation capabilities of the drone swarm, and reduces the possibility of operation failure due to interference.

[0126] Specifically, please refer to Figure 4As shown, this is a logic diagram for determining the interference level category of a drone swarm according to an embodiment of the present invention. The interference assessment module is used to determine the interference level category of the drone swarm, including...

[0127] If the involved characterization parameter of the drone swarm is greater than or equal to the involved characterization parameter threshold, then the interference level of the drone swarm is determined to be a strong interference category.

[0128] If the interference characterization parameter of the drone swarm is less than the threshold of the interference characterization parameter, then the interference level of the drone swarm is determined to be weak interference.

[0129] The threshold of the involved characterization parameter is predetermined. The involved characterization parameter is determined by calculating the threshold when the number of drones is equal to the threshold for the number of drones and the relative position density is equal to the threshold for the density.

[0130] Specifically, the involved scheduling module is used to adjust the scheduling of the drone swarm based on the category of interference level, including,

[0131] If the interference level of the drone swarm is classified as strong interference, then the flight trajectory of the drone swarm should be changed based on the involved characteristics.

[0132] If the interference level of the drone swarm is classified as weak interference, then the execution speed of the drone swarm will be reduced.

[0133] Specifically, the involved scheduling module is used to determine whether to change the flight trajectory of the UAV swarm based on involved characteristics, including:

[0134] Used to obtain relevant features based on command execution data, including the number of drones connected to areas with frequent wind shear and the corresponding complexity of command switching differences;

[0135] If the number of connected drones outside the area with frequent wind shear exceeds the threshold for the number of connected drones or / and the complexity of command switching differences exceeds the complexity threshold, then the flight trajectory of the drone swarm will be changed.

[0136] In this embodiment, the purpose of setting thresholds for the number of associated drones and complexity is to characterize the situation where drones affected by wind shear have a significant impact on unaffected drones. By acquiring historical data of several drone swarms cooperating in the same operation, several historical wind shear frequent areas are identified. Historical data on the number of associated drones outside each wind shear frequent area and historical data on the complexity difference of instruction switching are called to solve for the average number of associated drones and the average complexity, which are then used as the benchmark quantities under normal circumstances. Based on the purpose of setting the above two thresholds, the threshold for the number of associated drones is determined as the product of the average number of associated drones and the connection deviation coefficient, and the threshold for complexity is determined as the product of the average complexity and the complexity offset coefficient. The connection deviation coefficient is selected within the interval [1.2, 1.3], preferably 1.2 in practice, and the complexity offset coefficient is selected within the interval [1.2, 1.25], preferably 1.2 in practice.

[0137] Specifically, drones that have a positional connection with drones in areas with frequent wind shear (such as being adjacent to each other in any direction) and drones that have a sequential relationship in command execution are identified as associated drones.

[0138] In this embodiment, the number of actions required for a single instruction is used as the complexity, which will not be elaborated further.

[0139] In this embodiment, there is no limitation on the way to change the flight trajectory of the drone swarm. The flight trajectory that is far away from the area with frequent wind shear can be selected from several pre-stored flight trajectories to continue the collaborative operation.

[0140] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A low-altitude operation unmanned aerial vehicle cluster cooperative scheduling system, characterized in that, Comprising: a task storage module including a trajectory storage unit for storing flight trajectory data of a UAV group, an instruction storage unit for storing instruction execution data of each UAV, and an image storage unit for storing image data of a flight task; an analysis and marking module for identifying task resource features of the UAV group according to the instruction execution data, evaluating a mutual interference characteristic value of the UAV group based on the task resource features, and marking the UAV group; an adjustment and prediction module for analyzing and predicting the UAV group based on the marking result of the analysis and marking module, including, adjusting a detection frequency for the UAV group according to the mutual interference characteristic value, obtaining environment dispersion features of each flight coverage area, determining a wind shear frequent area based on the environment dispersion features, and predicting a time node at which the UAV group reaches the wind shear frequent area; an interference evaluation module for determining flight trajectories of the UAV group at the time node, obtaining a number of UAVs and a relative position density in the wind shear frequent area, evaluating a mutual interference characteristic parameter of the UAV group, and determining an interference degree category of the UAV group; a mutual interference scheduling module for scheduling and adjusting the UAV group based on the interference degree category, including, determining whether to change the flight trajectories of the UAV group based on the mutual interference features; or, reducing the execution speed of the UAV group; the analysis and marking module for evaluating the mutual interference characteristic value of the UAV group based on the task resource features, including, obtaining task resource features including the same frequency spectrum utilization and the same frequency band signal communication density; using the ratio of the same frequency spectrum utilization to a utilization threshold as a first mutual interference feature; using the ratio of the same frequency band signal communication density to a communication density threshold as a second mutual interference feature; determining the sum of the first mutual interference feature and the second mutual interference feature as the mutual interference characteristic value; the adjustment and prediction module for determining the wind shear frequent area based on the environment dispersion features, including, calling environment dispersion features of each flight coverage area, including a maximum height difference value of ground objects and a mean distance of adjacent ground objects; if any flight coverage area does not meet the environment dispersion condition, determining the flight coverage area as the wind shear frequent area; wherein the environment dispersion condition includes that the maximum height difference value of ground objects is less than a maximum height difference threshold and the mean distance of adjacent ground objects is greater than a distance mean threshold; the interference evaluation module for evaluating the mutual interference characteristic parameter of the UAV group, including, using the ratio of the number of UAVs to a UAV number threshold as a first interference feature; using the ratio of the relative position density to a density threshold as a second interference feature; determining the sum of the first interference feature and the second interference feature as the mutual interference characteristic parameter; the adjustment and prediction module for predicting the time node at which the UAV group reaches the wind shear frequent area, including, extracting execution times of a plurality of instructions and corresponding flight movement distances based on the instruction execution data; acquiring a current execution instruction and determining a subsequent instruction sequence of the current execution instruction; determining a region execution instruction corresponding to an edge of a wind shear frequent region according to a flight movement distance of each execution instruction in the subsequent instruction sequence; determining a plurality of intermediate execution instructions contained in the current execution instruction to the region execution instruction based on the subsequent instruction sequence; calculating a total execution time of each intermediate execution instruction; adding a current time to the total execution time as the time node; the involvement scheduling module is used to determine whether to change a flight trajectory of the UAV group based on the involvement feature, including, acquiring the involvement feature based on the instruction execution data, including a number of associated connection UAVs outside the wind shear frequent region and a corresponding instruction switching difference complexity; if the number of associated connection UAVs outside the wind shear frequent region is greater than a threshold value of the number of associated connection UAVs or / and the instruction switching difference complexity is greater than a complexity threshold value, the flight trajectory of the UAV group is changed. 2.The low-altitude operation drone swarm cooperative scheduling system according to claim 1, characterized in that, the analysis marking module is used to mark the UAV group, including, if a mutual interference representation value of the UAV group is greater than or equal to a mutual interference representation threshold value, the analysis marking module sets a cooperative turbulence label for the UAV group. 3.The low-altitude operation drone swarm cooperative scheduling system according to claim 2, characterized in that, the adjustment prediction module is used to analyze and predict the UAV group based on a marking result of the analysis marking module, including, if the UAV group is set with the cooperative turbulence label, the UAV group is analyzed and predicted.

4. The low-altitude operation drone cluster cooperative scheduling system according to claim 1, characterized in that, the interference evaluation module is used to determine an interference degree category of the UAV group, including, if an involvement representation parameter of the UAV group is greater than or equal to an involvement representation parameter threshold value, the interference degree category of the UAV group is determined as a strong interference category; if the involvement representation parameter of the UAV group is less than the involvement representation parameter threshold value, the interference degree category of the UAV group is determined as a weak interference category.

5. The low-altitude operation drone cluster cooperative scheduling system according to claim 4, characterized in that, the involvement scheduling module is used to schedule and adjust the UAV group based on the interference degree category, including, if the interference degree category of the UAV group is the strong interference category, it is determined whether to change the flight trajectory of the UAV group based on the involvement feature; if the interference degree category of the UAV group is the weak interference category, the execution speed of the UAV group is reduced.

Images