Path optimization method and system for unmanned aerial vehicle logistics distribution

Abstract

The invention discloses a path optimization method and system for unmanned aerial vehicle logistics distribution, and relates to the technical field of unmanned aerial vehicle logistics distribution, and the method comprises the following steps: obtaining all executable distribution paths, screening an unmanned aerial vehicle logistics distribution default execution path, obtaining unmanned aerial vehicle distribution state parameters, and analyzing unmanned aerial vehicle logistics distribution state characterization parameters. Path influence parameters of default distribution sub-paths are collected, unmanned aerial vehicle default distribution sub-path optimization label information is judged, all standby sub-paths are counted, logistics adaptation execution priority values of all the standby sub-paths are analyzed, and therefore unmanned aerial vehicle logistics distribution optimal sub-paths are screened and optimized execution is carried out. The unmanned aerial vehicle distribution efficiency and safety can be improved, complex and changeable meteorological conditions and obstacle conditions can be effectively handled, the distribution time and energy consumption are reduced, the adaptability of the unmanned aerial vehicle in a complex environment is enhanced, and smooth completion of a distribution task is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle logistics distribution, and specifically to a path optimization method and system for unmanned aerial vehicle logistics distribution. Background Art

[0002] With the continuous economic growth and the booming development of e-commerce, consumers' expectations for the speed of product delivery and service quality are constantly increasing. Drone logistics delivery has emerged as an innovative solution. Drones are gradually playing an important role in the field of logistics and delivery due to their flexibility, efficiency and freedom from terrain restrictions.

[0003] Existing technologies, such as the invention patent with announcement number: CN113283827B, are a two-stage UAV logistics path planning method based on deep reinforcement learning. First, by preprocessing the logistics distribution area and related data, a deep reinforcement learning model is constructed, and the corresponding UAV flight state space, action space and reward value function are established. The deep reinforcement learning model is trained by combining offline learning and online learning methods; secondly, a two-stage optimization method is used to plan the logistics distribution path and flight path in the UAV logistics process. The UAV flight path planning stage is mainly completed based on real-time action selection based on deep reinforcement learning.

[0004] The prior art, such as the invention patent with announcement number: CN110222890B, is a double-layer path optimization method and system for vehicle and drone logistics distribution. The method includes: establishing a double-layer path for logistics distribution including a main path for vehicle distribution and a companion route for drones; grouping customer nodes that need distribution into neighborhoods according to the double-layer path, and each neighborhood group corresponds to a section of the double-layer path; respectively reallocating the positions of customer nodes in each neighborhood group on their corresponding double-layer paths to determine the most cost-saving path for each neighborhood group, merging the most cost-saving paths for each neighborhood group, and obtaining the double-layer path for vehicle and drone logistics distribution.

[0005] Based on the above solutions, it can be seen that the current drone logistics distribution path optimization method needs to be improved in terms of real-time and adaptability. It usually plans distribution based on a fixed path and adjusts and optimizes it during the distribution process. However, in actual drone logistics distribution application scenarios, the factors affecting distribution are diverse and uncertain. Real-time adjustment and optimization overly rely on the drone's real-time perception of the surrounding environment. It may not be possible to quickly re-plan the optimal path, increasing delivery time and energy consumption. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides a path optimization method and system for drone logistics distribution, which can effectively solve the problems involved in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: In a first aspect, the present invention provides a path optimization method for drone logistics distribution, which is characterized by comprising the following steps: S1, obtain each executable delivery path between the starting node and the terminal arrival node of the drone logistics delivery, record them as each executable delivery path, count the environmental impact data and obstacle distribution data of each executable delivery path, and screen the default execution path of the drone logistics delivery based on the environmental impact data and obstacle distribution data of each executable delivery path.

[0008] S2, controls the UAV logistics distribution with the default execution path of the UAV logistics distribution, monitors the logistics distribution process, obtains the UAV delivery status parameters, and analyzes the UAV logistics distribution status characterization parameters.

[0009] S3, obtain the default execution path between the path node that the drone is about to reach and the next path node, mark it as the default delivery sub-path, collect the path influencing parameters of the default delivery sub-path, and determine the drone's default delivery sub-path optimization label information in combination with the drone's logistics delivery state characterization parameters. The drone's default delivery sub-path optimization label information includes demand optimization and no optimization required.

[0010] S4, when the result of the optimization label information of the drone's default delivery sub-path is determined to be demand optimization, the various alternative delivery sub-paths between the path node that the drone is about to reach and the next path node are counted and marked as alternative sub-paths, the path interference data of each alternative sub-path is obtained, and the logistics adaptation execution priority value of each alternative sub-path is analyzed, thereby screening the optimal sub-path for drone logistics delivery and optimizing the execution.

[0011] The second aspect of the present invention provides a path optimization system for drone logistics delivery, including: a drone logistics delivery default execution path screening module, which is used to obtain each executable delivery path between the drone logistics delivery starting node and the terminal arrival node, recorded as each executable delivery path, and count the environmental impact data and obstacle distribution data of each executable delivery path, and based on the environmental impact data and obstacle distribution data of each executable delivery path, screen the drone logistics delivery default execution path.

[0012] The drone logistics delivery status analysis module controls the drone logistics delivery based on the default execution path of the drone logistics delivery, monitors the logistics delivery process, obtains the drone delivery status parameters, and analyzes the drone logistics delivery status characterization parameters.

[0013] The default delivery sub-path optimization determination module is used to obtain the default execution path between the path node that the drone is about to reach and the next path node, mark it as the default delivery sub-path, collect the path influencing parameters of the default delivery sub-path, and determine the drone's default delivery sub-path optimization label information in combination with the drone's logistics delivery state characterization parameters. The drone's default delivery sub-path optimization label information includes demand optimization and no optimization required.

[0014] The optimal sub-path screening module for drone logistics distribution is used to count the various alternative distribution sub-paths between the path node that the drone is about to reach and the next path node when the drone's default delivery sub-path optimization label information is determined as demand optimization, mark them as alternative sub-paths, obtain the path interference data of each alternative sub-path, and analyze the logistics adaptation execution priority value of each alternative sub-path, thereby screening the optimal sub-path for drone logistics distribution and optimizing its execution.

[0015] Compared with the prior art, the embodiments of the present invention have at least the following beneficial effects: (1) The present invention provides a path optimization method and system for drone logistics delivery, which can improve the efficiency and safety of drone delivery. By accurately acquiring and analyzing the environmental impact data and obstacle distribution data of each executable delivery path, combined with the real-time delivery status parameters of the drone, the default execution path is screened out before delivery, and the sub-path optimization requirements are determined in real time during the flight, and the optimal sub-path is adjusted in time, effectively coping with complex and changeable meteorological conditions and obstacles, reducing delivery time and energy consumption, enhancing the adaptability of the drone in complex environments, and ensuring the smooth completion of the delivery task.

[0016] (2) The present invention screens the default execution path for UAV logistics delivery based on the environmental impact data and obstacle distribution data of each executable delivery path. In the early stage of path planning, it fully considers meteorological factors and obstacle conditions, which can effectively avoid the UAV from encountering extreme weather or complex obstacle environments during the delivery process, improve the scientificity and rationality of path selection, and the accurately screened default execution path enables the UAV to fly along a relatively optimal trajectory in the initial delivery stage, reducing the speed reduction, energy consumption increase and collision risk caused by environmental factors, laying a solid foundation for the smooth implementation of subsequent delivery tasks, ensuring delivery efficiency and safety, and reducing operating costs and potential losses.

[0017] (3) The present invention determines the optimization label information of the drone's default delivery sub-path by combining the parameters characterizing the drone's logistics delivery status, and evaluates the adaptability of the current default delivery sub-path during the delivery process, so that the drone can timely and accurately identify whether the path needs to be optimized, avoiding problems such as inefficiency and excessive energy consumption caused by continuing to fly on an unsuitable path. By dynamically adjusting the path, it ensures that the drone always operates on the optimal path that matches its own status and environmental conditions, thereby improving delivery efficiency, reducing energy consumption, and enhancing flight safety, providing a guarantee for the efficient and stable operation of drone logistics delivery.

[0018] (4) The present invention screens the optimal sub-paths for UAV logistics distribution and optimizes their execution, so that the UAV can switch to the most suitable path in time to continue flying when facing complex and changing environments and real-time distribution status changes. This not only avoids delivery delays caused by poor paths and greatly improves delivery efficiency, but also avoids energy consumption caused by flying on bad or mismatched paths, reduces the loss of UAVs, and extends their service life. At the same time, the optimized path can better adapt to the environment, thereby reducing safety risks such as collisions, ensuring the safety and stability of the distribution process, and improving the overall performance of UAV logistics distribution.

[0019] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a schematic diagram of the method flow of the present invention.

[0021] Figure 2 It is a schematic diagram of system module connection of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] See also Figure 1 As shown, an embodiment of the present invention provides a path optimization method for drone logistics delivery, including the following steps: S1, obtaining each executable delivery path between the drone logistics delivery starting node and the terminal arrival node, recorded as each executable delivery path, counting the environmental impact data and obstacle distribution data of each executable delivery path, and based on the environmental impact data and obstacle distribution data of each executable delivery path, screening the drone logistics delivery default execution path.

[0024] It should be understood that the acquisition of each executable delivery path between the drone logistics delivery starting node and the terminal arrival node refers to the set of all theoretically fixed paths available for drone flight from the delivery starting node to the terminal arrival node determined during the drone logistics delivery task planning stage based on multiple factors such as the geographic information system data of the delivery area, airspace restriction information, and the drone's own performance parameters.

[0025] In this embodiment, the environmental impact data and obstacle distribution data of each executable delivery path are counted, wherein: the environmental impact data of each executable delivery path includes the average wind speed, average humidity, average temperature and air pressure fluctuation value of each executable delivery path.

[0026] It should be noted that the environmental impact data of each executable delivery path is obtained by acquiring and analyzing the meteorological data collected by the meteorological station in the logistics distribution area. The meteorological station is equipped with high-precision meteorological measuring instruments such as anemometers, hygrometers, thermometers, barometers, etc., which can collect meteorological data in real time.

[0027] The obstacle distribution data is specifically obtained by the following method: obtaining a three-dimensional spatial distribution map of the drone logistics distribution area, and segmenting and extracting the three-dimensional spatial distribution map of each executable distribution path area.

[0028] It should be understood that the segmentation and extraction of the three-dimensional spatial distribution map of each executable delivery path area is a specific process of recording each executable delivery path as a segmentation baseline of the drone logistics delivery area, and based on the pre-set minimum width required for drone logistics flight, extending each segmentation baseline of the drone logistics delivery area to both sides with the minimum width required for drone logistics flight, thereby constructing each executable delivery path plane, and obtaining the three-dimensional spatial distribution map of each executable delivery path area based on vertical cutting of each executable delivery path plane.

[0029] Based on the three-dimensional spatial distribution map of each executable delivery path area, the volume of each executable delivery path area is obtained, and the unit length of the cube unit division corresponding to the volume of each area preset in the database is extracted. The unit length of the cube unit division corresponding to the volume of each executable delivery path area is mapped and extracted, and recorded as the unit length of the cube unit division of each executable delivery path area.

[0030] The three-dimensional spatial distribution map of each executable delivery path is evenly divided into cubic units according to the unit length of the cubic unit division unit of each executable delivery path area. The number of cubic units occupied by each obstacle is identified and located, and the volume of all obstacles is counted. The cumulative obstacle volume of each executable delivery path is traversed in turn and obtained.

[0031] In a specific embodiment, the scale of the three-dimensional spatial distribution map of each executable delivery path is 1:1000. For example, the volume of a certain executable delivery path area is 2000 cubic meters, and the corresponding cubic unit division unit length in the database is 2 meters. Then, according to the determined cubic unit division unit length of 2 meters, the three-dimensional spatial distribution map of the executable delivery path area is divided along the x, y, and z coordinate axes. In the x-axis direction, starting from the minimum coordinate value of the area, a division plane is determined every 2 meters. Similarly, similar operations are performed in the y-axis and z-axis directions. In this way, the entire area is divided into a series of cubic units with a side length of 2 meters.

[0032] Identify and locate the point cloud data of each obstacle in the three-dimensional spatial distribution map of each executable delivery path area, identify and extract the shortest interval distance between the highest point of each obstacle and the corresponding executable delivery path, and traverse and obtain the minimum distance between each executable path and the highest point of the obstacle in turn.

[0033] It should be understood that, in a specific embodiment, point cloud data can be obtained by taking images of the same scene from different angles using a stereo camera, and the depth information of the object is calculated by comparing the parallax in the images to generate a three-dimensional point cloud.

[0034] The vertical height of each obstacle in each executable delivery path area is counted, and the path point corresponding to the shortest interval distance between the highest point of each obstacle and the corresponding executable delivery path is recorded as each influencing path point. The vertical height of each influencing path point in each executable delivery path area is counted. If the vertical height of the highest point of an obstacle in each executable delivery path area is greater than or equal to the vertical height of the nearest influencing path point, the highest point of the obstacle is recorded as the estimated obstacle crossing point, thereby counting the estimated number of obstacle crossing points of each executable path.

[0035] The three-dimensional spatial distribution map of each executable delivery path area is projected into a two-dimensional distribution map, and the obstacle pixels are identified and located to calculate the area occupied by the obstacle. The obstacle distribution area ratio is calculated based on the area of ​​the two-dimensional distribution map, thereby obtaining the obstacle distribution area ratio of each executable delivery path.

[0036] The cumulative obstacle volume of each executable delivery path, the minimum distance between each executable path and the highest point of the obstacle, the estimated number of obstacle points crossed by each executable path, and the proportion of the obstacle distribution area of ​​each executable delivery path are combined as the obstacle distribution data of each executable delivery path.

[0037] In this embodiment, the default execution paths for drone logistics delivery are screened, and the specific screening process is as follows: the execution fit index of each executable delivery path is analyzed according to the environmental impact data and obstacle distribution data of each executable delivery path, and the execution fit index of each executable delivery path is used to characterize the degree of fit of the drone logistics delivery execution of each executable delivery path.

[0038] In a specific embodiment, the execution compatibility index of each executable delivery path is obtained in the following manner: Extract the ideal environmental impact data and reference obstacle distribution data preset in the database.

[0039] The ideal environmental impact data includes the ideal wind speed, ideal humidity, ideal temperature and reference air pressure fluctuation values ​​for drone logistics delivery.

[0040] The reference obstacle distribution data includes the reference path obstacle volume of the drone logistics delivery path, the minimum distance between the reference path and the highest point of the obstacle, the estimated number of obstacle points crossed by the reference path, and the proportion of the reference path obstacle distribution area.

[0041] The ideal environmental impact data and reference obstacle distribution data are obtained by averaging the historical data of environmental impact data and obstacle distribution data of each executable delivery path before establishing the database.

[0042] According to the environmental impact data, obstacle distribution data, ideal environmental impact data and reference obstacle distribution data of each executable delivery path, the execution fit index of each executable delivery path is obtained through analysis and processing.

[0043] , in, is the execution fit index of the ith executable delivery path, is the average wind speed of the ith executable delivery path, The ideal wind speed for drone logistics delivery, is the average humidity of the ith executable delivery route, Ideal humidity for drone logistics delivery, is the average temperature of the ith executable delivery route, The ideal temperature for drone logistics delivery, is the air pressure fluctuation value of the ith executable delivery route, is the reference air pressure fluctuation value for drone logistics delivery. is the cumulative obstacle volume of the ith executable delivery path, is the reference path obstacle volume of the UAV logistics delivery path, is the minimum distance between the ith executable path and the highest point of the obstacle, is the minimum distance between the reference path of the UAV logistics delivery path and the highest point of the obstacle, is the estimated number of obstacle points crossed by the i-th executable path, Estimate the number of obstacles that can be crossed for the reference path of the UAV logistics delivery route. is the obstacle distribution area ratio of the i-th executable delivery path, is the percentage of obstacle distribution area on the reference path of the UAV logistics delivery path, is the average wind speed weight, is the average humidity weight, is the average temperature weight, is the air pressure fluctuation weight, is the cumulative obstacle volume weight, is the minimum distance weight between the path and the highest point of the obstacle, To estimate the weight of the number of obstacle crossing points, is the weight of the obstacle distribution area, i is the number of each executable delivery path, , m is the number of executable delivery paths, and e is a natural constant.

[0044] It should be noted that the average wind speed weight, average humidity weight, average temperature weight, air pressure fluctuation value weight, cumulative obstacle volume weight, minimum distance weight between the path and the highest point of the obstacle, estimated number of obstacle crossing points weight and obstacle distribution area ratio weight all have a value range between 0 and 1. In this embodiment, the average wind speed weight is the average wind speed weight preset in the database, which represents the numerical value of the influence of the average wind speed on the execution fit index of the executable delivery path. The average humidity weight is the average humidity weight preset in the database, which represents the numerical value of the influence of the average humidity on the execution fit index of the executable delivery path. The average temperature weight is a numerical value. The average temperature weight preset in the database indicates the numerical value of the influence of the average temperature on the execution fit index of the executable delivery path. The air pressure fluctuation value weight is the air pressure fluctuation value weight preset in the database, indicating the numerical value of the influence of the air pressure fluctuation value on the execution fit index of the executable delivery path. The cumulative obstacle volume weight is the cumulative obstacle volume weight preset in the database, indicating the numerical value of the influence of the cumulative obstacle volume on the execution fit index of the executable delivery path. The minimum distance weight between the path and the highest point of the obstacle is the minimum distance weight between the path and the highest point of the obstacle preset in the database, indicating the minimum distance between the path and the highest point of the obstacle. The weight of the estimated number of obstacle crossing points is the weight of the estimated number of obstacle crossing points preset in the database, which indicates the influence of the estimated number of obstacle crossing points on the execution fit index of the executable delivery path. The weight of the obstacle distribution area ratio is the weight of the obstacle distribution area ratio preset in the database, which indicates the influence of the obstacle distribution area ratio on the execution fit index of the executable delivery path. When used, the preset average wind speed weight, average humidity weight, average temperature weight, air pressure fluctuation value weight, cumulative obstacle volume weight, path and obstacle weight can be directly obtained from the database. The corresponding relationship between the minimum distance weight between the highest point of the obstacle, the estimated number of obstacle crossing points and the weight of the obstacle distribution area ratio may be a preset mapping relationship. For example, the average wind speed, average humidity, average temperature, air pressure fluctuation value, cumulative obstacle volume, the minimum distance between the path and the highest point of the obstacle, the estimated number of obstacle crossing points and the obstacle distribution area ratio are respectively mapped with the average wind speed weight, average humidity weight, average temperature weight, air pressure fluctuation value weight, cumulative obstacle volume weight, the minimum distance weight between the path and the highest point of the obstacle, the estimated number of obstacle crossing points and the obstacle distribution area ratio preset in the database to form a mapping set.The real-time average wind speed, average humidity, average temperature, air pressure fluctuation value, cumulative obstacle volume, minimum distance between the path and the highest point of the obstacle, estimated number of obstacle crossing points and obstacle distribution area ratio are input into the mapping set to obtain the average wind speed weight, average humidity weight, average temperature weight, air pressure fluctuation value weight, cumulative obstacle volume weight, minimum distance between the path and the highest point of the obstacle, estimated number of obstacle crossing points weight and obstacle distribution area ratio weight, where the mapping relationship is one-to-one correspondence. ,

[0045] It should also be noted that in this embodiment, the execution fit index of the executable delivery path is obtained by processing the executable delivery path environmental impact data and obstacle distribution data, taking into account the mutual influence between these parameters. For example, there is a close relationship between wind speed and air pressure. According to the Bernoulli principle, the air pressure in the area with higher wind speed is relatively low. High-speed airflow accelerates heat exchange. Changes in wind direction may cause the drone to pass through different air pressure areas, resulting in changes in air pressure fluctuation values. For example, when the drone flies from a high-pressure area to a low-pressure area and the wind direction has a certain angle with the flight direction, the air pressure change will cause the drone to produce vertical force changes, affecting the flight altitude stability and increasing the flight altitude fluctuation extreme value. The wind direction will affect the distribution of heat on the surface of the drone. Different wind directions may cause different parts of the drone to be heated or dissipated differently. Air pressure fluctuations will affect the convection and heat exchange process of the air. When the air pressure decreases, the air may rise and cool, resulting in a decrease in local temperature. Conversely, when the air pressure increases, the air sinks and compresses, and the temperature may increase. Higher wind speeds will cause the drone to be subject to stronger airflow disturbances when approaching obstacles. When encountering an area with a large cumulative obstacle volume, strong winds may make it difficult for the drone to accurately control the flight trajectory, increase the risk of collision with obstacles, and affect the minimum distance and the estimated number of obstacle crossing points. For example, when there are many obstacles in a narrow passage and the wind speed is high, the drone may be blown toward the obstacle by the wind, which will reduce the minimum distance and increase the estimated number of obstacle crossing points. Wind direction will affect the flight path of the drone in the obstacle area, and air pressure fluctuations will affect the stability of the drone's flight altitude. In areas with many obstacles, unstable flight altitude will increase the risk of collision with obstacles. For example, when the air pressure suddenly drops, the drone may descend. If there is an obstacle below at this time, the minimum distance will decrease and the estimated number of obstacle crossing points may increase. A large cumulative obstacle volume usually means that the obstacles are densely distributed, which will result in a decrease in the minimum distance between each execution path and the highest point of the obstacle because the space available for the drone to safely pass is reduced. At the same time, dense obstacles will increase the number of estimated obstacle crossing points, and the obstacle distribution area will also increase accordingly. The paths with smaller minimum distances have more obstacles around them, and the estimated number of obstacle crossing points may increase, because the drone is more likely to approach obstacles and need to cross more obstacles during flight. At the same time, a smaller minimum distance is usually associated with a larger obstacle distribution area, because densely distributed obstacles will lead to a smaller minimum distance.

[0046] In a specific embodiment, by analyzing the execution fit index of each executable delivery path, a scientific and reasonable path selection basis is provided for the drone in the early stage of path planning, avoiding it from encountering extreme weather or complex obstacle environments during delivery, improving the accuracy and scientificity of path selection, and enabling the drone to fly along a relatively optimal trajectory in the initial delivery stage, reducing the negative impact of environmental factors on speed, energy consumption and safety, and laying the foundation for the smooth implementation of delivery tasks. At the same time, through a comprehensive evaluation of multiple factors, it is possible to fully consider various influences in the delivery process, effectively improve delivery efficiency and safety, enhance the adaptability of drones in complex environments, and improve the overall quality and reliability of drone logistics delivery.

[0047] The executable delivery path corresponding to the maximum execution fit index is extracted and recorded as the default execution path for drone logistics delivery.

[0048] In a specific embodiment, the default execution path for drone logistics delivery is screened based on the environmental impact data and obstacle distribution data of each executable delivery path. In the early stage of path planning, meteorological factors and obstacle conditions are fully considered, which can effectively avoid the drone from encountering extreme weather or complex obstacle environments during the delivery process, improve the scientificity and rationality of path selection, and the accurately screened default execution path enables the drone to fly along a relatively optimal trajectory in the initial delivery stage, reducing the speed reduction, increased energy consumption and collision risks caused by environmental factors, laying a solid foundation for the smooth implementation of subsequent delivery tasks, ensuring delivery efficiency and safety, and reducing operating costs and potential losses.

[0049] S2, controls the UAV logistics distribution with the default execution path of the UAV logistics distribution, monitors the logistics distribution process, obtains the UAV delivery status parameters, and analyzes the UAV logistics distribution status characterization parameters.

[0050] In this embodiment, the parameters characterizing the drone logistics delivery status are analyzed, and the specific analysis process is as follows: the drone delivery status parameters include the extreme value difference of the drone's attitude angle deviation in the flown section, the extreme value difference of the flight altitude fluctuation, the total energy consumption and the extreme value difference of the flight speed change.

[0051] It should be noted that the drone delivery status parameters are obtained through the drone's built-in sensor device, which includes a gyroscope, a barometric altimeter, a power sensor and a speed sensor.

[0052] It should also be noted that the extreme deviation of the attitude angle of the UAV in the flown section is obtained by continuously monitoring and calculating the maximum and minimum deviations between the attitude angle and the ideal flight attitude angle through the built-in gyroscope of the UAV from takeoff to the current flown path, and then performing difference processing. The gyroscope can accurately measure the rotational angular velocity of the UAV around three coordinate axes (pitch, roll, yaw), and then integrate to obtain real-time attitude angle information, and compare these real-time attitude angles with the preset ideal attitude angles that should be maintained in a stable flight state, for example, the pitch angle and roll angle are close to 0 degrees, and the yaw angle is determined according to the predetermined flight direction, and the deviation values ​​are calculated one by one. Among the series of deviation values ​​generated in the entire flown section, the positive value with the largest absolute value is the maximum deviation of the attitude angle, and the negative value with the largest absolute value is the minimum deviation of the attitude angle, which provides a key basis for evaluating the stability and control accuracy of the UAV flight, and helps to further analyze the overall flight status of the UAV in the flown section and predict the risks that may be faced in subsequent flights.

[0053] According to the delivery status parameters of the drone on the flown section, the drone logistics delivery status characterization parameters are analyzed and processed to obtain the drone logistics delivery status characterization parameters, which are used to characterize the flight status of the drone on the flown section.

[0054] In a specific embodiment, the drone logistics delivery status characterization parameter is obtained in the following manner: The reference state parameters of drone delivery stored in the database are extracted, wherein the reference state parameters of drone delivery include the reference attitude angle deviation extreme value difference of drone delivery, the reference flight altitude fluctuation extreme value difference, the reference total energy consumption and the reference flight speed change extreme value difference.

[0055] The reference state parameters of the UAV delivery are obtained by averaging a large amount of historical data on attitude angle deviation extreme value difference, flight altitude fluctuation extreme value difference, total energy consumption and flight speed change extreme value difference before establishing the database.

[0056] , in, is the parameter representing the state of UAV logistics delivery. is the extreme value difference of the attitude angle deviation of the UAV in the flight section. is the extreme value difference of the reference attitude angle deviation of the drone delivery, is the extreme value difference of the flight altitude fluctuation of the UAV in the flight section, is the extreme value difference of the reference flight altitude fluctuation of drone delivery, is the total energy consumed by the drone in the flight segment, is the reference total energy consumption of drone delivery, is the extreme value difference of the flight speed change of the UAV in the flight section. is the extreme value difference of the reference flight speed change of drone delivery, is the extreme difference weight of attitude angle deviation, is the flight altitude fluctuation extreme value difference weight, is the total energy consumption weight, is the weight of the extreme difference of flight speed change, and e is a natural constant.

[0057] It should be noted that the weight of the attitude angle deviation extreme value difference, the flight altitude fluctuation extreme value difference, the total energy consumption weight and the flight speed change extreme value difference all have a value range between 0 and 1. In this embodiment, the attitude angle deviation extreme value difference weight is the attitude angle deviation extreme value difference weight preset in the database, which indicates the numerical value of the influence of the attitude angle deviation extreme value difference on the parameter characterizing the state of the UAV logistics delivery. The flight altitude fluctuation extreme value difference weight is the flight altitude fluctuation extreme value difference weight preset in the database, which indicates the numerical value of the influence of the flight altitude fluctuation extreme value difference on the parameter characterizing the state of the UAV logistics delivery. The total energy consumption weight is the total energy consumption weight preset in the database, which indicates the numerical value of the influence of the total energy consumption on the parameter characterizing the state of the UAV logistics delivery. The flight speed change extreme value difference weight is the flight speed change extreme value difference weight preset in the database, which indicates the influence of the flight speed change extreme value difference on the UAV. The numerical value of the influence degree of the logistics distribution state characterization parameter can directly obtain the preset attitude angle deviation extreme value difference weight, flight altitude fluctuation extreme value difference weight, total energy consumption weight and flight speed change extreme value difference weight from the database when used, and the corresponding relationship can be a pre-set mapping relationship. For example, the attitude angle deviation extreme value difference, flight altitude fluctuation extreme value difference, total energy consumption and flight speed change extreme value difference are respectively formed into a mapping set with the attitude angle deviation extreme value difference weight, flight altitude fluctuation extreme value difference weight, total energy consumption weight and flight speed change extreme value difference weight preset in the database, and the real-time attitude angle deviation extreme value difference, flight altitude fluctuation extreme value difference, total energy consumption and flight speed change extreme value difference are respectively input into the mapping set to obtain the attitude angle deviation extreme value difference weight, flight altitude fluctuation extreme value difference weight, total energy consumption weight and flight speed change extreme value difference weight, wherein the mapping relationship is one-to-one corresponding.

[0058] It should also be noted that in this embodiment, the drone logistics distribution state characterization parameters are obtained by analyzing and processing the drone distribution state parameters of the flown section, taking into account the mutual influence between these parameters. For example, when the drone has a large attitude angle deviation extreme value in the flown section, such as a large pitch angle or roll angle deviation, the angle between the drone's wing or fuselage and the airflow will change, thereby making the air resistance distribution uneven, which will increase the power required for the drone to maintain flight, and then lead to an increase in total energy consumption. In order to correct the attitude deviation, the drone's flight control system will adjust the motor speed or the rudder angle. This process will cause the flight speed to change, so that the flight speed change extreme value increases. A large flight altitude fluctuation extreme value means that the drone cannot stably maintain a predetermined altitude during flight. Frequent altitude adjustments will cause the drone to need to constantly change power output, increase energy consumption, and increase total energy consumption. During the altitude adjustment process, the pitch angle of the drone will change, thereby affecting the attitude angle. The increase in total energy consumption may be due to the large resistance encountered by the drone during flight, which is usually accompanied by a decrease in flight speed. In order to maintain a certain delivery efficiency, the drone may try to increase power output, but if the energy supply is limited or the power system cannot meet the demand, the flight speed may fluctuate greatly, resulting in an increase in the extreme value of flight speed change. Frequent acceleration and deceleration will cause the momentum of the drone to change frequently, which puts higher requirements on flight attitude control and easily causes attitude angle deviation. Unstable flight speed will also affect the altitude control of the drone. According to the principles of aerodynamics, changes in flight speed will cause changes in lift. When the speed decreases, the lift decreases, and the drone may show a tendency to sink. In order to maintain altitude, it is necessary to adjust the attitude or increase power, which will further affect the flight altitude fluctuation and increase the extreme value of flight altitude fluctuation. At the same time, frequent speed adjustments will also consume more energy, resulting in an increase in total energy consumption.

[0059] In a specific embodiment, by analyzing the parameters characterizing the state of drone logistics delivery, the flight state of the drone in the flown section can be effectively evaluated, the flight state of the drone can be grasped, and the operator can timely understand the actual situation of the drone during the delivery process so as to make more reasonable decisions, which helps to improve the overall performance of drone logistics delivery, ensure the smooth completion of delivery tasks, enhance the adaptability of drones in complex environments, reduce delivery delays caused by poor flight conditions, and improve delivery efficiency and safety.

[0060] In a specific embodiment, the drone logistics delivery status threshold preset in the database is extracted. If the drone logistics delivery status characterization parameter is less than the drone logistics delivery status threshold, the drone flight control continues. If the drone logistics delivery status characterization parameter is greater than or equal to the drone logistics delivery status threshold, the drone is controlled to fly to the nearest mission turning point and stop.

[0061] It should be noted that the drone logistics delivery status threshold is extracted from the database and is used to measure whether the drone's current flight status is at a critical indicator for safely and efficiently performing delivery tasks.

[0062] In a specific embodiment, there are multiple ways to set the drone logistics distribution state threshold. On the one hand, it can be determined through a large amount of actual flight test data. Under different meteorological conditions and drone load conditions, various flight state parameters of the drone are collected, and these data are analyzed in detail to determine the boundary values ​​of the state parameters under which the drone can operate stably and ensure the distribution efficiency under different conditions. These boundary values ​​are processed comprehensively, such as taking the average value, weighted average, or setting a certain safety margin according to the actual situation to obtain the drone logistics distribution state threshold. Once the threshold is exceeded, it means that the drone may face greater risks or a serious decline in efficiency, and corresponding measures need to be taken in time, such as flying to the nearest mission turning point for adjustment or maintenance to ensure the smooth progress of the distribution task.

[0063] It should also be noted that if the parameter characterizing the drone's logistics delivery status is less than the drone's logistics delivery status threshold, it means that the drone's current flight status is relatively stable and all flight parameters are within a reasonable range. If the parameter characterizing the drone's logistics delivery status is greater than or equal to the drone's logistics delivery status threshold, it means that the drone's current flight status is abnormal or faces a greater risk, causing its flight performance to be affected. At this time, control the drone to fly to the nearest mission turning point and stop, so as to facilitate timely inspection, maintenance or adjustment of the drone to ensure the safety and smooth progress of subsequent delivery tasks.

[0064] It should be understood that the mission turning point refers to the mission turning point of drone logistics distribution. In a specific embodiment, the locations of fixed logistics facilities such as logistics distribution centers within the distribution area can be used as mission turning points. When the drone status is abnormal, flying to these locations is convenient for equipment maintenance, energy replenishment or cargo redeployment and other operations. It can also be a pre-set safe area on the distribution route that can be temporarily docked and has certain security conditions, such as a specially set drone emergency landing field. When encountering sudden severe weather conditions, the drone can quickly fly here to take shelter and wait for the weather conditions to improve before continuing the delivery mission or accepting further instructions and arrangements, thereby effectively ensuring the safety of the drone and the smooth progress of the delivery mission.

[0065] S3, obtain the default execution path between the path node that the drone is about to reach and the next path node, mark it as the default delivery sub-path, collect the path influencing parameters of the default delivery sub-path, and determine the drone's default delivery sub-path optimization label information in combination with the drone's logistics delivery state characterization parameters. The drone's default delivery sub-path optimization label information includes demand optimization and no optimization required.

[0066] It should be noted that the path node refers to a location identifier with a specific logical meaning set in the distribution path planning process based on multiple factors such as the distribution area's geographical information, meteorological data, obstacle distribution, and logistics distribution strategy, rather than an actual physical entity.

[0067] In this embodiment, the path influencing parameters of the default delivery sub-path are collected. The specific process is as follows: the average wind speed, average humidity, air pressure fluctuation value and average humidity of the default delivery sub-path during the period when the drone is expected to pass are obtained, and combined as the meteorological data of the default delivery sub-path.

[0068] It should be noted that the method for obtaining the estimated time period for the drone to pass is as follows: obtain the distance between the drone's current location and the starting point of the default delivery sub-path, collect the drone's flight speed through the drone's built-in speed sensor, and then divide the distance by the speed to calculate the time required to reach the starting point of the default delivery sub-path, simultaneously obtain the length of the default delivery sub-path, calculate the flight time required for the drone to pass through the default delivery sub-path, and based on the time required to reach the starting point of the default delivery sub-path and the flight time required for the drone to pass through the default delivery sub-path, obtain the estimated time period for the drone to pass.

[0069] The number of drones in the default delivery sub-path during the period when the drones are expected to pass through, the average flight speed of drones, and the number of drones flying in the opposite direction are obtained, and the flight influencing parameters of the path used as the default delivery sub-path are combined.

[0070] It should be noted that the flight influencing parameters of the default delivery sub-path are collected by the UAV logistics delivery control terminal, and the UAV logistics delivery control terminal is used to store the flight status data of each UAV in real time.

[0071] The meteorological data of the default delivery sub-path and the path in-flight impact parameters of the default delivery sub-path are combined as the path impact parameters of the default delivery sub-path.

[0072] In this embodiment, the drone's default delivery sub-path optimization label information is determined, and the specific determination process is as follows: the drone's default delivery sub-path optimization label information includes demand optimization and no need for optimization.

[0073] According to the path influence parameters of the default delivery sub-path, the path interference indicator parameters of the default delivery sub-path are analyzed and processed to obtain the path interference indicator parameters of the default delivery sub-path, and the path interference indicator parameters of the default delivery sub-path are used to characterize the difficulty of drone delivery on the default delivery sub-path when the drone is expected to pass through the time period.

[0074] In a specific embodiment, the path interference indicator parameter of the default delivery sub-path is obtained in the following specific method: The ideal meteorological data and reference flight influencing parameters stored in the database are extracted, wherein the ideal meteorological data include the ideal average wind speed, the ideal humidity, the ideal air pressure fluctuation value and the ideal average humidity, and the reference flight influencing parameters include the reference number of UAVs in the path, the reference average flight speed of UAVs and the reference number of UAVs flying in the opposite direction.

[0075] It should be noted that the ideal meteorological data and reference flight influencing parameters are obtained by acquiring historical data of meteorological data and flight influencing parameters and performing mean processing before establishing a database.

[0076] , in, is the path interference indicator parameter of the default distribution sub-path, is the average wind speed of the default delivery sub-route, is the ideal average wind speed, is the average humidity of the default delivery sub-route, For ideal humidity, is the air pressure fluctuation value of the default delivery sub-route, is the ideal air pressure fluctuation value, is the average humidity of the default delivery sub-route, For the ideal average humidity, is the number of drones in the default delivery sub-path, is the number of reference drones in the path, is the average flight speed of the drone in the default delivery sub-path, is the average flight speed of the reference UAV in the path, is the number of reverse-flying drones for the default delivery sub-path, is the number of drones flying in reverse direction of the reference path, is the weather data weight of the distribution sub-path, is the parameter weight affecting the path in flight, and e is a natural constant.

[0077] It should be understood that the softplus function is a built-in function in Python. .

[0078] It should be noted that the meteorological data weight of the distribution sub-path and the path in-flight influence parameter weight have a value range of 0 to 1. In this embodiment, the meteorological data weight of the distribution sub-path is the meteorological data weight of the distribution sub-path preset in the database, which represents the numerical value of the influence degree of the meteorological data of the distribution sub-path on the path interference indicator parameter of the default distribution sub-path. The path in-flight influence parameter weight is the path in-flight influence parameter weight preset in the database, which represents the numerical value of the influence degree of the path in-flight influence parameter on the path interference indicator parameter of the default distribution sub-path. When used, the preset meteorological data weight of the distribution sub-path and the path in-flight influence parameter weight can be directly obtained from the database, and the corresponding relationship can be a pre-set mapping relationship. For example, the meteorological data of the distribution sub-path and the path in-flight influence parameter respectively form a mapping set with the meteorological data weight of the distribution sub-path and the path in-flight influence parameter weight preset in the database, and the real-time meteorological data of the distribution sub-path and the path in-flight influence parameter are respectively input into the mapping set to obtain the meteorological data weight of the distribution sub-path and the path in-flight influence parameter weight, wherein the mapping relationship is one-to-one correspondence.

[0079] It should also be noted that in this embodiment, the path interference indicator parameters of the default delivery sub-path are obtained by analyzing and processing the path influence parameters of the default delivery sub-path, taking into account the mutual influence between these parameters. For example, a higher average wind speed may lead to an increase in air pressure fluctuations, because the flow of wind may cause air disturbances, thereby affecting the air pressure distribution. The increase in the air pressure fluctuation value will affect the flight altitude control of the drone, increasing the extreme value of the flight altitude fluctuation. In addition, when the average wind speed is high, the flow of air will accelerate the evaporation and diffusion of water, which may cause the average humidity to change. Changes in wind direction may cause the drone to pass through different air pressure areas, resulting in changes in the air pressure fluctuation value during flight. Unstable air pressure will affect the height stability of the drone and cause flight altitude fluctuations. Air pressure fluctuations will affect the convection and diffusion of air, thereby affecting the distribution and evaporation of water, and then affecting the average humidity. For example, when the air pressure decreases, the air may rise and cool, resulting in condensation of water vapor and an increase in local humidity. When there are a large number of drones on the path and the shortest interval is small, the mutual interference of airflow between drones will be more obvious. Under complex meteorological conditions (such as high wind speed and unstable wind direction), this interference will be further aggravated. For example, when multiple drones are flying against the wind and the intervals are small, the wake generated by the drone in front will affect the flight of the drone behind, increasing the difficulty for the drone behind to maintain a stable flight attitude. When a drone flying in the opposite direction meets a drone flying in the normal direction, the relative speed is large. In the case of wind, it is more likely to cause airflow disturbances, affecting the flight speed and attitude of all drones involved, and increasing the difficulty of stable flight.

[0080] In a specific embodiment, by analyzing the path interference indicator parameters of the default delivery sub-path, it is possible to determine whether there are potential risks in the default delivery sub-path during the delivery process, and to know the path status in a timely manner to avoid continuing to fly on an unsuitable path, resulting in low efficiency, excessive energy consumption, and other problems. At the same time, it provides a key basis for path optimization decisions. When the path interference indicator parameters show that the path is not well adapted, the drone can adjust the path in a timely manner to ensure that it always runs on the optimal path that matches its own status and environmental conditions, thereby improving delivery efficiency, reducing energy consumption, enhancing flight safety, and ensuring efficient and stable operation of drone logistics delivery.

[0081] According to the drone logistics delivery state characterization parameters, the delivery correction factors corresponding to each delivery state characterization parameter interval in the database are extracted, and the delivery correction factors corresponding to the drone logistics delivery state characterization parameters are mapped and extracted, which are recorded as drone logistics delivery state correction factors.

[0082] Based on the UAV logistics delivery status correction factor and the path interference indicator parameters of the default delivery sub-path, the path adaptation index of the default delivery sub-path is analyzed.

[0083] In a specific embodiment, the path adaptation index of the default delivery sub-path is obtained in the following manner: , in, is the path adaptation index of the default delivery sub-path, is the path interference indicator parameter of the default distribution sub-path, is the correction factor of UAV logistics delivery status, and e is a natural constant.

[0084] It should be understood that the sigmoid function is a built-in function in Pytnon. .

[0085] In a specific embodiment, by analyzing the path adaptation index of the default delivery sub-path, it is possible to accurately reflect the degree of adaptation of the default delivery sub-path to the current flight status and environmental conditions of the drone, providing a clear basis for judging whether the drone should continue to fly along the path. This helps to enhance the adaptability of the drone in complex and changing environments, ensure flight safety, reduce potential problems such as collision risks caused by improper path selection, and improve the overall stability and reliability of drone logistics delivery.

[0086] Extract the preset path adaptation verification threshold in the database.

[0087] It should be noted that the path adaptation verification threshold is extracted from the database and is used to reflect the critical state of adaptation of the drone delivery path and factors such as the drone flight status and path environment.

[0088] In a specific embodiment, the path adaptation verification threshold is pre-set in the database and can be obtained by a variety of methods. For example, a large number of sample data of path adaptation indicators of drones in different flight states flying in different path environments are collected, and these sample data are comprehensively and deeply statistically analyzed and processed to obtain the evaluation value of the degree of path adaptation, and then these evaluation values ​​are weighted averaged or calculated by taking specific percentile values ​​to obtain the path adaptation verification threshold. Or experienced experts in the field of drone logistics and distribution can judge the reasonable limits of drone path adaptation under various circumstances based on long-term accumulated practical experience to set the threshold. This threshold can effectively judge whether the current default distribution sub-path is suitable for continued flight during the drone delivery process, and provide a key judgment basis for the drone's path optimization decision.

[0089] If the path adaptation index of the default delivery sub-path is greater than the path adaptation verification threshold, the optimization label information of the drone's default delivery sub-path will be marked as not requiring optimization, and a flight instruction will be issued simultaneously to continue flying with the default delivery sub-path.

[0090] If the path adaptation index of the default delivery sub-path is less than or equal to the path adaptation verification threshold, the optimization label information of the drone's default delivery sub-path is marked as demand optimization.

[0091] It should also be noted that if the path adaptation index of the default delivery sub-path is greater than the path adaptation verification threshold, it means that under the current drone logistics delivery state, the degree of adaptation between the default delivery sub-path and the drone flight state has reached a relatively ideal level, which means that the path is highly adaptable for the drone to continue flying. The drone can complete the delivery task along this path in a relatively stable, efficient and safe state. There is no need for additional path optimization operations, and the drone can continue to fly on the default delivery sub-path.

[0092] If the path adaptation index of the default delivery sub-path is less than or equal to the path adaptation verification threshold, it means that the adaptation degree of the current default delivery sub-path does not meet the expected standard. In order to ensure the smooth progress of the subsequent delivery tasks of the drone, it is necessary to optimize the drone flight path to find a more suitable backup delivery sub-path, thereby improving delivery efficiency, ensuring flight safety and reducing potential risks such as energy consumption.

[0093] In a specific embodiment, the drone's default delivery sub-path optimization label information is determined by combining the drone's logistics delivery status characterization parameters, and the adaptability of the current default delivery sub-path is evaluated during the delivery process, so that the drone can timely and accurately identify whether the path needs to be optimized, avoiding problems such as inefficiency and excessive energy consumption caused by continuing to fly on an unsuitable path. By dynamically adjusting the path, it is ensured that the drone always operates on the optimal path that matches its own status and environmental conditions, thereby improving delivery efficiency, reducing energy consumption, and enhancing flight safety, providing a guarantee for the efficient and stable operation of drone logistics delivery.

[0094] S4, when the result of the optimization label information of the drone's default delivery sub-path is determined to be demand optimization, the various alternative delivery sub-paths between the path node that the drone is about to reach and the next path node are counted and marked as alternative sub-paths, the path interference data of each alternative sub-path is obtained, and the logistics adaptation execution priority value of each alternative sub-path is analyzed, thereby screening the optimal sub-path for drone logistics delivery and optimizing the execution.

[0095] It should be understood that the backup sub-path refers to other potential flight paths that the drone can choose between the path node to be reached and the next path node.

[0096] In this embodiment, the path interference data of each standby sub-path includes the path length of each standby sub-path, the number of obstacles, the average wind speed in the expected passing time period, and the average electromagnetic interference intensity in the expected passing time period.

[0097] It should be noted that the estimated passing time period is obtained in the same manner as the estimated passing time period of the above-mentioned default delivery sub-route.

[0098] It should also be noted that the path length and the number of obstacles can be obtained by obtaining a three-dimensional distribution map of the area corresponding to the backup sub-path and analyzing and calculating therefrom. The wind speed can be obtained by an anemometer, and the electromagnetic interference intensity can be obtained by an electromagnetic interference monitoring device.

[0099] In this embodiment, the logistics adaptation execution priority value of each backup sub-path is analyzed, thereby screening the optimal sub-path for drone logistics distribution and optimizing the execution. The specific analysis process is as follows: based on the path interference data of each backup sub-path, the logistics adaptation execution priority value of each backup sub-path is analyzed and processed. The logistics adaptation execution priority value of each backup sub-path is used to characterize the priority of each backup sub-path for logistics distribution execution.

[0100] In a specific embodiment, the path interference data of each standby sub-path is obtained in the following manner: Reference path interference data stored in a database is extracted, wherein the reference path interference data includes a reference path length, a reference obstacle quantity, an ideal wind speed, and a reference average electromagnetic interference intensity.

[0101] It should be noted that the reference path interference data is obtained by collecting historical data of path interference data and performing mean processing before establishing the database.

[0102] , in, The priority value for logistics adaptation execution of the jth backup sub-path, is the path length of the jth backup subpath, is the reference path length, is the number of obstacles on the jth backup subpath, is the number of reference obstacles, is the average wind speed during the expected passing period of the jth backup subpath, For the ideal wind speed, is the average electromagnetic interference intensity of the jth backup sub-path during the expected period, is the reference average electromagnetic interference intensity, is the path length weight, is the weight of the number of obstacles, is the average wind speed weight, is the average electromagnetic interference intensity weight, j is the number of each backup sub-path, , n is the number of backup sub-paths.

[0103] It should be noted that the path length weight, obstacle number weight, average wind speed weight and average electromagnetic interference intensity weight all have value ranges between 0 and 1. In this embodiment, the path length weight is the path length weight preset in the database, which indicates the numerical value of the influence of the path length on the logistics adaptation execution priority value of the backup sub-path. The obstacle number weight is the obstacle number weight preset in the database, which indicates the numerical value of the influence of the obstacle number on the logistics adaptation execution priority value of the backup sub-path. The average wind speed weight is the average wind speed weight preset in the database, which indicates the numerical value of the influence of the average wind speed on the logistics adaptation execution priority value of the backup sub-path. The average electromagnetic interference intensity weight is the average electromagnetic interference intensity weight preset in the database, which indicates the average electromagnetic interference The numerical value of the influence of the interference intensity on the logistics adaptation execution priority value of the backup sub-path can be directly obtained from the database when used, and the corresponding relationship can be a pre-set mapping relationship. For example, the path length, the number of obstacles, the average wind speed and the average electromagnetic interference intensity are respectively mapped with the path length weight, the obstacle number weight, the average wind speed weight and the average electromagnetic interference intensity weight preset in the database to form a mapping set, and the real-time path length, the obstacle number weight, the average wind speed and the average electromagnetic interference intensity are respectively input into the mapping set to obtain the path length weight, the obstacle number weight, the average wind speed weight and the average electromagnetic interference intensity weight, wherein the mapping relationship is one-to-one correspondence.

[0104] It should also be noted that in this embodiment, the logistics adaptation execution priority value of each spare sub-path is obtained by analyzing and processing the path interference data of each spare sub-path, taking into account the mutual influence between these parameters. For example, the longer the path length, the greater the possibility of passing through different terrains and regions, and the probability of encountering obstacles is also increased accordingly. Longer paths are more likely to cross different meteorological areas and are more likely to encounter different wind speed conditions. Longer paths may bring drones closer to more electromagnetic interference sources, such as high-voltage lines, communication base stations, etc. More obstacles will change the local airflow environment. When the drone flies in an area with dense obstacles, the airflow will form a complex flow pattern between the obstacles, generating turbulence and eddy currents. When the wind speed is high, it will also amplify the impact of obstacles. Strong winds may cause some lightweight obstacles to move or shake, increasing the risk of drones colliding with obstacles. Areas with more obstacles may block or reflect electromagnetic signals, change the propagation path and intensity of electromagnetic signals. For example, obstacles made of metal materials may shield or interfere with electromagnetic signals, causing the electromagnetic interference intensity to change in local areas, increasing the complexity of electromagnetic interference. When the wind speed is high, it will affect the propagation of electromagnetic signals. Strong winds may intensify the movement of particles in the air. These particles interact with electromagnetic signals, causing them to attenuate or scatter, thereby changing the distribution and actual impact of electromagnetic interference intensity.

[0105] In a specific embodiment, by analyzing the logistics adaptation execution priority value of each backup sub-path, when the UAV needs to optimize the path, the optimal sub-path can be quickly screened out, so that the UAV can switch to the most suitable path in time to continue flying, avoiding delivery delays caused by poor paths, greatly improving delivery efficiency, reducing energy consumption caused by flying on harsh or mismatched paths, and extending the service life of the UAV. At the same time, it helps to improve the UAV's ability to cope with complex environments, reduce safety risks such as collisions caused by improper path selection, ensure the safety and stability of the delivery process, improve the overall performance of UAV logistics delivery, enhance the reliability and quality of delivery services, and better meet logistics delivery needs.

[0106] The backup sub-path corresponding to the maximum logistics adaptation execution priority value is extracted and recorded as the optimal sub-path for logistics distribution. At the same time, the drone path change instruction is issued to control the drone to perform delivery flight along the optimal sub-path for logistics distribution when it is about to reach the path node.

[0107] In a specific embodiment, by screening the optimal sub-paths for drone logistics distribution and optimizing them, the drone can switch to the most suitable path in time to continue flying when facing complex and changing environments and real-time distribution status changes, which not only avoids delivery delays caused by poor paths, greatly improves delivery efficiency, but also avoids energy consumption caused by flying on bad or mismatched paths, reduces drone losses, and extends its service life. At the same time, the optimized path can better adapt to the environment, thereby reducing safety risks such as collisions, ensuring the safety and stability of the distribution process, and improving the overall performance of drone logistics distribution.

[0108] See also Figure 2 As shown, an embodiment of the present invention provides a path optimization system for drone logistics delivery, including: a drone logistics delivery default execution path screening module, which is used to obtain each executable delivery path between the drone logistics delivery starting node and the terminal arrival node, recorded as each executable delivery path, and count the environmental impact data and obstacle distribution data of each executable delivery path, and based on the environmental impact data and obstacle distribution data of each executable delivery path, screen the drone logistics delivery default execution path.

[0109] The drone logistics delivery status analysis module controls the drone logistics delivery based on the default execution path of the drone logistics delivery, monitors the logistics delivery process, obtains the drone delivery status parameters, and analyzes the drone logistics delivery status characterization parameters.

[0110] The default delivery sub-path optimization determination module is used to obtain the default execution path between the path node that the drone is about to reach and the next path node, mark it as the default delivery sub-path, collect the path influencing parameters of the default delivery sub-path, and determine the drone's default delivery sub-path optimization label information in combination with the drone's logistics delivery state characterization parameters. The drone's default delivery sub-path optimization label information includes demand optimization and no optimization required.

[0111] The optimal sub-path screening module for drone logistics distribution is used to count the various alternative distribution sub-paths between the path node that the drone is about to reach and the next path node when the drone's default delivery sub-path optimization label information is determined as demand optimization, mark them as alternative sub-paths, obtain the path interference data of each alternative sub-path, and analyze the logistics adaptation execution priority value of each alternative sub-path, thereby screening the optimal sub-path for drone logistics distribution and optimizing its execution.

[0112] In a specific embodiment, by providing a path optimization method and system for drone logistics distribution, the efficiency and safety of drone delivery can be improved. By accurately acquiring and analyzing the environmental impact data and obstacle distribution data of each executable delivery path, combined with the real-time delivery status parameters of the drone, the default execution path is screened out before delivery, and the sub-path optimization needs are determined in real time during the flight, and the optimal sub-path is adjusted in time to effectively cope with complex and changeable meteorological conditions and obstacles, reduce delivery time and energy consumption, enhance the adaptability of drones in complex environments, and ensure the smooth completion of delivery tasks.

[0113] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0114] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that technicians in the relevant technical field can understand and use the present invention well. As long as they do not deviate from the structure of the present invention or exceed the scope defined by the present invention, they should all belong to the protection scope of the present invention.

Claims

1. A path optimization method for drone logistics distribution, characterized by: The following steps are involved: S1, obtain each executable delivery path between the starting node and the terminal arrival node of the drone logistics delivery, record it as each executable delivery path, count the environmental impact data and obstacle distribution data of each executable delivery path, and screen the default execution path of the drone logistics delivery based on the environmental impact data and obstacle distribution data of each executable delivery path; S2, control the UAV logistics distribution with the default execution path of the UAV logistics distribution, monitor the logistics distribution process, obtain the UAV distribution status parameters, and analyze the UAV logistics distribution status characterization parameters; S3, obtaining the default execution path between the path node that the drone is about to reach and the next path node, marking it as the default delivery sub-path, collecting the path influencing parameters of the default delivery sub-path, and determining the optimization label information of the drone default delivery sub-path in combination with the drone logistics delivery state characterization parameters, wherein the drone default delivery sub-path optimization label information includes demand optimization and no optimization required; S4, when the result of the optimization label information of the drone's default delivery sub-path is determined to be demand optimization, the various alternative delivery sub-paths between the path node that the drone is about to reach and the next path node are counted and marked as alternative sub-paths, the path interference data of each alternative sub-path is obtained, and the logistics adaptation execution priority value of each alternative sub-path is analyzed, thereby screening the optimal sub-path for drone logistics delivery and optimizing the execution.

2. A path optimization method for drone logistics distribution according to claim 1, characterized in that: The statistical data of environmental impact and obstacle distribution of each executable delivery path includes: The environmental impact data of each executable delivery route include the average wind speed, average humidity, average temperature and air pressure fluctuation value of each executable delivery route; The obstacle distribution data is specifically obtained in the following manner: Obtain the three-dimensional spatial distribution map of the drone logistics distribution area, and segment and extract the three-dimensional spatial distribution map of each executable delivery path area; The three-dimensional spatial distribution map of each executable delivery path is evenly divided into cubic units, the number of cubic units occupied by each obstacle is identified and located, and the volume of all obstacles is counted, and the cumulative obstacle volume of each executable delivery path is traversed in turn to obtain; Identify and locate the point cloud data of each obstacle in the three-dimensional spatial distribution map of each executable delivery path area, identify and extract the shortest interval distance between the highest point of each obstacle and the corresponding executable delivery path, and traverse and obtain the minimum distance between each executable path and the highest point of the obstacle in turn; The vertical height of each obstacle in each executable delivery path area is counted, and the path point corresponding to the shortest interval between the highest point of each obstacle and the corresponding executable delivery path is recorded as each influencing path point. The vertical height of each influencing path point in each executable delivery path area is counted. If the vertical height of the highest point of an obstacle in each executable delivery path area is greater than or equal to the vertical height of the nearest influencing path point, the highest point of the obstacle is recorded as the estimated obstacle crossing point, thereby counting the number of estimated obstacle crossing points of each executable path; The three-dimensional spatial distribution map of each executable delivery path area is projected into a two-dimensional distribution map, and the obstacle pixel points are identified and located, thereby calculating the area occupied by the obstacle, and the obstacle distribution area ratio is calculated according to the area of ​​the two-dimensional distribution map, thereby obtaining the obstacle distribution area ratio of each executable delivery path; The cumulative obstacle volume of each executable delivery path, the minimum distance between each executable path and the highest point of the obstacle, the estimated number of obstacle points crossed by each executable path, and the proportion of the obstacle distribution area of ​​each executable delivery path are combined as the obstacle distribution data of each executable delivery path.

3. A path optimization method for drone logistics distribution according to claim 2, characterized in that: The default execution path of the screening drone logistics distribution is as follows: Analyzing the execution fit index of each executable delivery path according to the environmental impact data and obstacle distribution data of each executable delivery path, wherein the execution fit index of each executable delivery path is used to characterize the execution fit degree of the drone logistics delivery of each executable delivery path; The executable delivery path corresponding to the maximum execution fit index is extracted and recorded as the default execution path for drone logistics delivery.

4. The path optimization method for drone logistics distribution according to claim 1 is characterized by: The specific analysis process of analyzing the characteristic parameters of the drone logistics distribution state is as follows: The drone delivery status parameters include the attitude angle deviation extreme value difference, flight altitude fluctuation extreme value difference, total energy consumption and flight speed change extreme value difference of the drone in the flown section; According to the delivery status parameters of the drone on the flown section, the drone logistics delivery status characterization parameters are analyzed and processed to obtain the drone logistics delivery status characterization parameters, which are used to characterize the flight status of the drone on the flown section.

5. The path optimization method for drone logistics distribution according to claim 1 is characterized by: The specific process of collecting the path influence parameters of the default delivery sub-path is as follows: Obtain the average wind speed, average humidity, air pressure fluctuation value and average humidity of the default delivery sub-route during the period when the drone is expected to pass, and combine them as the meteorological data of the default delivery sub-route; Obtain the number of drones in the default delivery sub-path during the period when the drone is expected to pass, the average flight speed of the drones, and the number of drones flying in the opposite direction, and combine them with the flight influencing parameters of the path used as the default delivery sub-path; The meteorological data of the default delivery sub-path and the path in-flight impact parameters of the default delivery sub-path are combined as the path impact parameters of the default delivery sub-path.

6. A path optimization method for drone logistics distribution according to claim 5, characterized in that: The specific determination process of determining the optimization label information of the drone default delivery sub-path is as follows: According to the path influence parameters of the default distribution sub-path, the path interference indicator parameters of the default distribution sub-path are obtained by analysis and processing; According to the drone logistics delivery state characterization parameters, the delivery correction factors corresponding to each delivery state characterization parameter interval in the database are extracted, and the delivery correction factors corresponding to the drone logistics delivery state characterization parameters are mapped and extracted, which are recorded as drone logistics delivery state correction factors; Based on the UAV logistics delivery status correction factor and the path interference indicator parameters of the default delivery sub-path, the path adaptation index of the default delivery sub-path is analyzed; Extracting the path adaptation verification threshold preset in the database; If the path adaptation index of the default delivery sub-path is greater than the path adaptation verification threshold, the optimization label information of the default delivery sub-path of the drone is marked as not requiring optimization, and a flight instruction is issued to continue to use the default delivery sub-path; If the path adaptation index of the default delivery sub-path is less than or equal to the path adaptation verification threshold, the optimization label information of the drone's default delivery sub-path is marked as demand optimization.

7. The path optimization method for drone logistics distribution according to claim 1, characterized in that: The path interference data of each standby sub-path includes the path length of each standby sub-path, the number of obstacles, the average wind speed within the expected passing time period, and the average electromagnetic interference intensity within the expected passing time period.

8. A path optimization method for drone logistics distribution according to claim 7, characterized in that: The logistics adaptation execution priority value of each backup sub-path is analyzed, thereby screening the optimal sub-path for drone logistics distribution and optimizing the execution. The specific analysis process is as follows: According to the path interference data of each backup sub-path, the logistics adaptation execution priority value of each backup sub-path is obtained by analyzing and processing, and the logistics adaptation execution priority value of each backup sub-path is used to represent the priority degree of each backup sub-path for logistics distribution execution; The backup sub-path corresponding to the maximum logistics adaptation execution priority value is extracted and recorded as the optimal sub-path for logistics distribution. At the same time, the drone path change instruction is issued to control the drone to perform delivery flight along the optimal sub-path for logistics distribution when it is about to reach the path node.

9. A path optimization method for drone logistics distribution according to claim 6, characterized in that: The path adaptation index of the default delivery sub-path is obtained in the following way: ， in, is the path adaptation index of the default delivery sub-path, is the path interference indicator parameter of the default distribution sub-path, is the correction factor of UAV logistics delivery status, and e is a natural constant.

10. A path optimization system for drone logistics distribution, characterized by: include: The UAV logistics delivery default execution path screening module is used to obtain each executable delivery path between the UAV logistics delivery starting node and the terminal arrival node, recorded as each executable delivery path, and count the environmental impact data and obstacle distribution data of each executable delivery path. Based on the environmental impact data and obstacle distribution data of each executable delivery path, the UAV logistics delivery default execution path is screened; The drone logistics distribution status analysis module controls the drone logistics distribution based on the default execution path of the drone logistics distribution, monitors the logistics distribution process, obtains the drone delivery status parameters, and analyzes the drone logistics distribution status characterization parameters; The default delivery sub-path optimization determination module is used to obtain the default execution path between the path node that the drone is about to reach and the next path node, mark it as the default delivery sub-path, collect the path influencing parameters of the default delivery sub-path, and determine the optimization label information of the drone default delivery sub-path in combination with the drone logistics delivery state characterization parameters. The drone default delivery sub-path optimization label information includes demand optimization and no optimization required; The optimal sub-path screening module for drone logistics distribution is used to count the various alternative distribution sub-paths between the path node that the drone is about to reach and the next path node when the drone's default delivery sub-path optimization label information is determined as demand optimization, mark them as alternative sub-paths, obtain the path interference data of each alternative sub-path, and analyze the logistics adaptation execution priority value of each alternative sub-path, thereby screening the optimal sub-path for drone logistics distribution and optimizing its execution.

Images