Unmanned aerial vehicle path planning method based on meteorological aid decision-making system

Abstract

The invention provides an unmanned aerial vehicle path planning method based on a meteorological auxiliary decision-making system. The unmanned aerial vehicle path planning method comprises the following steps: constructing a meteorological obstacle model based on a clustering algorithm; constructing a three-dimensional search space; preprocessing the data in the step S1 and the step S2; and an improved artificial potential field method is adopted for the data preprocessed in the step S3. The method has the beneficial effects that for high influence weather modeling, the modeling method performs data thinning through a clustering algorithm, so that the environment modeling speed is increased; when the unmanned aerial vehicle flies around from the top or the bottom of the high-influence weather, a certain safety range is considered, so that the planned air route is safer.

Description

Technical Field

[0001] The invention belongs to the technical field of unmanned aerial vehicles, and in particular relates to a path planning method for unmanned aerial vehicles based on a meteorological auxiliary decision system. Background Art

[0002] With the development of digital and intelligent technologies, drones have been widely used in many fields such as agriculture, logistics, and public safety, demonstrating their advantages of flexibility, low cost, and high efficiency. Path planning technology is the basis for drones to perform tasks and is also one of the key technologies in the field of drones. This technology needs to plan a collision-free path from the starting point to the end point while meeting various constraints to ensure the safe flight of the drone.

[0003] The current UAV path planning technology can be mainly divided into: sampling-based path planning algorithm, intelligent search-based path planning algorithm and reinforcement learning-based path planning algorithm. Among them, the artificial potential field method has the characteristics of fast planning speed and easy implementation when solving the three-dimensional path planning problem of UAVs, and is widely used in UAV path planning. At present, the unreachable target problem and local optimal solution faced by the artificial potential field method have been widely studied and discussed. However, in complex environments, especially for fixed-wing UAVs with long range, high speed and high flight altitude, it is necessary to consider the impact of weather factors on the path. In addition, the local optimal problem of the artificial potential field method under the influence of various meteorological factors also needs to be urgently solved. Summary of the invention

[0004] In view of this, the present invention aims to propose a UAV path planning method based on a meteorological auxiliary decision system to solve at least one problem existing in the above-mentioned prior art.

[0005] To achieve the above object, the technical solution of the present invention is achieved as follows: A method for UAV path planning based on a meteorological decision-making aid system comprises the following steps: S1. Constructing meteorological obstacle model based on clustering algorithm; S2, construct a three-dimensional search space; S3, preprocessing the data of step S1 and step S2; S4, using an improved artificial potential field method on the data pre-processed in step S3; In step S1, a meteorological obstacle model is constructed based on a clustering algorithm, including: S11, removing abnormal data in the original meteorological file; S12, according to the threshold values ​​of different meteorological elements in the original meteorological file, dividing the data of the original meteorological file into three types: low-impact weather, high-impact weather and critical conditions; S13. Use clustering thinning method to thin out the contour data of high-impact weather; S14, determining the circumscribed circle of the data after thinning in step S13 as the meteorological obstacle models of different altitude layers.

[0006] Furthermore, in step S2, a three-dimensional search space is constructed, including: S21, obtaining the starting point and end point information of the drone; S22, construct a rectangular area with the start point and the end point expanded by 5°; S23, intercepting the meteorological obstacle information in the rectangular area and constructing a no-fly area, where the no-fly area is a three-dimensional search space.

[0007] Furthermore, in step S3, the data of step S1 and step S2 are preprocessed, including: Determine whether the starting point and the end point of the UAV are located inside the meteorological obstacle. If not, proceed to step S4. Otherwise, give a prompt and re-enter the starting point and the end point.

[0008] Furthermore, in step S4, the artificial potential field method is improved, and the UAV moves toward the target point under the action of the gravitational force of the target point and the repulsive force of the obstacle, including: S41. Set the current position of the drone , denoted as , target point location , denoted as , calculate the gravitational potential field by the gravitational potential field calculation method; And calculate the gravitational force at the current position; S42, calculating the nearest threat point; S43, adding the distance between the current position and the target point into the calculation formula of the repulsive potential field; S44, the UAV moves towards the target point under the action of the resultant force, and the resultant force is calculated; S45: When the drone is moving toward the target point, if the resultant force is not 0, continue to execute step S46. When the resultant force is 0, the drone falls into a local optimum. , denoted as , adopt the climbing and turning parallel re-planning strategy to jump out of the obstacle and calculate the distance Nearest weather obstruction , select key waypoints , denoted as , re-plan the path from the starting point to the key waypoint, and from the key waypoint to the target point in sections; by and The distance is the radius, the step length is 1°, and circular motion is performed until the local optimum is jumped out, and the circular motion is calculated; S46. The UAV moves toward the target point under the combined traction until it reaches the target point.

[0009] Furthermore, in step S41, the gravitational potential field is calculated as follows: ; In the formula, represents the gravitational potential field, is the gravitational coefficient, is the distance between the current position and the target point; The gravitational force at the current position is calculated as follows: ; in, Indicates the gravitational force at the current position. The current position of the drone , The target point position , is the gravitational coefficient, is the distance between the current position and the target point, represents partial derivative.

[0010] Furthermore, in step S42, the nearest threat point is calculated, including: Set up obstacles , meteorological obstacles , denoted as ;in, and are the longitude and latitude of the obstacle, and are the altitudes of the upper and lower surfaces of the meteorological obstacle, respectively. is the bottom radius of the meteorological obstacle; the nearest threat point is calculated based on the relative height of the current position of the drone and the meteorological obstacle, and the bottom radius of the meteorological obstacle is used as the safe range for detour. The calculation method is as follows: ; In the formula, Indicates the nearest threat point of a single meteorological obstacle, Indicates the obstacle circle at the same height as the current position of the drone, with the center ,radius ; Indicates the obstacle circle that the drone needs to consider when flying around the top or bottom of a meteorological obstacle. When flying around the top, the center of the circle ,radius ; When flying around from the bottom, the center of the circle ,radius ; At this time, the safety range .

[0011] Furthermore, in step S43, the distance between the current position and the target point is added to the calculation formula of the repulsive potential field, and the calculation method is as follows: ; In the formula, represents the repulsive potential field formed by meteorological obstacles, represents the repulsion coefficient, Indicates the distance between the current point and the nearest threat point of the i-th meteorological obstacle, Indicates The repulsive force range of a meteorological obstacle, represents a positive constant; the current position is affected by The repulsion force of a meteorological obstacle is calculated as follows: ; ; ; in, It represents the repulsive force of meteorological obstacles on the UAV. represents the first part of the negative gradient of the repulsive potential field, represents the second part of the negative gradient of the repulsive potential field.

[0012] Further, in step S44, the drone moves towards the target point under the action of the resultant force, and the resultant force calculation formula is as follows: ; In the formula, represents the total force acting on the drone, Indicates the gravitational force at the current position. The current position of the drone , m represents the number of meteorological obstacles, represents the repulsive force of the i-th meteorological obstacle on the UAV.

[0013] Furthermore, in step S45, the arc motion calculation formula is as follows: ; In the formula, is the step length.

[0014] Compared with the prior art, the UAV path planning method based on the meteorological decision-making auxiliary system described in the present invention has the following advantages: (1) The UAV path planning method based on the meteorological decision-making support system described in the present invention models high-impact weather. The modeling method uses a clustering algorithm to perform data thinning to improve the speed of environmental modeling. When the UAV flies around the top or bottom of the high-impact weather, a certain safety range is taken into account to make the planned route safer.

[0015] (2) The UAV path planning method based on the meteorological decision-making system described in the present invention, when trapped in a local optimum, the UAV adopts a re-planning strategy of climbing and turning in parallel, and selects a strategy that takes a shorter time to jump out of the local optimal position, so that the planning result is more reasonable and more efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings: Figure 1 This is a schematic diagram of the principle flow of the planning method according to an embodiment of the present invention; Figure 2 A schematic diagram of the implementation principle of the nearest threat point selection according to an embodiment of the present invention; Figure 3 It is a schematic diagram of the implementation principle of the climbing strategy according to an embodiment of the present invention; Figure 4 A schematic diagram of the implementation principle of the steering strategy according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the climbing strategy results of Example 1 of the present invention; Figure 6 This is a schematic diagram of the steering strategy results of Example 1 of the present invention. DETAILED DESCRIPTION

[0017] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0018] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and the like are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, features defined as "first", "second", and the like may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0019] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood by specific circumstances.

[0020] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0021] Glossary: Clustering thinning: It is a data preprocessing technology, whose main purpose is to reduce the density of data while retaining the main data features, thereby simplifying the data analysis process. This method is often used in data mining and machine learning to reduce the computational burden and improve algorithm efficiency.

[0022] like Figures 1 to 4 As shown, a UAV path planning method based on a meteorological decision-making system includes the following steps: (1) Construct a meteorological obstacle model based on a clustering algorithm. (a) Eliminate abnormal data in the original meteorological file. (b) According to the thresholds of different meteorological elements, divide the data into three types: low-impact weather, high-impact weather, and critical conditions. (c) Use cluster sampling method to thin out the contour data of high-impact weather. (d) Determine the circumscribed circle of the thinned data as the obstacle model of different altitude layers.

[0023] (2) Construct a three-dimensional search space. (a) Obtain the starting and ending point information of the drone. (b) Construct a rectangular area with a 5° extension from the starting and ending points. (c) Intercept the meteorological obstacle information within the rectangular area and construct a no-fly zone.

[0024] (3) Preprocessing. Determine whether the starting point and end point of the drone are inside the meteorological obstacle. If not, proceed to step (4). Otherwise, give a prompt and re-enter the starting point and end point.

[0025] (4) Improved artificial potential field method. The drone moves toward the target point under the action of the target point's gravity and the obstacle's repulsion. The specific steps are: (a) Set the current position of the drone , denoted as , target point location , denoted as . Then the gravitational potential field is calculated as follows: ; In the formula, is the gravitational coefficient, is the distance between the current position and the target point. The gravitational force on the current position is calculated as follows: ; (b) Calculate the nearest threat point. Suppose the obstacle set , meteorological obstacles , denoted as .in and are the longitude and latitude of the obstacle, and are the altitudes of the upper and lower surfaces of the meteorological obstacle, respectively. is the bottom radius of the meteorological obstacle. The nearest threat point is calculated based on the relative height of the current position of the drone and the meteorological obstacle, such as Figure 2 At the same time, the bottom radius of the meteorological obstacle is used as the safe range for flying around. The specific calculation method is as follows: ; In the formula, Indicates the obstacle circle at the same height as the current position of the drone, with the center ,radius . Indicates the obstacle circle that the drone needs to consider when flying around the top or bottom of a meteorological obstacle. When flying around the top, the center of the circle ,radius When flying around from the bottom, the center of the circle ,radius . At this time, the safety range .

[0026] (c) To solve the problem of unreachable targets, the distance between the current position and the target point is added to the calculation formula of the traditional repulsive potential field. The specific calculation method is as follows: ; In the formula, represents the repulsion coefficient, Indicates the distance between the current point and the nearest threat point of the i-th meteorological obstacle, Indicates The repulsive force range of a meteorological obstacle, represents a positive constant. The current position is affected by The repulsion force of a meteorological obstacle is calculated as follows: ; ; ; (d) The UAV moves towards the target point under the action of the resultant force. The formula for calculating the resultant force is as follows: ; Where m represents the number of meteorological obstacles.

[0027] (e) When the drone is moving towards the target point, if the resultant force is not 0, continue to execute step (f). When the resultant force is 0, the drone falls into a local optimum. , denoted as . Use the climbing and turning parallel re-planning strategy to jump out of the obstacle. The schematic diagram of the climbing strategy implementation is as follows Figure 3 Calculate the distance Nearest weather obstruction , select key waypoints , denoted as The path from the starting point to the key waypoint and from the key waypoint to the target point is re-planned in sections. Figure 4 As shown. and The distance is the radius, the step length is 1°, and circular motion is performed until the local optimum is jumped out. The specific calculation formula for circular motion is as follows: ; In the formula, The climbing strategy and the steering strategy are run in parallel, and the strategy with the shortest time consumption is selected as the strategy to escape from the local optimum.

[0028] (f) The UAV moves towards the target point under the combined force until it reaches the target point.

[0029] The present invention uses a clustering method to model the meteorological environment of high-impact weather. A certain safety range is considered when the UAV flies around high-impact weather. When the artificial potential field method falls into a local optimum, a replanning strategy based on climbing and turning in parallel is selected to jump out of the local optimum with the strategy that takes the shortest planning time.

[0030] The present invention can take high-impact weather into account in the UAV path planning algorithm. The present invention simulates the meteorological environment and abstracts the high-impact weather area as a cylindrical obstacle based on the clustering algorithm. In view of the local optimal solution problem of the artificial potential field method, the present invention adopts a parallel replanning strategy of UAV climbing and turning to jump out of the local optimal solution, so that the UAV can fly around the high-impact weather area.

[0031] The advantages of the improved artificial potential field method designed by the present invention that takes high-impact weather into consideration are: (1) for modeling high-impact weather, the modeling method performs data thinning through a clustering algorithm, thereby improving the speed of environmental modeling; (2) when the UAV flies around the top or bottom of high-impact weather, a certain safety range is taken into consideration, making the planned route safer; (3) when trapped in a local optimum, the UAV adopts a re-planning strategy of climbing and turning in parallel, and selects a strategy that takes a shorter time to jump out of the local optimal position, making the planning result more reasonable and more efficient.

[0032] Example 1 In the specific implementation, the following steps are included: (1) Construct a meteorological obstacle model based on a clustering algorithm. (a) Eliminate abnormal data in the original meteorological file. (b) According to the thresholds of different meteorological elements, divide the data into three types: low-impact weather, high-impact weather, and critical conditions. (c) Use cluster sampling method to thin out the contour data of high-impact weather. (d) Determine the circumscribed circle of the thinned data as the obstacle model of different altitude layers.

[0033] (2) Construct a three-dimensional search space. (a) Get the starting point of the drone START and destination information GOAL (b) Construct a rectangular area with a 5° extension from the starting point and the end point. (c) Intercept the meteorological obstacle information within the rectangular area , construct a no-fly zone.

[0034] Example: Set the starting point START (40, 10, 0) and the end point GOAL (180, 120, 40) of the drone, and set multiple weather obstacles , the corresponding elements represent the horizontal coordinate, vertical coordinate, lower base height and upper base height of the cylindrical meteorological obstacle and the radius of the cylinder. In the example, the meteorological obstacles are set to a state where multiple obstacles are arranged side by side to verify the effectiveness of the nearest threat point and parallel replanning strategy introduced in the improved artificial potential field method proposed in the present invention.

[0035] (3) Preprocessing. Determine whether the starting point and end point of the drone are inside the meteorological obstacle. If not, proceed to step (4). Otherwise, give a prompt and re-enter the starting point and end point.

[0036] (4) Improved artificial potential field method. The drone moves toward the target point under the action of the target point's gravity and the obstacle's repulsion. The specific steps are: (a) Set the current position of the drone , denoted as , target point location , denoted as . Then the gravitational potential field is calculated as follows: ; In the formula, gravitational coefficient, The distance between the current position and the target point. The gravitational force on the current position is calculated as follows: ; Example: Step 1, Step 2, Step 3, Step 16 The components of the gravitational force on the drone on the x, y, and z axes are shown in Table 1.

[0037] Table 1 .

[0038] (b) Calculate the nearest threat point. Suppose the obstacle set , meteorological obstacles , denoted as .in and are the longitude and latitude of the obstacle, and are the altitudes of the upper and lower surfaces of the meteorological obstacle, respectively. is the bottom radius of the meteorological obstacle. The nearest threat point is calculated based on the relative height of the current position of the drone and the meteorological obstacle, such as Figure 2 At the same time, the bottom radius of the meteorological obstacle is used as the safe range for flying around. The specific calculation method is as follows: ; In the formula, Indicates the obstacle circle at the same height as the current position of the drone, with the center ,radius . Indicates the obstacle circle that the drone needs to consider when flying around the top or bottom of a meteorological obstacle. When flying around the top, the center of the circle ,radius When flying around from the bottom, the center of the circle ,radius . At this time, the safety range .

[0039] Example: In steps 1, 2, 3, and 16, the nearest threat points of four weather obstacles to the drone are calculated as shown in Table 2.

[0040] Table 2 .

[0041] (c) To solve the problem of unreachable targets, the distance between the current position and the target point is added to the calculation formula of the traditional repulsive potential field. The specific calculation method is as follows: ; In the formula, represents the repulsion coefficient, Indicates the distance between the current point and the nearest threat point of the i-th meteorological obstacle, Indicates The repulsive force range of a meteorological obstacle, represents a positive constant. The current position is affected by The repulsion force of a meteorological obstacle is calculated as follows: ; ; ; (d) The UAV moves towards the target point under the action of the resultant force. The formula for calculating the resultant force is as follows: ; Where m represents the number of meteorological obstacles.

[0042] Example: Step 1, Step 2, Step 3, Step 16 The components of the repulsive force on the drone on the x, y, and z axes are shown in Table 3.

[0043] Table 3 .

[0044] Based on steps (a), (b), and (c), the obstacle avoidance path of the drone is planned. The resultant force is the vector sum of the gravitational force and the resultant repulsive force. When running to step 16, the resultant repulsive force is very large, indicating that the distance to the obstacle is very close. At this time, the path is reversed. Repeating the cycle will cause the path to oscillate and fail to reach the target point. Continue to execute the parallel replanning strategy (e).

[0045] (e) When the drone is moving towards the target point, if the resultant force is not 0, continue to execute step (f). When the resultant force is 0, the drone falls into a local optimum. , denoted as . Use the climbing and turning parallel re-planning strategy to jump out of the obstacle. The schematic diagram of the climbing strategy implementation is as follows Figure 3 Calculate the distance Nearest weather obstruction , select key waypoints , denoted as The path from the starting point to the key waypoint and from the key waypoint to the target point is re-planned in sections. Figure 4 As shown. and The distance is the radius, the step length is 1°, and circular motion is performed until the local optimum is jumped out. The specific calculation formula for circular motion is as follows: ; In the formula, The climbing strategy and the steering strategy are run in parallel, and the strategy with the shortest time consumption is selected as the strategy to escape from the local optimum.

[0046] Example: The result of climbing strategy example 1 is shown in the figure Figure 5 As shown. Select the key waypoint (60,60,84). Re-plan the path from the starting point to the key waypoint and from the key waypoint to the target point. The total length of the re-planned path is 248.92. The result of the steering strategy example 1 is shown in the figure Figure 6 Steps 17 to 39 are the arc motion stage, and the positions of the turning points are shown in Table 4.

[0047] Table 4 .

[0048] The total length of the planned path is 248.15. Select the turning strategy for replanning. Continue to execute (f) after jumping out of the local optimal point.

[0049] (f) The UAV moves towards the target point under the combined force until it reaches the target.

[0050] The present invention first establishes a mathematical model for high-impact weather factors, performs path planning in a three-dimensional search space based on an improved artificial potential field method, and assists in UAV mission planning. A parallel replanning strategy is added to the existing algorithm model for solving the problem of unreachable targets to solve the problem of local optimal solutions under high-impact meteorological conditions.

[0051] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A UAV path planning method based on a meteorological decision-making aid system, characterized in that: The following steps are involved: S1. Constructing meteorological obstacle model based on clustering algorithm; S2, construct a three-dimensional search space; S3, preprocessing the data of step S1 and step S2; S4, using an improved artificial potential field method on the data pre-processed in step S3; In step S1, a meteorological obstacle model is constructed based on a clustering algorithm, including: S11, removing abnormal data in the original meteorological file; S12, according to the thresholds of different meteorological elements in the original meteorological file, dividing the data of the original meteorological file into three types: low-impact weather, high-impact weather and critical conditions; S13. Use clustering thinning method to thin out the contour data of high-impact weather; S14, determining the circumscribed circle of the data after thinning in step S13 as the meteorological obstacle models of different altitude layers.

2. The method for UAV path planning based on a meteorological decision-making system according to claim 1, characterized in that: In step S2, a three-dimensional search space is constructed, including: S21, obtaining the starting point and end point information of the drone; S22, construct a rectangular area with the start point and the end point expanded by 5°; S23, intercepting the meteorological obstacle information in the rectangular area and constructing a no-fly area, where the no-fly area is a three-dimensional search space.

3. The method for UAV path planning based on a meteorological decision-making system according to claim 2, characterized in that: In step S3, the data of step S1 and step S2 are preprocessed, including: Determine whether the starting point and the end point of the UAV are located inside the meteorological obstacle. If not, proceed to step S4. Otherwise, give a prompt and re-enter the starting point and the end point.

4. The method for UAV path planning based on a meteorological decision-making system according to claim 3 is characterized in that: In step S4, the artificial potential field method is improved, and the UAV moves toward the target point under the action of the gravity of the target point and the repulsion of the obstacle, including: S41. Set the current position of the drone , denoted as , target point location , denoted as , calculate the gravitational potential field by the gravitational potential field calculation method; And calculate the gravitational force at the current position; S42, calculating the nearest threat point; S43, adding the distance between the current position and the target point into the calculation formula of the repulsive potential field; S44, the UAV moves towards the target point under the action of the resultant force, and the resultant force is calculated; S45: When the drone is moving toward the target point, if the resultant force is not 0, continue to execute step S46. When the resultant force is 0, the drone falls into a local optimum. , denoted as , adopt the climbing and turning parallel re-planning strategy to jump out of the obstacle and calculate the distance Nearest weather obstruction , select key waypoints , denoted as , re-plan the path from the starting point to the key waypoint, and from the key waypoint to the target point in sections; by and The distance is the radius, the step length is 1°, and circular motion is performed until the local optimum is jumped out, and the circular motion is calculated; S46. The UAV moves toward the target point under the combined traction until it reaches the target point.

5. The method for UAV path planning based on a meteorological decision-making system according to claim 4, characterized in that: In step S41, the gravitational potential field is calculated as follows: ； In the formula, represents the gravitational potential field, is the gravitational coefficient, is the distance between the current position and the target point; The gravitational force at the current position is calculated as follows: ； in, Indicates the gravitational force at the current position. The current position of the drone , The target point position , is the gravitational coefficient, is the distance between the current position and the target point, represents partial derivative.

6. The method for UAV path planning based on a meteorological decision-making aid system according to claim 4, characterized in that: In step S42, the nearest threat point is calculated, including: Set up obstacles , meteorological obstacles , denoted as ;in, and are the longitude and latitude of the obstacle, and are the altitudes of the upper and lower surfaces of the meteorological obstacle, respectively. is the bottom radius of the meteorological obstacle; the nearest threat point is calculated based on the relative height of the current position of the drone and the meteorological obstacle, and the bottom radius of the meteorological obstacle is used as the safe range for detour. The calculation method is as follows: ； In the formula, Indicates the nearest threat point of a single meteorological obstacle, Indicates the obstacle circle at the same height as the current position of the drone, with the center ,radius ; Indicates the obstacle circle that the drone needs to consider when flying around the top or bottom of a meteorological obstacle. When flying around the top, the center of the circle ,radius ; When flying around from the bottom, the center of the circle ,radius ; At this time, the safety range .

7. The method for UAV path planning based on a meteorological decision-making aid system according to claim 4, characterized in that: In step S43, the distance between the current position and the target point is added to the calculation formula of the repulsive potential field, and the calculation method is as follows: ； In the formula, represents the repulsive potential field formed by meteorological obstacles, represents the repulsion coefficient, Indicates the distance between the current point and the nearest threat point of the i-th meteorological obstacle, Indicates The repulsive force range of a meteorological obstacle, represents a positive constant; the current position is affected by The repulsion force of a meteorological obstacle is calculated as follows: ； ； ； in, It represents the repulsive force of meteorological obstacles on the UAV. represents the first part of the negative gradient of the repulsive potential field, represents the second part of the negative gradient of the repulsive potential field.

8. The method for UAV path planning based on a meteorological decision-making aid system according to claim 4, characterized in that: In step S44, the drone moves towards the target point under the action of the resultant force, and the resultant force calculation formula is as follows: ； In the formula, represents the total force acting on the drone, Indicates the gravitational force at the current position. The current position of the drone , m represents the number of meteorological obstacles, represents the repulsive force of the i-th meteorological obstacle on the UAV.

9. The method for UAV path planning based on a meteorological decision-making aid system according to claim 4, characterized in that: In step S45, the arc motion calculation formula is as follows: ； In the formula, is the step length.

Images