Urban intelligent cooperative combat-oriented unmanned aerial vehicle flight path planning method

Abstract

The invention relates to an unmanned aerial vehicle flight path planning method for urban intelligent cooperative operation, and the method comprises the steps: obtaining a three-dimensional grid of a flight channel of an unmanned aerial vehicle in a target city three-dimensional model according to the coordinates of a starting point and the coordinates of a target point under a flight constraint condition, carrying out the danger coefficient assignment of each grid, and carrying out the calculation of the risk coefficient. According to a preset first selection planning method, a central point coordinate of a network is selected in a selectable range as an intermediate node of a track, according to a preset second selection planning method, a two-dimensional plane is generated by taking the intermediate node as a center, the two-dimensional plane is expanded, a three-dimensional space is generated, an expanded part is taken as a selectable range, and the three-dimensional space is stored in the selectable range. And selecting the next node of the flight path in the range until the horizontal distance between the intermediate node and the target point coordinate is smaller than the preset distance, and generating the flight path of the unmanned aerial vehicle according to all the intermediate nodes to complete the flight path planning of the unmanned aerial vehicle. By adopting the method, the flight path planning of the unmanned aerial vehicle can be performed efficiently and accurately.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence science and technology, and in particular to a method for unmanned aerial vehicle (UAV) trajectory planning for urban intelligent collaborative operations. Background Art

[0002] Due to the high flexibility, strong maneuverability, low safety risk factor and low cost of drones, drones are widely used in search and patrol, reconnaissance and surveillance, disaster relief, logistics distribution, agricultural irrigation and other fields, and have very broad application prospects. Especially in the military field, drones can perform high-risk tasks such as reconnaissance and strikes, which can effectively reduce the risk of casualties of combatants. In recent years, drones' intelligent coordinated urban operations have attracted much attention.

[0003] Trajectory planning is one of the key technologies for UAV urban intelligent collaborative operations. It mainly refers to determining the best trajectory from the starting point to the target point for the UAV under certain conditions, taking into account factors such as safety, trajectory distance and time cost. Trajectory planning directly affects the time efficiency, economic efficiency and combat success rate of urban intelligent collaborative operations, and has important research significance.

[0004] However, common UAV trajectory planning methods are divided into two categories, global and local, according to the degree of understanding of environmental information. The global trajectory planning method relies on all the information of the environmental map to plan the trajectory. Although it pursues the global optimal path, it cannot cope with sudden obstacles. The local trajectory planning method can collect environmental information in real time for planning, but it is easy to fall into the local optimum, which is not the global optimum. Summary of the invention

[0005] Based on this, it is necessary to provide an efficient and accurate UAV trajectory planning method for urban intelligent collaborative operations to address the above technical problems.

[0006] A method for unmanned aerial vehicle trajectory planning for urban intelligent collaborative operations, characterized in that the method comprises:

[0007] Obtain the 3D model of the target city, the coordinates of the starting and target points of the track, and the flight constraints of the drone;

[0008] In the three-dimensional city model, a flyable channel of the UAV is obtained according to the coordinates of the starting point and the target point and under flight constraints, and the flyable channel is divided into three-dimensional grids to obtain a three-dimensional grid of the flyable channel;

[0009] According to the danger information data, assigning a danger coefficient to each grid in the three-dimensional grid of the flyable channel;

[0010] According to the preset first selection planning method, a selectable range of the next node of the track is generated with the coordinates of the starting point as the center, and the coordinates of the center point of a three-dimensional network are selected within the selectable range as the next node of the track, i.e., the intermediate node;

[0011] According to the preset second selection planning method, a two-dimensional plane is generated with the intermediate node as the center, and is extended according to the direction of the target point coordinates, a three-dimensional space is generated according to the extended two-dimensional plane, and the extended part is used as the selectable range, and the next node of the track is selected within the selectable range;

[0012] Until the horizontal distance between the intermediate node and the target point coordinates is less than the preset distance, the next node is set as the target point coordinates, and the UAV track is generated according to all the intermediate nodes to complete the UAV track planning.

[0013] In one embodiment, the flight constraints include: a minimum turning radius constraint and a flight altitude constraint.

[0014] In one embodiment, the flyable channel is represented as:

[0015] TD={(x,y,z)|t1≤x≤t2,t3≤y≤t4,H min ≤z≤H max}

[0016] in,

[0017] In the above formula, α represents a preset parameter, H min and H max They represent the minimum and maximum values ​​of the flight altitude in the flight constraint conditions, respectively. 0 ,y 0 ) represents the starting point coordinates, (x N ,y N ) represents the target point coordinates.

[0018] In one embodiment, the first selection planning method includes:

[0019] Taking the coordinates of the starting point as the center, generating the selectable range according to a preset size;

[0020] Calculating the first generation value of the three-dimensional grid that satisfies the flight constraint condition within the selectable range;

[0021] The center coordinate of the three-dimensional grid corresponding to the minimum first-generation value is selected as the next node of the track, that is, the intermediate node.

[0022] In one embodiment, the first generation value is calculated using the formula:

[0023]

[0024] In the above formula, β∈(0,1) and ε0∈(0,0.1) are preset parameters, GN represents the three-dimensional grid where the end point DTN(xN,yN) is located, the function D(,) represents the distance between the two three-dimensional grids, WX(G) represents the danger coefficient of the three-dimensional grid G, and G0 represents the center coordinates of the starting point coordinates.

[0025] In one embodiment, the second selection planning method includes:

[0026] Taking the position of the middle node as the center, an initial two-dimensional plane is generated according to a preset size;

[0027] Determine an expansion direction according to the coordinates of the starting point and the target point, and expand the initial two-dimensional plane according to the expansion direction to obtain an expanded two-dimensional plane;

[0028] Generate a three-dimensional space according to the expanded two-dimensional plane, and use the expanded part as a selectable range;

[0029] The second generation value of the three-dimensional grid that meets the flight constraint condition within the selectable range is calculated, and the center coordinate of the three-dimensional grid corresponding to the minimum second generation value is selected as the next node of the track.

[0030] In one embodiment, determining the expansion direction according to the starting point coordinates and the target point coordinates includes: determining two expansion directions according to the relationship between the starting point coordinates and the target point coordinates.

[0031] In one embodiment, when the initial two-dimensional plane is expanded according to the expansion direction:

[0032] Adding a row of grids to the initial two-dimensional plane according to two expansion directions to form a new two-dimensional plane;

[0033] Calculating the difference between the new two-dimensional plane and the initial two-dimensional plane, and if the difference is less than a preset parameter, continuing to expand on the new two-dimensional plane;

[0034] Until the difference is greater than a preset parameter, the currently generated new two-dimensional plane is used as the expanded two-dimensional plane.

[0035] In one embodiment, the second generation value is calculated using the formula:

[0036]

[0037] In the above formula, β∈(0,1) and ε0∈(0,0.1) are preset parameters, GN represents the three-dimensional grid where the end point DTN(xN,yN) is located, the function D(,) represents the distance between the two three-dimensional grids, WX(G) represents the risk factor of the three-dimensional grid G, G0 represents the center coordinates of the starting point coordinates, G m-1 Indicates the position coordinates of the previous intermediate node.

[0038] The above-mentioned unmanned aerial vehicle trajectory planning method for urban intelligent collaborative operations, in the three-dimensional model of the target city, according to the starting point coordinates and the target point coordinates and under the flight constraints, obtains the unmanned aerial vehicle's flyable channel, and divides it into three-dimensional grids, assigns a risk coefficient to each grid in the three-dimensional grid of the flyable channel according to the danger information data, generates a selectable range of the next node of the trajectory with the starting point coordinates as the center according to the preset first selection planning method, and selects the center point coordinates of a three-dimensional network within the selectable range as the next node of the trajectory, that is, the intermediate node, according to the preset second selection planning method, generates a two-dimensional plane with the intermediate node as the center, and expands it according to the direction of the target point coordinates, generates a three-dimensional space according to the expanded two-dimensional plane, and takes the expanded part as the selectable range, selects the next node of the trajectory within the selectable range, until the horizontal distance between the intermediate node and the target point coordinates is less than the preset distance, then the next node is set as the target point coordinates, and generates the unmanned aerial vehicle's trajectory according to all the intermediate nodes to complete the unmanned aerial vehicle trajectory planning. The method can be used to efficiently and accurately plan the unmanned aerial vehicle trajectory. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A schematic diagram of a flow chart of a method for unmanned aerial vehicle trajectory planning for urban intelligent collaborative operations in one embodiment;

[0040] Figure 2 is a schematic diagram of four expandable directions of a grid in one embodiment;

[0041] Figure 3 It is a schematic diagram of the expansion of the grid range in two directions in an embodiment. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0043] The existing UAV trajectory planning methods have the problems of not being able to select a suitable search range for the actual environment, high algorithm complexity, and low accuracy. Figure 1As shown, a UAV trajectory planning method for urban intelligent collaborative operations is provided, which specifically includes the following steps:

[0044] Step S100, obtaining the three-dimensional city model corresponding to the target city, the coordinates of the starting point and the target point of the track, and the flight constraints of the UAV.

[0045] Step S110, in the three-dimensional city model, according to the coordinates of the starting point and the target point and under the flight constraint conditions, the flyable channel of the UAV is obtained, and the flyable channel is divided into three-dimensional grids to obtain the flyable channel three-dimensional grid.

[0046] Step S120, assigning a danger coefficient to each grid in the three-dimensional grid of the flyable channel according to the danger information data.

[0047] Step S130, according to the preset first selection planning method, a selectable range of the next node of the track is generated with the starting point coordinates as the center, and the center point coordinates of a three-dimensional network are selected within the selectable range as the next node of the track, that is, the intermediate node.

[0048] Step S140, according to the preset second selection planning method, a two-dimensional plane is generated with the middle node as the center, and it is expanded according to the direction of the target point coordinates, a three-dimensional space is generated according to the expanded two-dimensional plane, and the expanded part is used as the selectable range, and the next node of the track is selected within the selectable range.

[0049] Step S150, until the horizontal distance between the intermediate node and the target point coordinates is less than the preset distance, the next node is set as the target point coordinates, and the UAV track is generated according to all the intermediate nodes to complete the UAV track planning.

[0050] In this embodiment, the starting point and the end point of the track are first determined on the three-dimensional model corresponding to the designated target city, then the flight constraints of the drone are determined, the channel where the drone can fly is divided into three-dimensional grids, and a risk coefficient is assigned to each grid. Then, starting from the starting point, the next node is determined according to the cost value 1 of each grid in the selection range, and then the grid selection range of the current node is determined by an adaptive method, and the next node is determined by the cost value 2 of the grid in the range. Finally, the distance relationship between the current node and the end point is determined. If the conditions are met, the flight route composed of all nodes is output. If the conditions are not met, the iterative process of determining the next node through the adaptive grid selection method and the cost value 2 is continued until the distance relationship with the end point is met. The method can select a suitable search range according to the actual environment, and the cost calculation method has low complexity and high accuracy, which has good practical value.

[0051] In step S100, in the three-dimensional city model, the coordinates of the starting point and the target point of the track are represented as DT0(x0, y0) and DTN(xN, yN) respectively.

[0052] Specifically, the flight constraints include: minimum turning radius constraint and flight altitude constraint.

[0053] Furthermore, assuming that the minimum turning radius of the drone is R min , the turning radius of any point on the planned track is r, then the minimum turning radius constraint can be expressed as: r ≥ R min .

[0054] Furthermore, assuming that the maximum flight altitude of the drone is H min , the minimum flight altitude is H min , then the constraint condition of the flight height h can be expressed as: H max ≥h≥H min .

[0055] In step S110, the flyable channel is represented as:

[0056] TD={(x,y,z)|t1≤x≤t2,t3≤y≤t4,H min ≤z≤H max} (1)

[0057] in,

[0058] In formula (1), α represents a pre-set parameter, H min and H max They represent the minimum and maximum values ​​of the flight altitude in the flight constraints, respectively. 0 ,y 0 ) represents the coordinates of the starting point, (x N ,y N ) represents the target point coordinates.

[0059] Furthermore, the flyable channel represented by formula (1) is divided into three-dimensional grids, and the size of each grid is A×A×B, where B represents the height of the grid, and A and B are pre-set parameters. Three-dimensional grid of the flyable channel.

[0060] In step S120, a danger coefficient WX(G) is assigned to each grid G ​​based on the existing danger information. The value range of the danger coefficient is [0,1]. When the danger coefficient is 0, it means that the grid is very safe. When the danger coefficient is 1, it means that the grid is prohibited from passing. The larger the danger coefficient, the more dangerous it is to pass through the grid.

[0061] In step S130, when planning the next node of the starting point coordinates, the first selection planning method adopted includes: taking the starting point coordinates as the center, generating a selectable range according to a preset size, calculating the first generation value of the three-dimensional grid that meets the flight constraints within the selectable range, and selecting the center coordinates of the three-dimensional grid corresponding to the minimum first generation value as the next node of the track, i.e., the intermediate node.

[0062] In this embodiment, the drone starts from the starting point DT0(x0, y0), at this time, let m = 1, take the grid G0 where DT0(x0, y0) is located as the center, and take DT0(x0, y0) as the center, according to the preset size, here take 3×3×3 as an example, the generated domain Ω 0 (G0) is used as the selection range of the next intermediate node position. In the selectable range, there are 3×3×3-1=26 grids to choose from.

[0063] Furthermore, according to the flight constraints, Ω 0 The 26 grids in (G0) are re-judged, and the cost values ​​of the grids that meet the flight constraints are calculated to obtain the first generation value, and the center point of the grid with the smallest cost value is selected as the next node, that is, the middle node of the entire track.

[0064] In this embodiment, the first generation value is calculated using the formula:

[0065]

[0066] In formula (2), β∈(0,1) and ε0∈(0,0.1) are preset parameters, GN represents the three-dimensional grid where the end point DTN(xN,yN) is located, the function D(,) represents the distance between the two three-dimensional grids, WX(G) represents the danger coefficient of the three-dimensional grid G, and G0 represents the center coordinates of the starting point coordinates.

[0067] Specifically, the function D(,) represents the calculation of the Euclidean distance between the center pixels of two grids.

[0068] Specifically, select the grid with the smallest cost value, that is, G m =minJ1(G), let the grid G m The center pixel of the new node DT is selected as the current node m (x m ,y m ,z m ) is the position coordinate of the next node, and finally set m=m+1.

[0069] In step 140, when the next node of the intermediate node other than the next node of the planning starting point coordinates is the next node, that is, when m>1, the current intermediate node DT is known.m-1 (x m-1 ,y m-1 ,z m-1 ) is located in the grid G m-1 If G m-1 The area Ω where the three-dimensional area is 3×3×3 in size is centered m-1 (G m-1 ) is the initial selection range, i.e., the node planning method in step S130. However, in order to speed up the algorithm, an adaptive grid selection range method, i.e., the second selection planning method, is adopted in this method. In this method, the height of the selection range is not considered first, and it is only expanded on the two-dimensional plane, and then the height is superimposed on the expanded two-dimensional plane.

[0070] In this embodiment, the second selection planning method includes: taking the position of the intermediate node as the center, generating an initial two-dimensional plane according to a preset size, determining the expansion direction according to the coordinates of the starting point and the target point, expanding the initial two-dimensional plane according to the expansion direction to obtain the extended two-dimensional plane, generating a three-dimensional space according to the extended two-dimensional plane, and taking the extended part as the selectable range, calculating the second-generation value of the three-dimensional grid that meets the flight constraints within the selectable range, and selecting the center coordinates of the three-dimensional grid corresponding to the minimum second-generation value as the next node of the track.

[0071] Specifically, the position of the intermediate node DT m-1 (x m-1 ,y m-1 ,z m-1 ) as the center, and generate an initial two-dimensional plane according to a preset size. In this embodiment, taking 3×3 as an example, the domain δ0(G m-1 ) is recorded as the initial two-dimensional plane Ψ0.

[0072] In this embodiment, determining the extension direction according to the starting point coordinates and the target point coordinates includes: determining two extension directions according to the relationship between the starting point coordinates and the target point coordinates.

[0073] Specifically, on the initial two-dimensional plane Ψ0, there are four directions that can be extended, and they are recorded as direction 1, direction 2, direction 3, and direction 4, respectively, as follows: Figure 3 shown.

[0074] Specifically, according to the positional relationship between the starting point coordinate DT0 (x0, y0) and the end point coordinate DTN (xN, yN), the extended range is further simplified, as shown in Table 1:

[0075] Table 1

[0076] Positional Relationship Direction of expansion xN≥x0,yN≥y0 Direction 1, Direction 2 xN<x0,yN<y0 Direction 3, Direction 4 xN≥x0,yN<y0 Direction 2, Direction 3 xN<x0,yN≥y0 Direction 1, Direction 4

[0077] As shown in Table 1, according to the positional relationship between the starting point coordinates and the end point coordinates, two extension directions can be obtained and recorded as direction v1 and direction v2.

[0078] In this embodiment, when the initial two-dimensional plane is expanded according to the expansion direction: a row of grids is added to the initial two-dimensional plane Ψ0 according to the two expansion directions v1 and v2 to form a new two-dimensional plane Ψ1, such as Figure 3 Next, the difference between the new two-dimensional plane Ψ1 and the initial two-dimensional plane Ψ0 is calculated. If the difference is less than the preset parameter, the expansion is continued on the new two-dimensional plane Ψ1, that is, Ψ0=Ψ1, and the expansion is continued on Ψ0 until the difference is greater than the preset parameter, and the currently generated new two-dimensional plane is used as the expanded two-dimensional plane.

[0079] Specifically, the difference between the new two-dimensional plane Ψ1 and the initial two-dimensional plane Ψ0 is calculated using the following formula:

[0080]

[0081] In formula (3), γ represents a predetermined adjustment parameter.

[0082] Furthermore, after obtaining the expanded two-dimensional plane, only its outer contour grid set, that is, the last extended grid, is selected, and then the height range is added to the outer contour grid, including the height of the upper and lower two layers of grids and its own grid, a total of three layers of outer contour grids, forming a three-dimensional grid selection area, that is, recorded as newΩ m-1 (G m-1 ) is the final selection range.

[0083] Furthermore, according to the current node DT m-1 (x m-1 ,y m-1 ,z m-1 ) is located in the grid G m-1 , and the next selection range is newΩ m-1 (G m-1 ), and then make a judgment based on the flight constraints within this selection range, and calculate the cost value of the grid that meets the flight constraints, that is, the second generation value.

[0084] Specifically, the second generation value is calculated using the formula:

[0085]

[0086] In formula (4), β∈(0,1) and ε0∈(0,0.1) are preset parameters, GN represents the three-dimensional grid where the end point DTN(xN,yN) is located, the function D(,) represents the distance between two three-dimensional grids, WX(G) represents the risk factor of the three-dimensional grid G, G0 represents the center coordinates of the starting point coordinates, G m-1 Indicates the position coordinates of the previous intermediate node.

[0087] Furthermore, the grid with the smallest value in the second generation is selected, that is, G m =minJ2(G), let the grid G m The center pixel of the new node DT is selected as the current node m (x m ,y m ,z m ).

[0088] In step S150, after performing the intermediate node planning in step S140 for multiple times, when DT m (x m ,y m ,z m ) and the horizontal distance between the end point DTN (xN, yN) If it is less than twice the width of the grid, that is, 2A, the termination condition is met, and the next node is directly set as the end point. The set of all nodes {DT 1 (x 1 ,y 1 ,z 1 ),…,DT m (x m ,y m ,z m )}, forming the flight route of the drone. That is, after each intermediate node is obtained, the distance between the newly obtained intermediate node and the target point is calculated. If it does not meet the termination condition, m=m+1 is set until the termination condition is met.

[0089] In the above-mentioned UAV trajectory planning method for urban intelligent collaborative combat, in the three-dimensional model of the target city, according to the coordinates of the starting point and the target point and under the flight constraints, the flyable channel of the UAV is obtained, and the three-dimensional grid is segmented, and the danger coefficient is assigned to each grid in the three-dimensional grid of the flyable channel according to the danger information data, and the selectable range of the next node of the trajectory is generated with the coordinates of the starting point as the center according to the preset first selection planning method, and the center point coordinates of a three-dimensional network are selected in the selectable range as the next node of the trajectory, that is, the intermediate node, according to the preset second selection planning method, a two-dimensional plane is generated with the intermediate node as the center, and it is extended according to the direction of the target point coordinates, and a three-dimensional space is generated according to the extended two-dimensional plane, and the extended part is used as the selectable range, and the next node of the trajectory is selected in the selectable range until the horizontal distance between the intermediate node and the target point coordinates is less than the preset distance, then the next node is set as the target point coordinates, and the UAV trajectory is generated according to all the intermediate nodes to complete the UAV trajectory planning. The method can select a suitable search range according to the actual environment, and the cost calculation method has low complexity and high accuracy, and has good practical value.

[0090] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0091] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0092] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0093] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A UAV trajectory planning method for urban intelligent collaborative operations, characterized in that: The method comprises: Obtain the 3D model of the target city, the coordinates of the starting and target points of the track, and the flight constraints of the drone; In the three-dimensional city model, a flyable channel of the UAV is obtained according to the coordinates of the starting point and the target point and under flight constraints, and the flyable channel is divided into three-dimensional grids to obtain a three-dimensional grid of the flyable channel; According to the danger information data, assigning a danger coefficient to each grid in the three-dimensional grid of the flyable channel; According to the preset first selection planning method, a selectable range of the next node of the track is generated with the coordinates of the starting point as the center, and the coordinates of the center point of a three-dimensional network are selected within the selectable range as the next node of the track, i.e., the intermediate node; According to the preset second selection planning method, a two-dimensional plane is generated with the intermediate node as the center, and is extended according to the direction of the target point coordinates, a three-dimensional space is generated according to the extended two-dimensional plane, and the extended part is used as the selectable range, and the next node of the track is selected within the selectable range; Until the horizontal distance between the intermediate node and the target point coordinates is less than the preset distance, the next node is set as the target point coordinates, and the UAV track is generated according to all the intermediate nodes to complete the UAV track planning.

2. The UAV trajectory planning method according to claim 1, characterized in that: The flight constraints include: a minimum turning radius constraint and a flight altitude constraint.

3. The UAV trajectory planning method according to claim 1, characterized in that: The flyable channel is represented as: TD={(x,y,z)|t1≤x≤t2,t3≤y≤t4,H min ≤z≤H max } in, In the above formula, α represents a preset parameter, H min and H max They represent the minimum and maximum values ​​of the flight altitude in the flight constraint conditions, (x0, y0) represents the coordinates of the starting point, (x N ,y N ) represents the target point coordinates.

4. The UAV trajectory planning method according to claim 2, characterized in that: The first selection planning method comprises: Taking the coordinates of the starting point as the center, generating the selectable range according to a preset size; Calculating the first generation value of the three-dimensional grid that satisfies the flight constraint condition within the selectable range; The center coordinate of the three-dimensional grid corresponding to the minimum first-generation value is selected as the next node of the track, that is, the intermediate node.

5. The UAV trajectory planning method according to claim 4, characterized in that: To calculate the first generation value, use the formula: In the above formula, β∈(0,1) and ε0∈(0,0.1) are preset parameters, GN represents the three-dimensional grid where the end point DTN(xN,yN) is located, the function D(,) represents the distance between the two three-dimensional grids, WX(G) represents the danger coefficient of the three-dimensional grid G, and G0 represents the center coordinates of the starting point coordinates.

6. The UAV trajectory planning method according to claim 1, characterized in that: The second selection planning method comprises: Taking the position of the middle node as the center, an initial two-dimensional plane is generated according to a preset size; Determine an expansion direction according to the coordinates of the starting point and the target point, and expand the initial two-dimensional plane according to the expansion direction to obtain an expanded two-dimensional plane; Generate a three-dimensional space according to the expanded two-dimensional plane, and use the expanded part as a selectable range; The second generation value of the three-dimensional grid that meets the flight constraint condition within the selectable range is calculated, and the center coordinate of the three-dimensional grid corresponding to the minimum second generation value is selected as the next node of the track.

7. The UAV trajectory planning method according to claim 6, characterized in that: Determining the expansion direction according to the starting point coordinates and the target point coordinates includes: determining two expansion directions according to the relationship between the starting point coordinates and the target point coordinates.

8. The UAV trajectory planning method according to claim 7, characterized in that: When the initial two-dimensional plane is expanded according to the expansion direction: Adding a row of grids to the initial two-dimensional plane according to two expansion directions to form a new two-dimensional plane; Calculating the difference between the new two-dimensional plane and the initial two-dimensional plane, and if the difference is less than a preset parameter, continuing to expand on the new two-dimensional plane; Until the difference is greater than a preset parameter, the currently generated new two-dimensional plane is used as the expanded two-dimensional plane.

9. The UAV trajectory planning method according to claim 8, characterized in that: To calculate the second generation value, the formula is: In the above formula, β∈(0,1) and ε0∈(0,0.1) are preset parameters, GN represents the three-dimensional grid where the end point DTN(xN,yN) is located, the function D(,) represents the distance between the two three-dimensional grids, WX(G) represents the risk factor of the three-dimensional grid G, G0 represents the center coordinates of the starting point coordinates, G m-1 Indicates the position coordinates of the previous intermediate node.

Images