Method, device and medium for optimizing path of unmanned aerial vehicle in strong-rejection space

Abstract

The application relates to a method, device, equipment and medium for optimizing the path of a UAV in a strong denial space. The method comprises the following steps: obtaining a task area in the strong denial space and information related to the task area; performing path planning in the task area according to the information related to the task area, threat area constraint conditions and UAV attribute constraint conditions to obtain a first planning path; obtaining a plurality of threat areas in the task area which satisfy the threat area constraint conditions; obtaining a threat window according to the distance between each threat area and the first planning path; and performing secondary path planning on the first planning path in the threat window to obtain an optimized UAV planning path, wherein the flight path after the secondary path planning is in a spiral shape. The method can effectively improve the survival rate of the UAV in the strong denial space.

Description

Technical Field

[0001] This application relates to the field of unmanned aerial vehicle (UAV) swarm control technology, and in particular to a method, apparatus, device, and medium for optimizing UAV paths in a strongly denied space. Background Technology

[0002] Building a strong denial zone for unmanned aerial vehicle (UAV) systems is a common defensive measure for the defending side. The attacking side, on the other hand, faces the practical problem of performing tasks such as reconnaissance and positioning, jamming and suppression, target designation, direct strike, and coordinated countermeasures under strong denial conditions. It is foreseeable that the confrontation between UAV systems around area denial and anti-denial will inevitably be the future trend.

[0003] Path planning for aircraft essentially involves finding the optimal or feasible flight trajectory from the starting point to one or more target points within a specified mission area, while satisfying known constraints. However, most existing path planning methods are designed for obstacle avoidance and shortest path optimization, and algorithm research focuses on aspects such as algorithm complexity, real-time performance, and resource consumption, while modeling real-world application scenarios in an idealized way. This leads to a decrease in the survivability of UAVs when applying existing UAV path planning methods in strongly denied spaces. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, device, and medium for optimizing UAV paths in a strongly denied space that can improve the survivability of UAVs, addressing the aforementioned technical problems.

[0005] A method for optimizing the path of a drone in a strongly denied space, the method comprising:

[0006] Acquire the task region and related information, wherein the task region is located within a strong denial space;

[0007] Based on the information related to the mission area, path planning is performed within the mission area under the constraints of the threat zone and the UAV's own attributes to obtain the first planned path.

[0008] Multiple threat regions satisfying the threat region constraints are obtained within the task area;

[0009] The threat window is obtained based on the distance between each threat region and the first planned path;

[0010] A secondary path planning is performed on the first planned path located within the threat window to obtain an optimized UAV planned path, wherein the route after the secondary path planning is spiral-shaped.

[0011] In one embodiment, the threat zone constraint is derived from the effective range of the adversary's ground-based air defense radar and the counterattack system.

[0012] In one embodiment, path planning is performed under threat zone constraints and UAV own attribute constraints, employing any one of the following algorithms: shortest tangent method, genetic algorithm, RRT fast search random tree algorithm, or UAV intelligent avoidance decision algorithm based on deep reinforcement learning.

[0013] In one embodiment, multiple threat regions satisfying the threat region constraints are obtained within the task area, including:

[0014] The task area is gridded based on the task area information;

[0015] The attributes of each grid are determined based on the threat zone constraints to obtain multiple grids with threat attributes;

[0016] Clustering algorithms are used to merge adjacent grids with threat attributes to obtain multiple threat regions.

[0017] In one embodiment, the threat window is obtained based on the distance between each of the threat regions and the first planned path, including:

[0018] The first planned path consists of multiple point coordinates, and the threat distance between each point coordinate and the boundary of the adjacent threat area is calculated sequentially.

[0019] Based on the first preset threshold and the threat distance, the corresponding point coordinates are determined to be either a threat point or a safe point;

[0020] The corresponding initial threat window center line segment is formed by continuous threat points. If the distance between two adjacent initial threat window center lines is less than the second preset value, the two initial threat window center line segments are merged to obtain the threat window center line segment.

[0021] The threat window is generated based on the center line segment of the threat window.

[0022] In one embodiment, generating the threat window based on the center line segment of the threat window includes:

[0023] For each threat window center segment, the width of the threat window is dynamically determined based on the minimum distance from each point on the center segment to the adjacent threat area;

[0024] The threat windows are generated based on their center line segments and widths.

[0025] In one embodiment, the motion equation of the drone within the threat window is expressed as:

[0026] xk=Rvsin(ωT)

[0027] yk=Rhcos(ωT)

[0028] zk = V 变 T

[0029] In the above formula, the parameter that can be adjusted according to the maneuverability of the UAV is the flight speed V. 变 The horizontal spiral radius Rh and the vertical spiral radius Rv.

[0030] This application also provides a drone path optimization device in a strongly denied space, the device comprising:

[0031] The information acquisition module is used to acquire the task area and related information, wherein the task area is located within the strong denial space;

[0032] The first path planning module is used to perform path planning within the task area based on the information related to the task area, under the constraints of the threat zone and the UAV's own attributes, to obtain the first planned path.

[0033] A threat region acquisition module is used to acquire multiple threat regions within the task area that satisfy the threat region constraints.

[0034] The threat window acquisition module is used to obtain a threat window based on the distance between each of the threat regions and the first planned path;

[0035] The secondary path planning module is used to perform secondary path planning on the first planned path located within the threat window to obtain an optimized UAV planned path, wherein the route after secondary path planning is spiral-shaped.

[0036] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program performing the following steps:

[0037] Acquire the task region and related information, wherein the task region is located within a strong denial space;

[0038] Based on the information related to the mission area, path planning is performed within the mission area under the constraints of the threat zone and the UAV's own attributes to obtain the first planned path.

[0039] Multiple threat regions satisfying the threat region constraints are obtained within the task area;

[0040] The threat window is obtained based on the distance between each threat region and the first planned path;

[0041] A secondary path planning is performed on the first planned path located within the threat window to obtain an optimized UAV planned path, wherein the route after the secondary path planning is spiral-shaped.

[0042] A computer-readable storage medium having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0043] Acquire the task region and related information, wherein the task region is located within a strong denial space;

[0044] Based on the information related to the mission area, path planning is performed within the mission area under the constraints of the threat zone and the UAV's own attributes to obtain the first planned path.

[0045] Multiple threat regions satisfying the threat region constraints are obtained within the task area;

[0046] The threat window is obtained based on the distance between each threat region and the first planned path;

[0047] A secondary path planning is performed on the first planned path located within the threat window to obtain an optimized UAV planned path, wherein the route after the secondary path planning is spiral-shaped.

[0048] The aforementioned method, apparatus, equipment, and medium for optimizing UAV paths within a strong denial space acquire a mission area within that space and related information. Based on this information, path planning is performed within the mission area under threat zone constraints and UAV attribute constraints to obtain a first-stage planned path. Multiple threat zones satisfying the threat zone constraints are then identified within the mission area. Threat windows are determined based on the distances between each threat zone and the first-stage planned path. A second-stage path planning is then performed on the first-stage planned path located within these threat windows to obtain an optimized UAV planned path. The optimized path exhibits a spiral shape. This method effectively improves the survival rate of UAVs within a strong denial space. Attached Figure Description

[0049] Figure 1 This is a flowchart illustrating a method for optimizing the path of a drone within a strongly denied space, as shown in one embodiment.

[0050] Figure 2 This is a schematic diagram of the helical speed-changing maneuver of the threat window area in one embodiment;

[0051] Figure 3 This is a structural block diagram of a drone path optimization device in a strongly denied space according to one embodiment;

[0052] Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0054] In existing technologies, most aircraft (UAV) path planning methods are designed for obstacle avoidance and shortest path optimization. Furthermore, algorithm research focuses on the complexity, real-time performance, and resource consumption of these algorithms, resulting in idealized modeling of real-world application scenarios. This leads to low UAV survival rates when applying existing UAV path planning methods in strongly denied spaces. In this application, as... Figure 1 As shown, a method for optimizing the path of a UAV in a strongly denied space is provided, which specifically includes the following steps:

[0055] Step S100: Obtain the task region and related information. The task region is located within the strong denial space.

[0056] Step S110: Based on the information related to the mission area, perform path planning within the mission area under the constraints of the threat zone and the UAV's own attributes to obtain the first planned path.

[0057] Step S120: Obtain multiple threat regions within the task area that satisfy the aforementioned threat region constraints.

[0058] Step S130: Obtain the threat window based on the distance between each threat area and the first planned path.

[0059] Step S140: Perform secondary path planning on the first planned path located within the threat window to obtain the optimized UAV planned path, wherein the route after secondary path planning is spiral-shaped.

[0060] In this embodiment, a threat window is defined on the first planned path based on the relationship between the first planned path and multiple threat areas within the strong denial space, and secondary path planning is performed within this threat window. This allows the UAV to better cope with various threats when passing through the threat window, thereby improving the survival rate of the UAV when performing tasks within the strong denial space.

[0061] In step S100, this method is designed for scenarios where drones or aircraft are performing tasks in a strongly denied space. Therefore, before performing the first path planning, it is necessary to obtain relevant information within the task area in order to obtain a reasonable and efficient first planned path. In this embodiment, the relevant information includes geographical information, such as terrain, precise geographical coordinates and boundary coordinates of the task area, weather conditions, physical obstacle information, adversary threat information, and task target information.

[0062] In step S110, during the initial path planning, it is necessary to clearly define the threat areas within the mission area so that the first path planning can effectively avoid any threatening areas. Depending on the scenario and target of this method, the threat area constraints arise from the operational range of the adversary's ground-based air defense radar and the countermeasures attack system. More specifically, these constraints are defined by the detection area of ​​the adversary's ground-based air defense radar and the attack range of the countermeasures attack system within the mission area.

[0063] In this embodiment, path planning is performed under the constraints of the threat zone and the UAV's own attributes, using any one of the following algorithms: shortest tangent method, genetic algorithm, RRT fast search random tree algorithm, and UAV intelligent avoidance decision algorithm based on deep reinforcement learning.

[0064] Furthermore, the inherent constraints of the UAV include speed constraints, turning radius constraints, stall radius constraints, climb constraints, onboard resource constraints, and inter-UAV collision avoidance constraints. These constraints are set according to the specific circumstances of the UAV performing the mission.

[0065] Meanwhile, it can be seen that the path planning methods used in the first path planning were all designed for obstacle avoidance and shortest path. For example, in the modeling of the threat zone, although static and dynamic threats were distinguished, the threat zone was still defined with clear geometric boundaries. The selection of navigation points during flight was also a binary choice, with two possible options: feasible and infeasible. However, in real combat environments, the causes of threat zones are complex. Some threats come from static terrain, which are essentially physical obstacles. Other threats come from the deployment of enemy defense forces. Moreover, within the same threat zone, multiple types of denial and defense equipment may be deployed, including navigation denial, firepower strikes, electromagnetic countermeasures, and human-in-the-loop systems, which together constitute the defense forces of the threat zone. Under the synergistic effect of these forces, the boundary of the threat zone will inevitably become very vague and dynamically changing, rather than simple and clear. Therefore, for UAV path planning algorithms under strong denial conditions, the influence of these boundary zones needs to be further considered.

[0066] Therefore, in this method, based on the first planned path, the threat window is further divided, and the planned path within the threat window is planned a second time to avoid possible threats, thereby improving the survival rate of the drone.

[0067] In step 120, the task area is further refined based on threat constraints to obtain multiple threat regions that satisfy the threat region constraints. Specifically, this includes: first, the task area is gridded according to the task area information; second, the attributes of each grid are determined according to the threat region constraints to obtain multiple grids with threat attributes; and third, a clustering algorithm is used to merge adjacent grids with threat attributes to obtain multiple threat regions.

[0068] In this embodiment, the threat area is circular.

[0069] Furthermore, when gridding the mission area information, the grid size is set according to the UAV's flight accuracy, threat detection accuracy, and mission requirements to ensure that the divided network is sufficiently fine to reflect the details of the threat area. When judging the threat attributes of each grid, the judgment can be made based on the detection area of ​​the adversary's ground-based defense radar and the attack range of the adversary's attack system. When the center point of a grid falls within the radar's detection range or attack range, the grid is marked as "containing threat data".

[0070] Specifically, spatial clustering algorithms (such as DBSCAN) are used to merge adjacent meshes with threat attributes. Adjacent meshes can be defined based on their geometric proximity or shared threat sources. Through cluster analysis, these adjacent threatening meshes are merged to form multiple threat regions.

[0071] In this method, the concept of a threat window is established. After the flight path of the UAV in the mission area is obtained by running the above algorithm, the threat window is divided according to the Euclidean spatial distance relationship between the planned path and the threat area. That is, when some segments of the planned path may overlap with the threat area, it is judged that the segment of the path is within the threat window, which means that the UAV has a certain survival risk when flying on this segment of the path.

[0072] Specifically, in step S130, the threat window is obtained based on the distance between each threat area and the first planned path, including: the first planned path consists of multiple point coordinates; the threat distance between each point coordinate and the boundary of the adjacent threat area is calculated sequentially; the corresponding point coordinates are determined as threat points or safe points based on a first preset threshold and the threat distance; the corresponding preliminary threat window center line segment is formed based on consecutive threat points; if the distance between two adjacent preliminary threat window center lines is less than a second preset value, the two preliminary threat window center line segments are merged to obtain the threat window center line segment; and the threat window is generated based on the threat window center line segment.

[0073] In this embodiment, it can be understood that the first planned path may consist of multiple discrete coordinate points. The threat distance between each coordinate point and the boundary of the adjacent threat area is calculated in sequence. Here, the threat distance refers to the minimum distance between the coordinate point and the boundary of the adjacent threat area.

[0074] In some embodiments, the first preset value can be set to 3 kilometers. When the threat distance is less than 3 kilometers, the point is identified as a threat point; otherwise, the point is a safe point.

[0075] In this embodiment, when merging the center line segments of two preliminary threat windows, 0.5 kilometers can be used as a second preset value. Two preliminary threat windows with a distance less than the second preset value are merged to form a complete threat window.

[0076] In this embodiment, generating the threat window based on the center line segment of the threat window includes: for each threat window center line segment, dynamically determining the width of the threat window based on the minimum distance from each point on the center line segment to the adjacent threat area, and generating the threat window based on the center line segment and width of each threat window.

[0077] Specifically, when the distance from the center line segment to the adjacent threat area is small, the width of the threat window can be adjusted to be larger to provide sufficient safety margin. When the distance is large, the window width can be reduced accordingly.

[0078] For path segments within the threat window, secondary planning is required to design paths with certain penetration capabilities. In this method, the proposed three-dimensional spatial spiral variable-speed maneuver is a path form derived from this secondary planning. This path form is an effective form of penetration maneuver, which can be understood as an active jamming maneuver performed under the target's aiming pressure. This situation is similar to the UAV combat environment under strong denial conditions, where UAVs flying in denied space inevitably face pressure from ground radar scanning or tracking lock-on.

[0079] like Figure 2The diagram illustrates the division of the threat window and the changes in the drone's trajectory within it. The green area indicates the drone is within its planned path, exhibiting a smooth straight line trajectory. The primary objectives at this stage are to shorten range, conserve fuel, increase flight speed, and shorten mission execution time. The red area indicates the drone is within the threat window region, exhibiting a spiral trajectory. Here, the main objective is to maximize the drone's survival probability, even at the expense of non-critical metrics such as increased power consumption, extended range, and longer mission execution time.

[0080] Specifically, during secondary path planning within the threat window, in the trajectory coordinate system OX... k Y k Z k The motion equations of the UAV within the threat window are expressed as follows:

[0081] xk=Rvsin(ωT)

[0082] yk=Rhcos(ωT)

[0083] zh=V 变 T

[0084] In the above formula, the parameter that can be adjusted according to the maneuverability of the UAV is the flight speed V. 变 The parameters are the horizontal spiral radius Rh and the vertical spiral radius Rv. The specific settings for flight speed and the horizontal / vertical spiral radius must meet the flight performance constraints of the UAV itself, as well as the requirements for mission time, terrain avoidance, etc. Generally, flight speed V becomes a mandatory adjustment parameter, while the horizontal and vertical spiral radii are optional. When the vertical spiral radius Rv is large, the UAV's elevation changes drastically during spiral motion, increasing the difficulty of detection by ground radar. When the horizontal spiral radius Rh is large, the UAV's motion exhibits a zigzag pattern.

[0085] Preferably, within the threat window region, provided that the aircraft's maneuverability is satisfied, the flight speed V is calculated as 0.8 times the maximum flight speed. 变 To retrieve the value.

[0086] In the aforementioned method for optimizing UAV paths within a strong denial space, the method, apparatus, equipment, and medium acquire information about the mission area and related information within the strong denial space. Based on this information, path planning is performed within the mission area under threat zone constraints and UAV attribute constraints to obtain a first-stage planned path. Multiple threat zones satisfying the threat zone constraints are then identified within the mission area. Threat windows are determined based on the distances between each threat zone and the first-stage planned path. A second-stage path planning is then performed on the first-stage planned path located within the threat windows to obtain an optimized UAV planned path. The optimized path exhibits a spiral shape after the second-stage path planning. This method can effectively improve the survival rate of UAVs within a strong denial space.

[0087] It should be understood that, although Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed 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 some of the sub-steps or stages of other steps.

[0088] In one embodiment, such as Figure 3 As shown, a UAV path optimization device in a strongly denied space is provided, comprising: an information acquisition module 200, a first path planning module 210, a threat region acquisition module 220, a threat window acquisition module 230, and a second path planning module 240, wherein:

[0089] Information acquisition module 200 is used to acquire a task area and information related to the task area, wherein the task area is located within a strong denial space;

[0090] The first path planning module 210 is used to perform path planning within the task area based on the information related to the task area, under the constraints of the threat zone and the UAV's own attributes, to obtain the first planned path.

[0091] Threat region obtaining module 220 is used to obtain multiple threat regions that satisfy the threat region constraints within the task area;

[0092] The threat window acquisition module 230 is used to obtain a threat window based on the distance between each of the threat regions and the first planned path;

[0093] The secondary path planning module 240 is used to perform secondary path planning on the first planned path located within the threat window to obtain an optimized UAV planned path, wherein the route after secondary path planning is spiral.

[0094] Specific limitations regarding the UAV path optimization device in a strongly denied space can be found in the limitations of the UAV path optimization method in a strongly denied space described above, and will not be repeated here. Each module in the aforementioned UAV path optimization device in a strongly denied space can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0095] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When executed by the processor, the computer program implements a method for optimizing the path of a UAV in a strongly denied space. The display screen can be an LCD screen or an e-ink display screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0096] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0097] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0098] Acquire the task region and related information, wherein the task region is located within a strong denial space;

[0099] Based on the information related to the mission area, path planning is performed within the mission area under the constraints of the threat zone and the UAV's own attributes to obtain the first planned path.

[0100] Multiple threat regions satisfying the threat region constraints are obtained within the task area;

[0101] The threat window is obtained based on the distance between each threat region and the first planned path;

[0102] A secondary path planning is performed on the first planned path located within the threat window to obtain an optimized UAV planned path, wherein the route after the secondary path planning is spiral-shaped.

[0103] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0104] Acquire the task region and related information, wherein the task region is located within a strong denial space;

[0105] Based on the information related to the mission area, path planning is performed within the mission area under the constraints of the threat zone and the UAV's own attributes to obtain the first planned path.

[0106] Multiple threat regions satisfying the threat region constraints are obtained within the task area;

[0107] The threat window is obtained based on the distance between each threat region and the first planned path;

[0108] A secondary path planning is performed on the first planned path located within the threat window to obtain an optimized UAV planned path, wherein the route after the secondary path planning is spiral-shaped.

[0109] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, 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. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0110] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0111] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for optimizing the path of a UAV in a strongly denied space, characterized in that, The method includes: Acquire the task region and related information, wherein the task region is located within a strong denial space; Based on the information related to the mission area, path planning is performed within the mission area under the constraints of the threat zone and the UAV's own attributes to obtain the first planned path. Multiple threat regions satisfying the threat region constraints are obtained within the task area; A threat window is obtained based on the distance between each threat region and the first planned path. Specifically, the first planned path consists of multiple point coordinates. The threat distance between each point coordinate and the boundary of the adjacent threat region is calculated sequentially. The corresponding point coordinates are determined to be threat points or safe points based on a first preset threshold and the threat distance. A corresponding preliminary threat window center line segment is formed based on consecutive threat points. If the distance between two adjacent preliminary threat window center lines is less than a second preset value, the two preliminary threat window center line segments are merged to obtain a threat window center line segment. The threat window is generated based on the threat window center line segment. A secondary path planning is performed on the first planned path located within the threat window to obtain an optimized UAV planned path, wherein the route after the secondary path planning is spiral-shaped.

2. The UAV path optimization method according to claim 1, characterized in that, The threat zone constraints are derived from the effective range of the adversary's ground-based air defense radar and the counter-attack system.

3. The UAV path optimization method according to claim 1, characterized in that, Path planning is performed under the constraints of the threat zone and the inherent properties of the UAV, using any one of the following algorithms: shortest tangent method, genetic algorithm, RRT fast search random tree algorithm, or UAV intelligent avoidance decision algorithm based on deep reinforcement learning.

4. The UAV path optimization method according to claim 3, characterized in that, Multiple threat regions satisfying the threat region constraints are obtained within the task area, including: The task area is gridded based on the task area information; The attributes of each grid are determined based on the threat zone constraints to obtain multiple grids with threat attributes; Clustering algorithms are used to merge adjacent grids with threat attributes to obtain multiple threat regions.

5. The UAV path optimization method according to claim 4, characterized in that, The step of generating the threat window based on the center line segment of the threat window includes: For each threat window center segment, the width of the threat window is dynamically determined based on the minimum distance from each point on the center segment to the adjacent threat area; The threat windows are generated based on their center line segments and widths.

6. The UAV path optimization method according to any one of claims 1-5, characterized in that, The motion equation of the drone within the threat window is expressed as: ； ； ； In the above formula, the parameter that can be adjusted according to the maneuverability of the UAV is the flight speed. Horizontal spiral radius and vertical spiral radius .

7. A path optimization device for unmanned aerial vehicles (UAVs) in a strongly denied space, characterized in that, The device includes: The information acquisition module is used to acquire the task area and related information, wherein the task area is located within the strong denial space; The first path planning module is used to perform path planning within the task area based on the information related to the task area, under the constraints of the threat zone and the UAV's own attributes, to obtain the first planned path. A threat region acquisition module is used to acquire multiple threat regions within the task area that satisfy the threat region constraints. The threat window acquisition module is used to obtain a threat window based on the distance between each threat region and the first planned path. Specifically, the first planned path consists of multiple point coordinates. The threat distance between each point coordinate and the boundary of the adjacent threat region is calculated sequentially. The corresponding point coordinates are determined to be threat points or safe points based on a first preset threshold and the threat distance. A corresponding preliminary threat window center line segment is formed based on consecutive threat points. If the distance between two adjacent preliminary threat window center lines is less than a second preset value, the two preliminary threat window center line segments are merged to obtain a threat window center line segment. The threat window is generated based on the threat window center line segment. The secondary path planning module is used to perform secondary path planning on the first planned path located within the threat window to obtain an optimized UAV planned path, wherein the route after secondary path planning is spiral-shaped.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images