Multi-unmanned aerial vehicle reconnaissance cooperative path planning method, device and equipment in battlefield environment and storage medium

Abstract

The invention provides a multi-unmanned aerial vehicle reconnaissance cooperative path planning method, device and equipment in a battlefield environment and a storage medium, and the method comprises the steps: planning a flight path of each unmanned aerial vehicle according to the type of a sensor configured on each unmanned aerial vehicle, carrying out the recognition of the flight path to obtain a path segment in a radar threat region, and carrying out the recognition of the path segment in the radar threat region; an entry point and a departure point of each path are calculated, a constraint solving model is constructed, the maximum voyage constraint of each unmanned aerial vehicle is set by taking minimization of the path section as a target function, and an initial path is generated in combination with a greedy strategy; and finally, constructing an optimization model in which the entry points and the departure points are matched with the unmanned aerial vehicle base, taking minimization of distances from all the entry points and departure points to the corresponding base as a target, obtaining final path distribution after matching, and splicing the entry points, the target point sequence and the departure points of each path to form a complete flight path. The problem that when multiple sensor platforms are planned at the same time, the requirements of different investigation loads for task modes cannot be considered is solved.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle path planning, and particularly to a multi-unmanned aerial vehicle reconnaissance collaborative path planning method, device, equipment and storage medium in a battlefield environment. Background Art

[0002] With the continuous decline in the cost of unmanned aerial vehicle platforms and the continuous improvement of sensor performance, the collaborative reconnaissance of multiple unmanned aerial vehicles has become an important means to obtain large-scale and high-timeliness intelligence. Currently, the path planning of multi-unmanned aerial vehicle reconnaissance mainly relies on the classical traveling salesman problem (TSP) and distributed task allocation methods, and generates flight routes for each unmanned aerial vehicle through exhaustive or heuristic algorithms to cover all target points. However, these methods have the following deficiencies in actual military or security reconnaissance scenarios: Existing technologies often only use the total flight distance or total time consumption as the optimization goal, ignoring the risks and costs of passing through enemy radar threat areas during the reconnaissance process. Although some studies introduce a weight model to distinguish between dangerous areas and safe areas, when simultaneously planning for multiple sensor platforms, they cannot take into account the requirements of different reconnaissance payloads for mission modes, and it is also difficult to preferentially reduce the stay length in the threat area on the premise of ensuring full coverage. Secondly, for unmanned aerial vehicles equipped with different sensors, whether it is a lidar or a high-resolution camera that needs to "fly over each point" to complete high-precision shooting, or an electronic monitoring payload with radius coverage capabilities, existing methods generally use unified modeling and directly execute TSP or clustering + TSP examples on the original target point set. When the number of nodes is large, the combination explosion occurs, and the calculation time is difficult to meet the requirements of real-time deployment.

[0003] In view of this, this application is proposed. Summary of the Invention

[0004] The present invention discloses a multi-unmanned aerial vehicle reconnaissance collaborative path planning method, device, equipment and storage medium in a battlefield environment, aiming to solve the problem that when simultaneously planning for multiple sensor platforms, the requirements of different reconnaissance payloads for mission modes cannot be taken into account.

[0005] The first embodiment of the present invention provides a multi-unmanned aerial vehicle reconnaissance collaborative path planning method in a battlefield environment, including: According to the sensor type configured on each unmanned aerial vehicle, plan the flight path of each unmanned aerial vehicle, where the flight path includes a first path corresponding to a first sensor type and a second path corresponding to a second sensor type, and the second path includes performing clustering processing on target points to generate virtual target points; Identify the flight path to obtain the path segments within the radar threat area, calculate the entry point and departure point of each path, construct a constraint solving model, use the minimization of the path segments as the objective function, set the maximum range constraint of each unmanned aerial vehicle, and generate an initial path in combination with a greedy strategy; Construct an optimization model where the entry and exit points match the UAV base. With the goal of minimizing the distances from all entry and exit points to their corresponding bases, obtain the final path assignment after matching, and splice the entry points, target point sequences, and exit points of each path to form a complete flight route.

[0006] Preferably, it further includes: for the flight route after splicing, if the first target point is a radar station and the flight distance from the base to the radar area of this radar station is equal to the radar radius, delete the corresponding entry and exit points, and directly connect the radar station to the base.

[0007] Preferably, the first path passes through all the first - type target points in sequence and starts from the base and finally returns to the base.

[0008] Preferably, the second path is as follows: perform clustering processing on the set of target points carrying the second sensor type, cover the real target points with circles of radius N kilometers, obtain all the centers of the clustering circles as virtual target points, and use the set of virtual target points to plan and generate the second path, where all real target points are covered by at least one clustering circle.

[0009] Preferably, it further includes: when planning the paths of the UAVs from the base to the entry and exit points, construct an objective function such that the path weight between intersection pairs on the same route is 0, and the weight between intersection pairs of different paths is infinite.

[0010] Preferably, when the objective function is to minimize the path segment, assign a weight of 1 to the path within the radar area and a weight of 0 outside the area.

[0011] The second embodiment of the present invention provides a multi - UAV reconnaissance cooperation path planning device in a battlefield environment, including: A flight path planning unit for planning the flight paths of each UAV according to the sensor types configured on each UAV, where the flight paths include a first path corresponding to the first sensor type and a second path corresponding to the second sensor type, and the second path includes performing clustering processing on target points to generate virtual target points; A threat area recognition unit for identifying the flight paths to obtain the path segments within the radar threat area, calculating the entry and exit points of each path, constructing a constraint - solving model, with the goal of minimizing the path segment, setting the maximum flight range constraint of each UAV, and generating an initial path in combination with the greedy strategy; A splicing unit for constructing an optimization model where the entry and exit points match the UAV base, with the goal of minimizing the distances from all entry and exit points to their corresponding bases, obtaining the final path assignment after matching, and splicing the entry points, target point sequences, and exit points of each path to form a complete flight route.

[0012] The third embodiment of the present invention provides a multi-UAV reconnaissance collaborative path planning device in a battlefield environment, including a memory and a processor. A computer program is stored in the memory and can be executed by the processor to implement a multi-UAV reconnaissance collaborative path planning method in a battlefield environment as described in any one of the above.

[0013] The fourth embodiment of the present invention provides a computer-readable storage medium, characterized in that it stores a computer program that can be executed by the processor of the device where the computer-readable storage medium is located to implement a multi-UAV reconnaissance collaborative path planning method in a battlefield environment as described in any one of the above.

[0014] Based on the multi-UAV reconnaissance collaborative path planning method, device, equipment and storage medium provided by the present invention, first, according to the types of sensors configured on each UAV, plan the flight path of each UAV, identify the flight path to obtain the path segments within the radar threat area, calculate the entry point and departure point of each path, and then construct a constraint solving model with minimizing the path segments as the objective function, set the maximum flight range constraint of each UAV, and generate an initial path in combination with the greedy strategy; finally, construct an optimization model that matches the entry point and departure point with the UAV base, with minimizing the distance from all entry points and departure points to the corresponding base as the objective, and obtain the final path allocation after matching, and splice the entry point, target point sequence and departure point of each path to form a complete flight route. It solves the problem that when multiple sensor platforms are planned simultaneously, the requirements of different reconnaissance payloads for mission modes cannot be taken into account. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a schematic flowchart of a multi-UAV reconnaissance collaborative path planning method in a battlefield environment provided by the first embodiment of the present invention; Figure 2 is a route map of the first type of sensor payload UAV provided by the present invention within the radar area; Figure 3 is an enlarged view of the area after clustering processing of the second type of sensor payload UAV provided by the present invention; Figure 4 is an enlarged view of a partial area after clustering processing of the second type of sensor payload UAV provided by the present invention; Figure 5 is a route map of the second type of sensor payload UAV provided by the present invention within the radar area; Figure 6 is the overall flight route map of the first type of sensor payload UAV provided by the present invention; Figure 7It is the overall flight route map of the second type of sensor payload UAV provided by the present invention; Figure 8 It is the module schematic diagram of a multi-UAV reconnaissance cooperation path planning device in a battlefield environment provided by the second embodiment of the present invention; Detailed implementation manners Next, the technical solutions in the embodiments of the present invention will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0016] For a better understanding of the technical solutions of the present invention, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0017] It should be clear that the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0018] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms of "a", "the" and "said" used in the embodiments of the present invention and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0019] It should be understood that the term " / and" used herein is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0020] Depending on the context, the word "if" as used herein can be interpreted as "when" or "while" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if determined" or "if detecting (stated condition or event)" can be interpreted as "when determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)".

[0021] The "first / second" mentioned in the embodiments is only used to distinguish similar objects and does not represent a specific sorting of the objects. It can be understood that the "first / second" can be interchanged in a specific order or sequence when permitted. It should be understood that the objects distinguished by the "first / second" can be interchanged under appropriate circumstances so that the embodiments described herein can be implemented in an order other than those illustrated or described herein.

[0022] The following will make a detailed description of specific embodiments of the present invention with reference to the accompanying drawings.

[0023] The present invention discloses a multi-UAV reconnaissance collaborative path planning method, device, equipment and storage medium in a battlefield environment, aiming to solve the problem that when multiple sensor platforms are planned simultaneously, the requirements of different reconnaissance payloads for mission modes cannot be taken into account.

[0024] Please refer to Figure 1 , the first embodiment of the present invention provides a multi-UAV reconnaissance collaborative path planning method in a battlefield environment, which can be executed by a multi-UAV reconnaissance collaborative path planning device (hereinafter referred to as the planning device) in a battlefield environment. Specifically, it is executed by one or more processors in the planning device to at least achieve the following steps: S101. According to the sensor types configured on each UAV, plan the flight path of each UAV. Among them, the flight path includes a first path corresponding to the first sensor type and a second path corresponding to the second sensor type, and the second path includes performing clustering processing on target points to generate virtual target points; In this embodiment, the planning device can be a terminal with data processing capabilities such as a configured workstation or a server, which can establish a communication connection with each UAV. The corresponding operating system and application software can be installed in the planning device, and the functions required in this embodiment can be realized through the combination of the operating system and the application software.

[0025] The planning device first reads the sensor types configured on each UAV and plans the corresponding flight path accordingly. For the UAV equipped with the first sensor type, based on the point-by-point shooting task required by this type, the path planning module directly marks all the first-type target points on the map and connects them to generate a closed-loop flight path that starts from the base, flies over each target point in turn, and then returns to the base; this flight path ensures that each target point is accurately covered and the total flight distance does not exceed the maximum flight range of the UAV.

[0026] For the UAV equipped with the second type of sensor, first consider all real target points as data points, and use a circle with a radius of N kilometers to perform coverage clustering on them. The device selects the center of the circle as the virtual target point within each coverage circle, ensuring that each real target point is covered by at least one circle. Subsequently, the path planning module connects these virtual target points in sequence to generate a closed-loop flight path that also starts from the base, flies over all virtual target points one by one, and then returns to the base. By separately planning these two paths with different attributes, it not only meets the high requirements of the first sensor for per-point accuracy but also makes full use of the coverage advantage of the second sensor, significantly reducing the repeated flight and stay time in the target area.

[0027] S102. Identify the flight path to obtain the path segments within the radar threat area, calculate the entry point and exit point of each path, construct a constraint solving model, use the minimization of the path segment as the objective function, set the maximum flight range constraint for each UAV, and generate an initial path in combination with the greedy strategy. In this embodiment, for the UAV equipped with a high-precision imaging sensor (i.e., the first sensor type), first carry out the path planning of "minimizing radar area sensitivity". With the help of the OR-Tools beam solver, convert the "flight distance within the radar threat area" into an optimization objective: for any path passing through the radar detection range, the corresponding distance segment is assigned a weight of 1, and the weight is 0 outside this range. Under this objective function and the constraint of "the total flight mileage shall not exceed the maximum endurance", the solver quickly generates an initial flight path in combination with the greedy strategy.

[0028] On the preliminary flight path, further refine the key points for entering and leaving the radar area: calculate the intersection points of the base to the first reconnaissance point and the return of the last reconnaissance point with the radar boundary. Although the shortest straight-line path naturally falls on the edge of the radar detection, directly returning often exceeds the endurance limit due to being too long. To balance safety and feasibility, construct a "pair of intersection points" mechanism. While ensuring the shortest entry / exit from the radar area, select the pair of boundary tangent points Pn1 (entry point) and Pn2 (exit point) that best meet the endurance conditions as the new nodes for path planning. Finally, organically connect all the radar area intersection points with the original target points within the area, completing a closed-loop flight path that can effectively conduct reconnaissance in high-risk areas and save the endurance consumption to the greatest extent, as Figure 2 shown (the orange points are the UAV bases, there are 2 UAVs at each UAV base, the black points and red points are all target points, among which there is a radar at the red points, the light red circles represent the areas that can be detected by the radar, the purple lines represent the routes of UAV 1 with payload S1 within the radar area, the purple points represent the positions where UAV 1 with payload S1 enters and leaves the radar, the green lines represent the routes of UAV 2 with payload S1 within the radar area, and the green points represent the positions where UAV 2 with payload S1 enters and leaves the radar).

[0029] For the UAV equipped with the second type of sensor, its sensing range has significant coverage characteristics. It can simultaneously complete the reconnaissance of multiple target points within a radius of 7.5 kilometers below the aircraft. Combining this feature, the target points can be classified using the clustering algorithm. By drawing circles with a radius of 7.5 kilometers, the number of circles should be minimized and all target points need to be covered. Through the clustering algorithm, multiple circles and the center coordinates of each circle can be calculated. The center coordinates are virtual target points. The UAV only needs to fly above these center coordinate points of the circles to cover all the reconnaissance target points. The center is the virtual target point to be reconnoitered. As follows Figure 3 shown (both black points and red points are target points, among which the red points have radars, the blue points are virtual target points after clustering processing, and the light blue circular area represents the reconnaissance coverage range of the UAV carrying the S2 sensor at the position of the virtual target point): Among them, the blue points are the centers (virtual target points), the light blue is the reconnaissance range of 7.5 kilometers, and the purple are the target points. From Figure 4 (both black points and red points are target points, among which the red points have radars, the blue points are virtual target points after clustering processing, and the light blue circular area represents the reconnaissance coverage range of the UAV carrying the S2 sensor at the position of the virtual target point), it can be clearly seen that after clustering processing, the number of points to fly to is greatly reduced. Some target groups only need to pass through 5 points, and even some target groups only need to pass through one point to cover all the target points in that target group; Plan the path of the reconnaissance virtual target points. Use the set of center coordinate points plus the set of coordinate points of the UAV base, and adopt the constraint solver in the OR-Tools library to minimize the coverage area within the radar area as the optimization goal. To achieve this goal, model the solver accordingly: construct the objective function, assign a weight of 1 when the path is within the radar area and a weight of 0 outside the radar area, and solve for the minimum value of the objective function. At the same time, set the constraint conditions to ensure that the total flight range of the UAV does not exceed its maximum endurance. In the initial solution stage, select the constraint programming solver provided by OR-Tools and generate the path based on the greedy strategy. Calculate the path of the UAV with the second payload and the path within the radar area; link the intersection points and the target points within the radar area. At this time, the path planning within the radar area has been completed. At this time, the planned path is as Figure 5 shown (the orange points are UAV bases, and there are 2 UAVs at each UAV base. Both black points and red points are target points, among which the red points have radars. The light red circles represent the areas that can be detected by the radars. The blue lines represent the routes of the UAVs with payload S2 within the radar area, and the blue points represent the positions where the UAVs with payload S2 enter and leave the radar); S103. Construct an optimization model that matches the entry points and exit points with the UAV bases. With the goal of minimizing the distances from all entry points and exit points to the corresponding bases, obtain the final path allocation after matching, and splice the entry points, target point sequences, and exit points of each path to form a complete flight route.

[0030] In this embodiment, the constraint solver in the OR-Tools library is used with the goal of minimizing the shortest distance from the intersection pairs to the bases. To achieve this goal, the corresponding modeling is performed on the solver: construct the objective function, and set the following weight strategy in the model construction: if the two ends of the path are the intersection pairs on the same route, assign a path weight of 0; if they belong to different paths, assign an infinite weight. This can effectively ensure that each pair of intersections is assigned to the same flight path. Select the constraint programming solver provided by OR-Tools and generate paths based on the greedy strategy.

[0031] Please combine Figure 6 and Figure 7 , (the purple line represents the complete route of UAV 1 carrying payload S1, the purple dots represent the positions where UAV 1 carrying payload S1 enters and exits the radar, the green line represents the complete route of UAV 2 carrying payload S1, the green dots represent the positions where UAV 2 carrying payload S1 enters and exits the radar, the blue line represents the complete route of the UAV carrying payload S2, and the blue dots represent the positions where the UAV carrying payload S2 enters and exits the radar), splice the calculated paths from the UAV bases to the target points and the UAVs carrying the first type of sensor and the UAVs carrying the second type of sensor, that is, complete the planning of the complete UAV path, and achieve the flight path plan with the shortest flight time of the UAV in the enemy radar detection area under the constraint conditions such as endurance.

[0032] In a possible implementation manner of the present invention, it may further include: for the flight route after splicing, if the first target point is a radar station and the flight distance from the base to the radar area of the radar station is equal to the radar radius, delete the corresponding entry point and exit point, and directly connect the radar station to the base.

[0033] It should be noted that after the path planning is completed, the flight path is further optimized, especially for the special case where the starting point is the radar station, and the path is trimmed. If the first target point of a certain flight route is exactly a radar station, and the flight length of the path directly returning from this radar station to the UAV base in the radar area is exactly equal to the radar detection radius, that is, flying exactly along the edge without generating additional exposure distance, then it can be considered that this section of the path has achieved the optimal radar penetration strategy. In this case, continuing to retain the processing of the intersection points of the path and the radar boundary will instead introduce redundant nodes, increase the total distance, and cause additional scheduling complexity. Therefore, a path trimming mechanism based on "first target determination" is proposed: if the above boundary equal-length condition is met, the intersection points entering and leaving the radar area are directly deleted, and the radar station and the base are directly connected instead, which will neither increase the exposure distance in the radar area nor effectively reduce the total flight route length and improve the overall execution efficiency.

[0034] In a certain typical test scenario, the above method is used for solving, and finally the following efficient task allocation and path planning results are obtained: Among them, a total of 2 UAVs carrying S1 payloads are required, and only 1 UAV carrying S2 payload is needed to complete the global coverage task. The key indicators of each path are as follows: UAV 1 of S1: The flight distance in the radar area is 845.25 km, and the total path length is 1186.47 km; UAV 2 of S1: The flight distance in the radar area is 449.24 km, and the total path length is 1040.24 km; UAV of S2: The flight distance in the radar area is 1143.48 km, and the total path length is 1733.59 km.

[0035] While the above three paths meet all the task coverage requirements, their total flight distances are all much lower than the maximum flight range limit (2000 km) set for the UAVs, fully meeting the task constraint conditions. More importantly, this solution can be stably output by the algorithm in a short time through the multi-level path construction and risk minimization strategy proposed in this embodiment.

[0036] Please refer to Figure 8 , the second embodiment of the present invention provides a multi-UAV reconnaissance collaborative path planning device in a battlefield environment, including: A flight path planning unit 201, configured to plan the flight path of each UAV according to the sensor type configured on each UAV, where the flight path includes a first path corresponding to a first sensor type and a second path corresponding to a second sensor type, and the second path includes performing clustering processing on target points to generate virtual target points; The threat area recognition unit 202 is configured to identify the flight path to obtain the path segments within the radar threat area, calculate the entry points and departure points of each path, construct a constraint solving model, use the minimization of the path segments as the objective function, set the maximum flight range constraint for each UAV, and generate an initial path in combination with the greedy strategy; The splicing unit 203 is configured to construct an optimization model that matches the entry points and departure points with the UAV bases, use the minimization of the distances from all entry points and departure points to the corresponding bases as the objective, obtain the final path allocation after matching, and splice the entry points, target point sequences, and departure points of each path to form a complete flight route.

[0037] The third embodiment of the present invention provides a multi-UAV reconnaissance collaborative path planning device in a battlefield environment, including a memory and a processor. A computer program is stored in the memory and can be executed by the processor to implement a multi-UAV reconnaissance collaborative path planning method as described in any one of the above.

[0038] The fourth embodiment of the present invention provides a computer-readable storage medium, characterized in that it stores a computer program that can be executed by the processor of the device where the computer-readable storage medium is located to implement a multi-UAV reconnaissance collaborative path planning method as described in any one of the above.

[0039] Based on the multi-UAV reconnaissance collaborative path planning method, device, equipment, and storage medium provided by the present invention, first, according to the types of sensors configured on each UAV, plan the flight path of each UAV, identify the flight path to obtain the path segments within the radar threat area, calculate the entry points and departure points of each path. Then, construct a constraint solving model, use the minimization of the path segments as the objective function, set the maximum flight range constraint for each UAV, and generate an initial path in combination with the greedy strategy. Finally, construct an optimization model that matches the entry points and departure points with the UAV bases, use the minimization of the distances from all entry points and departure points to the corresponding bases as the objective, obtain the final path allocation after matching, and splice the entry points, target point sequences, and departure points of each path to form a complete flight route. This solves the problem that when multiple sensor platforms are planned simultaneously, the requirements of different reconnaissance payloads for mission modes cannot be taken into account.

[0040] Exemplarily, the computer program described in the third and fourth embodiments of the present invention can be divided into one or more modules. The one or more modules are stored in the memory and executed by the processor to complete the present invention. The one or more modules can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program in the device for realizing multi-UAV reconnaissance collaborative path planning in a battlefield environment. For example, the device described in the second embodiment of the present invention.

[0041] The so-called processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the method for multi-UAV reconnaissance collaborative path planning in a battlefield environment, and uses various interfaces and circuits to connect the whole to realize various parts of the method for multi-UAV reconnaissance collaborative path planning in a battlefield environment.

[0042] The memory can be used to store the computer program and / or module. By running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory, the processor realizes various functions of the method for multi-UAV reconnaissance collaborative path planning in a battlefield environment. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, a text conversion function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, text message data, etc.), etc. In addition, the memory can include high-speed random access memory, and can also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0043] Among them, if the implemented module is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice within the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0044] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the attached drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that they have a communication connection, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement it without creative work.

[0045] As described above, the above are only the preferred specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A multi-UAV reconnaissance collaborative path planning method in a battlefield environment, characterized in that Including: Plan the flight path of each UAV according to the sensor type configured on each UAV, where the flight path includes a first path corresponding to a first sensor type and a second path corresponding to a second sensor type, and the second path includes performing clustering processing on target points to generate virtual target points; Identify the flight path to obtain path segments within the radar threat area, calculate the entry point and exit point of each path, construct a constraint solving model, use the minimization of the path segment as the objective function, set the maximum flight range constraint of each UAV, and generate an initial path in combination with a greedy strategy; Construct an optimization model that matches the entry point and exit point with the UAV base, use the minimization of the distance from all entry points and exit points to the corresponding base as the objective, obtain the final path allocation after matching, and splice the entry point, target point sequence, and exit point of each path to form a complete flight route.

2. The multi-UAV reconnaissance collaborative path planning method in a battlefield environment according to claim 1, wherein, It also includes: for the flight route after splicing, if the first target point is a radar station and the flight distance in the radar area from the base to the radar station is equal to the radar radius, delete the corresponding entry point and exit point, and directly connect the radar station to the base.

3. The multi-UAV reconnaissance collaborative path planning method in a battlefield environment according to claim 1, wherein The first path sequentially passes through all first-type target points and finally returns to the base starting from the base.

4. A multi-UAV reconnaissance collaborative path planning method in a battlefield environment according to claim 1, characterized in that, The second path is as follows: perform clustering processing on the set of target points equipped with the second sensor type, cover the real target points with a circle of radius N kilometers, obtain all the centers of the clustering circles as virtual target points, and use the set of virtual target points to plan and generate the second path, where all real target points are covered by at least one clustering circle.

5. The multi-UAV reconnaissance collaborative path planning method in a battlefield environment according to claim 1, wherein, It also includes: When planning the path of the UAV from the base to the entry point and exit point, construct an objective function such that the path weight between intersection pairs on the same path is 0, and the weight between intersection pairs of different paths is infinite.

6. The multi-UAV reconnaissance cooperative path planning method in a battlefield environment according to claim 1, characterized in that, When using the minimization of the path segment as the objective function, assign a weight of 1 to the path within the radar area and a weight of 0 to the area outside.

7. A multi-UAV reconnaissance collaborative path planning device in a battlefield environment, characterized in that, Including: A flight path planning unit for planning the flight path of each UAV according to the sensor type configured on each UAV, where the flight path includes a first path corresponding to a first sensor type and a second path corresponding to a second sensor type, and the second path includes performing clustering processing on target points to generate virtual target points; A threat area identification unit for identifying the flight path to obtain path segments within the radar threat area, calculating the entry point and exit point of each path, constructing a constraint solving model, using the minimization of the path segment as the objective function, setting the maximum flight range constraint of each UAV, and generating an initial path in combination with a greedy strategy; A splicing unit for constructing an optimization model that matches the entry point and exit point with the UAV base, using the minimization of the distance from all entry points and exit points to the corresponding base as the objective, obtaining the final path allocation after matching, and splicing the entry point, target point sequence, and exit point of each path to form a complete flight route.

8. A multi-UAV reconnaissance collaborative path planning device in a battlefield environment, characterized in that, It includes a memory and a processor. A computer program is stored in the memory and can be executed by the processor to implement a multi-UAV reconnaissance collaborative path planning method in a battlefield environment as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, A computer program is stored and can be executed by the processor of the device where the computer-readable storage medium is located to implement a multi-UAV reconnaissance collaborative path planning method in a battlefield environment as described in any one of claims 1 to 6.

Images