A Task Allocation and Path Planning Method and System for Urban Combat

Abstract

The present invention discloses a task assignment and path planning method and system for urban confrontation. The task assignment and path planning method for urban confrontation in the present invention includes obtaining real-time comprehensive situation information of an urban confrontation scenario containing the positions of various units of both sides in the confrontation; obtaining a shapefile image of the current confrontation area from GIS software; analyzing the shapefile image and extracting path key points in the urban road network; calculating passable paths between various units of both sides in the confrontation according to the positions of various units of both sides; establishing a maneuver efficiency constraint model, a maneuver threat constraint model, and a formation firepower constraint model; constructing an objective function; and solving the task assignment and path planning scheme. The purpose of the present invention is to achieve task assignment and path planning for urban confrontation and improve the applicability and accuracy of task assignment and path planning in different urban confrontation scenarios.

Description

Technical Field

[0001] The present invention belongs to the technical field of task allocation and path planning, and particularly relates to a task allocation and path planning method and system for urban confrontation. Background Art

[0002] In urban confrontation, reasonable task allocation and path planning for our units according to the confrontation objectives, confrontation plans, and real-time comprehensive situation of the confrontation are of great significance for reducing losses of personnel and weapons and equipment and improving confrontation effectiveness. Existing task allocation and path planning methods rarely consider the complex characteristics of urban confrontation (for example, key situation information such as road network structures and building distributions in different confrontation scenarios often have significant differences). Therefore, it is difficult for them to efficiently extract path key points and calculate passable paths in different urban confrontation scenarios.

[0003] In addition, when analyzing and predicting the maneuvering strategies and formation strategies of multiple units on our side, existing task allocation and path planning methods mostly lack comprehensive consideration of key confrontation elements such as unit types, unit basic attributes, day and night environments, and path conditions, and do not take into account the impacts of maneuvering efficiency, maneuvering threats, and formation firepower on task allocation and path planning schemes, resulting in insufficient practicality of the obtained schemes and difficulty in adapting to real urban confrontation tasks. Summary of the Invention

[0004] The technical problem to be solved by the present invention: Aiming at the above problems of the prior art, a task allocation and path planning method and system for urban confrontation are provided. The present invention aims to achieve task allocation and path planning for urban confrontation and improve the applicability and accuracy of task allocation and path planning in different urban confrontation scenarios.

[0005] To solve the above technical problems, the technical solution adopted by the present invention is as follows:

[0006] A task allocation and path planning method for urban confrontation, comprising the following steps:

[0007] S1, obtaining real-time comprehensive situation information of an urban confrontation scenario including the positions of each unit of both sides in the confrontation;

[0008] S2, obtaining a shapefile image of the current confrontation area from GIS software;

[0009] S3, analyzing the shapefile image and extracting path key points in the urban road network;

[0010] S4, calculating passable paths between each unit of both sides in the confrontation according to the positions of each unit of both sides in the confrontation;

[0011] S5. Calculate all the key confrontation elements regarding the passable paths by combining the real-time comprehensive situation information of the urban confrontation scenario and the passable paths between each unit of the two confronting sides, and establish a maneuver efficiency constraint model, a maneuver threat constraint model, and a formation firepower constraint model. The key confrontation elements include unit type, unit basic attributes, day and night environment, and path conditions;

[0012] S6. Construct an objective function based on the maneuver efficiency constraint model, the maneuver threat constraint model, and the formation firepower constraint model;

[0013] S7. Solve the task assignment and path planning scheme for the constructed objective function.

[0014] Optionally, step S3 includes:

[0015] S3.1. Binarize the shapefile image to obtain a binary image;

[0016] S3.2. Extract the polygon contour lines in the binary image to obtain the road network and building information of the city;

[0017] S3.3. Simplify the polygon contour lines and extract the vertices of the polygon contour lines as the path key points in the urban road network.

[0018] Optionally, step S4 includes:

[0019] S4.1. Use GPU or CPU parallel computing to analyze the connectivity between path key points: For any two path key points, calculate the difference in the ordinate and the difference in the abscissa between the two path key points, and take the maximum value of the two as the number of sampling points ; Uniformly sample points on the line segment connecting the two path key points, and perform an integer operation on the coordinates of each point. Finally, determine whether there are black points among the sampled points. If there are black points, it is determined that the two path key points are not connected; otherwise, it is determined that the two path key points are connected;

[0020] S4.2. Judge whether the position coordinates of each unit of the two confronting sides are inside the building according to the pixel values of the positions of each unit of the two confronting sides in the shapefile image. If the pixel value of the position coordinates in the shapefile image is black, it is determined that the unit is inside the building; otherwise, it means that the unit is not inside the building;

[0021] S4.3. For the units inside the building, consider the position coordinate points of the unit and the path key points corresponding to the building as connected; for the units not inside the building, judge the connectivity between the position coordinate points of the unit and each path key point one by one; Finally, obtain the connectivity between the units of the two confronting sides and all path key points;

[0022] S4.4. Calculate the passable paths between the units of both sides of the confrontation according to the connectivity between the confrontation units and all path key points using the specified path planning algorithm.

[0023] Optionally, the functional expression of the maneuver efficiency constraint model established in step S5 is:

[0024] ,

[0025] ,

[0026] where, is the maneuver time for our formation to move towards the th opponent unit; the Boolean variable indicates whether our th unit decides to attack the th opponent unit from the th passable path. If so, , otherwise , where , represents the number of our units, , represents the number of opponent units, , represents the th unit of ours to reach the total number of passable paths of the th opponent unit; represents the th unit of ours from the th passable path to attack the th opponent unit when the time required; represents the number of support units among all our units attacking the th opponent unit. The more support units, the higher the maneuver efficiency; represents the gain of the support unit to the maneuver efficiency;

[0027] The functional expression of the maneuver threat constraint model established in step S5 is:

[0028] ,

[0029] In the above formula, is the maneuver threat for our unit to move towards the th opponent unit, is the importance degree value of our th unit; represents that our Whether there is a feasible path when there are units. If there is a feasible path, ; Indicates the visibility distance of the th unit of our side attacking the th unit of the opponent when attacking from the th passable path; Indicates the comprehensive danger level of the path when the th unit of our side attacks the th unit of the opponent from the th passable path; Is the defense ability value of the th unit of our side;

[0030] The functional expression of the grouped firepower constraint model established in step S5 is:

[0031] ,

[0032] ,

[0033] Among them, Indicates the minimum ratio of the grouped firepower of our side to the firepower of the th unit of the opponent; Indicates the maximum ratio of the grouped firepower of our side to the firepower of the th unit of the opponent, Is the offensive firepower value of the th unit of the opponent; The boolean variable Indicates whether the th unit of our side decides to attack the th unit of the opponent from the th passable path. If so, , otherwise ; Is the offensive firepower value of the th unit of our side; Is the remaining firepower value of all our grouped units, Indicates the increase in the offensive firepower of our side's units by the logistics unit, Indicates the number of logistics units among all our units that attack the th unit of the opponent, Indicates the increase in the offensive firepower of our side's units by the command unit. The boolean variable Indicates whether the unit of our side attacking the th unit of the opponent can communicate with the command unit. If it can, , otherwise ; Indicates among all our units that attack the The number of command units for one unit is the offensive firepower value of the th unit of the opponent;

[0034] The functional expression of the objective function constructed in step S6 is:

[0035] ,

[0036] where respectively represent the weights of maneuver efficiency, remaining firepower, and maneuver threat.

[0037] Optionally, the comprehensive danger degree of the path when the th unit of our side attacks the th unit of the opponent from the th passable path is calculated by the following functional expression:

[0038] ,

[0039] where represents the comprehensive danger degree of the path when the th unit of our side attacks the th unit of the opponent from the th passable path; ~ respectively represent the weights of different elements, represents the bias, represents the number of traffic intersections or crossroads on the path when the th unit of our side attacks the th unit of the opponent from the th passable path; represents the number of bridges on the path when the th unit of our side attacks the th unit of the opponent from the th passable path; represents the number of tunnels on the path when the th unit of our side attacks the th unit of the opponent from the th passable path; represents the ratio of the length of the route covered by the opponent's firepower to the total route length when the th unit of our side attacks the th unit of the opponent from the th passable path.

[0040] Optionally, when the th unit of our side attacks the th unit of the opponent from the The calculation function expression for the time required for

[0041] ,

[0042] where, represents the time required for our th unit to attack the opponent's th unit from the th passable path; represents the distance of the path when our th unit attacks the opponent's th unit from the th passable path; represents whether there is a feasible path when our th unit attacks the opponent's th unit. If there is a feasible path, then , otherwise, ; represents the congestion level of the path when our th unit attacks the opponent's th unit from the th passable path; is the speed of our th unit. When the confrontation activity occurs during the day, the speed of our th unit is , where represents the maximum maneuvering speed of our th unit during the day; when the confrontation activity occurs at night, the speed of our th unit is , where represents the maximum maneuvering speed of our th unit at night.

[0043] Optionally, in step S7, the solution to the task assignment and path planning scheme for the constructed objective function is to use an improved multi-gene adaptive genetic-simulated annealing algorithm to solve the task assignment and path planning scheme for the constructed objective function, including:

[0044] S7.1, perform multi-gene coding on the problem of the task assignment and path planning scheme using a multi-layer multi-gene coding strategy. The multi-layer multi-gene coding strategy includes a task layer, a unit layer, and an action route layer. Among them, the task layer is mainly composed of task numbers and uses an integer coding strategy; the unit layer is composed of the numbers of our units, and a vacant gene mechanism is introduced to randomly set some genes to "-1" to indicate that the task is not assigned to any unit; the action route layer uses an integer coding strategy;

[0045] S7.2, initialize and generate an initial population based on the constraint conditions in the maneuver efficiency constraint model, maneuver threat constraint model, and formation firepower constraint model;

[0046] S7.3, calculate the fitness value for each individual in the current population using the objective function:

[0047] S7.4, sort the individuals in the current population according to the fitness value, select the individuals in the top specified proportion to form an elite population, and the remaining individuals are the ordinary population;

[0048] S7.5, perform adaptive simulated annealing on the elite population to generate new individuals. The adaptive simulated annealing to generate new individuals means randomly selecting in the neighborhood of the current individual and accepting the new individual according to a specified probability; select individuals in the ordinary population to cross with individuals in the elite population or perform self-crossing according to the adaptive probability where N iter represents the current iteration number, N epoch represents the total number of iterations; perform mutation operations on the ordinary population and the new individuals obtained by crossing with individuals in the elite population or performing self-crossing according to the adaptive mutation probability When performing the mutation operation, the number of mutation points is random, so that different individuals in the same population have different mutation points; only the unit layer and the action route layer participate in the mutation; select a specified number of feasible offspring from the current population and the new individuals as the new current population;

[0049] S7.6, determine whether the iteration number reaches the preset threshold. If it has not reached the preset threshold, jump to step S7.4 to continue the iteration; otherwise, calculate the fitness value for the new individuals in the new current population using the objective function, and screen out the individual with the best fitness value as the finally obtained optimal task allocation and path planning scheme.

[0050] In addition, the present invention also provides a task allocation and path planning system for urban confrontation, including a microprocessor and a memory connected to each other, and the microprocessor is programmed or configured to execute the task allocation and path planning method for urban confrontation.

[0051] In addition, the present invention also provides a computer-readable storage medium, in which a computer program or instruction is stored, and the computer program or instruction is programmed or configured to execute the task allocation and path planning method for urban confrontation through a processor.

[0052] In addition, the present invention also provides a computer program product, including a computer program or instruction, which is programmed or configured to execute the task allocation and path planning method for urban confrontation through a processor.

[0053] Compared with the prior art, the present invention mainly has the following advantages: The task allocation and path planning method for urban confrontation of the present invention extracts the road network distribution, building information, and path key points in the urban confrontation scenario to obtain multiple passable paths between each unit of both sides of the confrontation. On this basis, the method comprehensively considers key confrontation elements such as unit type, unit basic attributes, day and night environment, and path conditions, constructs a maneuver efficiency constraint model, a maneuver threat constraint model, and a formation firepower constraint model, and uses an improved multi-gene adaptive genetic-simulated annealing algorithm to solve a reasonable task allocation and path planning scheme. First, the present invention realizes a general mechanism for extracting urban road network features and path key points, which can be applied to different urban confrontation scenarios. Secondly, in the process of generating the task allocation and path planning scheme, the present invention uniformly optimizes the scheme from three aspects: maneuver efficiency, maneuver threat, and formation firepower through the maneuver efficiency constraint model, the maneuver threat constraint model, and the formation firepower constraint model. The present invention can extract path key points from different confrontation areas and obtain multiple passable paths between any two points, and can efficiently generate a task allocation and path planning scheme based on the real-time confrontation situation information, so as to obtain the maneuver strategy and formation strategy of our units, thereby realizing task allocation and path planning for urban confrontation and improving the applicability and accuracy of task allocation and path planning in different urban confrontation scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a schematic diagram of the basic process of the method in the embodiment of the present invention.

[0055] Figure 2 It is a schematic diagram of the connectivity judgment principle between path key points in the embodiment of the present invention.

[0056] Figure 3 It is a schematic diagram of the principle of parallel processing in the embodiment of the present invention.

[0057] Figure 4 It is a schematic diagram of the flow of the improved multi-gene adaptive genetic-simulated annealing algorithm in the embodiment of the present invention.

[0058] Figure 5 It is a schematic diagram of the multi-layer multi-gene coding method adopted in the embodiment of the present invention.

[0059] Figure 6 It is the original Shapefile image of City 1 and the result of image binarization in the embodiment of the present invention.

[0060] Figure 7 It is the result of extracting the image polygon contour line of City One in the embodiment of the present invention.

[0061] Figure 8 It is the result of extracting the path key points of City One in the embodiment of the present invention.

[0062] Figure 9 It is the result of searching for the passable path between any two points in City One in the embodiment of the present invention.

[0063] Figure 10 It is the task allocation and path planning result of City One in the embodiment of the present invention when the weight of the objective function is at a certain value.

[0064] Figure 11 It is the task allocation and path planning result of City One in the embodiment of the present invention when the weight of the objective function is at a certain value.

[0065] Figure 12 It is the task allocation and path planning result of City One in the embodiment of the present invention when the weight of the formation firepower is at a certain value.

[0066] Figure 13 It is the task allocation and path planning result of City One in the embodiment of the present invention when the weight of the formation firepower is at a certain value.

[0067] Figure 14 It is the top view of City Two based on the Unreal Engine in the embodiment of the present invention.

[0068] Figure 15 It is the task allocation and path planning result of City Two in the embodiment of the present invention when the weight of the objective function is at a certain value.

[0069] Figure 16 It is the task allocation and path planning result of City Two in the embodiment of the present invention when the weight of the objective function is at a certain value.

[0070] Figure 17 It is the task allocation and path planning result of City Two in the embodiment of the present invention when the weight of the objective function is at a certain value.

[0071] Figure 18 It is the task allocation and path planning result of City Two in the embodiment of the present invention when the weight of the objective function is at a certain value.

[0072] Figure 19 It is the task allocation and path planning result of City Two in the embodiment of the present invention when the weight of the formation firepower is at a certain value.

[0073] Figure 20 For the urban two - formation firepower weight in the embodiments of the present invention Task allocation and path planning results at this time.

[0074] Figure 21 For the urban two - formation firepower weight in the embodiments of the present invention Task allocation and path planning results at this time. Detailed implementation manners

[0075] In order to enable those skilled in the art of the present technology to better understand the technical solution of the present invention, the technical solution of the present invention will be further described in detail below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0076] As Figure 1 shown, the task allocation and path planning method for urban confrontation in this embodiment includes the following steps:

[0077] S1. Obtain the real - time comprehensive situation information of the urban confrontation scene including the positions of each unit of both sides of the confrontation;

[0078] S2. Obtain the shapefile image of the current confrontation area from the GIS software;

[0079] S3. Analyze the shapefile image and extract the path key points in the urban road network;

[0080] S4. Calculate the passable paths between each unit of both sides of the confrontation according to the positions of each unit of both sides of the confrontation;

[0081] S5. Combine the real - time comprehensive situation information of the urban confrontation scene and the passable paths between each unit of both sides of the confrontation to calculate all key confrontation elements regarding the passable paths and establish a maneuver efficiency constraint model, a maneuver threat constraint model, and a formation firepower constraint model. The key confrontation elements include unit type, unit basic attributes, day - night environment, and path conditions;

[0082] S6. Construct an objective function based on the maneuver efficiency constraint model, the maneuver threat constraint model, and the formation firepower constraint model;

[0083] S7. Solve the task allocation and path planning scheme for the constructed objective function.

[0084] In obtaining the real - time comprehensive situation information of the urban confrontation scene including the positions of each unit of both sides of the confrontation in step S1, the key is the position information of each unit of both sides of the confrontation. In addition, some other parameter definitions are also included. The real - time comprehensive situation information in this embodiment is obtained from the real game confrontation scene. The real - time comprehensive situation information of the confrontation specifically includes:

[0085] Our side's The position of the th unit, where represents the abscissa of our th unit, represents the ordinate of our th unit, , represents the total number of our units. The position of the th unit of the opponent , where represents the abscissa of the th unit of the opponent, represents the ordinate of the th unit of the opponent, , represents the total number of the opponent's units.

[0086] The types of our units include 4 types: command units, logistics units, armored units, and support units, and a single unit can only belong to one of them. Among them, the Boolean variable represents whether our th unit is a command unit. If so, , otherwise . Similarly, the Boolean variable represents whether our th unit is a logistics unit. If so, , otherwise . The Boolean variable represents whether our th unit is an armored unit. If so, , otherwise . The Boolean variable represents whether our th unit is a support unit. If so, , otherwise .

[0087] The offensive firepower value of our th unit is closely related to the type of the unit and specifically satisfies the following conditions:

[0088] ,

[0089] Among them, the offensive firepower value of the command unit is represented as , the offensive firepower value of the logistics unit is represented as , the offensive firepower value of the armored unit is represented as , and the offensive firepower value of the support unit is represented as .

[0090] The offensive firepower value of the th unit of the opponent is .

[0091] The defensive ability value of the th unit of our side is also closely related to the type of the unit and specifically satisfies the following conditions:

[0092] ,

[0093] Among them, the defensive ability value of the command unit is expressed as , the defensive ability value of the logistics unit is expressed as , the defensive ability value of the armored unit is expressed as , the defensive ability value of the support unit is expressed as .

[0094] The importance degree value of the th unit of our side specifically satisfies the following conditions:

[0095] ,

[0096] Among them, the Boolean variable is used to indicate whether the confrontation activity occurs during the day or at night. If the confrontation activity occurs during the day, then ; if the confrontation activity occurs at night, then . The importance degree value of the command unit during the day is expressed as , and the importance degree value at night is expressed as . The importance degree value of the logistics unit is expressed as , the importance degree value of the armored unit is expressed as , and the importance degree value of the support unit is expressed as . When , the confrontation activity occurs during the day. At this time, the speed of the th unit of our side is , among which, represents the maximum maneuvering speed of the th unit of our side during the day; when , the confrontation activity occurs at night. At this time, the speed of the th unit of our side is , among which, represents the maximum maneuvering speed of the th unit of our side at night.

[0097] In this embodiment, step S2 obtains the shapefile image of the current confrontation area from the GIS software; Shapefile is a common data format for Geographic Information System (GIS), which is used to store geospatial data, such as the geometric shapes of points, lines, and polygons. In this embodiment, the Shapefile image data of the current urban confrontation area is directly obtained from the relevant GIS software.

[0098] Step S3 is used to analyze the Shapefile image data and extract the path key points in the urban road network. In this embodiment, step S3 includes:

[0099] S3.1, binarize the shapefile image to obtain a binary image;

[0100] As an optional implementation manner, in this embodiment, the cv2.cvtColor function in the computer vision and image processing open-source library OpenCV is used to convert the Shapefile image data in step two into a grayscale image, and the cv2.adaptiveThreshold function is used to perform adaptive thresholding to convert the grayscale image into a binary image.

[0101] S3.2, extract the polygon contour lines in the binary image to obtain the road network and building information of the city;

[0102] As an optional implementation manner, in this embodiment, the cv2.findContours function is used to extract the polygon contour lines in the binary image to obtain the road network and building information of the city;

[0103] S3.3, simplify the polygon contour lines and extract the vertices of the polygon contour lines as the path key points in the urban road network. As an optional implementation manner, in this embodiment, the shapely.geometry.Polygon function in the spatial geometry calculation open-source library Shapely is used to simplify the existing polygon contour lines, and then the polygon.exterior.coords function is used to extract the vertices of the polygon contour lines, and these vertices are the path key points.

[0104] Step S4 is used to analyze the connectivity between the path key points and calculate the passable paths between each unit of the two confronting sides according to the positions of each unit of the two confronting sides. Specifically, in this embodiment, step S4 includes:

[0105] S4.1, use GPU or CPU parallel computing to analyze the connectivity between the path key points: The method for judging the connectivity between the path key points is as Figure 2As shown, for any two path key points, calculate the difference in the vertical coordinates and the difference in the horizontal coordinates between the two path key points, and take the maximum value of the two as the number of sampling points ; Uniformly sample points on the line segment connecting the two path key points points, and perform rounding operations on the coordinates of each point. Finally, determine whether there are black points among the points obtained by sampling. If there are black points, it is determined that the two path key points are not connected; otherwise, it is determined that the two path key points are connected;

[0106] S4.2, According to the pixel values of the positions of each unit of the opposing sides in the shapefile image, determine whether the position coordinates of each unit of the opposing sides are inside the building. If the pixel value of the position coordinates in the shapefile image is black, it is determined that the unit is inside the building; otherwise, it means that the unit is not inside the building;

[0107] S4.3, For the units inside the building, regard the position coordinate points of the unit as connected to the path key points corresponding to the building; for the units not inside the building, judge the connectivity between the position coordinate points of the unit and each path key point one by one; finally, obtain the connectivity between the units of the opposing sides and all path key points;

[0108] S4.4, According to the connectivity between the units of the opposing sides and all path key points, use a specified path planning algorithm to calculate the passable paths between each unit of the opposing sides. For example, as an optional implementation manner, in this embodiment, the A* algorithm is used to calculate the passable paths between the units of the opposing sides, where the A* algorithm is a well-known path search algorithm.

[0109] In step S4.1, by using GPU or CPU parallel computing to analyze the connectivity between path key points, the aim is to use parallel processing to improve the efficiency of calculating and analyzing the connectivity between path key points. The basic idea of parallel processing is as Figure 3 shown. Assuming that the parallel processing is 3 threads (thread 1 to thread 3), then the first parallel processing can handle 3 tasks (data 1 to data 3) simultaneously. For thread 1, the data processed in the second time is 4, and the step number of the data processed by each thread is the number of threads. In this embodiment, the CUDA programming module in the Numba package is used to implement the parallel computing of the GPU. First, use the cuda.grid(2) method in the CUDA programming module to obtain the unique index of the cuda thread, and this index can be represented as a two-dimensional coordinate . Then, calculate respectively through cuda.gridDim.x × cuda.blockDim.x and cuda.gridDim.y × cuda.blockDim.y direction and The iteration step size in the direction. Here, cuda.gridDim represents the number of blocks in the grid, and cuda.blockDim represents the number of threads in a block. The product of the two gives the total number of threads in the grid. Since all threads process data simultaneously, the number of steps advanced in each iteration is equal to the total number of threads. For any two points and , if and are connected, then and are connected. To avoid duplicate calculations, for the points in the direction, start traversing from the starting point. For the points in the direction, start traversing from the currently traversed point. In addition, the idea of implementing parallel computing using the CPU is similar to that using the GPU. First, obtain the list of point pairs to be processed by each CPU according to the number of cores, and then use the map method of the Pool module in the Multiprocessing package to implement parallel computing.

[0110] Based on the adversarial real-time comprehensive situation information in step S1 and the passable paths between the adversarial units in step S4, in step S5 of this embodiment, all key adversarial elements regarding the passable paths are calculated, including:

[0111] Denotes the distance visible to the opponent's units when the th unit of our side attacks the th opponent's unit through the th passable path. The specific calculation steps of are as follows: First, uniformly sample path points on the th passable path when the th unit of our side attacks the th opponent's unit. Then, obtain the visible relationship between each path point and all opponent's units. For each path point, if there is at least one opponent's unit that can see the path point, then mark the path point as visible. If two adjacent path points are both visible, then the distance between the two path points is marked as the visible distance. After traversing path points, sum up all the visible distances to obtain the total distance visible to the opponent's units for this path

[0112] Denotes the distance visible to the opponent's units when the th unit of our side attacks the th opponent's unit through the When attacking the

[0113] th unit of our side, the congestion level of the path. from the th passable path to attack the th unit of the opponent, the number of traffic intersections or crossroads on the path; When attacking the th unit of our side, the number of bridges on the path when attacking the th unit of the opponent from the th passable path; When attacking the th unit of our side, the number of tunnels on the path when attacking the th unit of the opponent from the th passable path; When attacking the th unit of our side, the ratio of the length of the route covered by the opponent's firepower to the total route length when attacking the th unit of the opponent from the th passable path; When attacking the th unit of our side, the comprehensive danger level of the path when attacking the th unit of the opponent from the th passable path. The calculation function expression of the comprehensive danger level of the path when our side's th unit attacks the th unit of the opponent from the th passable path is:

[0114] ,

[0115] where represents the comprehensive danger level of the path when our side's th unit attacks the th unit of the opponent from the ~ respectively represent the weights of different elements, represents the bias, and represents the number of traffic intersections or crossroads on the path when our side's th unit attacks the th unit of the opponent from the th passable path; represents the number of bridges on the path when our side's th unit attacks the th unit of the opponent from the th passable path; The number of tunnels on the path when attacking the opponent's th unit via passable paths; Indicates the ratio of the length of the route covered by the opponent's firepower to the total route length when our th unit attacks the opponent's th unit via

[0116] Indicates the distance of the path when our th unit attacks the opponent's th unit via passable paths;

[0117] Indicates the time required when our th unit attacks the opponent's th unit via passable paths, and the calculation function expression for the time required when our th unit attacks the opponent's th unit via passable paths is:

[0118] ,

[0119] where indicates the time required when our th unit attacks the opponent's th unit via passable paths; indicates the distance of the path when our th unit attacks the opponent's th unit via passable paths; indicates whether there is a feasible path when our th unit attacks the opponent's th unit. If there is a feasible path, then , otherwise, ; indicates the congestion degree of the path when our th unit attacks the opponent's th unit via passable paths; is the speed of our th unit. When the confrontation activity occurs during the day, the speed of our th unit is , where indicates the speed of our The maximum maneuvering speed of a unit during the day; when the confrontation activity occurs at night, the speed of our th unit is , where represents the maximum maneuvering speed of our th unit at night.

[0120] In this embodiment, when establishing the maneuver efficiency constraint model in step S5, it is restricted that a single unit of ours cannot attack multiple opponent units simultaneously and can only select one attack path from the passable paths. For , the following constraints are satisfied:

[0121] ,

[0122] The maneuver efficiency of our unit needs to comprehensively consider the formation situation, path selection situation and the number of support units of our unit. For and , the function expression of the maneuver efficiency constraint model established in step S5 of this embodiment is:

[0123] ,

[0124] ,

[0125] where is the maneuvering time for our formation to move towards the th opponent unit; the Boolean variable represents whether our th unit decides to attack the th opponent unit from the th passable path. If so, , otherwise , where , represents the number of our units, , represents the number of opponent units, , represents the total number of passable paths for our th unit to reach the th opponent unit; represents the time required for our th unit to attack the th opponent unit from the th passable path; represents the number of support units among all our units that attack the th opponent unit. The more support units, the higher the maneuver efficiency; Indicates the gain of the protection unit to the maneuver efficiency, and there is:

[0126] ,

[0127] The maneuvering time for our formation to go to the th opponent unit The larger it is, the lower the maneuver efficiency.

[0128] The maneuver threat of our unit needs to comprehensively consider factors such as the formation situation, importance level, defense ability, path passability, path visible distance, and path comprehensive danger level of our unit. For and , the function expression of the maneuver threat constraint model established in step S5 of this embodiment is:

[0129] ,

[0130] In the above formula, is the maneuver threat for our unit to go to the th opponent unit, is the importance level value of our rd unit; Indicates whether there is a feasible path when our th unit attacks the th opponent unit. If there is a feasible path, then , otherwise, ; Indicates the visible distance of our th unit from the th passable path when attacking the th opponent unit by the opponent unit; Indicates the path comprehensive danger level of our th unit from the th passable path when attacking the th opponent unit; is the defense ability value of our rd unit;

[0131] The formation firepower of our unit needs to comprehensively consider factors such as the formation situation and attack ability of our unit. In order to limit the formation firepower of our unit within a reasonable range, the following constraints can be established:

[0132] ,

[0133] Among them, indicates the minimum ratio of our formation firepower to the firepower of the th opponent unit; Indicates the maximum ratio of the firepower of our formation to that of the th unit of the opponent; is the offensive firepower value of the th unit of the opponent; The functional expression of the formation firepower constraint model established in step S5 is:

[0134] ,

[0135] ,

[0136] wherein, Indicates the minimum ratio of the firepower of our formation to that of the th unit of the opponent; Indicates the maximum ratio of the firepower of our formation to that of the th unit of the opponent, is the offensive firepower value of the th unit of the opponent; The Boolean variable Indicates whether the th unit of ours decides to attack the th unit of the opponent from the th passable path. If so, , otherwise ; is the offensive firepower value of the th unit of ours; is the remaining firepower value of all our formations, Indicates the increase in the offensive firepower of our units by the logistics unit, Indicates the number of logistics units among all our units that attack the th unit of the opponent, Indicates the increase in the offensive firepower of our units by the command unit. The Boolean variable Indicates whether the unit of ours that attacks the th unit of the opponent can communicate with the command unit. If it can, , otherwise ; Indicates the number of command units among all our units that attack the th unit of the opponent, is the offensive firepower value of the th unit of the opponent.

[0137] According to the maneuver efficiency constraint model, the maneuver threat constraint model, and the formation firepower constraint model, it is necessary to minimize the maneuver threat of our units, maximize the maneuver efficiency and the remaining firepower. The functional expression of the objective function constructed in step S6 of this embodiment is:

[0138] ,

[0139] Among them, respectively represent the weights of maneuver efficiency, remaining firepower, and maneuver threat.

[0140] In step S7 of this embodiment, the task assignment and path planning scheme for solving the constructed objective function is to use an improved multi-gene adaptive genetic-simulated annealing algorithm to solve the task assignment and path planning scheme of the constructed objective function. Figure 4 It is a schematic flow chart of the improved multi-gene adaptive genetic-simulated annealing algorithm in this embodiment. In this embodiment, an improved multi-gene adaptive genetic-simulated annealing algorithm is used to solve the objective function, and then a reasonable task assignment and path planning scheme is generated. The process of this algorithm for solving the constraint model is as follows: First, according to the confrontation situation information such as the unit types and basic attributes of both sides in the confrontation, a multi-layer multi-gene coding that meets the constraint conditions is designed, and the initial population size is reasonably selected according to the number of units of both sides in the confrontation. Secondly, the objective function is mapped to the fitness value function of each chromosome. In each iteration, some dominant individuals are selected to form an elite population. At the same time, appropriate adaptive crossover factor α, mutation factor β, and simulated annealing factor γ are selected according to the scale of the units of both sides in the confrontation, and various crossover and mutation strategies are introduced. Finally, through multiple iterations of this framework, a better feasible solution is finally obtained. Specifically, as Figure 4 shown, the task assignment and path planning scheme for solving the constructed objective function in step S7 of this embodiment includes:

[0141] S7.1, For the problem of solving the task assignment and path planning scheme, a multi-gene coding is carried out using a multi-layer multi-gene coding strategy. As Figure 5 shown, the multi-layer multi-gene coding strategy includes a task layer, a unit layer, and an action route layer. Among them, the task layer is mainly composed of task numbers and adopts an integer coding strategy; the unit layer is composed of the numbers of our units, and the vacant gene mechanism is introduced to randomly set some genes to "-1" to indicate that the task is not assigned to any unit; the action route layer adopts an integer coding strategy;

[0142] S7.2, Initialize and generate the initial population based on the constraint conditions in the maneuver efficiency constraint model, maneuver threat constraint model, and formation firepower constraint model;

[0143] S7.3, Calculate the fitness value for each individual in the current population using the objective function respectively:

[0144] S7.4, Sort the individuals in the current population according to the fitness value, and select the individuals in the top specified proportion to form an elite population, and the remaining individuals are the ordinary population;

[0145] S7.5, generate new individuals from the elite population through adaptive simulated annealing. Generating new individuals through adaptive simulated annealing means randomly selecting in the neighborhood of the current individual and accepting the new individual according to a specified probability; select individuals in the ordinary population to perform crossover with individuals in the elite population or self-crossover according to an adaptive probability where N iter represents the current iteration number, N epoch represents the total number of iterations; perform mutation operations on the ordinary population and the new individuals obtained by performing crossover with individuals in the elite population or self-crossover according to an adaptive mutation probability When performing the mutation operation, the number of mutation positions is random, so that different individuals in the same population have different mutation positions; only the unit layer and the action route layer participate in the mutation; select a specified number of feasible offspring from the current population and the new individuals as the new current population;

[0146] S7.6, determine whether the number of iterations reaches the preset threshold. If it has not reached the preset threshold, jump to step S7.4 to continue the iteration; otherwise, calculate the fitness value from the new individuals in the new current population using the objective function, and select the individual with the best fitness value as the finally obtained optimal task assignment and path planning scheme.

[0147] See Figure 5 , in this embodiment, a multi-gene coding method is adopted. The designed multi-layer multi-gene coding strategy mainly includes a task layer, a unit layer, and an action route layer. The task layer is mainly composed of task numbers and adopts an integer coding strategy, which can be extended according to the actual number of tasks; the unit layer is composed of the numbers of our units, and a vacant gene mechanism is introduced, that is, randomly set some genes to "-1", indicating that the task is not assigned to any unit; the action route layer also adopts an integer coding strategy and can be extended according to the number of selectable action routes. After completing the unit gene coding, sort the population generated in each round of iteration according to the fitness value, and select the top 1 / 5 of the individuals to form the elite population, and the remaining individuals are the ordinary population. First, perform a crossover operation on the population. In this embodiment, an adaptive crossover operation is used. Individuals in the ordinary population select to perform crossover with individuals in the elite population or self-crossover according to an adaptive probability α, and its calculation method is:

[0148] ,

[0149] where N iter represents the current iteration number of the algorithm, N epochIndicates the total number of algorithm iterations. The variation law of this function is consistent with the law of the elite population participating in crossover. In the initial stage of algorithm iteration, in order to prevent the algorithm from converging too quickly, the probability of elite individuals participating in crossover is relatively small. This can maintain the diversity of the population structure while ensuring that the population evolves in a better direction. In the later stage of algorithm iteration, the population structure is relatively stable, and the probability of generating better solutions through crossover operations is low. At this time, increasing the probability of elite individuals participating in crossover can enable the algorithm to accelerate convergence while searching the solution space and save computing resources. On this basis, mutation operations are performed on some individuals in the population. The mutation operations mainly follow the following two principles: (1) The number of mutation points is random, that is, different individuals in the same population have different mutation points. (2) Only the unit layer and the action route layer participate in mutation. The reason is that if the target layer participates in mutation, some target genes will be lost, resulting in a large number of invalid offspring individuals.

[0150] In order to balance enriching the population diversity and avoiding excessive population differences, the EA-GA algorithm designs an adaptive mutation probability calculation method as shown in the following formula:

[0151] ,

[0152] where δ represents the probability of individual mutation, N iter represents the current iteration number of the algorithm, N epoch represents the total number of algorithm iterations. The calculation process is as follows: In the initial stage of algorithm iteration, in order to ensure the diversity of the offspring population and avoid premature convergence of the algorithm, the initial mutation probability of the parent population is set to 40%, and it decreases with the iteration process of the algorithm. In the later stage of algorithm iteration, the probability of finding better solutions decreases. At this time, its mutation probability is gradually reduced to 14.7%, which can accelerate convergence while meeting the optimization requirements of the offspring population.

[0153] Next, combining two specific urban scenarios (respectively expressed as City One and City Two), the specific implementation methods of the method proposed in this embodiment are described. First, the original Shapefile image of City One as shown on the left can be directly obtained from relevant GIS software. Second, the Shapefile image is converted into a grayscale image using the cv2.cvtColor function of the OpenCV library. Then, the cv2.adaptiveThreshold function is used to perform an adaptive thresholding operation on the grayscale image to convert the grayscale image into a binary image as shown on the right. After obtaining the binary image as shown in Figure 6 the left Figure 6 the right Figure 7After the binary image of City 1 shown on the left, the cv2.findContours function is further used to extract the polygon contour lines in the binary image to obtain the road network and building information of the city. The extraction result of the image polygon contour lines of City 1 is as shown in Figure 7 the right. After obtaining the image polygon contour lines of City 1 as shown in Figure 8 the left, the shapely.geometry.Polygon function in the Shapely library is used to simplify the existing polygon contour lines, and then the polygon.exterior.coords function is used to extract the vertices of the polygon contour lines. These vertices are the path key points. The extraction result of the image polygon vertices (path key points) of City 1 is as shown in Figure 8 the right. According to Figure 8 the path key points of City 1 shown on the right, combined with Figure 2 the connectivity judgment method between the path key points in Figure 3 and the basic idea of parallel computing in Figure 9 the parallel computing of the connectivity between all path key points of City 1 is implemented using the GPU and CPU. According to the obtained connectivity judgment results, the A* algorithm is used to solve the passable paths between any two points in City 1. The solution example is as shown in Figure 10 shown. As shown in

[0154] ,

[0155] where represent the weights of maneuver efficiency, remaining firepower, and maneuver threat respectively. When , the improved multi-gene adaptive genetic-simulated annealing algorithm in Figure 4 is used to solve the objective function, and the generated formation and maneuver strategies are as shown in Figure 10As shown. Our first unit forms a single formation and attacks the opponent's 0th unit along the planned route; our 7th unit forms a single formation and attacks the opponent's 3rd unit along the planned route; our 0th, 2nd, 3rd, and 6th units form a formation and attack the opponent's 1st unit along their respective planned routes; our 5th unit forms a formation and attacks the opponent's 2nd unit along the planned route. The results in the figure show that when occurs, our units will focus on the advantage of formation firepower during the attack, consider less the maneuver efficiency and maneuver threat factors, and emphasize steadily eliminating the opponent with several times the force of the opponent within sufficient time. When occurs, the generated formations and maneuver strategies are as Figure 11 shown. Our first unit forms a single formation and attacks the opponent's 3rd unit along the planned route; our 7th unit forms a single formation and attacks the opponent's 0th unit along the planned route; our 0th, 2nd, 3rd, and 6th units form a formation and attack the opponent's 1st unit along their respective planned routes; our 5th unit forms a single formation and attacks the opponent's 2nd unit along the planned route. The results in the figure show that our units no longer consider the factor of maneuver threat during the attack. While focusing on the advantage of formation firepower, they also emphasize the maneuver efficiency of the units, and emphasize eliminating the opponent steadily with several times the force of the opponent within limited time at all costs of threat. On the other hand, the formation firepower of our units needs to comprehensively consider factors such as the formation situation and attack ability of our units. In order to limit the formation firepower of our units within a reasonable range, the following constraints need to be considered:

[0156] ,

[0157] When the weight of the formation firepower constraint occurs, the generated formations and maneuver strategies are as Figure 12 shown. Our 6th unit forms a single formation and attacks the opponent's 2nd unit along the planned route; our 5th unit forms a single formation and attacks the opponent's 3rd unit along the planned route; our 3rd and 7th units form a formation and attack the opponent's 1st unit along their respective planned routes; our 0th unit forms a single formation and attacks the opponent's 0th unit, while our 1st, 2nd, and 4th units do not participate in this attack. The results in the figure show that the ratio (constraint) relationship between our formation firepower and the opponent's firepower can significantly affect the results of the formation and maneuver strategies. The smaller the ratio, the more it means that we hope to achieve the goal of eliminating the opponent's units with as few formation firepower resources as possible.

[0158] When the weight of the formation firepower constraint occurs, the generated formations and maneuver strategies are as Figure 13As shown in the figure. Our fifth unit forms a separate formation and attacks the opponent's third unit along the planned route; our sixth unit forms a separate formation and attacks the opponent's second unit along the planned route; our 0th and 3rd units form a formation and attack the opponent's 0th unit along their respective planned routes; our seventh unit forms a separate formation and attacks the opponent's first unit along the planned route. The results in the figure show that the higher the lower limit of the ratio between our formation firepower and the opponent's firepower, the more it means that we hope to use sufficient formation firepower resources to achieve the goal of eliminating the opponent's units.

[0159] This embodiment also conducts task assignment and path planning experiments in City Two based on the Unreal Engine as shown in Figure 14 the figure, and similar conclusions can be drawn as in City One, further verifying the effectiveness and rationality of the method proposed in this embodiment. Figure 15 、 Figure 16 、 Figure 17 and Figure 18 further verify the influence of the maneuver efficiency, remaining firepower, and maneuver threat weights of the objective function proposed in this embodiment on the task assignment and path planning results of our units. The results in the figure show that by controlling the weights between the first, second, and third optimization objectives in the objective function, the method proposed in this embodiment can generate different formations and maneuver strategies. Among them, the first optimization objective is related to maneuver efficiency. The greater the weight, the more the obtained formation and maneuver strategies focus on the rapidity and suddenness of maneuver, that is, quickly eliminating the opponent with limited troops; the second optimization objective is related to the remaining formation firepower. The greater the weight, the more the obtained formation and maneuver strategies focus on the advantage of offensive firepower, emphasizing steadily eliminating the opponent with several times the number of troops of the opponent within sufficient time; the third optimization objective is related to maneuver threat. The greater the weight, the more the obtained formation and maneuver strategies focus on reducing the possible threats during the maneuver process, thereby reducing the losses of our units. Figure 19 、 Figure 20 and Figure 21Further verified the influence of the weights of the formation firepower constraints proposed in this embodiment on the mission assignment and path planning results of our units. The results in the figure show that by controlling the upper and lower limits of the ratio between our formation firepower and the opponent's firepower, the method proposed in this embodiment can generate different formation and maneuver strategies. Among them, the larger the upper limit of the ratio between our formation firepower and the opponent's firepower, the more the obtained formation and maneuver strategies focus on using sufficient firepower to eliminate the opponent, and less consider the consumption of resources; the smaller the lower limit of the ratio between our formation firepower and the opponent's firepower, the more the obtained formation and maneuver strategies focus on using fewer firepower resources to eliminate the opponent and minimize the consumption of resources as much as possible. Thus, it is crucial to reasonably and efficiently assign tasks and plan paths for our units according to the confrontation objectives, confrontation plans, and real-time comprehensive confrontation situation in urban confrontation. The method of this embodiment proposes a mission assignment and path planning method for urban confrontation, which is used to analyze and predict the formation strategies and maneuver strategies of multiple our units. First, use the computer vision and image processing open-source library OpenCV and the spatial geometry calculation open-source library Shapely to analyze the Shapefile image of a specific confrontation area to obtain urban road network information and path key points. Secondly, based on the real-time comprehensive confrontation situation such as the positions of the units on both sides of the confrontation, the unit types, the basic attributes of the units, and the path key points, use the A* algorithm to search for multiple passable paths between each unit on both sides of the confrontation, and calculate the key confrontation elements such as the distance, congestion degree, and threat degree of all passable paths respectively. Then, construct a maneuver efficiency constraint model, a maneuver threat constraint model, and a formation firepower constraint model, and design an objective function to optimize the formation strategy and maneuver strategy. Finally, use the improved multi-gene adaptive genetic-simulated annealing algorithm to solve the objective function and generate a reasonable mission assignment and path planning scheme. The method of this embodiment realizes mission assignment and path planning for urban confrontation, and improves the applicability and accuracy of mission assignment and path planning in different urban confrontation scenarios.

[0160] This embodiment also provides a mission assignment and path planning system for urban confrontation, including a microprocessor and a memory connected to each other, and the microprocessor is programmed or configured to execute the mission assignment and path planning method for urban confrontation. This embodiment also provides a computer-readable storage medium, in which a computer program or instruction is stored, and the computer program or instruction is programmed or configured to execute the mission assignment and path planning method for urban confrontation through a processor. This embodiment also provides a computer program product, including a computer program or instruction, and the computer program or instruction is programmed or configured to execute the mission assignment and path planning method for urban confrontation through a processor.

[0161] The above are only the preferred embodiments of the present invention. The protection scope of the present invention is not limited to the above embodiments. All technical solutions falling within the concept of the present invention belong to the protection scope of the present invention. It should be noted that for those of ordinary skill in the art, several improvements and refinements made without departing from the principle of the present invention should also be regarded as within the protection scope of the present invention.

Claims

1. A task allocation and path planning method for urban confrontation, characterized in that: The steps include: S1, obtaining real-time comprehensive situation information of the urban confrontation scene including the positions of each unit of the confrontation parties; S2, obtain the shapefile image of the current confrontation area from the GIS software; S3, analyzes the shapefile image and extracts key points of paths in the urban road network; S4, calculating the traversable paths between the units of the two opposing sides according to the positions of the units of the two opposing sides; S5, combining the real-time comprehensive situation information of the urban confrontation scene and the traversable paths between the units of the two opposing sides, calculating all the key confrontation elements about the traversable paths and establishing a mobility efficiency constraint model, a mobility threat constraint model and a formation fire constraint model, wherein the key confrontation elements include unit type, unit basic attributes, day and night environment and path conditions; S6, constructing the objective function based on the mobility efficiency constraint model, mobility threat constraint model and group fire constraint model; S7, solve the task allocation and path planning solutions based on the constructed objective function.

2. The method for task allocation and path planning for urban confrontation according to claim 1 is characterized in that: Step S3 includes: S3.1, binarize the shapefile image to obtain a binary image; S3.2, extract polygon contours in the binary image to obtain the city’s road network and building information; S3.3, simplify the polygonal contour line and extract the vertices of the polygonal contour line as the path key points in the urban road network.

3. The task allocation and path planning method for urban confrontation according to claim 1 is characterized in that: Step S4 includes: S4.1, use GPU or CPU parallel computing to analyze the connectivity between key points on the path: for any two key points on the path, calculate the difference between the ordinate and the abscissa, and take the maximum value of the two as the number of sampling points ; Uniformly sample the line segment connecting two path key points points, and round the coordinates of each point, and finally determine the sampled Whether there is a black point among the points, if there is a black point, it is determined that the two key points on the path are not connected; otherwise, it is determined that the two key points on the path are connected; S4.2, judging whether the position coordinates of each unit of the opposing parties are in the building according to the pixel values ​​of the positions of each unit of the opposing parties in the shapefile image, if the pixel value of the position coordinates in the shapefile image is black, it is determined that the unit is in the building, otherwise, it is determined that the unit is not in the building; S4.3, for the unit in the building, the position coordinate point of the unit is considered to be connected with the key point of the path corresponding to the building; for the unit not in the building, the connectivity of the position coordinate point of the unit with each key point of the path is determined one by one; finally, the connectivity of the units of the two adversaries with all the key points of the path is obtained; S4.4, based on the connectivity between the units of the two adversaries and all key points of the path, use the specified path planning algorithm to calculate the traversable path between the units of the two adversaries.

4. The method for task allocation and path planning for urban confrontation according to claim 1 is characterized in that: The function expression of the maneuvering efficiency constraint model established in step S5 is: ， ， in, We will organize our team to go to The maneuver time of the opponent's unit; Boolean variable Indicates our Whether the unit decides from Passable paths to attack the opponent units, if so, then ,otherwise ,in , Indicates the number of our units, , represents the number of opponent units, , Indicates our Units reach the opponent's The total number of traversable paths per unit; Indicates our Units from Passable paths to attack the opponent The time required for each unit; Indicates the unit that attacks the opponent among all our units. The number of support units per unit. The more support units there are, the higher the mobility efficiency. It represents the gain of the support unit on maneuver efficiency; The function expression of the maneuver threat constraint model established in step S5 is: ， In the above formula, For our unit to go to The mobile threat of an opponent's unit, For our The importance value of each unit; Indicates our Units attack the opponent Is there a feasible path when there are units? If there is a feasible path, then ,otherwise, ; Indicates our Units from Passable paths to attack the opponent When there are units, the distance that can be seen by the opponent's units; Indicates our Units from Passable paths to attack the opponent The comprehensive hazard level of the path when the unit is For our The defensive capability value of each unit; The function expression of the group firepower constraint model established in step S5 is: ， ， in, Indicates that our team's firepower is in conflict with the opponent's team's The minimum ratio of firepower per unit; Indicates that our team's firepower is in conflict with the opponent's team's The maximum ratio of the firepower of each unit, For the opponent The offensive firepower value of a unit; Boolean variable Indicates our Whether the unit decides from Passable paths to attack the opponent units, if so, then ,otherwise ; For our The offensive firepower value of each unit; The remaining firepower value for all our formations, It indicates the increase in the offensive firepower of our units from the logistics units. Indicates the unit that attacks the opponent among all our units. The number of logistic units per unit, Indicates the gain of the command unit's offensive firepower to our unit, a Boolean variable Indicates attacking the opponent Can our units maintain communication with the command unit? If so, ,otherwise ; Indicates the unit that attacks the opponent among all our units. The number of command units of a unit, For the opponent The offensive firepower value of each unit; The function expression of the objective function constructed in step S6 is: ， in, They represent the weights of mobility efficiency, residual firepower and mobility threat respectively.

5. The method for task allocation and path planning for urban confrontation according to claim 4 is characterized in that: Our Units from Passable paths to attack the opponent The calculation function expression of the comprehensive danger degree of the path when the unit is: ， in, Indicates our Units from Passable paths to attack the opponent The comprehensive hazard level of the path when the unit is ~ Represent the weights of different factors. represents the bias, Indicates our Units from Passable paths to attack the opponent The number of traffic intersections or crossroads on the path when the unit is Indicates our Units from Passable paths to attack the opponent The number of bridges on the path when the unit is Indicates our Units from Passable paths to attack the opponent The number of tunnels on the path when the unit is Indicates our Units from Passable paths to attack the opponent The ratio of the route length covered by the opponent's firepower to the total route length when the opponent fires a unit.

6. The method for task allocation and path planning for urban confrontation according to claim 4 is characterized in that: Our Units from Passable paths to attack the opponent The calculation function expression of the time required for each unit is: ， in, Indicates our Units from Passable paths to attack the opponent The time required for each unit; Indicates that our unit is from Passable paths to attack the opponent The distance of the path when the unit is Indicates our Units attack the opponent Is there a feasible path when there are units? If there is a feasible path, then ,otherwise, ; Indicates our Units from Passable paths to attack the opponent The congestion level of the path when the unit is For our The speed of the unit, when the confrontation takes place during the day, our The speed of the unit is ,in, Indicates our The maximum maneuvering speed of a unit during the day; when the confrontation takes place at night, our The speed of the unit is ,in Indicates our The maximum maneuvering speed of a unit at night.

7. The method for task allocation and path planning for urban confrontation according to claim 1 is characterized in that: In step S7, the task allocation and path planning scheme for solving the constructed objective function is to use an improved multi-gene adaptive genetic-simulated annealing algorithm to solve the task allocation and path planning scheme for the constructed objective function, including: S7.1, a multi-layer polygene coding strategy is used to solve the problem of task allocation and path planning. The multi-layer polygene coding strategy includes a task layer, a unit layer and an action route layer. The task layer is mainly composed of task numbers and adopts an integer coding strategy; the unit layer is composed of the numbers of our units, and a vacant gene mechanism is introduced to randomly set some genes to "-1" to indicate that the task is not assigned to any unit; the action route layer adopts an integer coding strategy; S7.2, generating an initial population based on the constraints in the mobility efficiency constraint model, the mobility threat constraint model, and the group fire constraint model; S7.3, use the objective function to calculate the fitness value of each individual in the current population: S7.4, sort the individuals in the current population according to the fitness value, select the individuals with the specified proportion to form the elite population, and the rest of the individuals are the ordinary population; S7.5, the elite population is subjected to adaptive simulated annealing to generate new individuals, wherein the adaptive simulated annealing to generate new individuals refers to randomly selecting new individuals in the neighborhood of the current individual and accepting them according to a specified probability; the individuals in the ordinary population are subjected to adaptive probability. Select individuals from the elite population for crossover or self-crossover, where N iter Indicates the current iteration number, N epoch Represents the total number of iterations; the new individuals obtained by crossover or self-crossover between the common population and the individuals in the elite population are selected according to the adaptive mutation probability Implement mutation operation, and when implementing mutation operation, the number of mutation points is random, so that different individuals in the same population have different mutation points; only the unit layer and the action route layer participate in mutation; select a specified number of viable offspring from the current population and new individuals as the new current population; S7.6, determine whether the number of iterations reaches the preset threshold. If it has not reached the preset threshold, jump to step S7.4 to continue iteration; otherwise, use the objective function to calculate the fitness value of the new individuals in the new current population, and select the individual with the best fitness value as the final optimal task allocation and path planning solution.

8. A task allocation and path planning system for urban confrontation, comprising a microprocessor and a memory connected to each other, characterized in that: The microprocessor is programmed or configured to execute the task allocation and path planning method for urban confrontation as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program or instruction stored therein, characterized in that: The computer program or instruction is programmed or configured to execute the task allocation and path planning method for urban confrontation described in any one of claims 1 to 7 through a processor.

10. A computer program product comprising a computer program or instructions, characterized in that The computer program or instruction is programmed or configured to execute the task allocation and path planning method for urban confrontation described in any one of claims 1 to 7 through a processor.

Images