Multi-operator cooperative path planning method based on war game platform

Abstract

The invention discloses a multi-operator collaborative path planning method based on a war game platform, and aims to realize multi-target path planning based on an improved A * algorithm aiming at the problem that multi-operator collaborative planning passes through a dangerous area. According to the method, time nodes are introduced, so that operators can utilize time information to realize time coordination and space coordination; an evaluation function is improved, and danger avoidance of operators is realized by introducing damage cost; a coordinate rotation method is adopted, operator paths are optimized one by one based on a pre-planning result, the search dimension is reduced, the number of search nodes is reduced, and the planning efficiency is improved; experimental results show that the method can efficiently plan the cooperation path of the operator, the maneuvering time of the operator is shortened, and the damage cost of the operator is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of war game simulation and path planning, and in particular to a multi-operator collaborative path planning method based on a war game platform. Background Art

[0002] Wargame (military simulation) is to use certain rules to deduce the combat situation. Generally, wargame has three uses: first, to train officers' decision-making ability in actual combat; second, to make officers familiar with a certain combat idea; third, to deduce and analyze the actual strategy, campaign, and combat situation to find the appropriate strategy; it can be seen that it plays an important role in improving decision-making ability and optimizing tactical layout. At present, wargame is gradually becoming a hot topic in domestic research. By combining the idea of ​​wargame with modern information technologies such as modeling and simulation, computer networks, and parallel computing, a wargame system suitable for modern war simulation is established.

[0003] Chessboard + chess pieces + rules constitute the basic form of any chess game, and war chess is no exception. The chessboard of war chess is called a war chess map. The map used in war chess can be specially drawn according to the real terrain and scale, or it can be a virtual map containing various terrains. The chess pieces of the opposing parties are placed in a certain chess grid, which is often composed of hexagonal grids. Different hexagonal grids contain different information. The chess pieces of war chess represent certain combat units or battlefield events. The chess pieces representing combat units are called "unit operators", and the chess pieces representing battlefield events are called "event operators". War chess rules are the basic principles guiding the implementation of war chess simulations and are the core of war chess simulations. Whether the rules are reasonable or not affects the credibility of the results of the simulation analysis.

[0004] Path planning is the most basic problem in wargames. It is the basic ability of operators and is directly related to the operator's operational efficiency and battlefield survivability. In wargames, operators will perform various mobile tasks, and quickly crossing the threat zone is a common one. Within the specified time, quickly crossing the threat zone at the lowest cost requires coordination and joint planning between operators. Collaborative path planning focuses on the overall situation, emphasizes the coordination between operators, and comprehensively considers the relationship between operators to ensure the coordination and consistency of the entire system. In a complex and changing environment, collaborative path planning can not only enable operators to reach the target position efficiently and safely, but also help to achieve the overall tactical intention and improve combat effectiveness. Therefore, based on the hexagonal grid wargame map, it is very important to explore a path planning method with fast convergence speed, high accuracy and strong coordination.

[0005] Collaborative planning to cross dangerous areas requires short time and low damage, which is a typical multi-objective optimization problem. Domestic and foreign scholars have done a lot of meaningful research on this problem. At present, most of the existing technologies plan the path for one operator, and do not consider the coordination problem during the maneuvering of multiple operators. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention aims at the problem of multi-operator coordinated maneuvering in a hexagonal grid network. On the basis of the traditional A* algorithm, the concept of time nodes is introduced, and the common factor of the time consumed in crossing different hexagonal grids is used as the node period. The A* algorithm expands the search according to the time nodes, thus realizing the coordination of operators.

[0007] Based on the above purpose, the present invention provides a multi-operator collaborative path planning method based on a war game platform, comprising the following steps:

[0008] Step 1: Obtain actual task information and construct a hexagonal grid map, where one hexagonal grid corresponds to multiple time nodes;

[0009] Step 2: Construct the objective function of multi-operator collaborative path planning:

[0010] J=minf(L i ,L i + )

[0011] Among them, L i + is the path of other operators except the i-th operator, which is regarded as a fixed value in each optimization;

[0012] Step 3: Plan the initial path for each operator;

[0013] Step 4: Perform i rounds of optimization updates on each operator through the improved A* algorithm and output the collaborative planning path.

[0014] Furthermore, the time node includes two types of node information, namely, the time sequence number t of the current node k , the hexagonal grid k where the node is located.

[0015] Furthermore, the specific operation steps of step 4 are:

[0016] Step 4.1: Define and initialize the old list and the new list, and store the initial path planned in step 3 in the new list;

[0017] Step 4.2: Initialize the number of training rounds i = 1;

[0018] Step 4.3: If the old list stores the path data of the operators before the latest round of optimization, delete the path data of all the original operators in the old list, save the path data of the new list to the old list, and initialize the operator number j = 1;

[0019] Step 4.4: Delete the path data of operator j in the new list, optimize and update the path of operator j using the improved A* algorithm based on the remaining data of other operators, and store the updated path data back into the new list;

[0020] Step 4.5: Determine whether all operators have completed the i-th round of updates. If so, proceed to step 4.6. If not, set j=j+1 and proceed to step 4.4.

[0021] Step 4.6: Traverse the new list and the old list, and determine whether the operator path information in the new list and the old list is the same through string comparison, or whether the number of training rounds i reaches the preset update round number. If the path information is the same or the maximum update round number has been reached, the i-th round path update is completed, otherwise, set i=i+1 and go to step 4.3.

[0022] Further, the improved A* algorithm described in step 4.4 includes the following steps:

[0023] Step 4.4.1: Construct time node;

[0024] Step 4.4.2: Determine the time interval T according to the types of all operators, and obtain the time t required for the operator to cross the hexagonal grid with terrain m by the following formula: m (k):

[0025] t m (k) = r m *T r m ∈N* (2)

[0026] Among them, k represents the hexagonal grid where the time node is located; r m It represents the number of time nodes that the operator needs to go through to cross the hexagonal grid with a terrain of m;

[0027] Step 4.4.3: Define and initialize the open list and close list;

[0028] Step 4.4.4: Put the time node of the initial moment of the i-th operator into the open list;

[0029] Step 4.4.5: Determine whether the open list is empty. If so, the path planning of operator i fails and cannot reach the target point. If not, there is a time node in the open list, and go to step 4.4.6.

[0030] Step 4.4.6: Select a time node with the smallest estimated cost from the open list, delete it from the open list, and store the time node in the close list;

[0031] Step 4.4.7: Find the time node set A at the next moment corresponding to the time node stored in the close list in step 4.4.6, select the time node that has not yet completed the evaluation from the time node set A, and go to step 4.4.8;

[0032] Step 4.4.8: Based on the time sequence number t of the time node k and the hexagonal grid k where it is located to determine whether the time node of the unfinished evaluation selected in step 4.4.7 is in the close list. If so, proceed to step 4.4.10. If not, proceed to step 4.4.9.

[0033] Step 4.4.9: Based on the time sequence number t of the time node k and the hexagonal grid k where it is located to determine whether the time node selected in step 4.4.7 for the unfinished evaluation is in the open list. If not, proceed to step 4.4.10; if so, update the relevant information of the time node and proceed to step 4.4.11;

[0034] Step 4.4.10: Add the time node selected in step 4.4.7 to the open list and update the relevant information of the time node;

[0035] Step 4.4.11: Determine whether all nodes in the time node set A have been judged. If so, proceed to step 4.4.12. If not, proceed to step 4.4.7.

[0036] Step 4.4.12: Determine whether the spatial position information of all time nodes in the time node set A is the target point. If it is the target node, obtain the route of operator i through backtracking, complete the path optimization, and output the planned path; if not, go to step 4.4.6.

[0037] Furthermore, the node related information updated in step 4.4.9 and step 4.4.10 includes:

[0038] 1) Time serial number of the time node

[0039]

[0040] In the formula, r i Indicates the number of time nodes required to cross the i-th hexagonal grid in the shortest path from the starting point to hexagonal grid k;

[0041] 2) The actual cost of reaching the node

[0042] g(k)=α*ξ(k)+(1-α)*c(k)α∈[0,1]

[0043] In the formula, α represents the weight of the time cost; ξ(k) represents the time cost from the starting node to node k, which is represented by the number of time nodes experienced, that is, ξ(k) = t k , when the number of time nodes exceeds the limit, the time cost becomes infinite; c(k) represents the damage cost from the starting node to node k;

[0044] And the damage cost c at each time node in c(k) i for:

[0045]

[0046]

[0047] In the formula, represents the expected damage caused by the enemy operator e to multiple operators at time i; represents the position of one's own operator; n represents the position of the enemy operator; Indicates the operator type of the own side; j e Indicates the enemy operator type; Indicates the estimated health of the own counter; b e Indicates the health of the enemy operator e;

[0048] 3) The estimated cost of reaching the target point after passing this time node

[0049] f(k)=g(k)+h(k)

[0050] Where h(k) represents the estimated cost from spatial node k to the target node, that is, the lower limit of the cost from spatial node k to the target node;

[0051] and:

[0052]

[0053] Where x and y are the horizontal and vertical coordinates of the Cartesian coordinate system of the node respectively; q d ,r d ,s d Respectively represent the coordinates of the cube coordinate system corresponding to the target node, q k ,r k ,s k They respectively represent the coordinates of the cube coordinate system corresponding to the spatial node k.

[0054] Therefore, the present invention adopts the above-mentioned multi-operator collaborative path planning method based on the war game platform, which has the following beneficial effects:

[0055] Aiming at the problem of multiple operators cooperatively crossing danger zones in war game simulation, the present invention proposes an improved A* algorithm, which shortens the time of crossing danger zones and reduces the damage cost of operators by introducing time nodes, thereby realizing cooperative cover crossing danger zones; and adopts a coordinate rotation method to optimize the routes of operators in turn, which greatly reduces the number of nodes and improves the calculation speed; and selects the individual optimal route of operators as the initial route for optimization, thereby reducing the number of optimization times.

[0056] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 Flowchart for collaborative planning of multiple operators;

[0058] Figure 2 is a flow chart of the improved operator updating method;

[0059] Figure 3 This is the initial distribution diagram of Experiment 1.

[0060] Figure 4 This is the route planning diagram of the A* algorithm in Experiment 1.

[0061] Figure 5 Improved A* algorithm route planning diagram for Experiment 1.

[0062] Figure 6 This is the initial distribution diagram of Experiment 2.

[0063] Figure 7 This is the route planning diagram of the A* algorithm in Experiment 2.

[0064] Figure 8 Improved A* algorithm route planning diagram for Experiment 2. DETAILED DESCRIPTION

[0065] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, these 8 embodiments are only used to illustrate the present invention and are not used to limit the scope of the present invention. In addition, it should be understood that after reading the content taught by the present invention, those skilled in the art make various changes or modifications to the present invention, and these equivalent forms also fall within the scope defined by the claims attached to this application.

[0066] 1. Wargame Environment

[0067] Multi-operator collaborative path planning is affected by many factors, including topography, operator mobility, enemy deployment location, friendly force distribution, etc. In war game simulation, these factors are directly related to the speed and safety of operator mobility and need to be fully considered.

[0068] The operator's field of view is affected by factors such as terrain, objects, and distance. The weapons carried by operators have different ranges. Operators can only damage operators that are both in their field of view and range. Each damage can only target one operator. Multiple operators in the same grid will increase the damage effect, and there is a cooling interval between two attacks on each operator.

[0069] In the actual simulation process, operators are often required to control multiple operators to reach the predetermined location in the shortest time. This process needs to consider reducing the attack of enemy combat operators on our side, and reach the preset destination from the preset starting point at the fastest speed and in a way that maximizes the retention of manpower. Within the specified time, the earlier the destination is reached and the more operators can reach the destination, the better the task is considered to be completed. During the simulation process, enemy operators score by damaging our operators, and our operators score based on the time taken to cross the danger zone and the residual value. At the same time, the simulation has a task time limit, and operators that exceed the time limit and fail to reach the target point will not score.

[0070] The war game simulation environment is often composed of hexagonal grids. Different hexagonal grids contain different information, including terrain, facilities, etc. Terrain represents the relative height of the location relative to the lowest point in the map, which affects the operator's mobility, observation, and firepower attack, etc. Common terrain features include forests, waters, soft land, roads, and railways. Special terrain features will have a certain impact on the operator's actions, such as reducing the speed of travel, changing the observation distance, and reducing the attack effect. Facilities are artificial conditions set in a certain area to achieve the purpose of confrontation, including roadblocks, indirect artillery fire areas, minefields, etc., which affect the operator's mobility, etc.

[0071] 2. The collaborative path planning method proposed in the present invention

[0072] (1) Basic principles of the A* algorithm

[0073] The A* algorithm combines heuristic search and conventional search. It is an extension of the Dijkstra algorithm and is widely used in path planning problems. While ensuring that the shortest path is found, it is guided by heuristic information and effectively prunes redundant nodes to reduce the search space and improve search efficiency.

[0074] At present, the A* algorithm is the most commonly used and efficient path planning algorithm in war games, and is applicable to hexagonal grid environments. In war games, each hexagonal grid is a spatial node. The A* algorithm constructs an evaluation function f(k) for the spatial node k to find the lower limit of the path cost passing through the node. The function to be evaluated consists of two parts, and its general expression is:

[0075] f(k)=g(k)+h(k) (3)

[0076] Where g(k) represents the minimum actual cost required to reach spatial node k from the starting node, and h(k) represents the estimated cost from spatial node k to the target node, that is, the lower limit of the cost from spatial node k to the target node.

[0077] The A* algorithm takes the point with the minimum current evaluation function as the center, expands the search to the surrounding adjacent nodes, and continuously iterates the search for new spatial nodes until the target node is found.

[0078] The estimated cost h(k) is used as heuristic information, and is generally represented by Euclidean distance or Manhattan distance. In a hexagonal grid environment, the position of each grid is represented by the coordinates (x, y). The minimum number of hexagonal grids required to pass from spatial node k to the target node is taken as the estimated cost h(k), as shown in formula (2):

[0079]

[0080] Where x and y are the horizontal and vertical coordinates of the Cartesian coordinate system of the node respectively; q d ,r d ,s d Respectively represent the coordinates of the cube coordinate system corresponding to the target node, q k ,r k ,s k They respectively represent the coordinates of the cube coordinate system corresponding to the spatial node k.

[0081] (2) Improved A* algorithm

[0082] In war games, multiple operators crossing a danger zone require coordination in both time and space. In the time dimension, operators should be prevented from appearing alternately in the enemy's field of vision to reduce the number of times the enemy's operators are damaged; in the space dimension, multiple operators should be prevented from being in the same grid to reduce the damage effect of the enemy's operators.

[0083] Based on this, in order to achieve the coordination of multi-operator maneuvers in the hexagonal grid network, the following concepts are introduced:

[0084] ①Build time node

[0085] The evaluation function constructed by the traditional A* algorithm for each spatial node does not contain any time information. Therefore, it can neither accurately evaluate the damage cost paid by the operator passing through the spatial node k, nor can it support multi-operator collaborative planning.

[0086] To solve the above problems, the present invention proposes the concept of time node, which is used to replace the original space node. A hexagonal grid corresponds to multiple time nodes, which are used to indicate the spatial position of the operator at a certain moment. The time node contains two kinds of information, namely, the time sequence number t of the current node and the time sequence number t of the current node. k , the hexagonal grid k where the node is located.

[0087] Due to the terrain, different types of operators spend different times crossing different hexagonal grids. Therefore, their common factor is taken as the time node period T, so that the time for an operator to pass through any hexagonal grid can be expressed by an integer number of time node periods, as shown in formula (3):

[0088] t m (k) = r m *T r m ∈N* (5)

[0089] Where, t m represents the time required for the operator to traverse a hexagonal grid with a terrain of m; r m It represents the number of time nodes that the operator needs to go through to cross the hexagonal grid with a terrain of m.

[0090] By selecting the time node period T, it is ensured that the information at every moment during the maneuvering process is recorded in the time node.

[0091] Therefore, the time sequence number of the time node entering hexagonal grid k is:

[0092]

[0093] In the formula, r i Indicates the number of time nodes required to cross the i-th hexagonal grid in the shortest path from the starting point to hexagonal grid k.

[0094] ②Actual cost function

[0095] In the traditional A* algorithm, only the path length is considered. However, in the actual context of crossing a dangerous area, time and safety factors need to be considered comprehensively.

[0096] The present invention takes time and security into consideration and constructs an actual cost function. The actual cost function constructed for a single operator is as follows:

[0097] g(k)=α*ξ(k)+(1-α)*c(k)α∈[0,1](5)

[0098] Where α represents the weight of the time cost, which is adjusted according to the time urgency of crossing the danger zone; ξ(k) represents the time cost from the starting node to node k, which can be expressed by the number of time nodes experienced, that is, ξ(k) = t k , when the number of time nodes exceeds the limit, the time cost becomes infinite; c(k) represents the damage cost from the starting node to node k.

[0099] The damage cost of each path is calculated by the damage cost c at each time node. i Composition, c i The expression is as follows:

[0100]

[0101]

[0102] In the formula, is the expected damage caused by the enemy operator e to multiple operators at time i, and is related to the position of the own operator Enemy operator position n, own operator type Enemy operator type j e , Estimated HP of your counter The enemy counter e's health b e related.

[0103] ③Coordinate rotation

[0104] The objective function of multi-operator collaborative path planning is:

[0105] J=minf(L 1 ,L 2 …L n ) (7)

[0106] Among them, f(L 1 ,L 2 …L n ) is the multi-operator path planning cost, which means that the total actual cost function must be minimized. It is related to the path L of n operators. 1 ,L 2 …L n It is an n-dimensional optimization problem, and the traditional A* algorithm is difficult to solve this problem.

[0107] In order to reduce the computational cost and the number of nodes, the coordinate rotation method is used to transform the multi-dimensional optimization problem (Formula 7) into a one-dimensional optimization problem:

[0108] J=minf(L i ,L i + ) (8)

[0109] Among them, L i+ is the path of operators other than the i-th operator, and is regarded as a fixed value in each optimization.

[0110] Theorem 1: When the cost function is determined, the result after the mth iteration is no worse than any previous iteration result.

[0111] The proof of the theorem is as follows:

[0112] prove

[0113] Assume the cost function before the pth iteration is f(L i ,L i + ) p-1 , the cost function before the pth iteration is f(L j ,L j + ) p , due to L i There are a finite number of possible values, so there exists L i p* So that:

[0114] f(L i ,L i + ) p-1 ≥f(L i p* ,L i + ) p-1

[0115] make

[0116] but

[0117] so,

[0118] J=f(L j ,L j + ) p =f(L i ,L i + ) p-1 ≤f(L i ,L i + ) p-2 ≤…≤f(L 1 ,L 1 + ) 1 ≤f(L 1 ,L 2 …L n )

[0119] Therefore, Theorem 1 holds. The proof is complete.

[0120] From Theorem 1, we can see that this algorithm can converge to the optimal solution or the local optimal solution, which ensures the effectiveness of multi-operator collaborative path planning.

[0121] ④Algorithm process

[0122] The present invention proposes a multi-operator collaborative path planning method based on a war game platform. Figure 1 As shown, it includes the following steps:

[0123] Step 1: Define the old list to store the path data of all operators before the latest round of optimization; and define the new list to store the updated path data of all operators;

[0124] Step 2: Plan the optimal route for each operator as the initial route and put it into the new list. Preferably, the traditional A* algorithm in the prior art can be used to plan the initial route for the operator;

[0125] Step 3: Initialize the number of training rounds i = 1;

[0126] Step 4: Delete the path data of all the original operators in the old list, save the path data of the new list into the old list, and initialize the operator number j = 1;

[0127] Step 5: Remove the path data of operator j in the new list, optimize and update the path of operator j using the improved A* algorithm based on the remaining data of other operators, and store the updated path data back into the new list;

[0128] Step 6: Determine whether all operators have completed the i-th round of updates. If so, proceed to step 7. If not, j=j+1 and proceed to step 5.

[0129] Step 7: Traverse each value in the new list and the old list, and determine whether the operator path information in the new list and the old list is the same through string comparison, or whether the preset number of update rounds has been reached. If so, the path update is completed, otherwise, set i=i+1 and go to step 4.

[0130] The update process of the operator update method (improved A* algorithm) described in step 5 is as follows: Figure 2 First, construct a time node, which contains two types of information: the time sequence number of the current node, t k, the hexagonal grid k where the node is located; secondly, set the open list and the close list: the open list includes all the time nodes to be examined. The hexagonal grids where these time nodes are located may become the hexagonal grids in the optimal path of the operator, but they still need to be evaluated later; the close list includes all the hexagonal grids that have completed the evaluation. The minimum cost from the initial node to the node in the close list has been determined and no additional evaluation is required.

[0131] The estimated cost consists of the actual cost and the cost to be estimated. The cost to be estimated is the distance from the hexagonal grid where the node is located to the target point. The actual cost consists of three parts. The first part is the time cost, which is determined by the time from the starting moment to the current moment. The second part is the damage cost, which is determined by the attack suffered by all friendly operators from the starting moment to the current moment. The third part is the overlapping cost, which is caused by the fact that the friendly operator being attacked is in the same grid as other friendly operators during the time period from the starting moment to the current moment.

[0132] Specifically, the specific steps of step 5 include:

[0133] Step 5.1: Determine the time interval T according to the types of all operators, where the types of operators include combat vehicles, unmanned combat vehicles, tanks, infantry, unmanned aerial vehicles, and helicopters;

[0134] Since each operator has a time value across each hexagonal grid, the time interval T can be determined by taking the common factor of all values;

[0135] Step 5.2: Define and initialize the open list and close list;

[0136] Step 5.3: Put the time node of the initial time of the i-th operator into the open list;

[0137] Step 5.4: Determine whether the open list is empty. If so, the path planning of operator i fails and cannot reach the target point. If not, there is a time node in the open list, and go to step 5.5.

[0138] Step 5.5: Select a time node with the smallest estimated cost f from the open list, delete it from the open list, and move the time node to the close list;

[0139] Step 5.6: Find the time node set A corresponding to the next moment of the time node moved into the close list in step 5.5, select the time node that has not been judged yet from the time node set A, and go to step 5.7;

[0140] The time node set of the next moment is the spatial position that the node can reach at the next moment. The time node set is constructed by judging whether the node can reach the next moment grid. When judging, if any grid cannot be reached, the time node set includes the current hexagonal grid of the next moment; if a grid can be reached, the time node set includes the grid of the next moment.

[0141] Step 5.7: Determine whether the time node selected in step 5.6 is in the close list based on the time serial number of the time node and the hexagonal grid where it is located. If so, proceed to step 5.10; if not, proceed to step 5.8;

[0142] Step 5.8: Determine whether the time node selected in step 5.6 is in the open list based on the time serial number of the time node and the hexagonal grid where it is located. If not, proceed to step 5.9; if yes, update the relevant information of the time node and proceed to step 5.10;

[0143] Step 5.9: Add the time node selected in step 5.6 to the open list and update the relevant information of the time node;

[0144] The relevant information of the node to be updated includes: ① the time span t from the moment of entering the hexagonal grid where the time node is located to the current moment of the time node; ② the actual cost g that has been incurred to reach the time node; ③ the estimated cost f to reach the target point after passing the time node;

[0145] Step 5.10: Determine whether all nodes in the time node set A have been judged. If so, proceed to step 5.11. If not, proceed to step 5.6.

[0146] Step 5.11: Determine whether each time node in the time node set A is a target node. If it is a target node, obtain the route of operator i through backtracking, complete the path optimization, and output the planned path; if not, go to step 5.5.

[0147] Example 1

[0148] The effectiveness of the proposed method is verified on the "Miaosuan·Land War Commander" platform. In the same environment, path planning experiments with and without coordination are carried out respectively, and the time cost and damage cost are compared to verify the effectiveness of coordination.

[0149] In order to verify the effectiveness of the collaborative algorithm, three groups of experiments and two experimental scenarios were set up. In each experimental environment, three red operators were set up to perform the task of crossing the danger zone, and three blue operators were set up to perform the interception and destruction mission.

[0150] Experiment 1 was conducted in scenario 1. The time limit for the operator to reach the target point was 800s. The information settings of the red and blue operators and the target point in scenario 1 are shown in Table 1. Figure 3 The spatial relationship between the red and blue operators at the initial positions is intuitively shown in the figure. The observation range of the blue operator basically covers the shortest path for the red operator to reach the target point.

[0151] Table 1 Initial position distribution of operators in Experiment 1

[0152]

[0153] In Experiment 1, two strategies, no coordination and multi-operator coordination, were used for path planning. The path planning results are shown in the following table. Figure 4 , Figure 5 As shown in the figure. In the uncoordinated planning route, the red operator is affected by the starting position and disperses through the danger zone, entering the attack range of different blue operators respectively. Red operator 2 and red operator 3 both choose to take a detour to reduce the time exposed to the damage range of the blue operator. In the coordinated planning, the red operators are close to each other and concentrate on crossing the danger zone. In the time dimension, they distinguish the front and back to avoid stacking and reduce the damage cost. Table 2 shows the time cost and the number of attacks by the blue operator under the two planning methods. From the time dimension, the coordinated planning route shortens the maneuvering time of the red operator, and the total time is shortened by 11.6%; from the safety dimension, the red operator in the uncoordinated planning was attacked by blue operator 2 and blue operator 3, and the number of attacks reached 8 times. The red operator in the coordinated planning was only attacked by blue operator 2. The red operator made full use of the firepower vacuum period of the blue operator, reduced detours, quickly crossed the danger zone, and achieved tactical cover avoidance.

[0154] Table 2 Experiment 1 Path Planning Time Cost Table

[0155]

[0156] Example 2

[0157] Experiment 2 was conducted in scenario 2. The time limit for the operator to reach the target point was 800s. Table 3 shows the information settings of the red and blue operators and the target point in scenario 2. Figure 6 The spatial relationship between the red and blue operators at the initial positions is intuitively shown.

[0158] Table 3 Initial position distribution of operators in Experiment 2

[0159]

[0160] Figure 7 The path without collaborative planning in Experiment 2 is demonstrated. The red operator crosses the danger zone according to the individual optimal path and is damaged by all the blue operators. Among them, the red operator 1 is damaged by two blue operators. Figure 8 The path of collaborative planning in Experiment 2 is shown. Red Operator 1 and Red Operator 3 move closer to each other and pass through the danger zone in coordination. The time and damage details of Experiment 2 can be seen in Table 4. The use of collaborative planning shortens the total time by 12.5%. The time cost of Red Operator 1 increases slightly, while the time costs of the other Red Operators are greatly reduced. The Red Operator successfully avoids the damage range of Blue Operator 1 and is only damaged by two Blue Operators. Due to time constraints, Red Operator 2 is difficult to coordinate, and the other Red Operators achieve mutual tactical cover and avoidance and coordinate to pass through the danger zone.

[0161] Example 3

[0162] Experiment 3 was conducted in scenario 1, and a total of 7 groups of comparative experiments were set up to verify the impact of task time requirements on collaboration. The time data and damage data of Experiment 3 are recorded in Table 4 and Table 5 respectively. Analysis of the data in Table 4 and Table 5 shows that when the task time is too tight, the operator can only move along the shortest path, the route is fixed, and collaboration is impossible; when there is no time limit, the operator can avoid being hit by spending a lot of time detouring, and there is no need for collaboration; but in most cases, the task has appropriate time requirements. At this time, collaborative planning can reduce both the time cost and the damage cost.

[0163] Table 4 Time cost table of experiment three

[0164]

[0165] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A multi-operator collaborative path planning method based on a war game platform, characterized in that: The following steps are involved: Step 1: Obtain actual task information and construct a hexagonal grid map, where one hexagonal grid corresponds to multiple time nodes; Step 2: Construct the objective function of multi-operator collaborative path planning: J=minf(L i ,L i + ) Among them, L i + is the path of other operators except the i-th operator, which is regarded as a fixed value in each optimization; Step 3: Plan the initial path for each operator; Step 4: Perform i rounds of optimization updates on each operator through the improved A* algorithm and output the collaborative planning path.

2. A multi-operator collaborative path planning method based on a war game platform as claimed in claim 1, characterized in that: The time node includes two types of node information, namely the time sequence number of the current node t k , the hexagonal grid k where the node is located.

3. The multi-operator collaborative path planning method based on a war game platform as claimed in claim 1, characterized in that: The specific steps of step 4 are as follows: Step 4.1: Define and initialize the old list and the new list, and store the initial path planned in step 3 in the new list; Step 4.2: Initialize the number of training rounds i = 1; Step 4.3: If the old list stores the path data of the operators before the latest round of optimization, delete the path data of all the original operators in the old list, save the path data of the new list to the old list, and initialize the operator number j = 1; Step 4.4: Delete the path data of operator j in the new list, optimize and update the path of operator j using the improved A* algorithm based on the remaining data of other operators, and store the updated path data back into the new list; Step 4.5: Determine whether all operators have completed the i-th round of updates. If so, proceed to step 4.

6. If not, set j=j+1 and proceed to step 4.

4. Step 4.6: Traverse the new list and the old list, and determine whether the operator path information in the new list and the old list is the same through string comparison, or whether the number of training rounds i reaches the preset update round number. If the path information is the same or the maximum update round number has been reached, the i-th round path update is completed, otherwise, set i=i+1 and go to step 4.

3.

4. The multi-operator collaborative path planning method based on a war game platform as claimed in claim 2, characterized in that: The modified A* algorithm described in step 4.4 includes the following steps: Step 4.4.1: Construct time node; Step 4.4.2: Determine the time interval T according to the types of all operators, and obtain the time t required for the operator to cross the hexagonal grid with terrain m by the following formula: m (k): t m (k)=r m *T r m ∈N* (1) Among them, k represents the hexagonal grid where the time node is located; r m It represents the number of time nodes that the operator needs to go through to cross the hexagonal grid with a terrain of m; Step 4.4.3: Define and initialize the open list and close list; Step 4.4.4: Put the time node of the initial moment of the i-th operator into the open list; Step 4.4.5: Determine whether the open list is empty. If so, the path planning of operator i fails and cannot reach the target point. If not, there is a time node in the open list, and go to step 4.4.

6. Step 4.4.6: Select a time node with the smallest estimated cost from the open list, delete it from the open list, and store the time node in the close list; Step 4.4.7: Find the time node set A at the next moment corresponding to the time node stored in the close list in step 4.4.6, select the time node that has not yet completed the evaluation from the time node set A, and go to step 4.4.8; Step 4.4.8: Based on the time sequence number t of the time node k and the hexagonal grid k where it is located to determine whether the time node of the unfinished evaluation selected in step 4.4.7 is in the close list. If so, proceed to step 4.4.

10. If not, proceed to step 4.4.

9. Step 4.4.9: Based on the time sequence number t of the time node k and the hexagonal grid k where it is located to determine whether the time node selected in step 4.4.7 for the unfinished evaluation is in the open list. If not, proceed to step 4.4.10; if so, update the relevant information of the time node and proceed to step 4.4.11; Step 4.4.10: Add the time node selected in step 4.4.7 to the open list and update the relevant information of the time node; Step 4.4.11: Determine whether all nodes in the time node set A have been judged. If so, proceed to step 4.4.

12. If not, proceed to step 4.4.

7. Step 4.4.12: Determine whether the spatial position information of all time nodes in the time node set A is the target point. If it is the target node, obtain the route of operator i through backtracking, complete the path optimization, and output the planned path; if not, go to step 4.4.

6.

5. The multi-operator collaborative path planning method based on a war game platform as claimed in claim 4, characterized in that: The node-related information updated in steps 4.4.9 and 4.4.10 includes: 1) Time serial number of the time node In the formula, r i Indicates the number of time nodes required to cross the i-th hexagonal grid in the shortest path from the starting point to hexagonal grid k; 2) The actual cost of reaching the node g(k)=α*ξ(k)+(1-α)*c(k) α∈[0,1] In the formula, α represents the weight of the time cost; ξ(k) represents the time cost from the starting node to node k, which is represented by the number of time nodes experienced, that is, ξ(k) = t k , when the number of time nodes exceeds the limit, the time cost becomes infinite; c(k) represents the damage cost from the starting node to node k; And the damage cost c at each time node in c(k) i for: In the formula, represents the expected damage caused by the enemy operator e to multiple operators at time i; represents the position of one's own operator; n represents the position of the enemy operator; Indicates the operator type of the own side; j e Indicates the enemy operator type; Indicates the estimated health of the own counter; b e Indicates the health of the enemy operator e; 3) The estimated cost of reaching the target point after passing this time node f(k)=g(k)+h(k) Where h(k) represents the estimated cost from spatial node k to the target node, that is, the lower limit of the cost from spatial node k to the target node; and: Where x and y are the horizontal and vertical coordinates of the Cartesian coordinate system of the node respectively; q d ,r d ,s d Respectively represent the coordinates of the cube coordinate system corresponding to the target node, q k ,r k ,s k They respectively represent the coordinates of the cube coordinate system corresponding to the spatial node k.

Images