A multi-priority dynamic coverage-oriented unmanned aerial vehicle cruise path planning method

Abstract

This invention discloses a UAV patrol path planning method for dynamic coverage with multiple priorities. First, the detection priorities of different parts of a region are sorted according to traversal period constraints, with high-frequency patrol detection for key areas and low-frequency patrol detection for general areas. Second, based on the priority sorting, a series of cyclical patrol path planning schemes are recursively constructed using a stochastic optimization algorithm, ensuring dynamic coverage of the region while satisfying the corresponding traversal period constraints. Finally, the patrol path planning schemes are analyzed and evaluated from the perspectives of redundancy and priority, outputting the optimal planning scheme. Compared with traditional path planning methods, this invention performs cyclical patrol detection according to priority, enabling focused dynamic coverage of the entire region, effectively improving the efficiency of UAV cooperative patrol detection, and accurately grasping regional changes. Furthermore, this invention can adaptively adjust the cooperative patrol path according to priority changes, efficiently utilizing UAV detection resources and flexibly adapting to changes in dynamic coverage requirements.

Description

Technical Field

[0001] This invention relates to unmanned aerial vehicle (UAV) cruise path planning, specifically to a UAV cruise path planning method for multi-priority dynamic coverage. Background Technology

[0002] Traditional UAV cooperative reconnaissance trajectory planning methods for static area coverage, under the premise of satisfying certain performance indicators, avoid obstacles and threat sources and plan the optimal flight route that can traverse the coverage area. The number of times the entire area is traversed is usually 1. For example, Berger et al. assigned scanning tasks to each UAV based on the differences in capabilities between the platform and the sensors, achieving effective scanning trajectory planning (BERGER C, WZOREK M, KVARNSTRÖMJ, et al. Area coverage with heterogeneous UAVs using scan patterns[C], 2016 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), Lausanne, Switzerland, 2016); Wang Ziliang et al. proposed an effective planning algorithm to assist UAVs in autonomously completing the coverage search of a given area (Wang Ziliang, Luo Delin, Wu Shunxiang, UAV trajectory planning method for concave polygon area coverage[J], Aviation Weapons, 2019, 26(1): 95–100); Zhang Xiaomeng et al. proposed an improved method for multi-UAV coverage trajectory planning based on region decomposition, zigzag scanning method and shape turning method (Zhang Xiaomeng, Hu Yongjiang, Li Wenguang et al.). An Improved Multi-UAV Coverage Track Planning Method [J], Journal of Ordnance Equipment Engineering, 2020, 41(10): 21-221. However, due to the dynamic complexity of the area, such as the movement of detection targets and the spread of fire, a single traversal is insufficient to grasp the dynamic changes of the area, especially the development and changes of key parts. Summary of the Invention

[0003] Purpose of the invention: To address the above-mentioned shortcomings, this invention provides a UAV cruise path planning method that focuses on cyclical cruise detection of different parts of a region and can flexibly and efficiently grasp the dynamic changes of the region, providing multi-priority dynamic coverage.

[0004] Technical Solution: To solve the above problems, this invention adopts a UAV cruise path planning method for multi-priority dynamic coverage, including the following steps:

[0005] (1) Divide the cruise area into grids to obtain several cruise squares, number the cruise squares and obtain the traversal period of each cruise square.

[0006] (2) Sort the cruise squares from shortest to longest according to their traversal period. If the traversal periods are the same, sort them from smallest to largest according to their cruise square numbers, thus obtaining the priority sort of the cruise squares.

[0007] (3) Based on the current cruise path planning scheme, take the cruise grid with the highest priority and the empty set of the traversal set as the first priority coverage grid, and plan the cruise path for the priority coverage grid: obtain other cruise grids within half a traversal cycle from the priority coverage grid as candidate cruise grids, and plan several candidate cruise paths that can cover the priority coverage grid according to the priority coverage grid and the candidate cruise grids.

[0008] (4) Based on several candidate cruise paths, depth-first recursion is performed according to priority order to recursively explore subsequent priority coverage squares and several candidate cruise paths that cover the squares, and find a cruise path planning scheme that can cover all cruise squares.

[0009] (5) Evaluate all cruise path planning schemes, output the optimal cruise path planning scheme, and conduct dynamic periodic cruises based on the optimal cruise path planning scheme.

[0010] Furthermore, the cruise area includes a no-fly zone and a cruise zone, and the cruise zone is divided into a grid to obtain a cruise grid.

[0011] Furthermore, the higher the cruise priority of the cruise grid, the shorter the corresponding traversal period, and the traversal period is an even number of time steps. Within each time step, the travel distance of each UAV is one cruise grid.

[0012] Furthermore, a shortest path distance matrix is ​​constructed for the cruise area after grid division. With the shortest path set matrix In step (3), based on the shortest path distance matrix With the shortest path set matrix Other cruise squares whose distance from the priority coverage square is within half a traversal period are obtained as candidate cruise squares.

[0013] The shortest path distance matrix The elements in Indicates the cruise grid and cruise grid The shortest cruise path length between;

[0014] The shortest path set matrix The elements in Indicates the cruise grid and cruise grid The set of shortest paths between.

[0015] Furthermore, in step (3), when planning several candidate cruise paths within the candidate cruise grid, the first... The optimal candidate cruise path for each priority coverage square, where... To explore the threshold;

[0016] The objective function and constraints for selecting candidate cruise paths are as follows:

[0017]

[0018]

[0019] in, For the first The set of cruise squares surrounded by candidate cruise paths. For passing through the cruise grid The set consisting of cruise route numbers, It is a rounding function. For the cruise grid The traversal period, To prioritize covering the grid The traversal period, For the first The number of the first cruise square traversed by the candidate cruise path. For the first The candidate cruise path passed through the first The number of each cruise square, To prioritize covering the grid The number, For the first Candidate cruise paths, For the first The length of each candidate cruise path.

[0020] Furthermore, in step (3), a stochastic optimization algorithm is used when planning several candidate cruise paths within the candidate cruise grid.

[0021] Furthermore, the evaluation of all cruise route planning schemes includes redundancy assessment and priority assessment. The calculation formula for redundancy assessment is as follows:

[0022]

[0023] in, For cruise route planning scheme Redundancy score, cruise path Path length, This represents the total number of patrol squares;

[0024] The formula for calculating the priority assessment is as follows:

[0025]

[0026] in, For cruise route planning scheme Priority score, For the cruise grid The lower the score, the higher the priority during the traversal cycle.

[0027] Furthermore, the cruise path planning scheme with the lowest redundancy score is selected as the optimal cruise path planning scheme. If there are multiple cruise path planning schemes with the lowest redundancy scores, the cruise path planning scheme with the lowest priority score is selected as the optimal cruise path planning scheme. The number of cruise paths in the optimal cruise path planning scheme is the number of UAVs required for the cruise.

[0028] The present invention also employs a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above method.

[0029] The present invention also employs a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above method.

[0030] Beneficial effects: Compared with the prior art, the significant advantages of this invention are: (1) It can perform cyclical patrol detection according to priority, which can dynamically cover the entire area with focus, effectively improve the efficiency of UAV cooperative patrol detection, and accurately grasp the changes in the area; (2) It can adaptively adjust the cooperative patrol path according to the priority change, make efficient use of unmanned detection resources, and flexibly adapt to the changes in dynamic coverage requirements. Attached Figure Description

[0031] Figure 1 This is a flowchart of the cruise path planning method of the present invention;

[0032] Figure 2 This refers to the drone cooperative patrol area in an embodiment of the present invention;

[0033] Figure 3 Fang Ge is an example of an implementation of this invention. Candidate cruise areas;

[0034] Figure 4This is the optimal cruise path planning scheme output in the implementation case of this invention. Detailed Implementation

[0035] like Figure 1 As shown in this embodiment, a UAV cruise path planning method for multi-priority dynamic coverage is presented. The UAV cooperative cruise area includes two parts: a no-fly zone and a cruise zone. The cruise zone is divided into a grid, wherein the cruise zone is composed of... It consists of interconnected squares, each square being a cruise square, denoted as _____. , … ; square grid ( The traversal period of ) is denoted as Each time step has a priority level, with higher priority levels resulting in shorter traversal periods and lower priority levels resulting in longer traversal periods. The traversal period is always an even number of time steps. Within each time step, each UAV travels one square, and its flight direction is... shaft or Axis; Drone patrol path planning for multi-priority dynamic coverage: Drone patrol path planning ensures that each grid cell is visited cyclically according to its traversal cycle, allowing for more flexible and accurate understanding of dynamic changes in the area. The specific steps for drone patrol path planning are as follows:

[0036] Step 1: Model the shortest path for the cruise area after grid division: Construct the shortest path distance matrix. With the shortest path set matrix Specifically, it includes:

[0037] Step 1.1, Constructing the Shortest Path Distance Matrix: Shortest path distance matrix of dimension The elements in the shortest path distance matrix Indicates a pair of squares The shortest cruise path length between, where , The calculation is performed using dynamic programming (see Shi Shaojian, Research on Dynamic Programming Algorithm [J], Computer Knowledge and Technology, 2020, (18): 48-49, which will not be repeated in this embodiment). Assuming the grid... square Neighbors Then the squares are The shortest path length between them is equal to the grid. and square Shortest path length With squares and square Shortest path length The minimum value of the sum is shown in the following formula;

[0038] (1)

[0039] Step 1.2, Constructing the Shortest Path Set Matrix: dimensional shortest path set matrix The elements in the shortest path set matrix Indicates a pair of squares The set of shortest paths between, where , Since the same shortest path length may correspond to multiple shortest paths, Similarly, dynamic programming is used to find the neighbor squares traversed by the shortest path. Thus, the grid pairs are obtained. The shortest path between them is:

[0040] (2)

[0041] Step 2, Cruise Path Planning Initialization: Cruise path planning initialization includes global element initialization such as cruise path exploration threshold setting, grid coverage priority sorting, and planning scheme set initialization, as well as recursive element initialization such as grid index initialization, grid coverage matrix initialization, and current planning scheme initialization. Specifically, it includes:

[0042] Step 2.1, Setting the cruise path exploration threshold: Set the exploration threshold. This indicates that for each square, only the previous squares that have been cycled through that square according to their traversal period are explored. The optimal cruise path;

[0043] Step 2.2, Grid Coverage Priority Sort: Grid coverage refers to a cruise path repeatedly passing through a grid, with a cycle period less than or equal to the grid's traversal period, and no unvisited grids within the cruise path's enclosed area. Priority sorting refers to sorting the grids by their traversal periods, prioritizing the coverage of grids with shorter traversal periods when constructing the cruise path. Specifically, the grids to be traversed... The squares are sorted in ascending order of their traversal period. If the traversal periods are the same, they are sorted in ascending order of their square numbers. This yields a square-coverage-first sorting algorithm. ,satisfy Subsequent cells will be sorted in this order and prioritized for covering cells with shorter traversal cycles.

[0044] Step 2.3, Initialization of the planning scheme set: Constructing the planning scheme set. Solution set Each element in the set represents a cruise path planning scheme, and each cruise path planning scheme is a set of cruise paths that satisfy the grid coverage requirement. Initialize to an empty set, i.e. ;

[0045] Step 2.4, Grid Index Initialization: Create the grid index. , indicating priority sorting in grid coverage. The starting exploration index is initialized to 1 because squares with shorter traversal cycles are explored first.

[0046] Step 2.5, Initialization of the grid covering matrix: Construction dimensional square covering matrix ,matrix Each element in For passing through the square The set consisting of cruise route numbers, 1, 2, ... The cruise path number is the number of the grid cell that the path preferentially covers, and the grid coverage matrix. All elements in the set are initialized to an empty set, i.e. ;

[0047] Step 2.6, Initialize the current planning scheme: Current cruise path planning scheme The plan indicates that... Let be a set consisting of several cruise paths that satisfy the grid coverage requirement, initialized as an empty set. ;

[0048] Step 3: Recursive exploration of planning schemes: Current circuit path planning scheme Based on the grid index Corresponding squares Initially, based on the shortest path distance matrix... With the shortest path set matrix The algorithm performs a depth-first recursive exploration based on priority, exploring the previous cells that cover the current cell. Find the optimal cruising path, and recursively explore the next level of cruising path. The recursive exploration process of the planning scheme is denoted as... The specific sub-steps include 3.1-3.3;

[0049] Step 3.1, Candidate Cruise Area Location: [Identify the candidate cruise area and assign it a number.] square As the priority coverage square, obtain its traversal period. According to the shortest path distance matrix With the shortest path set matrix Location distance grid exist All squares within are squares Candidate cruise areas ;

[0050] Step 3.2, Candidate Cruise Path Mining: A stochastic optimization algorithm is used to select candidate cruise paths within the cruise area. Before the excavation Priority coverage squares The optimal candidate cruise path. , The constraints that candidate cruise paths must meet include: (1) Candidate cruise paths should prioritize coverage grids. Start, to prioritize covering the squares The end, that is (2) The length of the candidate cruise path is a grid. traversal period ,Right now (3) Assume the set of squares enclosed by the candidate cruise paths is denoted as Then the set All squares within the cell are on the candidate path, i.e. , The newly added squares are sets. In the path The optimization objective is to maximize the weighted sum of the traversal cycles of the newly added covered squares, which were not covered by other cruise paths before the coverage. ,Right now

[0051]

[0052] (3)

[0053] Since the selected priority coverage squares are sorted from shortest to longest traversal period, all squares traversed by the candidate cruise path are either covered by previous cruise paths or covered by the current cruise path, and the cycle period can meet the traversal period constraint requirements of the square.

[0054] Step 3.3, Candidate Cruise Path Recursion: For each preceding... One optimal candidate cruise path , Perform the following sub-steps 3.3.1-3.3.5 respectively:

[0055] Step 3.3.1: Update the current planning scheme: Update the current patrol route planning scheme and add candidate patrol routes. ,Right now ;

[0056] Step 3.3.2, Grid Coverage Matrix Update: For candidate cruise paths After passing through all squares, update their traversal set in the square covering matrix, adding priority-covered squares to the traversal set. number ,Right now , , ;

[0057] Step 3.3.3, Grid Index Update: Update the grid index to the index of the grid that is the next empty set in the traversal, denoted as . ,satisfy and When all the sets corresponding to the squares are not empty, update the square index as follows: ;

[0058] Step 3.3.4, Grid Index Judgment: If the grid index satisfies... This indicates that all squares have been covered by the cruise path, and there is no need to perform the next level of recursion, thus updating the cruise path planning scheme set. If the current level of candidate cruise path recursion process ends, return to the previous step; otherwise, continue to the next step.

[0059] Step 3.3.5, Next Level Exploration: Continue recursively mining candidate cruise paths at the next level. That is, planning schemes for each circuit route. All of them return to step 3 to continue the next level of cruise path mining.

[0060] Step 4: Determine the planning scheme set. If the value is empty, output "No cruise planning scheme found" and end the process; otherwise, continue to step 5.

[0061] Step 5: Evaluation of Planning Schemes: Collection of Planning Schemes The various planning schemes in It is a set consisting of several cruise paths, and the scheme Each cruise path This covers several squares, and redundancy and priority assessments are performed for each planning scheme. Sub-steps include 5.1 and 5.2:

[0062] Step 5.1, Redundancy Assessment: Calculate the redundancy of each planning scheme. The sum of the lengths of all cruise paths and the total number of squares. The ratio of these values ​​is used as the redundancy score, as shown in the following formula:

[0063] (4)

[0064] A lower score indicates less redundancy in the covered squares;

[0065] Step 5.2, Priority Assessment: Calculate the priority of each planning scheme. The average traversal period of the squares covered by the inner cruise path is used as a priority score, as shown in the following formula:

[0066] (5)

[0067] A lower score indicates a shorter average traversal period for the covered squares, and a higher priority.

[0068] Step 6: Output the optimal planning scheme: If there is only one planning scheme with the lowest redundancy, then select it as the optimal scheme, as shown in the following formula:

[0069] (6)

[0070] If there is more than one planning scheme with the lowest redundancy, then the set of planning schemes with the lowest redundancy is selected. The option with the highest priority is selected as the optimal planning solution, as shown in the following formula:

[0071] (7)

[0072] Calculate the optimal planning scheme The number of cruise routes, which is the number of drones required for the cruise, is shown in the following formula:

[0073] (8)

[0074] Output the optimal planning solution Number of drones required for patrol .

[0075] This invention proposes a UAV cruise path planning method for multi-priority dynamic coverage, which organizes UAVs to conduct collaborative cruise exploration of the area. Key areas are explored cyclically with a short traversal period, while general areas are explored cyclically with a long traversal period. This method can efficiently utilize UAV resources and flexibly grasp the dynamic changes in the area.

[0076] In this embodiment, eight squares are used as an example, with each square representing a patrol square. The UAV collaborative patrol area includes two parts: a no-fly zone and a patrol zone. The patrol zone is composed of... It consists of interconnected squares, denoted as _____. , … ,like Figure 2 As shown, the square and All of these are high-priority, important parts, and their traversal period is two time steps, grid. and All of these are medium priority parts, with a traversal period of 4 time steps; the other four squares... , , , For parts with lower priority, the traversal period is 6 time steps. Within each time step, each UAV travels a distance of 1 square, and its flight direction is... shaft or Axis. Drone patrol path planning for multi-priority dynamic coverage is completed, enabling each grid cell to be visited by the drone cyclically according to its traversal period. This allows for a more flexible and accurate understanding of dynamic changes in the area. The drone patrol path planning steps are as follows:

[0077] Step 1.1, Constructing the Shortest Path Distance Matrix: Shortest path distance matrix of dimension The elements in the shortest path distance matrix Indicates a pair of squares The shortest cruise path length between, where , The matrix was constructed using dynamic programming, and the results are shown in the table below:

[0078] Table 1 Shortest path distance matrix Build

[0079]

[0080] Step 1.2, Constructing the Shortest Path Set Matrix: dimensional shortest path set matrix The elements in the shortest path set matrix Indicates a pair of squares The set of shortest paths between, where , The shortest path set matrix is ​​shown in Table 2:

[0081] Table 2 Shortest Path Set Matrix Build

[0082]

[0083] Step 2, Cruise Path Planning Initialization: Cruise path planning initialization includes the initialization of global elements such as cruise path exploration threshold setting, grid coverage priority sorting, and planning scheme set initialization, as well as the initialization of recursive elements such as grid index initialization, grid coverage matrix initialization, and current planning scheme initialization. Its sub-steps include 2.1-2.6.

[0084] Step 2.1, Setting the cruise path exploration threshold: Set the exploration threshold. This means that for each grid, only the first two optimal cruising paths that cycle through the grid according to its traversal period are explored.

[0085] Step 2.2, Grid Coverage Priority Sort: Sort the grids to be traversed... The squares are sorted in ascending order of their traversal period. If the traversal periods are the same, they are sorted in ascending order of their square numbers. This yields a square-coverage-first sorting algorithm. ;

[0086] Step 2.3, Initialization of the planning scheme set: Constructing the planning scheme set. Solution set Each element in the set represents a cruise path planning scheme, and each cruise path planning scheme is a set of cruise paths that satisfy the grid coverage requirement. Initialize to an empty set, i.e. ;

[0087] Step 2.4, Grid Index Initialization: Create the grid index. , indicating priority sorting in grid coverage. The initial exploration index in the array, because it prioritizes traversing squares with shorter traversal periods, is initialized to 1. ;

[0088] Step 2.5, Initialization of the grid covering matrix: Construct an 8-dimensional grid covering matrix. ,matrix Each element in For passing through the square The set consisting of cruise route numbers, 1, 2, ..., 8, the cruise path number is the number of the priority coverage square of that path, and the square coverage matrix. All elements in the set are initialized to an empty set, i.e. ;

[0089] Step 2.6, Initialize the current planning scheme: Current cruise path planning scheme The plan indicates that... Let be a set consisting of several cruise paths that satisfy the grid coverage requirement, initialized as an empty set. ;

[0090] Step 3: Recursive exploration of planning schemes:

[0091] Step 3 （1） First-level candidate cruise path mining: Current cruise path planning scheme Based on the grid index Corresponding squares Initially, based on the shortest path distance matrix... With the shortest path set matrix Explore the area covering the square as needed. Find the optimal cruising path, and recursively explore the next level of cruising path. The recursive exploration process of the planning scheme is denoted as... Specifically, it includes the following;

[0092] Step 3.1 （1） Candidate cruise area location: number square As the priority coverage square, obtain its traversal period. According to the shortest path distance matrix With the shortest path set matrix Location distance grid exist All squares within are squares Candidate cruise areas ,like Figure 3 As shown;

[0093] Step 3.2 （1） Candidate cruise path mining: A stochastic optimization algorithm is used to select candidate cruise paths within the cruise area. One optimal candidate cruise path was identified. = The constraints that satisfy the candidate cruise path include: (1) The candidate cruise path prioritizes the coverage of the grid. Start, to prioritize covering the squares End, (2) The length of the candidate cruise path is a grid. The traversal period is 2, (3) the grid set of candidate cruise paths. If all squares within the region are on the candidate path, the weighted sum of the traversal cycles of the newly added covered squares is... ;

[0094] Step 3.3 （1） Candidate cruise path recursion: For the optimal candidate cruise path = The following sub-steps are executed recursively:

[0095] Step 3.3.1 （1）Update the current patrol route plan: Update the current patrol route plan and add candidate patrol routes. ,Right now ;

[0096] Step 3.3.2 （1） Grid coverage matrix update: for candidate cruise paths After passing through all squares, update their traversal set in the square covering matrix, adding priority covers to the traversal set. Number 1, as shown in Table 3:

[0097] Table 3 Grid Covering Matrix

[0098]

[0099] Step 3.3.3 （1） Grid index update: Update the grid index to the index of the next empty grid cell in the traversal set, denoted as . ;

[0100] Step 3.3.4 （1） Grid index judgment: Grid index does not satisfy Proceed to the next step;

[0101] Step 3.3.5 （1） Next level of exploration: Continue to explore candidate cruise paths at level 2. ;

[0102] Step 3 （2） Candidate cruise path recursion (L2): Current cruise path planning scheme Based on the grid index Corresponding squares Initially, based on the shortest path distance matrix... With the shortest path set matrix Using a stochastic optimization algorithm, two optimal candidate cruise paths were identified. For the first two optimal candidate cruise paths... and The weighted sum of the traversal periods of the newly added covered squares for the two candidate paths are as follows:

[0103]

[0104]

[0105] For the first two optimal candidate cruise paths, and The following steps are executed recursively:

[0106] Step 3-1（2） :against Update the current planning scheme to Update the grid covering matrix For candidate cruise paths After passing through all squares (2, 5, 8), update their traversal set in the square covering matrix, adding priority coverage to the traversal set. Number 2 is shown in Table 4 below:

[0107] Table 4 Grid Covering Matrix

[0108]

[0109] Update the grid index to Continue to explore candidate cruise paths at level 3. ;

[0110] Step 3-1 （3） Candidate cruise path recursion (L3): Current cruise path planning scheme Based on the grid index Corresponding squares Initially, based on the shortest path distance matrix... With the shortest path set matrix A random optimization algorithm was used to find one optimal candidate cruise route, prioritizing coverage of the grid squares. , Perform the following steps respectively:

[0111] against Update the current planning scheme to Update the grid covering matrix For candidate cruise paths After passing through all squares (3, 4, 5, 6, 7, 8), update their traversal set in the square covering matrix, adding priority coverage to the traversal set. Number 4 is shown in Table 5 below:

[0112] Table 5 Grid Coverage Matrix

[0113]

[0114] Update the grid indexes when all the corresponding traversal sets for each grid cell are not empty. Determine if the square index satisfies This indicates that all squares have been covered by the cruise path, and there is no need to perform the next level of recursion, thus updating the cruise path planning scheme set. Return to level 2;

[0115] Step 3-2（2） For another optimal candidate cruise path at the second level Continue to target Update the current planning scheme to Update the grid covering matrix For candidate cruise paths After passing through all squares (2, 5, 4), update their traversal set in the square covering matrix, adding priority coverage to the traversal set. Number 2, as shown in Table 6 below.

[0116] Table 6 Grid Covering Matrix

[0117]

[0118] Update the grid index to Continue to explore candidate cruise paths at level 3. ;

[0119] Step 3-2 （3） For the third-level candidate cruise path recursion (L3) of another optimal candidate cruise path at the second level: Current cruise path planning scheme Based on the grid index Corresponding squares Initially, based on the shortest path distance matrix... With the shortest path set matrix A random optimization algorithm was used to find one optimal candidate cruise route, prioritizing coverage of the grid squares. , Perform the following steps respectively;

[0120] against Update the current planning scheme to Update the grid covering matrix For candidate cruise paths After passing through all squares (3, 4, 5, 6, 7, 8), update their traversal set in the square covering matrix, adding priority coverage to the traversal set. Number 8 is shown in Table 7 below:

[0121] Table 7 Grid Coverage Matrix

[0122]

[0123] Update the grid indexes when all the corresponding traversal sets for each grid cell are not empty. Determine if the square index satisfies This indicates that all squares have been covered by the cruise path, and there is no need to perform the next level of recursion, thus updating the cruise path planning scheme set. Return to level 2 and level 1 in sequence;

[0124] Step 4: Determine the planning scheme set. If not empty, continue to step 5;

[0125] Step 5: Evaluation of Planning Schemes: This involves evaluating the set of planning schemes. The two planning schemes were evaluated for redundancy and priority respectively:

[0126] Step 5.1, Redundancy Assessment: Calculate the redundancy of each planning scheme. The sum of the lengths of all cruise paths and the total number of squares. The ratio of the two planning schemes is used as the redundancy score. The two schemes have the same redundancy score, both being [value missing]. ;

[0127] Step 5.2, Priority Assessment: Calculate the priority of each planning scheme. The average traversal period of the grid covered by the inner cruise path, the first planning scheme The priority score is The second planning scheme The priority score is Therefore, the first option has the lowest score and is of higher priority;

[0128] Step 6: Output of the optimal planning scheme: The two planning schemes have the same redundancy score, but the priority evaluation score of the first planning scheme is lower. Therefore, the optimal planning scheme is: Calculate the optimal planning scheme The number of cruise routes, In other words, the number of drones required for the cruise, outputting the optimal planning scheme. Number of drones required for patrol ,like Figure 4 As shown, there are three cruise paths. , and They are represented by blue, brown, and green, respectively;

[0129] In this invention, the UAV cooperative cruise area is modeled using a series of interconnected squares, and the UAV cruise speed is uniformly assumed to be one square per unit time step. In practice, other models such as Veno diagrams can be flexibly used to represent more complex cruise units, and different UAV cruise speed values ​​can be set according to different specific scenario requirements.

Claims

1. A method for planning UAV cruise paths for multi-priority dynamic coverage, characterized in that, Includes the following steps: (1) Divide the cruise area into grids to obtain several cruise squares, number the cruise squares and obtain the traversal period of each cruise square. (2) Sort the cruise squares from shortest to longest according to their traversal period. If the traversal periods are the same, sort them from smallest to largest according to their cruise square numbers, thus obtaining the priority sort of the cruise squares. (3) Based on the current cruise path planning scheme, take the cruise grid with the highest priority and the empty set of the traversal set as the first priority coverage grid, and plan the cruise path for the priority coverage grid: obtain other cruise grids within half a traversal cycle from the priority coverage grid as candidate cruise grids, and plan several candidate cruise paths that can cover the priority coverage grid according to the priority coverage grid and the candidate cruise grids. (4) Based on several candidate cruise paths, depth-first recursion is performed according to priority order to recursively explore subsequent priority coverage squares and several candidate cruise paths that cover the squares, and find a cruise path planning scheme that can cover all cruise squares. (5) Evaluate all cruise path planning schemes, output the optimal cruise path planning scheme, and conduct dynamic periodic cruises based on the optimal cruise path planning scheme.

2. The UAV cruise path planning method for multi-priority dynamic coverage according to claim 1, characterized in that, The cruise area includes a no-fly zone and a cruise zone, and the cruise zone is divided into a grid to obtain cruise squares.

3. The UAV cruise path planning method for multi-priority dynamic coverage according to claim 1, characterized in that, The traversal period is an even number of time steps, and within each time step, the travel distance of each UAV is one cruising square.

4. The UAV cruise path planning method for multi-priority dynamic coverage according to claim 1, characterized in that, For the cruise area after grid division, construct the shortest path distance matrix. With the shortest path set matrix In step (3), based on the shortest path distance matrix With the shortest path set matrix Other cruise squares whose distance from the priority coverage square is within half a traversal period are obtained as candidate cruise squares. The shortest path distance matrix The elements in Indicates the cruise grid and cruise grid The shortest cruise path length between; The shortest path set matrix The elements in Indicates the cruise grid and cruise grid The set of shortest paths between.

5. The UAV cruise path planning method for multi-priority dynamic coverage according to claim 1, characterized in that, In step (3), when planning several candidate cruise paths within the candidate cruise grid, the first one is selected. The optimal candidate cruise path for each priority coverage square, where... To explore the threshold; The objective function and constraints for selecting candidate cruise paths are as follows: ； ； in, For the first The set of cruise squares surrounded by candidate cruise paths. For passing through the cruise grid The set consisting of cruise route numbers, It is a rounding function. For the cruise grid The traversal period, To prioritize covering the grid The traversal period, For the first The number of the first cruise square traversed by the candidate cruise path. For the first The candidate cruise path passed through the first The number of each cruise square, To prioritize covering the grid The number, For the first Candidate cruise paths, For the first The length of each candidate cruise path.

6. The UAV cruise path planning method for multi-priority dynamic coverage according to claim 5, characterized in that, In step (3), a stochastic optimization algorithm is used when planning several candidate cruise paths within the candidate cruise grid.

7. The UAV cruise path planning method for multi-priority dynamic coverage according to claim 1, characterized in that, The evaluation of all cruise route planning schemes includes redundancy assessment and priority assessment. The calculation formula for redundancy assessment is as follows: ； in, For cruise route planning scheme Redundancy score, cruise path Path length, This represents the total number of patrol squares; The formula for calculating the priority assessment is as follows: ； in, For cruise route planning scheme Priority score, For the cruise grid The lower the score, the higher the priority during the traversal cycle.

8. The UAV cruise path planning method for multi-priority dynamic coverage according to claim 7, characterized in that, The cruise path planning scheme with the lowest redundancy score is selected as the optimal cruise path planning scheme. If there are multiple cruise path planning schemes with the lowest redundancy scores, the cruise path planning scheme with the lowest priority score is selected as the optimal cruise path planning scheme. The number of cruise paths in the optimal cruise path planning scheme is the number of drones required for the cruise.

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

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 8.

Images