Multi-unmanned aerial vehicle cooperative route planning method and device based on MP-PG algorithm, equipment and medium
Patent Information
- Application Number
- CN202410971737.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-19
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing multi-UAV collaborative track planning method is computationally expensive and time-consuming in high-dimensional complex constraint problems, making it difficult to integrate multiple cost functions and constraints. Intelligent optimization algorithms have high computational complexity and are prone to local optimization. Influences computing efficiency.
Using a multi-UAV collaborative track planning method based on MP-PG algorithm, multiple cost functions and constraints are constructed by obtaining three-dimensional map information and threat information, including track length, flight altitude, threat, range, maneuverability, time With space collaborative constraints, a multi-objective adaptation function is constructed in combination with penalty function, and an MP-PG algorithm is used to solve the optimal track.
It reduces the computational complexity, improves the solution efficiency of the collaborative track planning problem of multiple drones, can effectively integrate multiple cost functions and constraints, avoid local optimization, and improves the algorithm's optimization ability.
Smart Images

Figure CN118913282A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of cooperative trajectory planning for unmanned aerial vehicles (UAVs), and in particular to a method, device, equipment and medium for cooperative trajectory planning for multiple UAVs based on an MP-PG algorithm. Background Art
[0002] At present, there are two main types of multi-UAV collaborative trajectory planning methods: traditional trajectory planning algorithms, such as A* algorithm, Dijkstra method, rapidly expanding random tree (RRT) algorithm, artificial potential field method, etc., and intelligent optimization algorithms inspired by biological evolution, such as the more traditional particle swarm algorithm, genetic algorithm, ant colony algorithm, and the newly proposed dung beetle algorithm, gray wolf algorithm, artificial bee colony algorithm, etc.
[0003] Traditional algorithms have the problems of large amount of calculation and long time consumption when solving high-dimensional complex constraint problems. Therefore, they are often used for trajectory planning in two-dimensional space. It is difficult to integrate multiple cost functions and constraints, and the optimal trajectory problem of multi-UAV collaborative trajectory planning is not considered comprehensively.
[0004] Intelligent optimization algorithms have limitations in solving problems. Their computational complexity is usually high. When used to process a large amount of sample data, more computer memory is required, which places high demands on the computer's computing power. In addition, they are prone to problems such as local optimality and low algorithm convergence rate.
[0005] The PG algorithm only performs single-track pathfinding each time it calculates. When solving the collaborative trajectory planning problem of multiple drones, it will prolong the solution time and affect the calculation efficiency. In addition, the algorithm does not consider the various cost functions and constraints in the trajectory planning problem, including the coordination of multiple drones. Summary of the invention
[0006] 1. Technical issues to be solved
[0007] In view of the shortcomings of the prior art, the present invention provides a multi-UAV collaborative trajectory planning method, device, equipment and medium based on the MP-PG algorithm, which has the advantages of reducing the complexity of the calculation process and solves the above-mentioned technical problems.
[0008] (II) Technical solution
[0009] To achieve the above object, the present invention provides the following technical solution: a multi-UAV collaborative trajectory planning method based on MP-PG algorithm, comprising the following steps:
[0010] S1. Obtain three-dimensional map information, multi-UAV coordination parameter information and threat information, and build the threat information into a cylindrical model to set the starting point and target point of the trajectory planning;
[0011] S2. Based on the acquired 3D map information, multi-UAV coordination parameter information and threat information, multiple cost functions and constraints are constructed, including the track length cost function C l , flight altitude cost function C h , threat cost function, track segment length constraint, maximum range constraint, maneuverability constraint, time coordination constraint and space coordination constraint, and establish a penalty function for each constraint, and then combine the penalty function with the cost function to construct a multi-objective adaptation function for multi-UAV collaborative track planning;
[0012] The threat cost function includes the threat cost function C for surface-to-air missiles, anti-aircraft guns, and severe weather. defense And the threat cost function C for the detection radar radar
[0013] S3. Solve the multi-objective adaptation function to obtain the optimal collaborative trajectory of multiple UAVs from the starting point to the target point.
[0014] As a preferred technical solution of the present invention, the expression of the cylinder model established in step S1 is as follows:
[0015]
[0016] in, and They represent the cylindrical models composed of the i-th surface-to-air missile, anti-aircraft gun, environmental threat zone of severe weather, and the i-th radar detection threat zone. Indicates the center point of the environmental threat zone, Indicates the center point of the radar detection threat area, and Respectively represent the height of the environmental threat zone and the radar detection threat zone, and They represent the threat radius of the environmental threat zone and the detection radius of the radar detection threat zone respectively. x, y, and z represent the three-dimensional coordinates of any point in the environmental or radar threat zone respectively.
[0017] As a preferred technical solution of the present invention, the track length cost function C in step S2 l The expression is as follows:
[0018]
[0019] Among them, C l represents the track length cost function, l i,j P represents the distance between the jth track point and the next track point in the i-th route. i,jrepresents the three-dimensional coordinates of the jth track point in the i-th route, P i,j+1 represents the three-dimensional coordinates of the j+1th track point in the ith route, Indicated by P i,j Starting point P i,j+1 is the end point of the track segment, Indicates track segment Length, It means summing the lengths of the inner n-1 track segments.
[0020] As a preferred technical solution of the present invention, the flight height cost function C h The expression is as follows:
[0021]
[0022] Among them, C h represents the flight height cost function, H i,j represents the flight altitude cost at the jth track point on the i-th route, h k Indicates the unit coefficient of flight altitude cost, Z i,j represents the altitude coordinate of the jth node in the i-th route, z max Indicates the maximum height, z min Indicates the minimum height, |*| indicates the absolute value operation of the internal data, Indicates the sum of the height costs of the internal n track points.
[0023] As a preferred technical solution of the present invention, the threat cost function includes the threat cost function C for surface-to-air missiles, anti-aircraft guns, and severe weather. defense And the threat cost function C for the detection radar radar , the specific expression is as follows:
[0024]
[0025] Where u represents the total number of environmental threat zones posed by surface-to-air missiles, anti-aircraft guns, and severe weather. represents the threat cost function of the environmental threat zone, μ represents the threat coefficient, Indicated by P i,j Starting point P i,j+1 is the end point of the track segment, l j express Subpath The jth node d j The radial distance to the center of the threat zone, represents the threat radius of the kth environmental threat zone, It represents the sum of the threat cost data of the internal n-1 track segments. Indicates the sum of the internal u data, in this paper, μ=10;
[0026]
[0027] Among them, g represents the number of radar detection threat areas, λ represents the radar detection intensity, l j express Subpath The jth node d j The radial distance to the center of the threat zone, represents the threat radius of the kth radar detection threat area, represents the threat cost function of the radar detection threat area, It represents the sum of the threat cost data of the internal n-1 track segments. It means summing up the internal g data, e means natural logarithm, and λ=5 in this paper.
[0028] As a preferred technical solution of the present invention, the expressions of the track segment length constraint, the maximum range constraint, the maneuverability constraint, the time coordination constraint and the space coordination constraint in step S2 are respectively as follows:
[0029] Track segment length constraints:
[0030] l i,j ≥l min , j∈[1,n-1]
[0031] Among them, l i,j It represents the distance between the jth track point and the next track point in the i-th route. min represents the shortest length of the track segment, and n represents the number of track points in the route;
[0032] Maximum range constraints:
[0033]
[0034] Among them, l i,j It represents the distance between the jth track point and the next track point in the ith route. min represents the shortest length of a track segment, represents the round trip range of the drone, L max It represents the maximum range of the UAV to perform the mission, and n represents the number of track points in the route;
[0035] Maneuverability constraints:
[0036]
[0037] in, represents the yaw angle of the jth node of the i-th route, θ i,j represents the pitch angle of the jth node of the i-th route, and θ max They represent the maximum yaw angle and the maximum pitch angle respectively, and the expressions of the yaw angle and the pitch angle are as follows:
[0038]
[0039] Among them, k i Indicated by P i,j-1 Starting point P i,j The end point of the track segment The projection in the horizontal direction, k i+1 Indicated by P i,j Starting point P i,j+1 The end point of the track segment In the horizontal projection, arccos and arctan represent the inverse cosine and inverse tangent trigonometric functions, respectively. |*| represents the modulus operation. i,j+1 ,y i,j+1 、z i,j+1 Represent the track point P i,j+1 The three-dimensional coordinates, x i,j ,y i,j 、z i,j Represent the track point P i,j The three-dimensional coordinates of
[0040] Time coordination constraints:
[0041] t I ≤t max
[0042] Among them, t I represents the flight time of the first UAV to complete the track, t max Indicates the time constraints for multiple UAVs to reach their respective target points;
[0043] Spatial coordination constraints:
[0044] d I-J ≥d safe
[0045] Among them, d I-J represents the minimum distance between the track points of the Ith UAV and the Jth UAV, d safe Indicates the minimum safe flying distance between drones;
[0046] The penalty function is expressed as follows:
[0047]
[0048] in, represents the penalty function of the I-th UAV;
[0049] The expression of the multi-objective adaptation function of multi-UAV collaborative trajectory planning is as follows:
[0050]
[0051] Among them, C l represents the track length cost function, C h represents the flight altitude cost function, C defense represents the threat cost function of the environmental threat zone and C radar represents the threat cost function of the radar detection area, K1, K2, K3 and K4 represent weight coefficients respectively, and the sum of the weight coefficients is 1. represents the penalty function, represents the trajectory cost function of the I-th UAV trajectory planning, Z represents the multi-objective adaptation function of multi-UAV collaborative trajectory planning, min represents the minimum value, and M represents the total number of UAVs.
[0052] As a preferred technical solution of the present invention, the specific steps of step S3 are as follows:
[0053] S3.1, initialization, using MP-PG algorithm to generate UAV tracks that meet the constraints and store them as individual α in the population;
[0054] S3.2, evaluation function index, clustering all individuals α;
[0055] S3.3, the fitness function calculates the fitness value of the track population;
[0056] S3.4. Compare the fitness values of individuals in the population and store the best individual in the population;
[0057] S3.5. Constrain all populations, discard the tracks that do not meet the constraints, retain the suboptimal population individuals, and update the population;
[0058] S3.6, merge all sub-populations, compare fitness values, and obtain the optimal solution for all sub-populations;
[0059] S3.7, iterative update. Repeat steps S3.3-S3.6. When the iteration process reaches the predetermined maximum number of times or the fitness value no longer changes, output the optimal cooperative trajectory group and the optimal value as the optimal solution to the multi-UAV cooperative trajectory planning problem; otherwise, return to step S3.3 to continue updating.
[0060] The present invention also provides a multi-UAV collaborative trajectory planning device based on the MP-PG algorithm, which is used to implement the multi-UAV collaborative trajectory planning method based on the MP-PG algorithm as described above, including a data collection module, a calculation construction module and a result output module;
[0061] The data collection module is used to obtain three-dimensional map information, multi-UAV coordination parameter information and threat information, and set the starting point and target point of the track planning;
[0062] The calculation construction module is used to establish multiple cost functions and constraints, and establish a penalty function for each constraint, and then combine the penalty function with the cost function to construct a multi-objective adaptation function for multi-UAV collaborative trajectory planning
[0063] The result output module is used to iteratively solve the multi-objective adaptation function of multi-UAV collaborative trajectory planning and calculate the optimal solution.
[0064] The present invention also provides a multi-UAV collaborative trajectory planning device based on the MP-PG algorithm, which is used to implement the multi-UAV collaborative trajectory planning method based on the MP-PG algorithm as mentioned above. The device includes: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the multi-UAV collaborative trajectory planning method based on the MP-PG algorithm as mentioned above is implemented.
[0065] The present invention also provides a multi-UAV collaborative trajectory planning device based on the MP-PG algorithm, which is used to implement the multi-UAV collaborative trajectory planning method based on the MP-PG algorithm as mentioned above. Computer program instructions are stored on the computer storage medium, and when the computer program instructions are executed by the processor, the multi-UAV collaborative trajectory planning method based on the MP-PG algorithm as mentioned above is implemented.
[0066] Compared with the prior art, the present invention provides a multi-UAV collaborative trajectory planning method, device, equipment and medium based on the MP-PG algorithm, which has the following beneficial effects:
[0067] 1. By applying the algorithm to the field of optimization problems, the present invention can improve the algorithm's optimization ability and the efficiency of solving the multi-UAV collaborative trajectory planning problem. At the same time, the multi-UAV collaborative trajectory planning problem is modeled as an optimization problem of a multi-objective adaptive function, aiming to reduce the complexity of the problem. BRIEF DESCRIPTION OF THE DRAWINGS
[0068] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION
[0069] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0070] See also Figure 1 , a multi-UAV collaborative trajectory planning method based on MP-PG algorithm, comprising the following steps:
[0071] S1. Obtain three-dimensional map information, multi-UAV coordination parameter information and threat information, and build the threat information into a cylindrical model to set the starting point and target point of the trajectory planning;
[0072] S2. Based on the acquired 3D map information, multi-UAV coordination parameter information and threat information, multiple cost functions and constraints are constructed, including the track length cost function C l , flight altitude cost function C h , threat cost function, track segment length constraint, maximum range constraint, maneuverability constraint, time coordination constraint and space coordination constraint, and establish a penalty function for each constraint, and then combine the penalty function with the cost function to construct a multi-objective adaptation function for multi-UAV collaborative track planning;
[0073] The threat cost function includes the threat cost function C for surface-to-air missiles, anti-aircraft guns, and severe weather. defense And the threat cost function C for the detection radar radar
[0074] S3. Solve the multi-objective adaptation function to obtain the optimal collaborative trajectory of multiple UAVs from the starting point to the target point.
[0075] Furthermore, the expression of the cylinder model established in step S1 is as follows:
[0076]
[0077] in, and They represent the cylindrical models composed of the i-th surface-to-air missile, anti-aircraft gun, environmental threat zone of severe weather, and the i-th radar detection threat zone. Indicates the center point of the environmental threat zone, Indicates the center point of the radar detection threat area, and Respectively represent the height of the environmental threat zone and the radar detection threat zone, and They represent the threat radius of the environmental threat zone and the detection radius of the radar detection threat zone respectively. x, y, and z represent the three-dimensional coordinates of any point in the environmental or radar threat zone respectively.
[0078] Furthermore, the flight path of the UAV is represented as a set of n track points, X i =(P i1 ,Pi2 ,P i3 ,...,P in ), each waypoint corresponds to the coordinate P in three-dimensional space ij =(x ij ,y ij , z ij ). Combining multiple cost functions and constraint functions, a multi-objective adaptation function for multi-UAV collaborative trajectory planning is established, including: i The track segment distance l between two adjacent nodes ij Expressed as Track length cost function C l The expression is as follows:
[0079]
[0080] Among them, C l represents the track length cost function, l i,j P represents the distance between the jth track point and the next track point in the i-th route. i,j represents the three-dimensional coordinates of the jth track point in the i-th route, P i,j+1 represents the three-dimensional coordinates of the j+1th track point in the ith route, Indicated by P i,j Starting point P i,j+1 is the end point of the track segment, Indicates track segment Length, It means summing the lengths of the inner n-1 track segments.
[0081] Furthermore, the flight height cost function C h The expression is as follows:
[0082]
[0083] Among them, C h represents the flight height cost function, H i,j represents the flight altitude cost at the jth track point on the i-th route, h k Represents the unit coefficient of flight altitude cost, z i,j represents the altitude coordinate of the jth node in the i-th route, z max Indicates the maximum height, z min Indicates the minimum height, |*| indicates the absolute value operation of the internal data, Indicates the sum of the height costs of the internal n track points.
[0084] Furthermore, the threat cost function includes the threat cost function C for surface-to-air missiles, anti-aircraft guns, and severe weather.defense And the threat cost function C for the detection radar radar , the specific expression is as follows:
[0085] Taking the threat areas of surface-to-air missiles, anti-aircraft guns, and severe weather as an example, the radius of the threat area is Track segment Node d in j d can be determined using the Euclidean distance formula j Distance from the threat center j , further determine l j equal The endpoints d1 and d n The subpaths between If any l j Less than Then it is determined that there is a threat in this track segment, and the threat cost is calculated by the following formula:
[0086]
[0087]
[0088] Where u represents the total number of environmental threat zones posed by surface-to-air missiles, anti-aircraft guns, and severe weather. represents the threat cost function of the environmental threat zone, μ represents the threat coefficient, Indicated by P i,j Starting point P i,j+1 is the end point of the track segment, l j express Subpath The jth node d j The radial distance to the center of the threat zone, represents the threat radius of the kth environmental threat zone, It represents the sum of the threat cost data of the internal n-1 track segments. Indicates the sum of the internal u data, in this paper, μ=10;
[0089]
[0090] Among them, g represents the number of threat areas detected by radar, λ represents the radar detection intensity, l j express Subpath The jth node d j The radial distance to the center of the threat zone, represents the threat radius of the kth radar detection threat area, represents the threat cost function of the radar detection threat area, It represents the sum of the threat cost data of the internal n-1 track segments. It means summing up the internal g data, e means natural logarithm, and λ=5 in this paper.
[0091] Furthermore, the expressions of the track segment length constraint, the maximum range constraint, the maneuverability constraint, the time coordination constraint and the space coordination constraint in step S2 are as follows:
[0092] Due to the constraints of the UAV's own maneuverability, before the UAV changes its flight attitude, it needs to reserve a certain buffer distance when planning the track. The track length constraint is:
[0093] l i,j ≥l min , j∈[1,n-1]
[0094] Among them, l i,j It represents the distance between the jth track point and the next track point in the ith route. min represents the shortest length of the track segment, and n represents the number of track points in the route;
[0095] In order to ensure that the UAV can successfully reach the target point to perform combat missions and return safely, it is necessary to constrain the maximum range of the UAV. Assume that the maximum range of the UAV to perform a mission is L max , then the maximum range constraint is:
[0096]
[0097] Among them, l i,j It represents the distance between the jth track point and the next track point in the ith route. min represents the shortest length of a track segment, represents the round trip range of the drone, L max It represents the maximum range of the UAV to perform the mission, and n represents the number of track points in the route;
[0098] P i Take point j as an example, Vector Sum The projections in the horizontal direction can be expressed as k i =(x ij -x i,j-1 ,y ij -y i,j-1 ) and k i +1=(x i,j+1 -x ij ,y i,j+1 -y ij ), maneuverability constraints:
[0099]
[0100] in, represents the yaw angle of the jth node of the i-th route, θ i,j represents the pitch angle of the jth node of the i-th route, and θ max They represent the maximum yaw angle and the maximum pitch angle respectively, and the expressions of the yaw angle and the pitch angle are as follows:
[0101]
[0102] Among them, k i Indicated by P i,j-1 Starting point P i,j The end point of the track segment The projection in the horizontal direction, k i+1 Indicated by P i,j Starting point P i,j+1 The end point of the track segment In the horizontal projection, arccos and arctan represent the inverse cosine and inverse tangent trigonometric functions, respectively. |*| represents the modulus operation. i,j+1 ,y i,j+1 、z i,j+1 Represent the track point P i,j+1 The three-dimensional coordinates, x i,j ,y i,j 、z i,j Represent the track point P i,j The three-dimensional coordinates of
[0103] Time coordination constraints:
[0104] t I ≤t max
[0105] Among them, t I represents the flight time of the first UAV to complete the track, t max Indicates the time constraints for multiple UAVs to reach their respective target points. If they are met, the UAV can complete the task within the time constraints.
[0106] Spatial coordination constraints:
[0107] d I-J ≥d safe
[0108] Among them, d I-J represents the minimum distance between the track points of the Ith UAV and the Jth UAV, d safe Indicates the minimum safe flight distance between drones. When multiple drones fly in coordination, it is necessary to ensure that the distance between drones is always not less than the minimum safe flight distance, that is, to avoid collisions between drones.
[0109] The penalty function is expressed as follows:
[0110]
[0111] in, represents the penalty function of the I-th UAV;
[0112] The expression of the multi-objective adaptation function of multi-UAV collaborative trajectory planning is as follows:
[0113]
[0114] Among them, C l represents the track length cost function, C h represents the flight altitude cost function, C defense represents the threat cost function of the environmental threat zone and C radar represents the threat cost function of the radar detection area, K1, K2, K3 and K4 represent weight coefficients respectively, and the sum of the weight coefficients is 1. represents the penalty function, represents the trajectory cost function of the I-th UAV trajectory planning, Z represents the multi-objective adaptation function of multi-UAV collaborative trajectory planning, min represents the minimum value, and M represents the total number of UAVs.
[0115] Furthermore, the specific steps of step S3 are as follows:
[0116] S3.1, initialization, using MP-PG algorithm to generate UAV tracks that meet the constraints and store them as individual α in the population;
[0117] S3.2, evaluation function index, clustering all individuals α;
[0118] S3.3, the fitness function calculates the fitness value of the track population;
[0119] S3.4. Compare the fitness values of individuals in the population and store the best individual in the population;
[0120] S3.5. Constrain all populations, discard the tracks that do not meet the constraints, retain the suboptimal population individuals, and update the population;
[0121] S3.6, merge all sub-populations, compare fitness values, and obtain the optimal solution for all sub-populations;
[0122] S3.7, iterative update. Repeat steps S3.3-S3.6. When the iteration process reaches the predetermined maximum number of times or the fitness value no longer changes, output the optimal cooperative trajectory group and the optimal value as the optimal solution to the multi-UAV cooperative trajectory planning problem; otherwise, return to step S3.3 to continue updating.
[0123] The present invention also provides a multi-UAV collaborative trajectory planning device based on the MP-PG algorithm, which is used to implement the multi-UAV collaborative trajectory planning method based on the MP-PG algorithm as described above, including a data collection module, a calculation construction module and a result output module;
[0124] The data collection module is used to obtain three-dimensional map information, multi-UAV coordination parameter information and threat information, and set the starting point and target point of the trajectory planning;
[0125] The calculation construction module is used to establish multiple cost functions and constraints, and establish a penalty function for each constraint. Then, the penalty function and the cost function are combined to construct a multi-objective adaptation function for multi-UAV collaborative trajectory planning.
[0126] The result output module is used to iteratively solve the multi-objective adaptation function of multi-UAV collaborative trajectory planning and calculate the optimal solution.
[0127] The present invention also provides a multi-UAV collaborative trajectory planning device based on the MP-PG algorithm, which is used to implement the multi-UAV collaborative trajectory planning method based on the MP-PG algorithm as mentioned above. The device includes: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the multi-UAV collaborative trajectory planning method based on the MP-PG algorithm as mentioned above is implemented.
[0128] The present invention also provides a multi-UAV collaborative trajectory planning device based on the MP-PG algorithm, which is used to implement the multi-UAV collaborative trajectory planning method based on the MP-PG algorithm as described above. Computer program instructions are stored on a computer storage medium. When the computer program instructions are executed by a processor, the multi-UAV collaborative trajectory planning method based on the MP-PG algorithm as described above is implemented.
[0129] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A multi-UAV collaborative trajectory planning method based on MP-PG algorithm, characterized by: The following steps are involved: S1. Obtain three-dimensional map information, multi-UAV coordination parameter information and threat information, and build the threat information into a cylindrical model to set the starting point and target point of the trajectory planning; S2. Based on the acquired 3D map information, multi-UAV coordination parameter information and threat information, multiple cost functions and constraints are constructed, including the track length cost function C l , flight altitude cost function C h , threat cost function, track segment length constraint, maximum range constraint, maneuverability constraint, time coordination constraint and space coordination constraint, and establish a penalty function for each constraint, and then combine the penalty function with the cost function to construct a multi-objective adaptation function for multi-UAV collaborative track planning; The threat cost function includes the threat cost function C for surface-to-air missiles, anti-aircraft guns, and severe weather. defense And the threat cost function C for the detection radar radar ; S3. Solve the multi-objective adaptation function to obtain the optimal collaborative trajectory of multiple UAVs from the starting point to the target point.
2. The multi-UAV collaborative trajectory planning method based on the MP-PG algorithm according to claim 1 is characterized by: The expression of the cylinder model established in step S1 is as follows: in, and They represent the cylindrical models composed of the i-th surface-to-air missile, anti-aircraft gun, environmental threat zone of severe weather, and the i-th radar detection threat zone. Indicates the center point of the environmental threat zone, Indicates the center point of the radar detection threat area, and Respectively represent the height of the environmental threat zone and the radar detection threat zone, and They represent the threat radius of the environmental threat zone and the detection radius of the radar detection threat zone respectively. x, y, and z represent the three-dimensional coordinates of any point in the environmental or radar threat zone respectively.
3. The multi-UAV collaborative trajectory planning method based on the MP-PG algorithm according to claim 2 is characterized in that: The track length cost function C in step S2 l The expression is as follows: Among them, C l represents the track length cost function, l i,j P represents the distance between the jth track point and the next track point in the i-th route. i,j represents the three-dimensional coordinates of the jth track point in the i-th route, P i,j+1 represents the three-dimensional coordinates of the j+1th track point in the ith route, Indicated by P i,j Starting point P i,j+1 is the end point of the track segment, Indicates track segment Length, It means summing the lengths of the inner n-1 track segments.
4. The multi-UAV collaborative trajectory planning method based on the MP-PG algorithm according to claim 2 is characterized by: The flight height cost function C h The expression is as follows: Among them, C h represents the flight height cost function, H i,j represents the flight altitude cost at the jth track point on the i-th route, h k Represents the unit coefficient of flight altitude cost, z i,j represents the altitude coordinate of the jth node in the i-th route, z max Indicates the maximum height, z min Indicates the minimum height, |*| indicates the absolute value operation of the internal data, Indicates the sum of the height costs of the internal n track points.
5. The multi-UAV collaborative trajectory planning method based on the MP-PG algorithm according to claim 2 is characterized by: The threat cost function includes the threat cost function C for surface-to-air missiles, anti-aircraft guns, and severe weather. defense And the threat cost function C for the detection radar radar , the specific expression is as follows: Where u represents the total number of environmental threat zones posed by surface-to-air missiles, anti-aircraft guns, and severe weather. represents the threat cost function of the environmental threat zone, μ represents the threat coefficient, Indicated by P i,j Starting point P i,j+1 is the end point of the track segment, l j express Subpath of The jth node d j The radial distance to the center of the threat zone, represents the threat radius of the kth environmental threat zone, It represents the sum of the environmental threat cost data of the internal n-1 track segments. Indicates the sum of the internal u data; Among them, g represents the number of radar detection threat areas, λ represents the radar detection intensity, l j express Subpath of The i-th node d j The radial distance to the center of the threat zone, represents the threat radius of the kth radar detection threat area, represents the threat cost function of the radar detection threat area, It represents the sum of the threat cost data of the internal n-1 track segments. It means summing up the internal g data, and e means the natural logarithm.
6. The multi-UAV collaborative trajectory planning method based on the MP-PG algorithm according to claim 2 is characterized by: The expressions of the track segment length constraint, the maximum range constraint, the maneuverability constraint, the time coordination constraint and the space coordination constraint in step S2 are respectively as follows: Track segment length constraints: L i,j ≥l min ,j∈[1,n-1] Among them, l i,j It represents the distance between the jth track point and the next track point in the ith route. min represents the shortest length of the track segment, and n represents the number of track points in the route; Maximum range constraints: Among them, l i,j represents the distance between the kth track point and the next track point in the ith route, l min represents the shortest length of a track segment, represents the round trip range of the drone, L max It represents the maximum range of the UAV to perform the mission, and n represents the number of track points in the route; Maneuverability constraints: in, represents the yaw angle of the jth node of the i-th route, θ i,j represents the pitch angle of the jth node of the i-th route, and θ max They represent the maximum yaw angle and the maximum pitch angle respectively, and the expressions of the yaw angle and the pitch angle are as follows: Among them, k i Indicated by P i,j-1 Starting point P i,j The end point of the track segment The projection in the horizontal direction, k i+1 Indicated by P i,j Starting point P i,j+1 The end point of the track segment In the horizontal projection, arccos and arctan represent the inverse cosine and inverse tangent trigonometric functions, respectively. |*| represents the modulus operation. i,j+1 ,y i,j+1 、z i,j+1 Represent the track point P i,j+1 The three-dimensional coordinates, x i,j ,y i,j 、z i,j Represent the track point P i,j The three-dimensional coordinates of Time coordination constraints: t I ≤t max Among them, t I represents the flight time of the first UAV to complete the track, t max Indicates the time constraints for multiple UAVs to reach their respective target points; Spatial coordination constraints: d I-J ≥d safe Among them, d I-J represents the minimum distance between the track points of the Ith UAV and the Jth UAV, d safe Indicates the minimum safe flying distance between drones; The penalty function is expressed as follows: in, represents the penalty function of the I-th UAV; The expression of the multi-objective adaptation function of multi-UAV collaborative trajectory planning is as follows: Among them, C l represents the track length cost function, C h represents the flight altitude cost function, C defense represents the threat cost function of the environmental threat zone and C radar represents the threat cost function of the radar detection area, K1, K2, K3 and K4 represent weight coefficients respectively, and the sum of the weight coefficients is 1. represents the penalty function, represents the trajectory cost function of the I-th UAV trajectory planning, Z represents the multi-objective adaptation function of multi-UAV collaborative trajectory planning, min represents the minimum value, and M represents the total number of UAVs.
7. The multi-UAV collaborative trajectory planning method based on the MP-PG algorithm according to claim 6 is characterized by: The specific steps of step S3 are as follows: S3.1, initialization, using MP-PG algorithm to generate UAV tracks that meet the constraints and store them as individual α in the population; S3.2, evaluation function index, clustering all individuals α; S3.3, the fitness function calculates the fitness value of the track population; S3.
4. Compare the fitness values of individuals in the population and store the best individual in the population; S3.
5. Constrain all populations, discard the tracks that do not meet the constraints, retain the suboptimal population individuals, and update the population; S3.6, merge all sub-populations, compare fitness values, and obtain the optimal solution for all sub-populations; S3.7, iterative update, repeat steps S3.3-S3.6, when the iteration process reaches the predetermined maximum number of times or the fitness value no longer changes, output the optimal cooperative trajectory group and the optimal value as the optimal solution to the multi-UAV cooperative trajectory planning problem; Otherwise, return to step S3.3 to continue updating.
8. A multi-UAV collaborative trajectory planning device based on MP-PG algorithm, used to implement the multi-UAV collaborative trajectory planning method based on MP-PG algorithm as claimed in any one of claims 1 to 7, characterized in that: It includes data collection module, calculation construction module and result output module; The data collection module is used to obtain three-dimensional map information, multi-UAV coordination parameter information and threat information, and set the starting point and target point of the track planning; The calculation construction module is used to establish multiple cost functions and constraints, and establish a penalty function for each constraint, and then combine the penalty function with the cost function to construct a multi-objective adaptation function for multi-UAV collaborative trajectory planning; The result output module is used to iteratively solve the multi-objective adaptation function of multi-UAV collaborative trajectory planning and calculate the optimal solution.
9. A multi-UAV collaborative trajectory planning device based on MP-PG algorithm, characterized by: The device includes: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, it implements the multi-UAV collaborative trajectory planning method based on the MP-PG algorithm as described in any one of claims 1 to 7.
10. A storage medium for multi-UAV collaborative trajectory planning based on MP-PG algorithm, characterized by: The computer storage medium stores computer program instructions, and when the computer program instructions are executed by the processor, the multi-UAV collaborative trajectory planning method based on the MP-PG algorithm as described in any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
Flight path planning method and device, and computer readable storage medium
CN110031007A
Task planning method for cooperative ground battle of manned and unmanned aerial vehicles
CN112733421A
Multi-unmanned aerial vehicle four-dimensional track collaborative planning method and system
CN112817330A
Unmanned aerial vehicle path planning method and device based on PG algorithm, equipment and medium
CN117346793A
Air-ground dual-purpose unmanned aerial vehicle path planning method
CN117687435A
