A flight path planning method and device for a flight platform cluster

Abstract

The application discloses a kind of flight platform cluster's track planning method and device, the method includes: collection obtains task demand information set and flight platform cluster technical index information set;The task demand information set includes the execution position and demand information of each to be executed task;The demand information includes demand task type information and the demand value of all technical indexes;The flight platform cluster technical index information set includes the execution task type information, position information and technical index value set of each flight platform;The technical index value set includes several technical index values;The task demand information set and flight platform cluster technical index information set are preprocessed, and obtain preprocessed information set;The preprocessed information set is subjected to track planning processing, and obtains the track set of flight platform cluster.

Description

Technical Field

[0001] This invention relates to the fields of trajectory control, industrial data processing, and strategy optimization, specifically to a trajectory planning method and apparatus for a flight platform cluster. Background Technology

[0002] With the rapid development of the low-altitude economy, flight platform swarm technology has been widely applied in various fields such as power line inspection, agricultural plant protection, logistics transportation, and disaster relief. Through the collaborative operation of multiple flight platforms, complex tasks that are difficult to complete with a single aircraft can be achieved, demonstrating a synergistic effect of "1+1>2". As the core key technology for collaborative operation of flight platform swarms, the effectiveness of flight path planning directly determines the efficiency, safety, and reliability of mission execution. Reasonable flight path planning enables flight platform swarms to safely and efficiently complete predetermined tasks in complex environments, while reducing energy consumption and avoiding flight conflicts.

[0003] Currently, existing flight platform cluster trajectory planning methods still have many shortcomings. In the matching process between flight platforms and tasks, traditional methods often employ simple type matching or single-index matching, lacking comprehensive quantitative analysis of multiple technical indicators. This makes it difficult to accurately select the most suitable flight platform for each task, easily leading to wasted flight platform resources or inefficient task completion. Simultaneously, in the trajectory planning modeling process, existing technologies often neglect the collaborative relationships between flight platforms and the correlations between tasks, making it difficult to achieve a precise correspondence between flight platform clusters and task sets. This results in planned trajectories that fail to fully leverage the synergistic advantages of the cluster, leading to problems such as trajectory redundancy, low task execution efficiency, and a high probability of flight conflicts. Furthermore, existing planning methods have poor adaptability in complex scenarios. When the flight platform cluster is large and the task types are complex and diverse, the solution efficiency and stability of the planning model are insufficient, making it difficult to quickly output the optimal trajectory set and failing to meet the real-time requirements of practical applications. Therefore, developing a method that can address the above-mentioned technical deficiencies and improve the accuracy, efficiency, and reliability of flight platform cluster trajectory planning has become an urgent technical problem to be solved by those skilled in the art. Summary of the Invention

[0004] This invention primarily addresses the problem that existing trajectory planning methods can no longer meet the increasing number of missions and diversified technical requirements, and how to improve the accuracy, efficiency, and reliability of trajectory planning for flight platform clusters. This invention discloses a trajectory planning method and apparatus for flight platform clusters.

[0005] In a first aspect, this invention discloses a trajectory planning method for a flight platform cluster, comprising: S1, collect a set of task requirement information and a set of technical indicator information for the flight platform cluster; the set of task requirement information includes the execution location and requirement information of each task to be executed; the requirement information includes requirement task type information and requirement values ​​of all technical indicators; the set of technical indicator information for the flight platform cluster includes execution task type information, location information and a set of technical indicator values ​​for each flight platform; the set of technical indicator values ​​includes several technical indicator values. S2, preprocess the task requirement information set and the flight platform cluster technical indicator information set to obtain a preprocessed information set; S3, perform trajectory planning processing on the preprocessed information set to obtain the trajectory set of the flight platform cluster.

[0006] The process of performing trajectory planning on the preprocessed information set to obtain the trajectory set of the flight platform cluster includes: S31, based on the requirement information of each task to be executed in the preprocessed information set, the flight platform cluster technical indicator information set in the preprocessed information set is filtered and matched to obtain a candidate flight platform set for each task to be executed; S32 performs trajectory planning on the set of candidate flight platforms for all pending tasks to obtain the trajectory set of the flight platform cluster.

[0007] Based on the requirement information of each task to be executed in the preprocessed information set, the technical indicator information set of the flight platform cluster in the preprocessed information set is filtered and matched to obtain a candidate flight platform set for each task to be executed, including: S311, based on the requirement task type information of each task to be executed in the preprocessed information set, a flight platform set that matches the requirement task type information is selected from the flight platform cluster technical indicator information set in the preprocessed information set. S312, For each task to be executed, the matching degree is calculated by using the required values ​​of all technical indicators of the task to be executed and the corresponding set of flight platforms that match the required task type information obtained by screening, and the corresponding matching matrix is ​​obtained. S313, perform threshold calculation on the matching matrix to obtain the matching threshold; S314, using the matching threshold, the set of matching flight platforms is filtered to obtain the set of candidate flight platforms for the task to be executed.

[0008] The process of performing trajectory planning on the candidate flight platform set for all pending tasks yields the trajectory set of the flight platform cluster, including: S321, Based on the set of candidate flight platforms for all tasks to be executed and the set of task requirement information in the preprocessed information set, construct the crowdless information and task group information. S322, Based on the aforementioned crowd information and task group information, construct a set of constraints; S323, Based on the aforementioned crowd information and task group information, an objective function is constructed; S324, Using the set of constraints and the objective function, a trajectory planning model is constructed; S325, Solve the trajectory planning model to obtain the trajectory set of the flight platform cluster.

[0009] The construction of the data without crowd information includes: Using the set of candidate flight platforms for all tasks to be executed in the preprocessed information set, a set U is constructed, U = Where m is the total number of candidate flight platforms, and no crowd information is defined. ,in, For group binary operations, it represents the collaborative operation relationship between flight platforms; The construction of the task group information includes: Let the set of tasks to be executed be T= Where n is the total number of tasks to be executed, and for each task... Its candidate flight platform set is Define task corresponding subgroup , A subgroup of G, i.e. And it satisfies all the axioms of the group; Define a group homomorphic mapping f and construct the mapping relationship. , so that for any ,have ,in, For a task set T, a binary operation represents the relationship between tasks; Task group information is constructed using the set of execution tasks, the group homomorphic mapping, and the subgroups corresponding to all tasks.

[0010] The set of constraints is constructed based on the aforementioned crowd information and task group information, including: A set of decision variables is constructed; the set of decision variables includes: initial task assignment variables. Continuing task allocation variables Location variables ; The parameter variable set is constructed as follows: The parameter variable set includes: candidate flight platforms initial position coordinates ,Task Execution location coordinates Candidate flight platform flight speed Candidate flight platform From the initial position Flight to mission Execution location single flight time Candidate flight platform From the task Execution location Flight to mission Execution location connecting flight time ,Task Execution time ; Construct a set of intermediate variables; the set of intermediate variables includes: candidate flight platforms. Total flight and execution time Total flight time of the flight platform cluster .

[0011] The expression for the objective function is: in, This is the overall objective variable, which is also the total flight time of the flight platform cluster. For flight platform Total task execution time Indicates flight platform The sum of the single flight times from the initial position to all assigned mission points. Indicates flight platform The sum of the connecting flight times between each assigned task point, Indicates flight platform The sum of the execution times for completing all assigned tasks.

[0012] A second aspect of the present invention discloses a trajectory planning device for a flight platform cluster, the device comprising: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the flight platform cluster's trajectory planning method.

[0013] In a third aspect, the present invention discloses a computer-readable storage medium storing computer instructions, which, when invoked by a computer, are used to execute the flight platform cluster trajectory planning method.

[0014] In a fourth aspect of this invention, an information data processing terminal is disclosed, which is used to implement the flight platform cluster trajectory planning method.

[0015] The beneficial effects of this invention are as follows: In the process of matching flight platforms with missions, this invention first selects flight platforms that meet the requirements based on mission type, and then further filters the flight platforms by calculating the matching degree of multiple technical indicators and solving the matching threshold. This achieves a precise match between flight platforms and mission requirements, and can select the most suitable set of candidate flight platforms to perform each mission, avoiding the waste of flight platform resources. At the same time, it ensures that each mission can be executed efficiently and with high quality, and improves the resource utilization and mission execution efficiency of the flight platform cluster.

[0016] This invention clarifies the collaborative operational relationships between flight platforms and the correlation relationships between tasks by constructing information on the flight platform group and task group without group information and task group information. It achieves a precise correspondence between flight platform group and task group by combining group axioms and group homomorphic mapping, so that trajectory planning can fully consider the collaborative characteristics of flight platforms and the correlation requirements of tasks. The planned trajectory can effectively avoid conflicts between flight platforms, realize the collaborative optimization of flight platform cluster, and further improve the overall efficiency of task execution.

[0017] This invention constructs a mapping relationship between flight platform clusters and task sets based on group theory. The flight platform cluster is considered a finite group, and the task set is considered the target set under the influence of this group. Through subgroup partitioning and element mapping, precise matching between flight platforms and tasks is achieved. Simultaneously, it combines integer programming, dynamic programming, and heuristic search ideas from operations research to construct a minimum total flight time optimization model under multiple constraints. Through the organic integration of multiple algorithms, the optimal solution for trajectory planning is obtained. Group theory is used to solve the problem of the rationality of the "flight platform-task" matching, while the operations research optimization model is used to solve the problem of the optimality of "trajectory path and time." The two work together to achieve high efficiency and scientific rigor in trajectory planning. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating the implementation of the method of the present invention. Detailed Implementation

[0019] To better understand the content of this invention, an embodiment is provided here.

[0020] Figure 1 This is a flowchart illustrating the implementation of the method of the present invention.

[0021] In a first aspect, this invention discloses a trajectory planning method for a flight platform cluster, comprising: S1, collect a set of task requirement information and a set of technical indicator information for the flight platform cluster; the set of task requirement information includes the execution location and requirement information of each task to be executed; the requirement information includes requirement task type information and requirement values ​​of all technical indicators; the set of technical indicator information for the flight platform cluster includes execution task type information, location information and a set of technical indicator values ​​for each flight platform; the set of technical indicator values ​​includes several technical indicator values. S2, preprocess the task requirement information set and the flight platform cluster technical indicator information set to obtain a preprocessed information set; S3, perform trajectory planning processing on the preprocessed information set to obtain the trajectory set of the flight platform cluster.

[0022] The preprocessing of the task requirement information set and the flight platform cluster technical indicator information set yields a preprocessed information set, including: S21, perform category discrimination processing on the task requirement information set and the flight platform cluster technical indicator information set to obtain the first information set; S22, perform data cleaning processing on the first information set to obtain a preprocessed information set.

[0023] The category discrimination process determines whether the attributes of each type of data in each information set are consistent with preset attributes, and deletes inconsistent data from the information set.

[0024] The data cleaning process includes smoothing noisy data and smoothing or deleting outliers; The process of performing trajectory planning on the preprocessed information set to obtain the trajectory set of the flight platform cluster includes: S31, based on the requirement information of each task to be executed in the preprocessed information set, the flight platform cluster technical indicator information set in the preprocessed information set is filtered and matched to obtain a candidate flight platform set for each task to be executed; S32 performs trajectory planning on the set of candidate flight platforms for all pending tasks to obtain the trajectory set of the flight platform cluster.

[0025] Based on the requirement information of each task to be executed in the preprocessed information set, the technical indicator information set of the flight platform cluster in the preprocessed information set is filtered and matched to obtain a candidate flight platform set for each task to be executed, including: S311, based on the requirement task type information of each task to be executed in the preprocessed information set, a flight platform set that matches the requirement task type information is selected from the flight platform cluster technical indicator information set in the preprocessed information set. S312, For each task to be executed, the matching degree is calculated by using the required values ​​of all technical indicators of the task to be executed and the corresponding set of flight platforms that match the required task type information obtained by screening, and the corresponding matching matrix is ​​obtained. S313, perform threshold calculation on the matching matrix to obtain the matching threshold; S314, using the matching threshold, the set of matching flight platforms is filtered to obtain the set of candidate flight platforms for the task to be executed.

[0026] For each task to be executed, the matching degree is calculated by using the required values ​​of all technical indicators of the task to be executed and the corresponding set of flight platforms that match the required task type information obtained through screening, to obtain the corresponding matching matrix, including: For each task to be executed, the set of technical indicator values ​​of each flight platform in the flight platform set that matches the required task type information obtained by filtering the task to be executed is used as a row vector. An indicator matrix is ​​constructed using the row vectors corresponding to the set of technical indicator values ​​of all flight platforms in the flight platform set. The elements of the row vectors are each technical indicator value in the set of technical indicator values. A requirement vector is constructed using the required values ​​of all technical indicators of the task to be executed; By subtracting the demand vector from each row vector of the index matrix, the corresponding difference vector is obtained; A matching matrix is ​​constructed by using all the difference vectors as row vectors; each row vector of the matching matrix corresponds to each row vector of the index matrix through the demand vector corresponding to the difference vector.

[0027] The step of calculating a threshold on the matching matrix to obtain a matching threshold includes: S3131, perform cross-correlation value calculation on the matching matrix to obtain a cross-correlation matrix; the elements of the i-th row and j-th column of the cross-correlation matrix are the cross-correlation values ​​of the i-th row vector and the j-th row vector of the difference matrix; S3132, Perform eigenvector processing on the cross-correlation matrix to obtain an eigenvector set; S3133, calculate the mean vector of all feature vectors in the feature vector set; the i-th element of the mean vector is the mean of the i-th element of all feature vectors in the feature vector set; S3134, Using the mean vector, perform joint calculation processing on the cross-correlation matrix to obtain the matching threshold. .

[0028] The expression for the joint calculation is: in, Let be the vector consisting of all diagonal elements of the cross-correlation matrix. It is the mean vector; and All are column vectors.

[0029] In the process of matching flight platforms with missions, this invention first selects flight platforms that meet the requirements based on mission type, and then further filters the flight platforms by calculating the matching degree of multiple technical indicators and solving the matching threshold. This achieves a precise match between flight platforms and mission requirements, and can select the most suitable set of candidate flight platforms to perform each mission, avoiding the waste of flight platform resources. At the same time, it ensures that each mission can be executed efficiently and with high quality, and improves the resource utilization and mission execution efficiency of the flight platform cluster.

[0030] This invention solves the matching threshold through joint calculation. First, the cross-correlation value of the matching matrix is ​​calculated to obtain the cross-correlation matrix. Then, through eigenvector processing and mean vector calculation, the matching threshold is obtained by joint operation with the diagonal element vectors of the cross-correlation matrix. This calculation method can fully explore the inherent correlation features in the matching matrix. Combined with multi-dimensional data for comprehensive analysis, the solved matching threshold has strong adaptability and pertinence. It can be dynamically adjusted according to different mission requirements and the technical indicators of different flight platform clusters, avoiding the screening bias caused by fixed thresholds. It can ensure that the selected candidate flight platforms fully meet the technical indicators of the mission, and avoid the waste of flight platform resources caused by over-screening. At the same time, it improves the scientificity and rationality of the matching threshold solution, further ensuring the reliability of the candidate flight platform screening results, and laying a solid foundation for the optimization of subsequent trajectory planning.

[0031] The step of using the matching threshold to filter the set of matching flight platforms to obtain a candidate set of flight platforms for the task to be executed includes: A requirement vector is constructed using the required values ​​of all technical indicators of the task to be executed; For each flight platform in the matching flight platform set, a row vector of the flight platform is constructed. The row vector of the flight platform is subtracted from the demand vector to obtain the corresponding first difference vector; Determine whether the magnitude of the first difference vector is less than the matching threshold, and add all flight platforms corresponding to the first difference vectors that are less than the matching threshold to the candidate flight platform set for the task to be executed.

[0032] The process of performing trajectory planning on the candidate flight platform set for all pending tasks yields the trajectory set of the flight platform cluster, including: S321, Based on the set of candidate flight platforms for all tasks to be executed and the set of task requirement information in the preprocessed information set, construct the crowdless information and task group information. S322, Based on the aforementioned crowd information and task group information, construct a set of constraints; S323, Based on the aforementioned crowd information and task group information, an objective function is constructed; S324, Using the set of constraints and the objective function, a trajectory planning model is constructed; S325, Solve the trajectory planning model to obtain the trajectory set of the flight platform cluster.

[0033] The construction of the data without crowd information includes: Using the set of candidate flight platforms for all pending tasks in the preprocessed information set, a set is constructed. Where m is the total number of candidate flight platforms, and no crowd information is defined. ,in, For a group, a binary operation represents the cooperative relationship between flight platforms. Without group information, the following group axioms are satisfied: (1) Closure: for any ,have That is, the result of the collaborative operation of any two candidate flight platforms is still an element in the set of candidate flight platforms (collaborative operation can be understood as two flight platforms jointly completing a certain task or relaying to complete a task). (2) Associative law: For any ,have ; (3) Unit element: exists For any ,have , here This represents a "no-cooperation" state, meaning the flight platform is performing the mission alone; (4) Inverse: for any ,exist , making , here Representative and Flight platforms that can return to a "non-cooperative" state after collaborative operations (such as in relay operations), After completing part of the task, The remaining tasks are then completed, and the collaboration between the two is equivalent to completing the task individually.

[0034] The construction of the task group information includes: Let the set of tasks to be executed be T= Where n is the total number of tasks to be executed, and for each task... Its candidate flight platform set is (Output from S31) Define the task corresponding subgroup , A subgroup of G, i.e. And it satisfies all the axioms of the group, which is used to describe the cooperative relationship between candidate flight platforms performing the task; Define a group homomorphic mapping f and construct the mapping relationship. , so that for any ,have ,in, For task set T, it is a binary operation that represents the relationship between tasks (such as the order of execution of tasks and parallel execution relationship). This mapping is used to achieve a precise correspondence between flight platform group and task group, and to ensure that the collaborative operation of flight platforms can match the association requirements of tasks. Task group information is constructed using the set of execution tasks, the group homomorphic mapping, and the subgroups corresponding to all tasks.

[0035] This invention constructs a trajectory planning model that includes a set of constraints and an objective function. Solving the model yields a trajectory set for a flight platform cluster. This model takes into account various factors such as mission requirements, flight platform technical specifications, and collaborative relationships. The planned trajectories not only meet the execution requirements of each mission but also achieve global optimization of the flight platform cluster, effectively reducing flight energy consumption, shortening mission execution time, and improving the rationality and optimality of trajectory planning.

[0036] The set of constraints is constructed based on the aforementioned crowd information and task group information, including: A set of decision variables is constructed; the set of decision variables includes: Initial task allocation variables , is a 0-1 variable, =1 indicates a candidate flight platform Assigned to perform tasks , =0 indicates a candidate flight platform Unassigned task ;in ( For the task The set of candidate flight platforms (output by S31), i=1,2,...,m,j=1,2,...,n.

[0037] Continuing task allocation variables , is a 0-1 variable, =1 indicates a candidate flight platform In performing the task Afterwards, the mission continued. , =0 indicates a candidate flight platform In performing the task After that, the mission will not continue. Where j,k=1,2,...,n, , (like and If there is no intersection, then (constantly 0).

[0038] Position variables , is a continuous variable Indicates candidate flight platform The position coordinates at time τ, where τ is the time variable. , The preset maximum allowable flight time, , j=1,2,...,n.

[0039] The parameter variable set is constructed as follows: The parameter variable set includes: Candidate flight platform initial position coordinates The information is provided by the flight platform cluster technical indicator information set in the preprocessed information set (S2 output), i=1,2,...,m; its coordinate form is... ,in , , They represent flight platforms respectively. The initial coordinates of the x-axis, y-axis, and z-axis in three-dimensional space, in meters (m).

[0040] Task Execution location coordinates The task requirement information set is provided by the preprocessed information set (S2 output), j=1,2,...,n; its coordinate form is... ,in , , Representing tasks The coordinates of the x-axis, y-axis, and z-axis in three-dimensional space, with the unit being meters (m).

[0041] Candidate flight platform flight speed The information is provided by the flight platform cluster technical indicator information set in the preprocessed information set (S2 output), i=1,2,...,m; the unit is meters per second (m / s), and It is a non-negative constant (the flight speed of the flight platform is not less than 0).

[0042] Candidate flight platform From the initial position Flight to mission Execution location single flight time The unit is seconds (s); candidate flight platform From the task Execution location Flight to mission Execution location connecting flight time The unit is seconds (s). Both flight times can be obtained by dividing the distance by the speed.

[0043] Task Execution time The task requirement information set is provided by the preprocessed information set (S2 output), j=1,2,...,n; the unit is seconds (s), which represents the fixed time required for the flight platform to complete the task after arriving at the task point.

[0044] Construct a set of intermediate variables; the set of intermediate variables includes: Candidate flight platform Total flight and execution time The unit is seconds (s), representing the flight platform. The total time taken to complete all assigned tasks (including flight time and task execution time) from the initial position.

[0045] Total flight time of the flight platform cluster The unit is seconds (s), which is the maximum total time taken by all flight platforms (since cluster operations require all tasks to be completed, the total time is determined by the flight platform with the longest time taken), and is also the objective function optimization object of the model.

[0046] The set of constraints includes: task allocation constraints, flight platform load constraints, successive flight constraints, flight speed constraints, position and time association constraints, and variable value constraints. The task allocation constraint (based on the group homomorphic mapping f) is expressed as follows: Each task to be executed It must be assigned to its set of candidate flight platforms. (Output from S31) One of the flight platforms executes the task, ensuring that no task is omitted or duplicated; this constraint is based on the definition of the group homomorphic mapping f, realizing a one-to-one correspondence between the flight platform group G and the task set T, which conforms to the matching logic of "flight platform-task".

[0047] The flight platform load constraints (based on subgroups) (the closure property), its expression is: in, as a candidate flight platform The maximum workload is provided by the flight platform cluster technical indicator information set in the preprocessed information set (it is an item in the technical indicator value set); this constraint indicates that the flight platform... Maximum Assignable One task, conforming to a subgroup The closed-loop requirements ensure that the collaborative operation of the flight platform does not exceed its technical capabilities.

[0048] The consecutive flight constraint (based on group binary operations) Its expression is: The first form indicates that the flight platform Only when tasks are assigned to be executed simultaneously and ( =1 and Only when =1) can it be from the task Continue flying to the mission ,Right now When =1; the second equation indicates that the flight platform Only when assigned to perform tasks Only then can one understand the task. Continuing flight to other missions, namely When =1; this constraint is based on the binary operation of the group. This ensures that the successive flights of the flight platform conform to the collaborative operation logic.

[0049] The flight speed constraint is expressed as follows: in, as a candidate flight platform The maximum flight speed is provided by the set of technical indicators of the flight platform cluster in the preprocessed information set; this constraint means that the flight speed of the flight platform cannot exceed its maximum technical limit to ensure flight safety and feasibility.

[0050] The expression for the location-time association constraint is as follows: in Indicates flight platform initial position With the task Execution location The Euclidean distance between them is calculated using the following formula: ; Indicates task Execution location With the task Execution location The Euclidean distance between them is calculated using the same formula as above; this constraint clarifies the relationship between flight time, flight distance, and flight speed, which conforms to the basic principles of kinematics.

[0051] The expression for the variable value constraint is as follows: Among them, the decision variables are clearly defined. , 0-1 variables, positional variables It is a three-dimensional real number vector to ensure that the variable values ​​conform to the actual physical meaning and decision-making logic.

[0052] The expression for the objective function is: in, This is the overall objective variable, which is also the total flight time of the flight platform cluster. For flight platform Total task execution time Indicates flight platform The sum of the single flight times from the initial position to all assigned mission points. At that time, the flight platform was included in the mission. Flight time , When =0, it is not included. Indicates flight platform The sum of the connecting flight times between each assigned task point, At that time, the flight platform was included in the mission. To the mission connecting flight time , When =0, it is not included. Indicates flight platform The sum of the execution times for completing all assigned tasks; When =1, it is included in the task. Execution time , At that time, it is not included.

[0053] The set of decision variables is the variable to be solved in the trajectory planning model; the solution value of the set of decision variables is used to construct the trajectory set of the flight platform cluster.

[0054] The task point is the location where the task to be executed will take place.

[0055] The objective function minimizes the maximum total flight time of all flight platforms, thereby minimizing the total flight time of the entire flight platform cluster and ensuring that the cluster efficiently completes all tasks.

[0056] The solution to the trajectory planning model can be obtained using heuristic algorithms or genetic algorithms.

[0057] Solving the trajectory planning model yields the trajectory set of the flight platform cluster, including: S3251 is a group theory-based flight platform-task grouping partitioning algorithm, whose input is the set of candidate flight platforms output by S31. And a set of preprocessed information; the output is a grouped flight platform-mission correspondence group, including: 1. Flight platform cluster based on Definition 1 For each task Collection of candidate flight platforms (S31 output), extract its subgroups The subgroup is calculated by the order of the group. The order is The number of medium-sized flight platforms), Divided into several cyclic subgroups (p=1,2,...,q, where q is the number of cyclic subgroups), each cyclic subgroup The flight platforms in the cluster have the same mission execution type (provided by the flight platform cluster technical indicator information set in the preprocessed information set), ensuring that the flight platforms in the same subgroup have the technical basis for collaborative operation.

[0058] 2. Based on group homomorphism mapping Calculate each cyclic subgroup With the task mapping coefficients The formula for calculating the mapping coefficient is: ,in Indicates flight platform Speed ​​and Mission The ratio of execution time to time reflects the efficiency of the flight platform in performing the task; mapping coefficient The larger the value, the more likely it is to be a cyclic subgroup. With the task The higher the match, the better.

[0059] 3. For each task Select the cyclic subgroup with the largest mapping coefficient. As the optimal execution subgroup for this task, the task With this subgroup The flight platforms are bound together to form "flight platform-mission" groups, ensuring that the grouped flight platforms can efficiently match mission requirements and laying the foundation for the generation of the initial solution.

[0060] S3252, Initial solution generation, including: 1. For each "flight platform-mission" group, based on the basic idea of ​​integer programming, construct a simplified mission allocation model, ignoring consecutive flight constraints (temporarily assuming that the flight platform only performs a single mission), and solve for the initial allocation scheme of flight platforms and missions within each group, i.e., determine... Initial value: For the set of flight platforms within the group and tasks Construct a simplified objective function The constraints are , The simplified model is solved by enumeration, and the result is obtained. The initial value (i.e., the flight time selected within this group) The shortest flight platform is assigned to the mission. ).

[0061] 2. Based on the initial task allocation scheme ( (Initial values), and combining the basic ideas of dynamic programming, determine the succession flight scheme of the flight platform ( (Initial value) For each flight platform Collect all the tasks initially assigned to it to form a task sequence. With "flying platform" With the objective of minimizing the total flight time between these tasks, a dynamic programming state transition equation is constructed: Let dp[s][e] be the flight platform. From the task Flight to mission The minimum follow-up flight time is given by the state transition equation. Where s and e are task sequences The task index in the middle; by solving this dynamic programming model, the flight platform is obtained. The optimal task execution order is determined, thereby determining The initial value (consistent with the optimal sequence of successive flights, =1, otherwise 0).

[0062] 3. Combining , Initial values, calculate for each flight platform Total time Thus, the total flight time of the cluster can be obtained. The initial values ​​are used to form the initial feasible solution of the model.

[0063] S3253, iterative optimization, including: By employing a combination of heuristic search and local optimization, the initial feasible solution is iteratively optimized to gradually reduce the total flight time of the cluster. The specific steps are as follows: 1. Determine the iteration termination condition: Set the maximum number of iterations N (preset value, set according to the task size, generally 50-200), or set the convergence threshold ε of the total flight time (preset value, in seconds, generally 0.1-1). Stop the iteration when the number of iterations reaches N, or when the difference between the total flight time of two consecutive iterations is less than ε.

[0064] 2. Iterative steps: (1) Local search: for each flight platform Fix the set of tasks assigned to it and adjust the order of task execution (i.e., adjust the task execution order). (The value of ), and based on the idea of ​​dynamic programming, the optimal task execution order of the flight platform is resolved, and the adjusted value is calculated. If the adjustment is Smaller than before adjustment If the proposed adjustment is successful, the adjustment plan will be retained; otherwise, the adjustment will be abandoned.

[0065] (2) Cross optimization: Select the two flight platforms with the longest total time in the cluster. , Extract the task sets assigned by both parties. , ,calculate and intersection ,Will The tasks in the process are swapped and reassigned (i.e., the tasks originally assigned to each other are swapped and reassigned). Task Assigned to Originally allocated Task Assigned to ), recalculate , Total time , If max( , ) is less than the original max( , If the condition is met, the swap plan should be retained; otherwise, the swap should be abandoned.

[0066] (3) Boundary optimization: For task allocation constraints and flight platform load constraints, optimize the solutions near the boundary (e.g., when the flight platform load reaches the limit). Fine-tune the solution where the task allocation is close to the upper limit of the constraint. For example, allocate some tasks of the overloaded flight platform to the flight platform with a lighter load and higher flight efficiency in the same subgroup, recalculate the total time, and retain the better fine-tuning solution.

[0067] (4) Update the solution: Take the optimal solution obtained from the above local search, cross optimization, and boundary optimization as the feasible solution for the current iteration, and update the solution. , The value of is used to calculate the total flight time of the cluster in the current iteration. .

[0068] 3. Repeat the above iterative steps until the iteration termination condition is met, and obtain the optimized feasible solution.

[0069] S3254, optimal solution output and track generation, including: 1. Extract from the optimized feasible solution , The optimal value is determined for each flight platform. The final task allocation scheme (i.e., the set of tasks to be allocated) and the order in which tasks are executed.

[0070] 2. For each flight platform Based on its initial position Assigning task execution location And the mission execution order, combined with position and time constraints, to calculate the flight platform Position coordinates of τ at each time point Forming a flight platform The continuous flight path curve; the specific calculation method is as follows: based on flight time , The flight process is divided into several time periods. Within each time period, the position coordinates of the flight platform at each moment are calculated based on the linear interpolation method to ensure that the flight path curve is continuous and smooth.

[0071] 3. Collect the continuous flight path curves of all flight platforms to form a flight path set of the flight platform cluster. This flight path set satisfies the objective of minimizing the total flight time and meets all constraints, which is completely consistent with the requirements of S3. It can be directly used as the output result of S3.

[0072] This trajectory planning model organically combines group theory and optimization theory from operations research. Through operations such as subgroup partitioning and homomorphic mapping in group theory, it solves the problem of precise matching between the flight platform and the mission, ensuring that the matching results meet the technical specifications of the flight platform and the requirements of the mission. By using the ideas of integer programming and dynamic programming from operations research, it constructs an optimization model that minimizes the total flight time, and ensures the feasibility of solving the model through multiple constraints.

[0073] The solution to this trajectory planning model adopts a multi-algorithm integration approach, combining group theory partitioning, integer programming, dynamic programming search, and heuristic optimization to improve the stability and efficiency of the model solution.

[0074] In all embodiments of the present invention, the variables involved in all computational expressions or mathematical functions have been dimensionlessized before computation.

[0075] In all embodiments of the present invention, the values ​​of the independent variables in the input of all computational expressions or mathematical functions meet the reasonable requirements of the input range of the computational expressions or mathematical functions, and can ensure that the computational expressions or mathematical functions can be calculated smoothly without violating physical laws or mathematical rules.

[0076] A second aspect of the present invention discloses a trajectory planning device for a flight platform cluster, the device comprising: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the flight platform cluster's trajectory planning method.

[0077] In a third aspect, the present invention discloses a computer-readable storage medium storing computer instructions, which, when invoked by a computer, are used to execute the flight platform cluster trajectory planning method.

[0078] In a fourth aspect of this invention, an information data processing terminal is disclosed, which is used to implement the flight platform cluster trajectory planning method.

[0079] The above description is merely an embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the present invention should be included within the scope of the claims of the present invention.

Claims

1. A trajectory planning method for a flight platform cluster, characterized in that, include: S1, collects a set of mission requirement information and a set of technical indicator information for the flight platform cluster; The task requirement information set includes the execution location and requirement information of each task to be executed; the requirement information includes the requirement task type information and the requirement values ​​of all technical indicators; the flight platform cluster technical indicator information set includes the execution task type information, location information and technical indicator value set of each flight platform; the technical indicator value set includes several technical indicator values. S2, preprocess the task requirement information set and the flight platform cluster technical indicator information set to obtain a preprocessed information set; S3, perform trajectory planning processing on the preprocessed information set to obtain the trajectory set of the flight platform cluster.

2. The trajectory planning method for a flight platform cluster as described in claim 1, characterized in that, The process of performing trajectory planning on the preprocessed information set to obtain the trajectory set of the flight platform cluster includes: S31, based on the requirement information of each task to be executed in the preprocessed information set, the flight platform cluster technical indicator information set in the preprocessed information set is filtered and matched to obtain a candidate flight platform set for each task to be executed; S32 performs trajectory planning on the set of candidate flight platforms for all pending tasks to obtain the trajectory set of the flight platform cluster.

3. The trajectory planning method for a flight platform cluster as described in claim 2, characterized in that, Based on the requirement information of each task to be executed in the preprocessed information set, the technical indicator information set of the flight platform cluster in the preprocessed information set is filtered and matched to obtain a candidate flight platform set for each task to be executed, including: S311, based on the requirement task type information of each task to be executed in the preprocessed information set, a flight platform set that matches the requirement task type information is selected from the flight platform cluster technical indicator information set in the preprocessed information set. S312, For each task to be executed, the matching degree is calculated by using the required values ​​of all technical indicators of the task to be executed and the corresponding set of flight platforms that match the required task type information obtained by screening, and the corresponding matching matrix is ​​obtained. S313, perform threshold calculation on the matching matrix to obtain the matching threshold; S314, using the matching threshold, the set of matching flight platforms is filtered to obtain the set of candidate flight platforms for the task to be executed.

4. The trajectory planning method for a flight platform cluster as described in claim 2, characterized in that, The process of performing trajectory planning on the candidate flight platform set for all pending tasks yields the trajectory set of the flight platform cluster, including: S321, Based on the set of candidate flight platforms for all tasks to be executed and the set of task requirement information in the preprocessed information set, construct the crowdless information and task group information. S322, Based on the aforementioned crowd information and task group information, construct a set of constraints; S323, Based on the aforementioned crowd information and task group information, an objective function is constructed; S324, Using the set of constraints and the objective function, a trajectory planning model is constructed; S325, Solve the trajectory planning model to obtain the trajectory set of the flight platform cluster.

5. The trajectory planning method for a flight platform cluster as described in claim 4, characterized in that, The construction of the data without crowd information includes: Using the set of candidate flight platforms for all tasks to be executed in the preprocessed information set, a set U is constructed, U = Where m is the total number of candidate flight platforms, and no crowd information is defined. ,in, For group binary operations, it represents the collaborative operation relationship between flight platforms; The construction of the task group information includes: Let the set of tasks to be executed be T= Where n is the total number of tasks to be executed, and for each task... Its candidate flight platform set is Define task corresponding subgroup , A subgroup of G, i.e. And it satisfies all the axioms of the group; Define a group homomorphic mapping f and construct the mapping relationship. , so that for any ,have ,in, For a task set T, a binary operation represents the relationship between tasks; Task group information is constructed using the set of execution tasks, the group homomorphic mapping, and the subgroups corresponding to all tasks.

6. The trajectory planning method for a flight platform cluster as described in claim 5, characterized in that, The set of constraints is constructed based on the aforementioned crowd information and task group information, including: A set of decision variables is constructed; the set of decision variables includes: initial task assignment variables. Continuing task allocation variables Location variables ; The parameter variable set is constructed as follows: The parameter variable set includes: candidate flight platforms initial position coordinates ,Task Execution location coordinates Candidate flight platform flight speed Candidate flight platform From the initial position Flight to mission Execution location single flight time Candidate flight platform From the task Execution location Flight to mission Execution location connecting flight time ,Task Execution time ; Construct a set of intermediate variables; the set of intermediate variables includes: candidate flight platforms. Total flight and execution time Total flight time of the flight platform cluster .

7. The trajectory planning method for a flight platform cluster as described in claim 6, characterized in that, The expression for the objective function is: in, This is the overall objective variable, which is also the total flight time of the flight platform cluster. For flight platform Total task execution time Indicates flight platform The sum of the single flight times from the initial position to all assigned mission points. Indicates flight platform The sum of the connecting flight times between each assigned task point, Indicates flight platform The sum of the execution times for completing all assigned tasks.

8. A trajectory planning device for a flight platform cluster, characterized in that, The device includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the flight platform cluster trajectory planning method as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, which, when invoked by a computer, are used to execute the flight platform cluster trajectory planning method as described in any one of claims 1 to 7.

10. An information data processing terminal, characterized in that, The information data processing terminal is used to implement the flight platform cluster trajectory planning method as described in any one of claims 1 to 7.

Images