Cooperative observation task planning method and device based on heterogeneous air-space platform

Abstract

The invention provides a collaborative observation task planning method and device based on a heterogeneous aerospace platform, and the method comprises the steps: determining optical satellite coverage geographic grid data based on a to-be-observed region, and enabling the to-be-observed region to be determined based on the position and the navigational speed of a to-be-observed target; determining an initial collaborative observation task planning scheme based on the optical satellite coverage geographic grid data, the unmanned aerial vehicle coverage geographic grid data and the airship coverage geographic grid data; and optimizing the initial collaborative observation task planning scheme according to a genetic algorithm and a simulated annealing algorithm to obtain a target collaborative observation task planning scheme. According to the collaborative observation task planning method and device based on the heterogeneous air-space platform provided by the invention, through two-stage iterative optimization of the simulated annealing-genetic algorithm, the method and device can be effectively applied to collaborative task planning based on three heterogeneous air-based and space-based earth observation platforms of an optical satellite, an airship and an unmanned aerial vehicle in a large area; and the observation capability during the emergency search of the marine target is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned platform mission planning, and in particular to a collaborative observation mission planning method and device based on a heterogeneous aerospace platform. Background Art

[0002] In recent years, earth remote sensing technology has developed rapidly, and various aerospace platforms such as optical satellites, airships, and drones have become important earth observation resources. All three types of platforms have the ability to carry precision observation payloads, and each has its own advantages and disadvantages in terms of observation mode, coverage, working cycle, and operating cost. For example, optical satellites have a large observation range, but the cost is high and continuous observation is impossible; drones have good maneuverability, easy payload loading, and high resolution, but a small range and a limited range; airship platforms have low observation costs, strong endurance, and flexible viewing angles, but they move slowly.

[0003] Due to the geographical characteristics of my country's coastline, some coastal areas and north-south ships sail along the meridians, which makes it impossible for shore-based AIS stations to obtain ship data, resulting in large gaps in AIS data along my country's coast, which makes it very passive in emergency operations. Maritime emergency search missions usually require rapid coverage and search of large areas of sea, which are characterized by time pressure and large search areas, far exceeding the observation capabilities of a single platform. Joint aerospace observation platforms, coordinated efficient collaborative task planning, and effective complementarity of aerospace observation resource advantages are an effective solution to the problem of emergency search for maritime targets in the absence of AIS data. Summary of the invention

[0004] The present invention provides a collaborative observation task planning method and device based on heterogeneous aerospace platforms, which are used to solve the technical problem of insufficient observation capability during emergency search of marine targets in the prior art.

[0005] The present invention provides a collaborative observation task planning method based on heterogeneous aerospace platforms, comprising the following steps.

[0006] Determining optical satellite coverage geographic grid data based on an area to be observed, wherein the area to be observed is determined based on a position and a speed of a target to be observed; Determining an initial collaborative observation mission planning scheme based on the optical satellite coverage geographic grid data, the drone coverage geographic grid data, and the airship coverage geographic grid data; The initial collaborative observation task planning scheme is optimized according to a genetic algorithm and a simulated annealing algorithm to obtain a target collaborative observation task planning scheme.

[0007] In some embodiments, determining an initial collaborative observation mission planning scheme based on the optical satellite coverage geographic grid data, the drone coverage geographic grid data, and the airship coverage geographic grid data includes: Based on the optical satellite coverage geographic grid data, the drone coverage geographic grid data and the airship coverage geographic grid data, heterogeneous platform task allocation is performed to determine the satellite observation task, the drone observation task and the airship observation task; Performing initial path planning based on the UAV observation mission and the airship observation mission, determining the UAV use cost, the airship use cost, the UAV flight time, and the airship flight time; Determine the fitness of each initial path plan based on the satellite observation mission, the use cost of the drone, the use cost of the airship, the flight time of the drone and the flight time of the airship; The initial path plan with the minimum fitness is determined as the initial collaborative observation task planning plan.

[0008] In some embodiments, performing heterogeneous platform task allocation based on the optical satellite coverage geographic grid data, the drone coverage geographic grid data, and the airship coverage geographic grid data to determine the satellite observation task, the drone observation task, and the airship observation task includes: Determine conflicting mission points among the mission points assigned to the satellite, the UAV, and the airship based on the distance difference matrix; Based on the conflicting mission points, the satellite observation mission, the UAV observation mission and the airship observation mission are determined.

[0009] In some embodiments, the initial collaborative observation task planning scheme is optimized according to the genetic algorithm and the simulated annealing algorithm to obtain the target collaborative observation task planning scheme, including: Performing genetic recombination and genetic mutation on the path of any platform in the initial collaborative observation task planning scheme according to the genetic algorithm to obtain a new path planning, and determining the fitness of each path planning; The target collaborative observation task planning scheme is determined according to the fitness of all paths and the simulated annealing algorithm.

[0010] In some embodiments, determining the target collaborative observation task planning scheme according to the fitness of all paths and the simulated annealing algorithm includes: The fitness of the initial collaborative observation task planning scheme and the fitness of the target collaborative observation task planning scheme are compared based on the temperature in the simulated annealing algorithm, and the target collaborative observation task planning scheme is updated.

[0011] In some embodiments, the method further comprises: The geographic grid data covered by the drone and the geographic grid data covered by the airship are determined based on the drone parameters and the airship parameters.

[0012] The present invention also provides a collaborative observation task planning device based on a heterogeneous aerospace platform, comprising the following modules: A first determination module is used to determine the optical satellite coverage geographic grid data based on the area to be observed, wherein the area to be observed is determined based on the position and speed of the target to be observed; A second determination module is used to determine an initial collaborative observation mission planning scheme based on the optical satellite coverage geographic grid data, the drone coverage geographic grid data, and the airship coverage geographic grid data; The first optimization module is used to optimize the initial collaborative observation task planning scheme according to the genetic algorithm and the simulated annealing algorithm to obtain the target collaborative observation task planning scheme.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements a collaborative observation mission planning method based on a heterogeneous aerospace platform as described in any one of the above-mentioned methods.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for planning collaborative observation tasks based on heterogeneous aerospace platforms as described in any one of the above is implemented.

[0015] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned collaborative observation task planning methods based on heterogeneous aerospace platforms.

[0016] The collaborative observation task planning method and device based on heterogeneous air-space platforms provided by the present invention can be effectively applied to collaborative task planning based on three heterogeneous air-based and space-based earth observation platforms, namely optical satellites, airships, and unmanned aerial vehicles, in large areas through dual-stage iterative optimization of simulated annealing-genetic algorithm, thereby improving the observation capability during emergency search of targets at sea. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 It is a flow chart of the collaborative observation task planning method based on heterogeneous aerospace platforms provided by the present invention.

[0019] Figure 2It is a structural schematic diagram of a collaborative observation mission planning device based on a heterogeneous aerospace platform provided in the invention example.

[0020] Figure 3 It is a schematic diagram of the physical structure of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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.

[0022] Figure 1 is a flow chart of a collaborative observation task planning method based on heterogeneous aerospace platforms provided by the present invention, such as Figure 1 As shown, the method includes the following: Step 101: Determine optical satellite coverage geographic grid data based on an area to be observed, wherein the area to be observed is determined based on the position and speed of a target to be observed.

[0023] Step 102: Determine an initial collaborative observation mission planning scheme based on the optical satellite coverage geographic grid data, the drone coverage geographic grid data, and the airship coverage geographic grid data.

[0024] Step 103: Optimize the initial collaborative observation task planning scheme according to the genetic algorithm and the simulated annealing algorithm to obtain the target collaborative observation task planning scheme.

[0025] Specifically, the area to be observed can be determined based on the known pre-accident information (position, speed) of the target to be observed. The satellite coverage geographic grid data, the drone coverage geographic grid data and the airship coverage geographic grid data are determined based on the area to be observed.

[0026] Then the simulated annealing algorithm is initialized. First, heterogeneous platform tasks are allocated according to the geographic grid data covered by optical satellites, the geographic grid data covered by drones, and the geographic grid data covered by airships to determine the satellite observation tasks, the drone observation tasks, and the airship observation tasks. Then, initial path planning is performed based on the drone observation tasks and the airship observation tasks to determine the drone usage cost, the airship usage cost, the drone flight time, and the airship flight time. Then, the fitness of each initial path plan is determined based on the satellite observation tasks, the drone usage cost, the airship usage cost, the drone flight time, and the airship flight time. Finally, the initial path plan with the smallest fitness is determined as the initial collaborative observation task planning plan.

[0027] Finally, the paths of the heterogeneous platforms are planned according to the genetic algorithm to obtain the target collaborative observation task planning scheme.

[0028] The collaborative observation task planning method based on heterogeneous air-space platforms provided by the present invention can be effectively applied to collaborative task planning based on three heterogeneous air-based and space-based earth observation platforms, namely optical satellites, airships and drones, in large areas through dual-stage iterative optimization of simulated annealing-genetic algorithm, thereby improving the observation capability during emergency search of targets at sea.

[0029] In some embodiments, the method further comprises: The geographic grid data covered by the drone and the geographic grid data covered by the airship are determined based on the drone parameters and the airship parameters.

[0030] Specifically, the predicted navigation distance of the target to be observed is calculated. is the target's speed before the accident, and the search time interval is , then the search duration is:

[0031] Then the predicted target navigation distance during the search period is:

[0032] Determine the area to be observed. The area to be observed is a spherical rectangular area with a side length of 2L constructed along the longitude and latitude directions with the target crash location as the center. is the radius of the earth, then if the target sails along the longitude or latitude, the geocentric angle corresponding to the sailing distance L is:

[0033] set up is the target crash location, where represents latitude, Represents longitude, the northwest vertex of the area to be observed , Northeast vertex , southwest vertex , southeast vertex The coordinates are:

[0034] The area to be observed is the coordinate point set The spherical rectangular area enclosed.

[0035] Divide the area to be observed into geographic grids of equal length along longitude and latitude. represents the geographic grid length, then the target maximum number of navigation grids is:

[0036] The area to be observed is divided into A rectangular grid area.

[0037] Calculate the coordinates of the center of the geographic grid. In the area to be observed, the coordinates of the center of the grid in the mth row along the latitude direction and the kth column along the longitude direction are:

[0038] make:

[0039] Calculate the center coordinates of each grid in the area to be observed in turn, and set it as the coordinate set of the area to be observed .

[0040] The area covered by the optical satellite observations is then calculated.

[0041] Calculate the visibility of the optical satellite to the area to be observed. For the constructed area to be observed, the Access analysis tool in the STK software is used to calculate the visibility of all optical satellites in the existing database to the area to be observed within the search time.

[0042] Create a new scene in the STK software and import all satellite TLE parameters in the existing optical satellite database.

[0043] Create a new area and set it as the area to be observed .

[0044] Use Access tools to set the visibility calculation time to the search time period , the calculation area is the area to be observed The output result is the set of visible satellites in the database for the area to be observed within the search time. And the corresponding visible time interval of each satellite ,in is the number of satellites visible for the area to be observed.

[0045] Calculate the optical satellite observation coverage area. Use STK and MATLAB co-simulation method to calculate the structured optical satellite observation coverage area.

[0046] Use STK Matlab Connector to establish the communication interface between software. Set the scene time to the search time period , import the visible satellite set calculated in the database TLE parameters.

[0047] Add the coordinates of the area to be observed. Added to the STK 3D interface.

[0048] Assume that any visible satellite is , the visible time is , add sensors, set appropriate side swing angles and beam opening angles so that the beam covers the area to be observed.

[0049] Through the software visualization interface, the simulation time is controlled and the visible satellites are obtained. , the visible time is The coordinate set of the area to be observed that can be covered is recorded as ,in for The satellite's coverage geographic grid coordinate set is: .

[0050] Visible satellite set Each satellite in , repeat the above steps and calculate the corresponding coverage geographic grid set as .

[0051] Then the instantaneous field of view of UAV and airship payload observation is calculated.

[0052] Calculate the instantaneous field of view radius of the drone and airship observation. Assume the hovering height of the drone is , the hovering height of the airship is , the field of view of the optical camera carried by the drone is , the field of view of the optical camera carried by the airship is , calculate the instantaneous field of view radius of the drone observation :

[0053] Calculation of instantaneous field of view radius of airship observation :

[0054] Assume that the hovering position of the drone at a certain moment is , the hovering position of the airship at a certain moment is The instantaneous field of view of the drone is based on the hovering position. is the center of the circle, The radius is the spherical circular area formed by the airship; the instantaneous field of view of the airship is the hovering position is the center of the circle, The radius is the circular area of ​​the spherical surface.

[0055] Calculate the coverage of drones and airships.

[0056] Calculate the number of geographic grids covered by drones:

[0057] in The number of geographic grids covered by the drone, is the geographic grid length.

[0058] Calculate the number of geographical grids covered by the airship:

[0059] in The number of geographic grid cells that the airship covers along the latitude line.

[0060] The collaborative observation task planning method based on heterogeneous air-space platforms provided by the present invention can be effectively applied to collaborative task planning based on three heterogeneous air-based and space-based earth observation platforms, namely optical satellites, airships and drones, in large areas through dual-stage iterative optimization of simulated annealing-genetic algorithm, thereby improving the observation capability during emergency search of targets at sea.

[0061] In some embodiments, determining an initial collaborative observation mission planning scheme based on the optical satellite coverage geographic grid data, the drone coverage geographic grid data, and the airship coverage geographic grid data includes: Based on the optical satellite coverage geographic grid data, the drone coverage geographic grid data and the airship coverage geographic grid data, heterogeneous platform task allocation is performed to determine the satellite observation task, the drone observation task and the airship observation task; Performing initial path planning based on the UAV observation mission and the airship observation mission, determining the UAV use cost, the airship use cost, the UAV flight time, and the airship flight time; Determine the fitness of each initial path plan based on the satellite observation mission, the use cost of the drone, the use cost of the airship, the flight time of the drone and the flight time of the airship; The initial path plan with the minimum fitness is determined as the initial collaborative observation task planning plan.

[0062] Specifically, the simulated annealing algorithm is initialized.

[0063] Initial algorithm parameter setting.

[0064] Initial parameter settings for drones, airships, and satellites. Set search limit time T, drone parameter set ,in The number of drones, The speed of the drone, Fuel cost for drones, Deploy the drone to a location, For the UAV's range, Number of geographic grids to cover for drones; airship parameter set ,in is the number of airships, is the airship speed, For the airship fuel cost, Deploy the airship to a location, For the UAV's range, The number of geographic grid cells to cover for the airship. , Specifically:

[0065] The cost of calling each satellite is .

[0066] Set the initial temperature to , cooling coefficient , threshold temperature . Set the current temperature .

[0067] Initial parameter setting of genetic algorithm. Set the number of chromosomes in the population to , the maximum number of iterations is , the probability of inner crossover , outer crossover probability , the number of inner crossovers , the number of outer crossings , mutation probability , number of mutations .

[0068] Task allocation on heterogeneous platforms.

[0069] Satellite task allocation. Randomly select the number of visible satellites , and in the visible satellite set China-Israel is the number, randomly select the visible satellite set , the corresponding coverage geographic grid set is , that is, the allocation of observation tasks to the satellite platform.

[0070] Initial mission allocation for drones and airships.

[0071] Calculate the number of sampling mission points for drones and airships, set :

[0072] Substitute the calculated instantaneous field of view radius of the drone and airship observation , , calculate the number of airship and drone missions:

[0073] in, Assign the number of tasks to the drones, Assign the number of missions to the airship.

[0074] Select the initial UAV and airship observation mission. In the coordinate set of the area to be observed In, randomly select coordinate points, denoted as ,satisfy , is the total mission set of UAVs and airships. Randomly select coordinate points, denoted as ,satisfy , which is the initial task assignment for the UAV. Calculation right The complement of , that is, the initial task allocation of the airship, is recorded as :

[0075] In some embodiments, performing heterogeneous platform task allocation based on the optical satellite coverage geographic grid data, the drone coverage geographic grid data, and the airship coverage geographic grid data to determine the satellite observation task, the drone observation task, and the airship observation task includes: Determine conflicting mission points among the mission points assigned to the satellite, the UAV, and the airship based on the distance difference matrix; Based on the conflicting mission points, the satellite observation mission, the UAV observation mission and the airship observation mission are determined.

[0076] Specifically, conflict detection.

[0077] Calculate the actual distance matrix. First, calculate the coordinate point set of the drone, airship, and satellite missions:

[0078] Among them, there are a total of UAV, airship and satellite mission points The coordinate point set is expressed as a geographic grid, that is: , then the horizontal coordinate m set of the UAV, airship, and satellite mission coordinate point set is , the ordinate k set of the UAV, airship, and satellite mission coordinate point set is . Calculate the actual distance matrix:

[0079] in, for -dimensional all-1 vector.

[0080] Compute the distance difference matrix.

[0081] Calculate the standard distance matrix of drones, airships, and satellites. Assume the number of satellite coverage grids is , then:

[0082] Will It is divided into three sections according to the three different mission points of UAV, airship and satellite. of The coordinate points are the UAV mission points. of The coordinate point is the airship mission point. of The coordinate point is the satellite mission point.

[0083] Calculated number of grids covered by drones and airships and , calculate the standard distance matrix of drone, airship and satellite respectively, where the number of satellite coverage grids is 1:

[0084] in, , , They are , , dimensional all-1 vector, , , They are , , dimensional all-zero vector.

[0085] Compute the standard distance matrix:

[0086] in, for dimensional identity matrix, is the matrix Hadamard product.

[0087] Calculate the distance difference matrix. According to the actual distance matrix, calculate the distance difference matrix:

[0088] in, for -dimensional upper triangular matrix.

[0089] Filter mission points with non-conflicting coverage. According to the distance difference matrix, filter mission points with non-conflicting coverage in the order of satellite > airship > drone.

[0090] Will All satellite mission points are retained, that is, .

[0091] Filter the airship mission points. First, the distance difference matrix Expressed as the difference between the distances of drones, airships, and satellites:

[0092] in, , , is the distance matrix of the mission points of UAV, airship and satellite, , , They are , , dimensional matrices, which are the distance matrices of the mission coordinate points between the UAV and the airship, the UAV and the satellite, and the airship and the satellite.

[0093] Calculate the airship conflict judgment vector:

[0094] in, judge Each element in Whether it is negative is calculated by the following formula:

[0095] in, For one Dimensional vector , each element corresponds to an airship mission point, if , then it is a conflicting task point and should be removed; if , then keep it, and record the selected airship mission point set as .

[0096] Filter drone mission points.

[0097] Calculate the UAV conflict judgment vector:

[0098] in, , To determine the weight of conflicts between drones, satellites and airships, For one Dimensional vector , each element corresponds to an airship mission point, if , then it is a conflicting task point and should be removed; if , then keep it, and record the selected UAV mission point set as .

[0099] Population initialization, initialize each chromosome in the population.

[0100] Chromosome initialization.

[0101] Initial path planning for drones and airships.

[0102] Initial path planning for the drone.

[0103] Use the kmeans tool in MATLAB to transform the UAV mission point set By clustering Group, set the input parameter to the drone mission point set , the number of drones , output Cluster centers, denoted as cluster center set , each cluster center Corresponding to the task point set .

[0104] The coordinate set of the area to be observed , find the cluster center set Each point The corresponding longitude and latitude coordinates , forming a cluster center coordinate set, recorded as:

[0105] Calculate the distance matrix The initial position of the drone is set by , and the cluster center coordinate set , calculate the distance matrix:

[0106] in, is the radius of the Earth.

[0107] Drone matching. Get the distance matrix The i-th row , calculate the minimum value, set it to , is the cluster center corresponding to the i-th drone .

[0108] Will The min column of is set to infinity:

[0109] Set up , repeat the above steps to get the cluster center set corresponding to each drone: .

[0110] Calculate the initial path of the drone. Assume the drone set is , take the cluster center task point set corresponding to the i-th UAV ,set up There are Task points. Calculate the relationship between each point and the cluster center point The tangent value of :

[0111] Calculate the tangent value of each point in turn to get the tangent value set , for the set of tangent values Sort from small to large and get , the points corresponding to the tangent values ​​are divided into Rearrange the order of and get the initial path of UAV i as .

[0112] Set up , repeat the above steps to get the initial path corresponding to each UAV: .

[0113] Initial airship path planning. Set the UAV mission point set Replaced with airship mission point set , get the airship collection The initial path corresponding to each airship .

[0114] Calculate the cost of drone and airship planning solutions.

[0115] Calculate the cost of the drone planning solution. The planning solution cost includes the drone flight distance, time and usage cost.

[0116] Calculate the flight distance of the drone.

[0117] For drone i, the initial path is:

[0118] The coordinate set of the area to be observed , find the initial path Each point The corresponding longitude and latitude coordinates , forming the initial path coordinate set, recorded as:

[0119] Drone i from The full path is:

[0120] set up is the spherical distance from point A to point B, and the longitude and latitude of points A and B are:

[0121] Then we have:

[0122] Calculate the flight distance of drone i as:

[0123] Set up Repeat the above steps to get the distance corresponding to each drone: .

[0124] Calculate the flight time of the drone. Calculate the flight time of the drone i:

[0125] Set up , and the flight time corresponding to each UAV is .

[0126] Calculate the cost of using a drone. Calculate the cost of using a drone:

[0127] Set up , and the usage cost of each drone is obtained as .

[0128] Calculate the cost of the airship planning solution. Replaced with the initial path point set of the airship , and the distances corresponding to each airship are , the flight time of each airship is , the corresponding use cost of each airship is .

[0129] Determine whether the UAV and airship planning schemes meet the endurance and time constraints.

[0130] Determine whether the drone planning scheme meets the endurance and time constraints.

[0131] Compare the distance and range of the drone ,like , then the endurance condition is met; otherwise, the endurance condition is not met.

[0132] calculate The longest sailing time , compare the longest navigation time with the search limit time T, if , then the time limit is met, otherwise, the endurance condition is not met.

[0133] Determine whether the airship planning scheme meets the endurance and time constraints.

[0134] Compare the distance and range of the airship ,like , then the endurance condition is met; otherwise, the endurance condition is not met.

[0135] calculate The longest sailing time , compare the longest navigation time with the search limit time T, if , then the time limit is met, otherwise, the endurance condition is not met.

[0136] If any of the two constraints of battery life and time limit is not met, repeat the above steps until the constraint is met.

[0137] Calculate the fitness function of the planning solution.

[0138] Set the fitness coefficient to , calculate the fitness function of the planning scheme:

[0139] in:

[0140] Repeat step Chromosome Initialization times, among which Initialize each chromosome to the number of chromosomes in the set population.

[0141] Assume that the fitness of each chromosome is , calculate the minimum fitness as , the corresponding chromosome is the global optimal chromosome .

[0142] The collaborative observation task planning method based on heterogeneous air-space platforms provided by the present invention can be effectively applied to collaborative task planning based on three heterogeneous air-based and space-based earth observation platforms, namely optical satellites, airships and drones, in large areas through dual-stage iterative optimization of simulated annealing-genetic algorithm, thereby improving the observation capability during emergency search of targets at sea.

[0143] In some embodiments, the initial collaborative observation task planning scheme is optimized according to the genetic algorithm and the simulated annealing algorithm to obtain the target collaborative observation task planning scheme, including: Performing genetic recombination and genetic mutation on the path of any platform in the initial collaborative observation task planning scheme according to the genetic algorithm to obtain a new path planning, and determining the fitness of each path planning; The target collaborative observation task planning scheme is determined according to the fitness of all paths and the simulated annealing algorithm.

[0144] Specifically, it can be determined whether the set threshold temperature has been reached. , the Metropolis criterion is used to generate a new optimal solution. Otherwise, the task allocation result is disturbed and the genetic algorithm is used to plan the path for each heterogeneous platform.

[0145] The task allocation results are disturbed, and the genetic algorithm is used to plan the paths for the heterogeneous platforms.

[0146] Initialize the population.

[0147] Calculate the cumulative probability. Suppose the chromosomes in the current population are , and its corresponding fitness is . Calculate the cumulative probability corresponding to each chromosome in the current population. Calculate the inverse of the chromosome adaptability in the current population, set as:

[0148] Calculate the selection probability, set it to :

[0149] Calculate the cumulative probability, set it to :

[0150] The roulette wheel method is used to select parent chromosomes, set .

[0151] from Select a random number , let the accumulated variable be i, and the initial setting be .

[0152] judge Is it true? If true, the i-th chromosome is selected as Otherwise, execute , repeat the above steps of selecting parent chromosomes.

[0153] Repeat the above steps once and select another chromosome .

[0154] Genetic recombination and mutation of parental chromosomes.

[0155] Genetic recombination. Suppose the selected airship and drone mission point set , The total number of mission points is , parental chromosomes It can be expressed as:

[0156] Select the recombinant gene. Randomly select a platform path from ,exist Randomly select a task point , as the gene to be recombined, if there is no task point in the path, reselect the path. Randomly select a platform path from ,exist Randomly select a task point , as the gene to be recombined, if there is no task point in the path, reselect the path.

[0157] Find matching genes. Search Genes to be recombined , as The paired gene of ;exist Search Genes to be recombined , set to .

[0158] Recombining the gene to be recombined and the paired gene. Genes to be recombined ,and Genes to be recombined Exchange, Paired genes in ,and Genes to be recombined Exchange and get two new chromosomes .

[0159] Genetic variation.

[0160] Select the mutant gene. Randomly select a platform path from ,exist Randomly select a task point , as the gene to be mutated.

[0161] Select the mutation position. Randomly select a platform path from ,exist Randomly select a task point , as the position to be mutated, if there is no task point in the path, there is no need to reselect.

[0162] Mutate to the selected position. Middle Path Mission points in Mutation to Path Mid-mission point After , if there is no task point in the path, add it directly to the path as the first task point, and the task point after mutation is set to .

[0163] Same as above, yes Perform gene mutation, and the task point after mutation is set to .

[0164] Calculate the offspring fitness value.

[0165] right , The cost of the UAV and airship planning schemes is calculated respectively, and it is determined whether the UAV and airship planning schemes meet the endurance and time constraints. If not, the steps of gene recombination and mutation are repeated until the constraints are met.

[0166] right , Calculate the fitness function of the planning scheme separately and get the fitness function .

[0167] Repeat the above steps times, and get NP offspring. Let:

[0168] The corresponding fitness functions are .

[0169] Gene screening. Chromosomes of the progeny population Put them together for screening to select the next generation population chromosomes .

[0170] Fitness function sorting. Fitness set for the current population chromosome and the offspring population chromosome Sort in ascending order, and get , and its corresponding chromosome is .

[0171] Take the first NP chromosomes as the next generation population, that is:

[0172] for , the corresponding chromosome is the global optimal chromosome .

[0173] Repeat the above steps for Second-rate.

[0174] Output the global optimal chromosome. Output the newly generated global optimal chromosome as , corresponding to the fitness .

[0175] The collaborative observation task planning method based on heterogeneous air-space platforms provided by the present invention can be effectively applied to collaborative task planning based on three heterogeneous air-based and space-based earth observation platforms, namely optical satellites, airships and drones, in large areas through dual-stage iterative optimization of simulated annealing-genetic algorithm, thereby improving the observation capability during emergency search of targets at sea.

[0176] In some embodiments, determining the target collaborative observation task planning scheme according to the fitness of all paths and the simulated annealing algorithm includes: The fitness of the initial collaborative observation task planning scheme and the fitness of the target collaborative observation task planning scheme are compared based on the temperature in the simulated annealing algorithm, and the target collaborative observation task planning scheme is updated.

[0177] Specifically, the Metropolis criterion is used to generate a new optimal solution. Suppose the current optimal chromosome is , corresponding to the fitness , the newly generated global optimal chromosome is , corresponding to the fitness .like , then accept the new optimal solution, replace ,by replace , as the current optimal solution; otherwise, calculate:

[0178] Select a random number between 0 and 1 ,judge Is it true? If so, accept the new optimal solution. replace ,by replace , as the current optimal solution; otherwise, the new optimal solution is rejected.

[0179] Update the temperature, calculating:

[0180] by replace as the current temperature; Output the optimal solution. Output the current optimal chromosome , and its corresponding fitness .

[0181] The collaborative observation task planning method based on heterogeneous air-space platforms provided by the present invention can be effectively applied to collaborative task planning based on three heterogeneous air-based and space-based earth observation platforms, namely optical satellites, airships and drones, in large areas through dual-stage iterative optimization of simulated annealing-genetic algorithm, thereby improving the observation capability during emergency search of targets at sea.

[0182] Figure 2 is a schematic diagram of the structure of a collaborative observation task planning device based on a heterogeneous aerospace platform provided by the invention example, such as Figure 2 As shown, the collaborative observation task planning device based on heterogeneous aerospace platforms provided by the present invention includes a first determination module 201, a second determination module 202, and a first optimization module 203, wherein: A first determination module 201 is used to determine the optical satellite coverage geographic grid data based on the area to be observed, wherein the area to be observed is determined based on the position and speed of the target to be observed; A second determination module 202 is used to determine an initial collaborative observation mission planning scheme based on the optical satellite coverage geographic grid data, the drone coverage geographic grid data, and the airship coverage geographic grid data; The first optimization module 203 is used to optimize the initial collaborative observation task planning scheme according to the genetic algorithm and the simulated annealing algorithm to obtain the target collaborative observation task planning scheme.

[0183] Specifically, the above-mentioned collaborative observation task planning device based on a heterogeneous aerospace platform provided in the embodiment of the present application can implement all the method steps implemented in the above-mentioned collaborative observation task planning method embodiment based on a heterogeneous aerospace platform, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those of the method embodiment will not be described in detail here.

[0184] Figure 3 is a schematic diagram of the physical structure of the electronic device provided by the present invention, such as Figure 3As shown, the electronic device may include: a processor 310, a communications interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communications interface 320 and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute a collaborative observation task planning method based on a heterogeneous aerospace platform, the method comprising: Determining optical satellite coverage geographic grid data based on an area to be observed, wherein the area to be observed is determined based on a position and a speed of a target to be observed; Determining an initial collaborative observation mission planning scheme based on the optical satellite coverage geographic grid data, the drone coverage geographic grid data, and the airship coverage geographic grid data; The initial collaborative observation task planning scheme is optimized according to a genetic algorithm and a simulated annealing algorithm to obtain a target collaborative observation task planning scheme.

[0185] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0186] In some embodiments, determining an initial collaborative observation mission planning scheme based on the optical satellite coverage geographic grid data, the drone coverage geographic grid data, and the airship coverage geographic grid data includes: Based on the optical satellite coverage geographic grid data, the drone coverage geographic grid data and the airship coverage geographic grid data, heterogeneous platform task allocation is performed to determine the satellite observation task, the drone observation task and the airship observation task; Performing initial path planning based on the UAV observation mission and the airship observation mission, determining the UAV use cost, the airship use cost, the UAV flight time, and the airship flight time; Determine the fitness of each initial path plan based on the satellite observation mission, the use cost of the drone, the use cost of the airship, the flight time of the drone and the flight time of the airship; The initial path plan with the minimum fitness is determined as the initial collaborative observation task planning plan.

[0187] In some embodiments, performing heterogeneous platform task allocation based on the optical satellite coverage geographic grid data, the drone coverage geographic grid data, and the airship coverage geographic grid data to determine the satellite observation task, the drone observation task, and the airship observation task includes: Determine conflicting mission points among the mission points assigned to the satellite, the UAV, and the airship based on the distance difference matrix; Based on the conflicting mission points, the satellite observation mission, the UAV observation mission and the airship observation mission are determined.

[0188] In some embodiments, the initial collaborative observation task planning scheme is optimized according to the genetic algorithm and the simulated annealing algorithm to obtain the target collaborative observation task planning scheme, including: Performing genetic recombination and genetic mutation on the path of any platform in the initial collaborative observation task planning scheme according to the genetic algorithm to obtain a new path planning, and determining the fitness of each path planning; The target collaborative observation task planning scheme is determined according to the fitness of all paths and the simulated annealing algorithm.

[0189] In some embodiments, determining the target collaborative observation task planning scheme according to the fitness of all paths and the simulated annealing algorithm includes: The fitness of the initial collaborative observation task planning scheme and the fitness of the target collaborative observation task planning scheme are compared based on the temperature in the simulated annealing algorithm, and the target collaborative observation task planning scheme is updated.

[0190] In some embodiments, the method further comprises: The geographic grid data covered by the drone and the geographic grid data covered by the airship are determined based on the drone parameters and the airship parameters.

[0191] Specifically, the above-mentioned electronic device provided in the embodiment of the present application can implement all the method steps implemented by the method embodiment in which the execution subject is the electronic device, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0192] On the other hand, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer can execute the collaborative observation task planning method based on heterogeneous aerospace platforms provided by the above methods, the method comprising: Determining optical satellite coverage geographic grid data based on an area to be observed, wherein the area to be observed is determined based on a position and a speed of a target to be observed; Determining an initial collaborative observation mission planning scheme based on the optical satellite coverage geographic grid data, the drone coverage geographic grid data, and the airship coverage geographic grid data; The initial collaborative observation task planning scheme is optimized according to a genetic algorithm and a simulated annealing algorithm to obtain a target collaborative observation task planning scheme.

[0193] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the collaborative observation task planning method based on heterogeneous aerospace platforms provided by the above methods, the method comprising: Determining optical satellite coverage geographic grid data based on an area to be observed, wherein the area to be observed is determined based on a position and a speed of a target to be observed; Determining an initial collaborative observation mission planning scheme based on the optical satellite coverage geographic grid data, the drone coverage geographic grid data, and the airship coverage geographic grid data; The initial collaborative observation task planning scheme is optimized according to a genetic algorithm and a simulated annealing algorithm to obtain a target collaborative observation task planning scheme.

[0194] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0195] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0196] It should also be noted that the terms "first", "second", etc. in the embodiments of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first" and "second" are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more.

[0197] In the embodiments of the present application, the term "and / or" describes the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0198] In the embodiments of the present application, the term "plurality" refers to two or more than two, and other quantifiers are similar.

[0199] In this application, "determine B based on A" means that the factor A should be considered when determining B. It is not limited to "B can be determined based on A alone", but should also include: "determine B based on A and C", "determine B based on A, C and E", "determine C based on A, and further determine B based on C", etc. In addition, it can also include taking A as a condition for determining B, for example, "when A meets the first condition, use the first method to determine B"; for example, "when A meets the second condition, determine B", etc.; for example, "when A meets the third condition, determine B based on the first parameter", etc. Of course, it can also be a condition that takes A as a factor for determining B, for example, "when A meets the first condition, use the first method to determine C, and further determine B based on C", etc.

[0200] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A collaborative observation mission planning method based on heterogeneous aerospace platforms, characterized in that: include: Determining optical satellite coverage geographic grid data based on an area to be observed, wherein the area to be observed is determined based on a position and a speed of a target to be observed; Determine an initial collaborative observation mission planning scheme based on the optical satellite coverage geographic grid data, the drone coverage geographic grid data, and the airship coverage geographic grid data; The initial collaborative observation task planning scheme is optimized according to a genetic algorithm and a simulated annealing algorithm to obtain a target collaborative observation task planning scheme.

2. The collaborative observation task planning method based on heterogeneous aerospace platforms according to claim 1 is characterized in that: The determining of an initial collaborative observation mission planning scheme based on the optical satellite coverage geographic grid data, the drone coverage geographic grid data, and the airship coverage geographic grid data includes: Based on the optical satellite coverage geographic grid data, the drone coverage geographic grid data and the airship coverage geographic grid data, heterogeneous platform task allocation is performed to determine the satellite observation task, the drone observation task and the airship observation task; Performing initial path planning based on the UAV observation mission and the airship observation mission, determining the UAV use cost, the airship use cost, the UAV flight time, and the airship flight time; Determine the fitness of each initial path plan based on the satellite observation mission, the use cost of the drone, the use cost of the airship, the flight time of the drone and the flight time of the airship; The initial path plan with the minimum fitness is determined as the initial collaborative observation task planning plan.

3. The collaborative observation task planning method based on heterogeneous aerospace platforms according to claim 2 is characterized in that: The performing heterogeneous platform task allocation based on the optical satellite coverage geographic grid data, the drone coverage geographic grid data and the airship coverage geographic grid data to determine the satellite observation task, the drone observation task and the airship observation task includes: Determine conflicting mission points among the mission points assigned to the satellite, the UAV, and the airship based on the distance difference matrix; Based on the conflicting mission points, the satellite observation mission, the UAV observation mission and the airship observation mission are determined.

4. The collaborative observation task planning method based on heterogeneous aerospace platforms according to claim 1 is characterized in that: The initial collaborative observation task planning scheme is optimized according to the genetic algorithm and the simulated annealing algorithm to obtain the target collaborative observation task planning scheme, including: Performing genetic recombination and genetic mutation on the path of any platform in the initial collaborative observation task planning scheme according to the genetic algorithm to obtain a new path planning, and determining the fitness of each path planning; The target collaborative observation task planning scheme is determined according to the fitness of all paths and the simulated annealing algorithm.

5. The method for planning collaborative observation tasks based on heterogeneous aerospace platforms according to claim 4 is characterized in that: The step of determining the target collaborative observation task planning scheme according to the fitness of all paths and the simulated annealing algorithm includes: The fitness of the initial collaborative observation task planning scheme and the fitness of the target collaborative observation task planning scheme are compared based on the temperature in the simulated annealing algorithm, and the target collaborative observation task planning scheme is updated.

6. The method for collaborative observation mission planning based on heterogeneous aerospace platforms according to claim 1 is characterized in that: The method further comprises: The geographic grid data covered by the drone and the geographic grid data covered by the airship are determined based on the drone parameters and the airship parameters.

7. A collaborative observation mission planning device based on heterogeneous aerospace platforms, characterized in that: include: A first determination module is used to determine the optical satellite coverage geographic grid data based on the area to be observed, wherein the area to be observed is determined based on the position and speed of the target to be observed; A second determination module is used to determine an initial collaborative observation mission planning scheme based on the optical satellite coverage geographic grid data, the drone coverage geographic grid data, and the airship coverage geographic grid data; The first optimization module is used to optimize the initial collaborative observation task planning scheme according to the genetic algorithm and the simulated annealing algorithm to obtain the target collaborative observation task planning scheme.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, it implements the collaborative observation mission planning method based on heterogeneous aerospace platforms as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the collaborative observation mission planning method based on heterogeneous aerospace platforms as described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the collaborative observation mission planning method based on heterogeneous aerospace platforms as described in any one of claims 1 to 6 is implemented.

Images