CN107169608A

CN107169608A - Multiple no-manned plane performs the distribution method and device of multitask

Info

Publication number: CN107169608A
Application number: CN201710389675.3A
Authority: CN
Inventors: 罗贺; 梁峥峥; 胡笑旋; 朱默宁; 王国强; 马华伟; 靳鹏; 夏维; 牛艳秋; 方向
Original assignee: Hefei University of Technology
Current assignee: Hefei University of Technology
Priority date: 2017-05-27
Filing date: 2017-05-27
Publication date: 2017-09-15
Anticipated expiration: 2037-05-27
Also published as: CN107169608B

Abstract

The embodiment of the invention discloses the distribution method and device that a kind of multiple no-manned plane performs multitask.Method includes：Obtain the positional information of multiple unmanned planes and target point, and unmanned plane and wind field kinematic parameter；Building each chromosome in initial population, initial population according to positional information and default genetic algorithm includes the European flight path of unmanned plane quantity；Unmanned plane during flying state is determined according to initial population, kinematic parameter and the hours underway of European path flight path section is completed, obtaining the corresponding all unmanned planes of each chromosome according to hours underway and MUAV VS EVRP models completes task time；Based on genetic algorithm, chromosome in population is intersected, made a variation, after predetermined iterations is reached, chosen unmanned plane and complete task time most short chromosome as the task allocative decision of unmanned plane.Unmanned aerial vehicle flight path planning problem is combined by the embodiment of the present invention with unmanned plane practical flight environment, and the optimal flight paths scheme for obtaining planning is better than the scheme of unmanned plane constant airspeed.

Description

Distribution method and device for multiple unmanned aerial vehicles to execute multiple tasks

Technical Field

The embodiment of the invention relates to the technical field of unmanned aerial vehicles, in particular to a method and a device for distributing multiple tasks executed by multiple unmanned aerial vehicles.

Background

Currently, unmanned Aerial vehicles (uavs) (unmanned Aerial vehicles) are widely used in the military and civilian fields, and can complete various tasks such as target reconnaissance, target tracking, information collection, rescue after earthquake, geological exploration and the like. For example, when multiple UAVs cooperatively detect targets, each UAV must be optimally assigned the target to be detected and planned with an optimal flight path. The problem is a task allocation and flight path planning joint optimization problem which is constrained by multiple factors and is also a non-deterministic problem.

With the research of UAV, environmental factors are gradually included in the research of the problem, especially in the problems of UAV mission allocation, flight path planning, flight control, etc., and how to reduce energy consumption, control the flight state of UAV so that the UAV consumes the least fuel to perform the most mission, has a better mission performing state and higher safety under the influence of the environmental factors is the main work of the current UAV research. The models currently used to solve the UAV mission allocation and mission planning problem are: a TSP model, a TOP model and a VRP model, wherein the TSP model is a model that minimizes the path cost of a traveler after passing all given target points under the condition of only a single traveler; the TOP model is a model that, in the presence of multiple members, allows each member to visit as many target points as possible, thereby maximizing the total profit for all members; the VRP model is a model that, under the condition that the number of vehicles is fixed, the vehicles visit a certain number of target points, and each target point can only be visited once in the process, so that the total distance or total time of UAV navigation is finally minimized.

In the process of implementing the embodiment of the present invention, the inventor finds that in actual operation, it is generally assumed that the speed of the drone is constant in a constant time in the model. However, this assumption is obviously unrealistic, so that the model cannot accurately simulate the actual motion state of the drone, and thus cannot perform optimal track planning.

Disclosure of Invention

One purpose of the embodiment of the invention is to solve the problem that in the prior art, because the speed of the unmanned aerial vehicle is set to be constant during flight path planning, a model cannot accurately simulate the actual motion state of the unmanned aerial vehicle, and further, optimal flight path planning cannot be given.

The embodiment of the invention provides a method for distributing multiple tasks executed by multiple unmanned aerial vehicles, which comprises the following steps:

s1, acquiring position information of a plurality of unmanned aerial vehicles and a plurality of target points, and motion parameters of the unmanned aerial vehicles and a wind field;

s2, constructing an initial population according to the position information of the unmanned aerial vehicles and the target points and a preset genetic algorithm, wherein each chromosome in the initial population comprises European flight paths of the number of the unmanned aerial vehicles, and each European flight path is completed by different unmanned aerial vehicles;

s3, determining the flight state of the unmanned aerial vehicle and the flight time of the unmanned aerial vehicle for completing the track section of the European flight path according to the initial population, the unmanned aerial vehicle and the motion parameters of the wind field, and acquiring the task completion time of all the unmanned aerial vehicles corresponding to the chromosomes in the initial population according to the flight time of the track section and the MUAV-VS-EVRP model;

and S4, performing crossover and mutation treatment on chromosomes in the initial population based on a genetic algorithm, and selecting the chromosome with the shortest task completion time of all unmanned aerial vehicles as the optimal task allocation scheme of the unmanned aerial vehicles after the predetermined iteration times are reached.

Optionally, the constructing an initial population according to the position information of the multiple unmanned aerial vehicles and the multiple target points and a preset genetic algorithm includes:

carrying out chromosome coding according to a coding mode of a preset genetic algorithm to generate an initial population with a preset scale; the chromosome is composed of target point information and unmanned aerial vehicle information; wherein the target point belongs to a setT₀Denotes the start of UAVs, N_TRepresenting the number of target points to which the drone belongsN_URepresenting the number of unmanned aerial vehicles;

the first behavior of the chromosome is the random full arrangement of the target points, the second behavior randomly selects the corresponding unmanned aerial vehicle for each target point according to the unmanned aerial vehicle set, and all the unmanned aerial vehicles in the unmanned aerial vehicle set are ensured to be selected at least once.

Optionally, determining a flight state of the unmanned aerial vehicle and a flight time of the unmanned aerial vehicle for completing a flight path segment of a european flight path according to the initial population, the unmanned aerial vehicle and the motion parameters of the wind field, and obtaining task completion time of all unmanned aerial vehicles corresponding to chromosomes in the initial population according to the flight time of the flight path segment and the MUAV-VS-EVRP model includes:

dividing the European flight path corresponding to each chromosome into a plurality of flight path segments according to the target point visited sequence of the European flight path;

determining the flight state of the unmanned aerial vehicle by combining wind field parameters according to the coordinates of the starting point and the coordinates of the ending point corresponding to each track section, and further acquiring the task completion time of all unmanned aerial vehicles of the unmanned aerial vehicle completing the track section;

and acquiring the task completion time of all unmanned aerial vehicles corresponding to the chromosomes according to the corresponding flight time of each track section.

Optionally, determining the flight state of the unmanned aerial vehicle by combining the wind field parameters according to the coordinates of the starting point and the coordinates of the ending point corresponding to each track segment, and further acquiring the flight time of the unmanned aerial vehicle for completing the track segment includes:

calculating and acquiring unmanned aerial vehicle U by adopting the following formula_iFrom target point T_jFly to target point T_kFlight time of the track segment:

wherein, U_iRepresenting the unmanned aerial vehicle performing the above tasks, U representing the set of unmanned aerial vehicles, T_jAs a starting point, the position of the probe,_Tkto end point, T represents the set of target points, V_g ⁱFor unmanned plane U_iThe ground speed between the two target points;

calculating and acquiring unmanned aerial vehicle U by adopting the following formula_iThe ground speed of (2):

wherein, V_a ⁱRepresenting the magnitude of space velocity, β_a ⁱRepresenting airspeed heading angle, V_g ⁱIndicating the magnitude of the ground speed, β_g ⁱWhich represents the heading angle of the ground speed,the size of the wind speed is shown,represents the wind direction;

calculating and acquiring unmanned aerial vehicle U by adopting the following formula_iAt T_jAnd T_kEuclidean distance between two points:

wherein, X and Y respectively represent the horizontal and vertical coordinates of the corresponding target point.

Optionally, obtaining task completion time of all unmanned aerial vehicles corresponding to chromosomes in the initial population according to the flight time of the flight path segment and the MUAV-VS-EVRP model includes:

acquiring the navigation time according to the MUAV-VS-EVRP model:

the constraint conditions are as follows:

wherein.Representing unmanned aerial vehicle by target point T_jFly to target point T_kThe time of flight of the vehicle,is a binary decision variable, andwhen UAVU_iWarp beam T_jFly to T_kWhen it is, thenIs 1, otherwiseHas a value of 0, N_TRepresenting the number of target points, N_URepresenting the number of drones.

Optionally, based on a genetic algorithm, performing intersection and mutation processing on chromosomes in the initial population, and after a predetermined number of iterations is reached, selecting a chromosome with the shortest task completion time of all the unmanned aerial vehicles as an optimal task allocation scheme for the unmanned aerial vehicles includes:

step 1, generating an initial solution by using the encoding method, generating an initial population with a preset scale, and calculating the fitness of the initial population according to the task completion time of all unmanned aerial vehicles corresponding to each chromosome in the population;

step 2, selecting two individuals (A, B) in a parent population to intersect by using a roulette method, wherein the intersection rule is that the intersection position in the individual A is randomly selected, then the first line of genes in the intersection position of the individual B, which is the same as the intersection position of the individual A, is searched, the intersection position genes in the chromosomes A and B are replaced to obtain new chromosomes C and D, whether the chromosomes C and D meet the constraint condition of the MUAV-VS-EVRP model is judged, if yes, the chromosomes A and B in the population are replaced by the chromosomes C and D, otherwise, the chromosomes which do not meet the constraint condition are subjected to constraint check, namely, when the number of unmanned aerial vehicles in the chromosomes A and B does not meet the constraint condition, one gene position is randomly selected and whether two or more unmanned aerial vehicle codes on the gene position exist or not is judged, if yes, the missing unmanned aerial vehicle codes are put into the gene position, otherwise, reselecting the gene position, generating chromosomes A and B in a chromosome replacement population meeting constraint conditions, and then continuously iteratively updating the population in the step 1 to obtain a new offspring population;

and 3, selecting one chromosome in the population in the step 2 for mutation by using a roulette method, wherein the method for mutating the chromosome is at least one of the following mutation methods, and the method comprises the following steps: performing target point variation on the first line of the chromosome; carrying out unmanned aerial vehicle variation on the second chromosome line;

the whole chromosome variation steps include: firstly, if the first line of the chromosome is mutated, randomly selecting two gene positions of the current chromosome and exchanging target point codes of the corresponding gene positions; selecting whether a second row is mutated or not and a mutation position, if so, randomly generating a value of the unmanned aerial vehicle code which is mutated and is different from the current position to replace an original value, judging whether the chromosome meets the constraint condition of the MUAV-VS-EVRP model or not, if so, replacing the chromosome in the population, otherwise, carrying out constraint check on the chromosome which does not meet the constraint condition, namely, randomly selecting a gene position and judging whether two or more unmanned aerial vehicle codes on the gene position exist or not aiming at the chromosome which does not meet the constraint condition when the number of the unmanned aerial vehicles in the chromosome is not met with the constraint condition, if so, putting the missing unmanned aerial vehicle code into the gene position, otherwise, reselecting the gene position, generating the chromosome which meets the constraint condition to replace the chromosome in the population, and continuously iterating and updating the population in the step 2 to obtain a new offspring population;

step 4, calculating the population fitness of the offspring and selecting the optimal solution of all solutions in the iteration;

step 5, judging whether the current iteration times reach a preset value or not, if not, combining the child population and the parent population in the step 3 according to a certain proportion to form a new parent population, and returning to the step 2; if so, ending the iteration, and taking the finally obtained optimal solution as a task allocation result of the unmanned aerial vehicle.

The embodiment of the invention provides a distribution device for multiple unmanned aerial vehicles to execute multiple tasks, which comprises:

the acquisition module is used for acquiring the position information of a plurality of unmanned aerial vehicles and a plurality of target points, and the motion parameters of the unmanned aerial vehicles and the wind field;

the first processing module is used for constructing an initial population according to the position information of the unmanned aerial vehicles and the target points and a preset genetic algorithm, and each chromosome in the initial population comprises European flight paths of the number of the unmanned aerial vehicles, and each European flight path is completed by different unmanned aerial vehicles;

the second processing module is used for determining the flight state of the unmanned aerial vehicle and the flight time of a track section of a European flight path of the unmanned aerial vehicle according to the initial population, the unmanned aerial vehicle and the motion parameters of a wind field, and acquiring the task completion time of all unmanned aerial vehicles corresponding to chromosomes in the initial population according to the flight time of the track section and an MUAV-VS-EVRP model;

and the third processing module is used for carrying out crossing and mutation processing on chromosomes in the initial population based on a genetic algorithm, and selecting the chromosome with the shortest task completion time of all the unmanned aerial vehicles as the optimal task allocation scheme of the unmanned aerial vehicles after the preset iteration times are reached.

Optionally, the first processing module is configured to perform chromosome coding according to a coding mode of a preset genetic algorithm to generate an initial population of a predetermined scale; the chromosome is composed of target point information and unmanned aerial vehicle information; wherein the target point belongs to a setT₀Denotes the start of UAVs, N_TRepresenting the number of target points to which the drone belongsN_URepresenting the number of unmanned aerial vehicles; the first behavior of the chromosome is the random full arrangement of the target points, the second behavior randomly selects the corresponding unmanned aerial vehicle for each target point according to the unmanned aerial vehicle set, and all the unmanned aerial vehicles in the unmanned aerial vehicle set are ensured to be selected at least once.

Optionally, the second processing module is configured to divide the european style flight path corresponding to each chromosome into a plurality of flight path segments according to the target point visited sequence of the european style flight path; determining the flight state of the unmanned aerial vehicle by combining wind field parameters according to the coordinates of the starting point and the coordinates of the ending point corresponding to each track section, and further acquiring the flight time of the unmanned aerial vehicle for completing the track section; and acquiring task completion time of all unmanned aerial vehicles corresponding to the chromosomes according to the corresponding flight time of each track section.

Optionally, the second processing module is configured to determine a flight state of the unmanned aerial vehicle according to coordinates of a start point and coordinates of a stop point corresponding to each track segment in combination with the wind field parameter, and further acquire a flight time for the unmanned aerial vehicle to complete the track segment, where the flight time includes:

According to the technical scheme, the method and the device for planning the flight path of the unmanned aerial vehicle accessing the multiple target points firstly analyze the wind field and the motion parameters of the unmanned aerial vehicle to obtain the actual flight state of the unmanned aerial vehicle in the wind field, and plan the flight path based on the actual flight state.

Drawings

The features and advantages of the present invention will be more clearly understood by reference to the accompanying drawings, which are illustrative and not to be construed as limiting the invention in any way, and in which:

fig. 1 is a schematic flow chart illustrating a method for allocating multiple drones to perform multiple tasks according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart illustrating a process for calculating the voyage time of the Dubins flight path according to an embodiment of the present invention;

FIG. 3 is a flow chart diagram illustrating a genetic algorithm provided by an embodiment of the present invention;

FIGS. 4 a-4 c show diagrams of operators in a genetic algorithm provided by an embodiment of the present invention;

FIG. 5 is a schematic diagram illustrating wind directions provided by an embodiment of the present invention;

FIG. 6 is a schematic diagram illustrating a velocity vector relationship provided by an embodiment of the present invention;

FIG. 7 is a schematic diagram illustrating an analysis of wind field effects on a UAV flying from A to C according to an embodiment of the present invention;

FIG. 8 illustrates a schematic diagram of segmenting a flight path provided by an embodiment of the present invention;

fig. 9 is a schematic structural diagram illustrating an allocation apparatus for multiple drones to perform multiple tasks according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.

Fig. 1 shows a schematic flow chart of a flight path planning method for multiple drones to access multiple target points, where, referring to fig. 1, the method may be implemented by a processor, and specifically includes the following steps:

110. acquiring position information of a plurality of unmanned aerial vehicles and a plurality of target points, and motion parameters of the unmanned aerial vehicles and a wind field;

it should be noted that, before the task allocation and the flight path planning are performed, the technician may set or actually measure the position information of the drone and the target points, and then input the position information into the processor.

In addition, the motion parameter of unmanned aerial vehicle can be that the technical staff sets for according to actual flight needs, and the motion parameter of wind field can be that the technical staff measures to draw or according to actual conditions setting.

120. According to the position information of the unmanned aerial vehicles and the target points and a preset genetic algorithm, an initial population is constructed, each chromosome in the initial population comprises European flight paths of the number of the unmanned aerial vehicles, and each European flight path is completed by different unmanned aerial vehicles;

130. determining the flight state of the unmanned aerial vehicle and the flight time of the unmanned aerial vehicle for completing the flight path of the European flight path according to the initial population, the unmanned aerial vehicle and the motion parameters of the wind field, and acquiring the task completion time of all unmanned aerial vehicles corresponding to chromosomes in the initial population according to the flight time of the flight path and an MUAV-VS-EVRP model;

140. and performing crossing and mutation treatment on chromosomes in the initial population based on a genetic algorithm, and selecting the chromosome with the shortest task completion time of all the unmanned aerial vehicles as the optimal task allocation scheme of the unmanned aerial vehicles after the preset iteration times are reached.

It will be appreciated that each iteration of intersection, mutation, and the like may have new individuals present, and then the calculation of the voyage time for the new chromosome is based on step 130, so that each european flight path corresponds to one voyage time.

It can be seen that, this embodiment firstly analyzes the wind field and the motion parameters of the unmanned aerial vehicle to obtain the actual flight state of the unmanned aerial vehicle in the wind field, and then plans the flight path based on the actual flight state.

The following is a detailed description of the steps in the examples of the present invention:

first, step 120 is explained in detail:

Then, referring to fig. 2, step 130 is explained in detail below:

210. dividing the European flight path corresponding to each chromosome into a plurality of flight path segments according to the target point visited sequence of the European flight path;

220. determining the flight state of the unmanned aerial vehicle by combining wind field parameters according to the coordinates of the starting point and the coordinates of the ending point corresponding to each track section, and further acquiring the flight time of the unmanned aerial vehicle for completing the track section;

230. and acquiring the task completion time of all unmanned aerial vehicles corresponding to the chromosomes according to the corresponding flight time of each track section.

Wherein step 220 comprises:

In addition, the step of calculating the task completion time of the unmanned aerial vehicle corresponding to the chromosome in the initial population comprises the following steps:

acquiring the task completion time of the unmanned aerial vehicle according to the MUAV-VS-EVRP model:

the constraint conditions are as follows:

Step 140 is described in detail below:

step 1, generating an initial solution by using the encoding method, generating an initial population of a preset scale, and calculating the fitness of the initial population according to the task completion time of the unmanned aerial vehicle corresponding to each chromosome in the population;

step 2, selecting two individuals (A, B) in a parent population to cross by using a roulette method, wherein the cross rule is that the cross position in the individual A is randomly selected, then the gene in the individual B, which is the same as the first line of the cross position of the individual A, is searched, the cross position gene in the chromosomes A and B is replaced to obtain new chromosomes C and D, whether the chromosomes C and D meet the constraint condition of the MUAV-VS-EVRP model or not is judged, if yes, the chromosomes A and B in the population are replaced by the chromosomes C and D, otherwise, the chromosomes which do not meet the constraint condition are subjected to constraint verification to generate chromosomes which meet the constraint condition to replace the chromosomes A and B in the population, and then the population in the step 1 is continuously updated in an iterative manner to obtain a new offspring population;

the whole chromosome variation steps include: firstly, if the first line of the chromosome is mutated, randomly selecting two gene positions of the current chromosome and exchanging target point codes of the corresponding gene positions; selecting whether a second row is mutated or not and a mutation position, if so, randomly generating a value of the unmanned aerial vehicle code which is different from the current position to replace the original value, judging whether the chromosome meets the constraint condition of the MUAV-VS-EVRP model or not after mutation, if so, replacing the chromosome in the population, otherwise, carrying out constraint check on the chromosome which does not meet the constraint condition, generating the chromosome which meets the constraint condition to replace the chromosome in the population, and continuously iterating and updating the population in the step 2 to obtain a new offspring population;

The principle of the genetic algorithm employed in the present invention will be described in detail below with reference to FIG. 3:

1. opening;

2. generating a population comprising a specified number of chromosomes, based on a technician's settings, the specified number may be specifically 100;

as shown in fig. 4a, chromosome a represents a possible solution for two unmanned aerial vehicles UAV to visit three target points in a stable wind field, i.e. UAV starts from starting point S (0,0), returns after visiting target point 3 and target point 1 in sequence, UAV starts from starting point S (0,0), returns after visiting target point 2. The second row in the code represents the code for the UAV to access the corresponding target point.

Wherein, chromosome A includes two european style flight paths and each european style flight path is accomplished by different unmanned aerial vehicle number one and No. two.

3. Calculating fitness of each chromosome;

it should be noted that, with the calculation method in step 140 in the corresponding embodiment of fig. 1, the flight time of the unmanned aerial vehicle to complete each european flight path is calculated, and the fitness of the chromosome is calculated based on the task time of the unmanned aerial vehicle, for example: the time for the unmanned aerial vehicle to complete the task is in inverse proportion to the fitness.

It should be understood that, after a specified number of populations are generated according to the encoding method in step 2, the fitness is calculated, and in the present invention, the calculation of the fitness is based on an objective function, and the calculation process is as follows:

4. selection operation

The selection operation is performed by roulette according to J'.

5. Crossover operation

By crossing the chromosomes of the parent generation, the superior genes in the parent generation can be inherited to obtain the superior offspring. Aiming at the MUAV-VS-EVRP problem, a single-point mapping method is adopted aiming at the current coding mode, namely, the crossed gene position of the parent chromosome A is randomly generated, the gene position corresponding to the same target point is found in the parent chromosome B, the child chromosome A, B is generated by crossing, and the constraint condition check is carried out on the child chromosome A, B.

Referring to fig. 4B, Parent agent a and agent B exist, the gene position randomly generated on agent a for crossing is 3, the gene position corresponding to the same target point on agent B is found, daughter chromosomes OffSpring a and OffSpring B are generated after crossing, constraint verification is performed on OffSpring a and OffSpring B, it is found that the unmanned aerial vehicle codes of OffSpring a all represent the same unmanned aerial vehicle and do not meet constraint conditions, therefore, mapping and crossing are performed on the randomly generated gene position of the unmanned aerial vehicle code of OffSpring a and the 3 rd gene position of agent a again, and OffSpring a meets the constraint conditions after crossing.

6. Mutation operation

The mutation is to prevent the genetic algorithm from falling into local optima. For the genetic algorithm for solving the sUav-DVS-VRP model, there are two cases of chromosomal variation: target point coding variation and course angle coding variation. Depending on the mutation probability, multiple mutations may or may not occur in the chromosome. The method meets the constraint that each target point in the model is accessed only once, ensures the feasibility of the sub-chromosomes, and adopts uniform variation for course angle coding.

Example mutation operations:

as shown in fig. 4c, Parent a exists, and performs target point mutation and unmanned aerial vehicle mutation on Parent a, first determines whether two types of mutations occur before performing mutation, randomly selects the coding gene positions when determining that the target point mutation occurs, where the selected gene positions are 1 and 3, and then exchanges the target values on the selected gene positions to obtain a new target point access sequence; and when the unmanned aerial vehicle mutation is judged to occur, randomly selecting a mutation gene position, wherein the selected gene position is 3, randomly generating an unmanned aerial vehicle code different from the current unmanned aerial vehicle code to replace the current value, and obtaining a new Parent A. And (3) carrying out constraint condition verification on the Parent A, finding that the unmanned aerial vehicle codes of the Parent A all represent the same unmanned aerial vehicle and are not in accordance with the constraint condition, carrying out mutation operation on the unmanned aerial vehicle codes of the Parent A again, selecting a mutation gene position of 2, randomly generating an unmanned aerial vehicle code different from the current unmanned aerial vehicle code to replace the current value, and obtaining that Offspring A meets the constraint condition.

7. Update operations

8. Selecting an optimal distribution scheme

9. Determine whether to terminate

10. Obtaining an optimal allocation scheme

11. End up

It should be noted that the above steps correspond to some of the steps in the embodiment corresponding to fig. 1, and therefore, the details of the similarities are not repeated here, and please specifically refer to the relevant contents in the embodiment corresponding to fig. 1.

The design principle of the present invention is explained in detail below with reference to the above genetic algorithm:

step one, in order to avoid the problem that the problem is too complex, the method adopts a regional fixed wind field to carry out wind field modeling, namely the wind speed and the wind direction of the wind field are unchanged in a specified region.

The wind field conditions for a known area may be expressed as:

wherein, V_wRepresenting the wind speed in the wind park, β_wIndicating the wind direction.

Wind speed V_wThe unit is m/s which is the moving distance of wind relative to the ground in unit time and the wind direction β_wIt refers to the direction from which wind blows, the unit of measurement of wind direction is generally expressed by azimuth, for example, on land, generally expressed by 16 azimuth, generally expressed by 36 azimuth on sea, and expressed by angle at high altitude, i.e. dividing the circumference into 360 degrees, where it is specified that westwind (W) is 0 degrees (i.e. 360 degrees), southeast wind (S) is 90 degrees, east wind (E) is 180 degrees, and northwest wind (N) is 270 degrees, as shown in fig. 5.

Step two, configuring the UAV

By using

Representing a quadrotor mhuav, the configuration of the mhuav in the air is defined as:

q＝(x，y，β_g) (4)

wherein,

wherein,andrepresenting the coordinates of a UAV in a cartesian inertial reference system; v_gGround speed β representing UAV_gRefers to the heading angle of the mqua.

To simplify the problem, the following assumptions are presented herein regarding the motion constraints that a UAV needs to satisfy during performance of a mission:

(1) the mUAVs are all isomorphic multi-rotor UAVs;

(2) considering the mUAV to have an obstacle avoidance function without considering the collision of the mUAV;

(3) consider that the mquavs are all flying at a fixed altitude;

(4) according to the flight envelope of the mUAV, there are upper and lower bounds on the flight speed of the mUAV at a given altitude, i.e., the flight speed of the mUAV at a fixed loadV_{a_min}And V_{a_max}Respectively representing the minimum and maximum values of the mhuav airspeed at a certain altitude;

(5) the multi-frame mUAVs start from a starting point and return to the starting point after executing a finished task.

Step three, calculating the actual flight state of the UAV

The actual speed of the UAV considering the wind influence is defined as the ground speed of the UAV with the size V_gAt this time, the heading angle of the UAV is β_gUAV ground speed vectorDefining the UAV theoretical velocity without considering wind influence as the airspeed of UAV with magnitude V_aAt this time, the heading angle of the UAV is β_aUAV airspeed vectorUAV airspeedGround speedSpeed of wind in wind fieldThe vector relationship of (a) is shown in fig. 6.

The relationship between the speed and the angle is as follows:

in the absence of wind, the wind is forced to flow,i.e. the UAV airspeed is equal to the ground speed.

The following example is illustrated in connection with fig. 7:

the UAV flies from S (0,0) to a (50,300) at an airspeed of 8m/S, is in a wind speed of 5m/S and a wind direction of south wind (Vw is 5m/S, β w is 90 °), and the airspeed and the ground speed of UAV during this process are obtained according to equation (7) and are shown in table 4-1.

TABLE 4-1 airspeed and ground speed comparison table for four-rotor Uav in windless and south wind environments

	Airspeed	Ground speed
			Environment of south wind	28.80km/h,35.5°	23.49km/h,80.5°
Windless environment	28.80km/h,80.5°	28.80km/h,80.5°

Step four, target point configuration

N_TThe set of individual target points may be represented as:

wherein the positions and the task volumes of all target points in the set are known. In the invention, there may be different types of tasks that need to be executed by the UAV at each target point, and each UAV may only execute one task at one target point in the process, that is, each target point needs to be visited by a different UAV, and each UAV may only visit a certain target point once.

Step five, calculating the navigation time

In the problem of UAV task allocation and flight path planning by taking flight time as a target, the UAV task allocation scheme determines the sequence of UAV access target points, flight path planning is carried out according to the UAV target point access sequence, UAV flight time is calculated according to the result of the flight path planning, and then whether the current UAV task allocation and flight path planning scheme is superior to the known scheme or not is determined according to the UAV flight time.

Because the navigation track of Uav between two points is the Euclidean distance, the navigation direction of Uav between the two points is fixed, and further the ground speed of Uav under a fixed wind field between the two points is not changed, but the ground speed of Uav under the fixed wind field is changed in a plurality of target point scenes from a target point, and the flight time of Uav is calculated as follows:

wherein,

denotes Uav at T_jAnd T_kEuclidean distance between two points, Uav ground speed between two pointsThe result is obtained from equation (7).

Thus, the task completion time of the mhuav may be calculated according to equation (8).

Wherein,denotes UAVU_iAt T_j、T_kTwo-point navigationA line time;

is a binary decision variable, andwhen UAVU_YWarp beam T_jFly to T_kWhen it is, thenIs 1, otherwiseIs 0;

taking 0 for J and k in J indicates that the UAV starts from the starting point or the path end points to the starting point.

In the solving process, the following constraint conditions are also required to be met:

the above conditions ensure that all destinations can be visited and only once.

The above conditions guarantee that UAV routes of UAV numbers are launched from the starting point and UAV paths of UAV numbers point to the same point.

The above conditions guarantee that there are routes of UAV number and the path of each UAV is a closed loop based on other constraints, that is, the navigation trajectory of UAV is an ordered route and finally returns to the starting point.

Therefore, the task completion time corresponding to each chromosome can be obtained based on the above formula, and the task allocation scheme with the shortest task completion time is selected from the task completion times.

The following detailed description of specific examples of the invention:

first, all simulation experiments were run in the environment of MatlabR2014a on 4G memory, 3.4ghz cpu hardware. The concrete description is as follows:

the UAV model is based on a mathematical model of the UAV, the airspeed of the UAV is 8m/S, two UAVs take off from a starting point S (0,0), and return to the point S (0,0) after the access task is completed; the wind field environment is fixed wind field, and wind speed and wind direction are unchangeable promptly in an experimental process to in order to guarantee that the UAV can fly safely, the wind speed size is 5 meters per second, and the wind direction is got east, 180 promptly, and the three target point coordinates that the UAV need visit are respectively: a (100,300), B (200,150), C (350,50), D (500, 150), E (650,100), F (400, 200), G (50, 250), H (250, 350) and I (50, 450).

According to the model and the algorithm provided by the invention, experiments are carried out in the east wind field environment and the test scene, and the task allocation with the shortest task completion time of the unmanned aerial vehicle in each wind field environment is obtained as shown in the table 3-1 (see fig. 8).

3-1

Method embodiments are described as a series of acts or combinations for simplicity of explanation, but it should be understood by those skilled in the art that the present invention is not limited by the order of acts or acts described, as some steps may occur in other orders or concurrently with other steps in accordance with the embodiments of the invention. Furthermore, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.

Fig. 9 is a schematic structural diagram of a flight path planning apparatus for a drone to access multiple target points, where referring to fig. 9, the apparatus includes: an obtaining module 101, a first processing module 102, a second processing module 103, and a third processing module 104, wherein:

the acquiring module 101 is configured to acquire position information of a plurality of unmanned aerial vehicles and a plurality of target points, and motion parameters of the unmanned aerial vehicles and a wind field;

the first processing module 102 is configured to construct an initial population according to the position information of the multiple unmanned aerial vehicles and the multiple target points and a preset genetic algorithm, wherein each chromosome in the initial population comprises unmanned and quantitative european paths, and each european flight path is completed by a different unmanned aerial vehicle;

the second processing module 103 is configured to determine a flight state of the unmanned aerial vehicle and a flight time of a flight path segment of an european flight path completed by the unmanned aerial vehicle according to the initial population, the unmanned aerial vehicle and the motion parameters of the wind field, and obtain a task completion time corresponding to a chromosome in the initial population according to the flight time of the flight path segment and the MUAV-VS-EVRP model;

and the third processing module 104 is configured to perform intersection and mutation processing on chromosomes in the initial population based on a genetic algorithm, and select a chromosome with the shortest task completion time as an optimal task allocation scheme of the unmanned aerial vehicle after a predetermined number of iterations is reached.

The following describes each functional block of the apparatus in detail:

the first processing module 102 is configured to perform chromosome coding according to a coding mode of a preset genetic algorithm to generate an initial population of a predetermined scale; the chromosome is composed of target point information and unmanned aerial vehicle information; wherein the target point belongs to a setT₀Denotes the start of UAVs, N_TRepresenting the number of target points to which the drone belongsN_URepresenting the number of unmanned aerial vehicles; the first behavior of the chromosome is the random full arrangement of the target points, the second behavior randomly selects the corresponding unmanned aerial vehicle for each target point according to the unmanned aerial vehicle set, and all the unmanned aerial vehicles in the unmanned aerial vehicle set are ensured to be selected at least once.

The second processing module 103 is used for dividing the European flight path corresponding to each chromosome into a plurality of flight path segments according to the target point visited sequence; determining the flight state of the unmanned aerial vehicle by combining wind field parameters according to the coordinates of the starting point and the coordinates of the ending point corresponding to each track section, and further acquiring the flight time of the unmanned aerial vehicle for completing the track section; and acquiring task completion time corresponding to the chromosome according to the corresponding flight time of each flight path segment.

Further, the second processing module 103 is configured to determine a flight state of the unmanned aerial vehicle according to coordinates of a start point and coordinates of an end point corresponding to each track segment in combination with the wind field parameters, and further acquire a flight time of the unmanned aerial vehicle completing the track segment includes:

the constraint conditions are as follows:

A third processing module 104, configured to perform the following steps: step 1, generating an initial solution by using the encoding method, generating an initial population with a preset scale, and calculating the fitness of the initial population according to the task completion time corresponding to each chromosome in the population; step 2, selecting two individuals (A, B) in a parent population to intersect by using a roulette method, wherein the intersection rule is that the intersection position in the individual A is randomly selected, then the first line of genes in the intersection position of the individual B, which is the same as the intersection position of the individual A, is searched, the intersection position genes in the chromosomes A and B are replaced to obtain new chromosomes C and D, whether the chromosomes C and D meet the constraint condition of the MUAV-VS-EVRP model is judged, if yes, the chromosomes A and B in the population are replaced by the chromosomes C and D, otherwise, the chromosomes which do not meet the constraint condition are subjected to constraint check, namely, when the number of unmanned aerial vehicles in the chromosomes A and B does not meet the constraint condition, one gene position is randomly selected and whether two or more unmanned aerial vehicle codes on the gene position exist or not is judged, if yes, the missing unmanned aerial vehicle codes are put into the gene position, otherwise, reselecting the gene position, generating chromosomes A and B in a chromosome replacement population meeting constraint conditions, and then continuously iteratively updating the population in the step 1 to obtain a new offspring population; and 3, selecting one chromosome in the population in the step 2 for mutation by using a roulette method, wherein the method for mutating the chromosome is at least one of the following mutation methods, and the method comprises the following steps: performing target point variation on the first line of the chromosome; carrying out unmanned aerial vehicle variation on the second chromosome line; the whole chromosome variation steps include: firstly, if the first line of the chromosome is mutated, randomly selecting two gene positions of the current chromosome and exchanging target point codes of the corresponding gene positions; selecting whether a second row has variation and a variation position, if so, randomly generating a value of the unmanned aerial vehicle code which has variation different from the current position to replace the original value, judging whether the chromosome meets the constraint condition of the MUAV-VS-EVRP model, if so, replacing the chromosome in the population, otherwise, carrying out constraint check on the chromosome which does not meet the constraint condition, namely, when the number of unmanned aerial vehicles in the chromosomes A and B does not meet the constraint condition, randomly selecting a gene position and judging whether two or more unmanned aerial vehicle codes on the gene position exist, if so, putting the missing unmanned aerial vehicle codes into the gene position, otherwise, reselecting the gene position, generating the chromosome which meets the constraint condition to replace the chromosome in the population and continuously iterating and updating the population in the step 2 to obtain a new offspring population; step 4, calculating the population fitness of the offspring and selecting the optimal solution of all solutions in the iteration; step 5, judging whether the current iteration times reach a preset value or not, if not, combining the child population and the parent population in the step 3 according to a certain proportion to form a new parent population, and returning to the step 2; if so, ending the iteration, and taking the finally obtained optimal solution as a task allocation result of the unmanned aerial vehicle.

As for the apparatus embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

It should be noted that, in the respective components of the apparatus of the present invention, the components therein are logically divided according to the functions to be implemented thereof, but the present invention is not limited thereto, and the respective components may be newly divided or combined as necessary.

Various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. In the device, the PC remotely controls the equipment or the device through the Internet, and accurately controls each operation step of the equipment or the device. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. The program for realizing the invention can be stored on a computer readable medium, and the file or document generated by the program has statistics, generates a data report and a cpk report, and the like, and can carry out batch test and statistics on the power amplifier. It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.

Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. A multi-unmanned aerial vehicle multitask execution distribution method is characterized by comprising the following steps:

2. The method of claim 1, wherein constructing the initial population according to the location information of the plurality of drones and the plurality of target points and a preset genetic algorithm comprises:

3. The method according to claim 1 or 2, wherein the determining the flight state of the drone and the flight time of the drone for completing the track segment of the european flight path according to the initial population, the drone and the motion parameters of the wind field, and the obtaining the task completion time of all the drones corresponding to the chromosomes in the initial population according to the flight time of the track segment and the MUAV-VS-EVRP model comprises:

determining the flight state of the unmanned aerial vehicle by combining wind field parameters according to the coordinates of the starting point and the coordinates of the ending point corresponding to each track section, and further acquiring the flight time of the unmanned aerial vehicle for completing the track section;

4. The method of claim 3, wherein determining the flight state of the unmanned aerial vehicle according to the coordinates of the starting point and the coordinates of the ending point corresponding to each track segment and in combination with the wind field parameters, and further obtaining the flight time of the unmanned aerial vehicle for completing the track segment comprises:

<mrow> <msubsup> <mi>t</mi> <mrow> <mo>(</mo> <msub> <mi>T</mi> <mi>j</mi> </msub> <mo>,</mo> <msub> <mi>T</mi> <mi>k</mi> </msub> <mo>)</mo> </mrow> <mi>i</mi> </msubsup> <mo>=</mo> <mfrac> <mrow> <msub> <mi>Length</mi> <mrow> <mo>(</mo> <msub> <mi>T</mi> <mi>j</mi> </msub> <mo>,</mo> <msub> <mi>T</mi> <mi>k</mi> </msub> <mo>)</mo> </mrow> </msub> </mrow> <mrow> <msup> <msub> <mi>V</mi> <mi>g</mi> </msub> <mi>i</mi> </msup> </mrow> </mfrac> <mo>,</mo> <mo>&ForAll;</mo> <msub> <mi>U</mi> <mi>i</mi> </msub> <mo>&Element;</mo> <mi>U</mi> <mo>,</mo> <mo>&ForAll;</mo> <msub> <mi>T</mi> <mi>j</mi> </msub> <mo>,</mo> <msub> <mi>T</mi> <mi>k</mi> </msub> <mo>&Element;</mo> <mi>T</mi> </mrow>

wherein, U_iDenotes the drone performing the above task, U denotes the set of drones,^T _jas a starting point, the position of the probe,_Tkto end point, T represents the set of target points, V_g ⁱFor unmanned plane U_iThe ground speed between the two target points;

<mrow> <mfenced open = "(" close = ")"> <mtable> <mtr> <mtd> <mrow> <msup> <msub> <mi>cos&beta;</mi> <mi>g</mi> </msub> <mi>i</mi> </msup> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <msup> <msub> <mi>sin&beta;</mi> <mi>g</mi> </msub> <mi>i</mi> </msup> </mrow> </mtd> </mtr> </mtable> </mfenced> <mo>&CenterDot;</mo> <msup> <msub> <mi>V</mi> <mi>g</mi> </msub> <mi>i</mi> </msup> <mo>=</mo> <mfenced open = "(" close = ")"> <mtable> <mtr> <mtd> <mrow> <msup> <msub> <mi>cos&beta;</mi> <mi>a</mi> </msub> <mi>i</mi> </msup> </mrow> </mtd> <mtd> <mrow> <msup> <msub> <mi>cos&beta;</mi> <mi>w</mi> </msub> <mi>i</mi> </msup> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <msup> <msub> <mi>sin&beta;</mi> <mi>a</mi> </msub> <mi>i</mi> </msup> </mrow> </mtd> <mtd> <mrow> <msup> <msub> <mi>sin&beta;</mi> <mi>w</mi> </msub> <mi>i</mi> </msup> </mrow> </mtd> </mtr> </mtable> </mfenced> <mfenced open = "(" close = ")"> <mtable> <mtr> <mtd> <mrow> <msup> <msub> <mi>V</mi> <mi>a</mi> </msub> <mi>i</mi> </msup> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <msup> <msub> <mi>V</mi> <mi>w</mi> </msub> <mi>i</mi> </msup> </mrow> </mtd> </mtr> </mtable> </mfenced> </mrow>

<mrow> <msub> <mi>Length</mi> <mrow> <mo>(</mo> <msub> <mi>T</mi> <mi>j</mi> </msub> <mo>,</mo> <msub> <mi>T</mi> <mi>k</mi> </msub> <mo>)</mo> </mrow> </msub> <mo>=</mo> <mi>s</mi> <mi>q</mi> <mi>r</mi> <mi>t</mi> <mrow> <mo>(</mo> <msup> <mrow> <mo>(</mo> <mrow> <msub> <mi>X</mi> <msub> <mi>T</mi> <mi>j</mi> </msub> </msub> <mo>-</mo> <msub> <mi>X</mi> <msub> <mi>T</mi> <mi>k</mi> </msub> </msub> </mrow> <mo>)</mo> </mrow> <mn>2</mn> </msup> <mo>+</mo> <msup> <mrow> <mo>(</mo> <mrow> <msub> <mi>Y</mi> <msub> <mi>T</mi> <mi>j</mi> </msub> </msub> <mo>-</mo> <msub> <mi>Y</mi> <msub> <mi>T</mi> <mi>k</mi> </msub> </msub> </mrow> <mo>)</mo> </mrow> <mn>2</mn> </msup> <mo>)</mo> </mrow> <mo>,</mo> <mo>&ForAll;</mo> <msub> <mi>T</mi> <mi>j</mi> </msub> <mo>,</mo> <msub> <mi>T</mi> <mi>k</mi> </msub> <mo>&Element;</mo> <mi>T</mi> </mrow>

5. The method of claim 3, wherein obtaining task completion times of all drones corresponding to chromosomes in the initial population according to the flight time of the flight path segment and the MUAV-VS-EVRP model comprises:

acquiring task completion time of all unmanned aerial vehicles according to the MUAV-VS-EVRP model:

<mrow> <mi>J</mi> <mo>=</mo> <mi>m</mi> <mi>a</mi> <mi>x</mi> <mo>{</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <msub> <mi>N</mi> <mi>U</mi> </msub> </munderover> <munderover> <mo>&Sigma;</mo> <mrow> <mi>j</mi> <mo>=</mo> <mn>0</mn> </mrow> <msub> <mi>N</mi> <mi>T</mi> </msub> </munderover> <munderover> <mo>&Sigma;</mo> <mrow> <mi>k</mi> <mo>=</mo> <mn>0</mn> </mrow> <msub> <mi>N</mi> <mi>T</mi> </msub> </munderover> <msubsup> <mi>X</mi> <mrow> <mo>(</mo> <msub> <mi>T</mi> <mi>j</mi> </msub> <mo>,</mo> <msub> <mi>T</mi> <mi>k</mi> </msub> <mo>)</mo> </mrow> <mi>i</mi> </msubsup> <msubsup> <mi>t</mi> <mrow> <mo>(</mo> <msub> <mi>T</mi> <mi>j</mi> </msub> <mo>,</mo> <msub> <mi>T</mi> <mi>k</mi> </msub> <mo>)</mo> </mrow> <mi>i</mi> </msubsup> <mo>}</mo> </mrow>

the constraint conditions are as follows:

<mrow> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <msub> <mi>N</mi> <mi>U</mi> </msub> </munderover> <munderover> <mo>&Sigma;</mo> <mrow> <mi>k</mi> <mo>=</mo> <mn>1</mn> </mrow> <msub> <mi>N</mi> <mi>T</mi> </msub> </munderover> <msubsup> <mi>X</mi> <mrow> <mo>(</mo> <msub> <mi>T</mi> <mi>j</mi> </msub> <mo>,</mo> <msub> <mi>T</mi> <mi>k</mi> </msub> <mo>)</mo> </mrow> <mi>i</mi> </msubsup> <mo>=</mo> <mn>1</mn> <mo>,</mo> <mo>&ForAll;</mo> <msub> <mi>U</mi> <mi>i</mi> </msub> <mo>&Element;</mo> <mi>U</mi> <mo>,</mo> <mo>&ForAll;</mo> <msub> <mi>T</mi> <mi>j</mi> </msub> <mo>&Element;</mo> <mi>T</mi> </mrow>

<mrow> <munderover> <mo>&Sigma;</mo> <mrow> <mi>k</mi> <mo>=</mo> <mn>1</mn> </mrow> <msub> <mi>N</mi> <mi>T</mi> </msub> </munderover> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <msub> <mi>N</mi> <mi>U</mi> </msub> </munderover> <msubsup> <mi>X</mi> <mrow> <mo>(</mo> <msub> <mi>T</mi> <mn>0</mn> </msub> <mo>,</mo> <msub> <mi>T</mi> <mi>k</mi> </msub> <mo>)</mo> </mrow> <mi>i</mi> </msubsup> <mo>=</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>k</mi> <mo>=</mo> <mn>1</mn> </mrow> <msub> <mi>N</mi> <mi>T</mi> </msub> </munderover> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <msub> <mi>N</mi> <mi>U</mi> </msub> </munderover> <msubsup> <mi>X</mi> <mrow> <mo>(</mo> <msub> <mi>T</mi> <mi>k</mi> </msub> <mo>,</mo> <msub> <mi>T</mi> <mn>0</mn> </msub> <mo>)</mo> </mrow> <mi>i</mi> </msubsup> <mo>=</mo> <msub> <mi>N</mi> <mi>U</mi> </msub> <mo>,</mo> <mo>&ForAll;</mo> <msub> <mi>U</mi> <mi>i</mi> </msub> <mo>&Element;</mo> <mi>U</mi> <mo>,</mo> <mo>&ForAll;</mo> <msub> <mi>T</mi> <mi>k</mi> </msub> <mo>&Element;</mo> <mi>T</mi> </mrow>

<mrow> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <msub> <mi>N</mi> <mi>U</mi> </msub> </munderover> <munderover> <mo>&Sigma;</mo> <mrow> <mi>j</mi> <mo>=</mo> <mn>0</mn> </mrow> <msub> <mi>N</mi> <mi>T</mi> </msub> </munderover> <munderover> <mo>&Sigma;</mo> <mrow> <mi>k</mi> <mo>=</mo> <mn>0</mn> </mrow> <msub> <mi>N</mi> <mi>T</mi> </msub> </munderover> <msubsup> <mi>X</mi> <mrow> <mo>(</mo> <msub> <mi>T</mi> <mi>j</mi> </msub> <mo>,</mo> <msub> <mi>T</mi> <mi>k</mi> </msub> <mo>)</mo> </mrow> <mi>i</mi> </msubsup> <mo>=</mo> <msub> <mi>N</mi> <mi>T</mi> </msub> <mo>+</mo> <msub> <mi>N</mi> <mi>U</mi> </msub> <mo>,</mo> <mo>&ForAll;</mo> <msub> <mi>U</mi> <mi>i</mi> </msub> <mo>&Element;</mo> <mi>U</mi> <mo>,</mo> <mo>&ForAll;</mo> <msub> <mi>T</mi> <mi>j</mi> </msub> <mo>,</mo> <msub> <mi>T</mi> <mi>k</mi> </msub> <mo>&Element;</mo> <mi>T</mi> </mrow>

wherein,representing unmanned aerial vehicle by target point T_jFly to target point T_kThe time of flight of the vehicle,is a binary decision variable, andwhen UAVU_iWarp beam T_jFly to T_kWhen it is, thenIs 1, otherwiseHas a value of 0, N_TRepresenting the number of target points, N_URepresenting the number of drones.

6. The method of claim 4, wherein the steps of performing crossover and mutation processing on chromosomes in the initial population based on a genetic algorithm, and selecting the chromosome with the shortest task completion time of all the unmanned aerial vehicles as the optimal task allocation scheme of the unmanned aerial vehicles after a predetermined number of iterations are achieved comprise:

7. A multi-unmanned aerial vehicle carries out multitask distribution device which is characterized by comprising:

the first processing module is used for constructing an initial population according to the position information of the unmanned aerial vehicles and the target points and a preset genetic algorithm, wherein each chromosome in the initial population comprises European flight paths of the number of the unmanned aerial vehicles, and each European flight path is completed by different unmanned aerial vehicles;

a third processing module, which is used for carrying out crossover and mutation processing on chromosomes in the initial population based on a genetic algorithm, and selecting all unmanned aerial vehicles to finish tasks after a preset iteration number is reached

And taking the chromosome with the shortest time as an optimal task allocation method of the unmanned aerial vehicle.

8. The apparatus of claim 7, wherein the first processing module is configured to perform chromosome coding according to a coding mode of a preset genetic algorithm to generate an initial population of a predetermined scale; the chromosome is composed of target point information and unmanned aerial vehicle information; wherein the target point belongs to a setT₀Denotes the start of UAVs, N_TRepresenting the number of target points to which the drone belongsN_URepresenting the number of unmanned aerial vehicles; the first behavior of the chromosome is the random full arrangement of the target points, the second behavior randomly selects the corresponding unmanned aerial vehicle for each target point according to the unmanned aerial vehicle set, and all the unmanned aerial vehicles in the unmanned aerial vehicle set are ensured to be selected at least once.

9. The apparatus according to claim 7 or 8, wherein the second processing module is configured to divide the Euclidean flight path corresponding to each chromosome into a plurality of flight path segments according to the sequence in which the target points of the Euclidean flight path are visited; performing the first step and the second step;

the first step comprises: calculating and acquiring unmanned aerial vehicle U by adopting the following formula_iFrom target point T_jFly to target point T_kFlight time of the track segment:

wherein, U_iRepresenting the unmanned aerial vehicle performing the above tasks, U representing the set of unmanned aerial vehicles, T_jAs a starting point, T_kTo end point, T represents the set of target points, V_g ⁱFor unmanned plane U_iThe ground speed between the two target points;

wherein X and Y respectively represent the horizontal and vertical coordinates of the corresponding target point;

the second step includes:

the constraint conditions are as follows:

10. The apparatus of claim 9, wherein the third processing module is configured to perform the following steps: