CN107037826B - Method and device for assigning unmanned aerial vehicle detection tasks - Google Patents

Abstract

The invention relates to a method and device for assigning unmanned aerial vehicle detection tasks. In the method, in the case where a multi-rotor unmanned aerial vehicle executes various tasks on multiple areas to be detected, the area to be detected that performs this task is first obtained. Information and multi-rotor UAV information, and then according to this information based on the preset UAV-O-OP model and genetic algorithm, the optimal solution that can make the model obtain the maximum total income is obtained, and the optimal solution is used as this The task assignment and trajectory planning results of the operation. The method provided by the invention can make the unmanned aerial vehicle automatically execute the operation task according to the result of automatic planning, and avoid being affected by human operation. In addition, since the method provided by the present invention uses the optimal solution of the preset maximizing revenue model as the result of track planning, the unmanned aerial vehicle that executes the task based on the result can also obtain the maximum total revenue while performing the task, It takes the shortest time to effectively improve the efficiency of the operation.

Description

Method and device for assigning unmanned aerial vehicle detection tasks

technical field

The invention relates to the technical field of unmanned aerial vehicles, in particular to a method and device for allocating detection tasks of unmanned aerial vehicles.

Background technique

With the continuous development of aviation technology, more and more high-tech equipment has been applied to the aviation field. Among many high-tech equipment, drones have quickly become a more important high-tech equipment in the process of aviation operations due to their advantages in high operating efficiency, low labor intensity, and low overall cost. For example, operational tasks such as aerial photography or scanning imaging can be performed. Current unmanned aerial vehicles can be roughly divided into two categories: multi-rotor (for example, four-rotor, six-rotor or eight-rotor drones, etc.) and fixed-wing. Among them, fixed-wing UAVs are widely used in aviation operations due to their long flight distance, large cruising area, fast flight speed, and high altitude.

However, in the process of implementing the present invention, the inventors found that since the current multi-rotor UAV operations are mainly based on manual remote control, the effect of actual operations is greatly affected by the operator's operating level, and through the artificial and visual way The planned flight path deviates seriously from the theoretical flight path, resulting in a high omission rate and repetition rate of UAV operations.

In addition, when a multi-rotor UAV completes a detection task for multiple areas to be detected, due to the limited flight time of the UAV in the process, how to select the area to be detected and path planning will make the income after completing the task The maximum (that is, to complete as many area detection tasks as possible and the total income of all areas after the area detection is completed), and to select the solution that takes the shortest time on the basis of the maximum income has also become an urgent problem to be solved.

Contents of the invention

An embodiment of the present invention provides a method and device for assigning unmanned aerial vehicle detection tasks, which are used to overcome the fact that the navigation of unmanned aerial vehicles is greatly affected by human operations in the prior art, and when using a multi-rotor unmanned aerial vehicle When operating multiple areas to be detected, it is impossible to plan the trajectory of the UAV reasonably to obtain the maximum total benefit and spend the shortest time.

In the first aspect, an embodiment of the present invention provides a method for assigning unmanned aerial vehicle detection tasks. When a multi-rotor unmanned aerial vehicle performs multiple detection tasks on multiple rectangular areas to be detected, the method includes:

Obtain the information of the area to be detected and the information of the multi-rotor UAV;

Obtain an initial solution that satisfies the preset UAV-O-OP model constraints, wherein the UAV-O-OP model is the objective function that the multi-rotor UAV obtains the maximum total income in this detection mission; the constraints The conditions include the flight time constraints of the multi-rotor UAV;

Using a preset genetic algorithm to solve the UAV-O-OP model based on the initial solution to obtain an optimal solution, and use the optimal solution as a task assignment result of a multi-rotor UAV to multiple areas to be detected .

In the second aspect, another embodiment of the present invention is a UAV detection task allocation device. When a multi-rotor UAV performs multiple detection tasks on multiple rectangular areas to be detected, the device includes:

An information acquisition unit is used to acquire the information of the area to be detected and the information of the multi-rotor UAV;

The initial solution acquisition unit is used to obtain an initial solution that satisfies the preset UAV-O-OP model constraints, wherein the UAV-O-OP model is the maximum total income obtained by the multi-rotor UAV in this detection mission. The objective function of; Described constraint condition comprises multi-rotor unmanned aerial vehicle flight duration constraint;

The optimal solution calculation unit is used to use a preset genetic algorithm to solve the UAV-O-OP model based on the initial solution to obtain an optimal solution, and use the optimal solution as a multi-rotor UAV to multi-rotor Task assignment results of the area to be detected.

An embodiment of the present invention provides a method for allocating UAV detection tasks. In this method, in the case where a multi-rotor UAV performs multiple tasks on multiple areas to be detected, first obtain the information for performing this task. The information of the area to be detected and the information of the multi-rotor UAV, and then based on this information based on the preset UAV-O-OP model and genetic algorithm, obtain the optimal solution that can make the model obtain the maximum total income, and the optimal solution The solution is used as the task assignment and track planning results of this operation. Compared with the existing manual remote control method, the method provided by the present invention can automatically obtain the mission and track planning of the UAV in this operation according to the preset model and algorithm, so that the UAV can follow the mission and flight path planning. Trajectory planning automatically executes job tasks and avoids being affected by human operations. In addition, since the method provided by the present invention uses the optimal solution of the preset maximizing revenue model as the result of track planning, the unmanned aerial vehicle that executes the task based on the result can also obtain the maximum total revenue while performing the task, It takes the shortest time to effectively improve the efficiency of the operation, so that the UAV operation form can be applied to a wider range of detection tasks.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiment. The drawings are only for the purpose of illustrating a preferred embodiment and are not to be considered as limiting the invention. Also throughout the drawings, the same reference numerals are used to designate the same components. In the attached picture:

Fig. 1 is a flow chart of an embodiment of a method for distributing unmanned aerial vehicle detection tasks provided by the present invention;

Fig. 2 (a)-2 (c) is the schematic diagram of detection mode of the region to be detected provided by the present invention;

Fig. 3 is a schematic diagram of the position of the entry point provided by the present invention;

Fig. 4 is a schematic diagram of the chromosome crossover process provided by the present invention;

Fig. 5 is a schematic diagram of chromosome variation rules provided by the present invention;

Fig. 6 is a schematic diagram of five regions to be detected provided by the present invention;

Fig. 7 is a schematic diagram of optimal solution convergence provided by the present invention;

Fig. 8 is a schematic structural diagram of an embodiment of a device for assigning drone detection tasks provided by the present invention.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

In the first aspect, the embodiment of the present invention provides a method for assigning UAV detection tasks. When a multi-rotor UAV performs various detection tasks on multiple rectangular areas to be detected, as shown in FIG. 1, the Methods include:

S101. Acquiring the information of the area to be detected and the information of the multi-rotor UAV;

S102. Obtain an initial solution that satisfies the constraints of the preset UAV-O-OP model, wherein the UAV-O-OP model is an objective function for the multi-rotor UAV to obtain the maximum total income in this detection mission; The above constraints include the flight time constraints of the multi-rotor UAV;

S103, using a preset genetic algorithm to solve the UAV-O-OP model based on the initial solution to obtain an optimal solution, and use the optimal solution as the task assignment of the multi-rotor UAV to multiple areas to be detected result.

An embodiment of the present invention provides a method for allocating UAV detection tasks. In this method, in the case where a multi-rotor UAV performs multiple tasks on multiple areas to be detected, first obtain the information for performing this task. The information of the area to be detected and the information of the multi-rotor UAV, and then based on this information based on the preset UAV-O-OP model and genetic algorithm, obtain the optimal solution that can make the model obtain the maximum total income, and the optimal solution The solution is used as the task assignment and track planning results of this operation. Compared with the existing manual remote control method, the method provided by the present invention can automatically obtain the mission and track planning of the UAV in this operation according to the preset model and algorithm, so that the UAV can follow the mission and flight path planning. Trajectory planning automatically executes job tasks and avoids being affected by human operations. In addition, since the method provided by the present invention uses the optimal solution of the preset maximizing revenue model as the result of track planning, the unmanned aerial vehicle that executes the task based on the result can also obtain the maximum total revenue while performing the task, It takes the shortest time to effectively improve the efficiency of the operation, so that the UAV operation form can be applied to a wider range of detection tasks.

During specific implementation, it can be understood that the objective function and constraint conditions contained in the UAV-O-OP model in the above method are important basis for the present invention to obtain optimal planning results, which can be set in various ways, as follows Describe one of the optional setting methods in detail.

The UAV-O-OP model is an orientation problem (OP). The performance of the multi-rotor UAV, the size of the area to be detected, and the path of the multi-rotor UAV when performing tasks also have an impact on the results of task assignment. The specific parameters and settings in the specific model are as follows:

(1) Multi-rotor UAV

Let U represent a multi-rotor UAV that performs the task to be detected; the UAV starts from the same starting point and returns to the starting point eventually. During the flight, the flying speed of the multi-rotor UAV is V, and all of them carry sensors with a detection radius _RD .

Combined with the characteristics of multi-rotor UAVs performing detection tasks, this paper makes the following assumptions:

(1) Multi-rotor UAVs have the ability to automatically avoid obstacles, and can adopt an autonomous avoidance control strategy in the face of collisions. The resulting path deviation is also small compared to the total flight path length, which can can be ignored;

(2) The multi-rotor UAVs all fly at the same cruising speed and cruising altitude, so as to achieve the best detection effect without considering the influence of other factors;

(3) The influence of the external environment on the flight trajectory of the multi-rotor UAV is not considered during the flight of the multi-rotor UAV;

(4) Fuel is limited during the flight of the multi-rotor UAV;

(2) Area to be detected

Let A ₀ , are the starting point and the ending point of the multi-rotor drone respectively, and the starting point and the ending point are the same in this paper; N _A is the area to be detected, and the area to be detected A _i is a rectangle whose vertex coordinates are (A _i1 , A _i2 , A _i3 , A _i4 ) and the area is S _i ; The set of regions is When the multi-rotor UAV is to scan the area A _i to be detected, the entry point of the multi-rotor UAV flying into the area to be detected is In _i , and the point of departure from the area to be detected is Out _i , and it is assumed that the multi-rotor UAV The drone must completely detect the entire area to be detected before leaving. At the same time, each area to be detected can only be detected once at most.

(3) Flight path

In the process of performing detection tasks by multi-rotor UAVs, it is not only necessary to complete the task through coverage scanning in the area to be detected, but also to fly between different areas to be detected to achieve switching between tasks, resulting in Two types of flight paths are proposed, that is, the flight paths between the areas to be detected and the flight paths within the area to be detected.

(1) The flight path of the multi-rotor UAV between the areas to be detected:

Between two areas A _i and A _j to be detected, the flight path length of the multi-rotor UAV is the Euclidean distance length. And the time spent by the multi-rotor UAV between two areas A _i and A _j to be detected is t _ij .

(2) The flight path of the multi-rotor UAV in the coverage scanning of the area to be detected Multi-rotor UAV operation mode:

Inside the area A _i to be detected, the multi-rotor UAV uses a parallel scanning strategy for path planning. During the coverage scan, the multi-rotor UAV enters from the point In _i of the area to be detected A _i , and the path after entering the area to be detected is parallel to a certain side of the area to be detected, and then leaves from the point Out _i . At this time, the multi-rotor UAV The time it takes for the UAV to detect and scan the area to be detected is t _i . At a given speed, the detection scanning time of the multi-rotor UAV depends on the number of turns. For the area to be detected in Figure 2(c), there are two different turning radius times, as shown in Figure 2(a) and Figure 2( b), where the number of turns in the track shown in Figure 2(b) is less than that shown in Figure 2(a), and the total path length is also smaller than that in Figure 2(a).

When a multi-rotor UAV uses a parallel scanning strategy to perform area detection tasks, it is necessary to determine the point and direction of entering the area to be detected. The point where the multi-rotor UAV enters the area to be detected can be any point, but when the distance between the entry point and the apex of the area to be detected is R _D , the number of turns of the multi-rotor UAV is the least, and the total path is the shortest. Since the areas to be detected in this paper are all rectangular, there are eight points at the distance _{RD from the vertex (as shown in Figure 3), which are {R D1 , R D2 ... R D8} }, so the multi-rotor UAV There are eight possible entry points In _i for entering the area to be detected, and the entry directions are all perpendicular to the side where the point is located. And the exit point can be uniquely determined by the entry point, because when the turning radius of the multi-rotor UAV is determined, the scanning radius is determined, the direction of entering the area to be detected is determined, and the side length of the area to be detected is determined, the number of turns is determined, and the multi-rotor UAV is unmanned. The direction of the aircraft leaving the area to be detected and the departure point Out _i are determined.

However, when detecting and scanning the area to be detected, not only the time spent inside the area to be detected needs to be considered, but also the time spent between the areas to be detected needs to be considered, and the time between the two needs to be balanced, so the time spent is no longer measured The standard, but the income of the detected area to be detected is used as the standard.

Therefore, aiming at the described task allocation problem of UAV detection, this paper takes the maximization of the total revenue after the multi-rotor UAV completes the task as the objective function of the optimization problem, and establishes the following mathematical model.

The objective function of the UAV-O-OP model is:

The constraints of the UAV-O-OP model are:

In the UAV-O-OP model, N _A represents the number of areas A _i to be detected; A ₀ , Represents the starting point and the end point of the multi-rotor UAV, and the starting point and the end point are the same point; S _i represents the area of the area A _i to be detected; P _i represents the income obtained by completing the task of the area A _i to be detected; t _i represents the time for the multi-rotor UAV to perform tasks in the detection area A _i according to the parallel scanning strategy; t _ij represents the time for the multi-rotor UAV to fly between the areas A _i and A _j to be detected; U _i represents the position of the area A _i to be detected in the route; _xi represents the situation of the multi-rotor UAV completing the task in the area A _i to be detected. If _xi = 1, it means that the detection task is completed. Otherwise, the multi-rotor UAV does not perform tasks in the detection area A _i ; y _ij indicates whether the multi-rotor UAV passes through the area A _i , A _j to be detected; if y _ij = 1, it means that the multi-rotor UAV passes through the area A to be detected _i , A _j , otherwise the multi-rotor UAV does not pass through the area to be detected A _i , A _j .

Among them, the objective function formula (1) is the maximum total income obtained by the multi-rotor UAV after performing the task; the constraint formula (2) is to ensure that the starting point of the path of the multi-rotor UAV is A ₀ , and the end point is Constraint (3) is to ensure that each area to be detected is visited at most once; constraint (4) is to ensure that the maximum flight time of the multi-rotor UAV cannot exceed E; constraint (5) and (6) are to prevent no The human-machine route forms a sub-loop; constraint (7) is the definition of the target and path variables.

It is not difficult to understand that after the UAV-O-OP model is obtained, the method provided in the embodiment of the present invention can solve the optimal solution of the UAV-O-OP model according to a preset genetic algorithm. The preset genetic algorithm for finding the optimal solution can be realized by various methods, and one of the optional methods will be described in detail below.

The general idea of the method provided by the embodiment of the present invention is: for the task allocation problem to be solved by the embodiment of the present invention, each feasible solution (that is, a solution satisfying the preset model constraints) can be expressed as a chromosome. The feasible solution population (that is, the initial parent population) can be composed of multiple chromosomes, and its scale can be defined according to the actual situation. After obtaining such an initial parent population, the initial parent population can be updated through chromosome crossover and mutation to form a new offspring population. Among them, the crossover here means that two parent chromosomes form two new offspring chromosomes according to the crossover probability, and the mutation here means that one chromosome forms a new chromosome according to the mutation probability. This cyclic process of cross mutation update is iterated continuously, and finally when the number of iterations reaches the preset value, the current optimal offspring chromosome is selected. An optimal solution, the optimal solution is the final task assignment result required by the present invention.

In this process, it involves the setting of the coding, crossover, mutation, and fitness function rules in the genetic algorithm so that the genetic algorithm after setting can be applied to solve the preset model to obtain the optimal solution. It can be understood that the setting of each function in the genetic algorithm can be implemented in many ways, and an optional function setting way will be described in detail below.

(1) Coding

The coding in the present invention includes the area to be detected, whether to execute the task of the area to be detected, and the entry point of the area to be detected, wherein the area to be detected belongs to the set {1,2,...N _A }, and the entry point of the area to be detected belongs to the set {R _D1 ,R _D2 ,...R _D8 }.

For example, Table 1 gives the content of each row of a chromosome after encoding. Among them, the first line of the chromosome is the information of the area to be detected, that is, the identification information of the area to be detected, the second line indicates whether the UAV performs the task of the area to be detected, 1 means yes, 0 means no, and the third line is unmanned The identification information of the entry point when the machine performs tasks in the area to be detected (the entry point label corresponds to the area to be detected R _D1 -R _D8 shown in FIG. 2 ). The whole chromosome indicates that the multi _- rotor UAV first enters the area to be detected at A3 from the entry point _{R D7} to complete the task, then enters the area A5 to be detected from the point R _D5 to complete the task, and then enters the area _A4 to be detected from the point R _D8 to complete the task The task finally returns to the starting point, but the targets A ₁ and A ₂ are not visited.

Table 1 Chromosome: N _A ＝5

Area to be detected 3 1 5 4 2 Whether to execute the task 1 0 1 1 0 entry point 7 1 5 8 6

(2) cross

The crossover mode selected in the embodiment of the present invention is to randomly select two crossover positions of the first chromosome, and then search for the same gene in the first row of the crossover position of the first chromosome in the second chromosome; The gene at the crossover position is replaced to obtain the third chromosome and the fourth chromosome;

For example, in Figure 4, the two parent chromosomes first randomly select two positions for crossover in parent A, and then find the same target region position of parent B to exchange, thus obtaining two new offspring chromosomes A and B .

(3) variation

In the present invention, the variation may be one gene or multiple genes. The chromosomal variation in this paper mainly includes the following situations: the order variation of the region to be detected, the variation of whether the multi-rotor UAV performs a task, and the variation of the entry point of the region to be detected. Among them, if the first row is mutated, the first row will be randomly arranged. If the second row is mutated, the mutation position will be determined, and the mission will be changed from the original non-multi-rotor UAV to the multi-rotor UAV. Execute the task, or on the contrary, if the third line mutates, determine the position of its mutation, and replace the entry point at the original mutation position with the randomly generated entry point;

For example, in Figure 5, chromosome A has undergone three mutations, the access sequence of the region to be detected is mutated from 3,1,5,4,2 to 4,2,1,3,5, and the second row and third column are changed from 1 to 0 means that the task of the area to be detected originally performed by the UAV is not performed, and the entry point of the third row and the first column is changed from _RD7 to _RD2 .

(4) Fitness function and selection

The fitness of the chromosome is:

Among them, N _A represents the number of the area A _i to be detected; S _i represents the area of the area A _i to be detected; P _{i represents} the income obtained by completing the task of the area A _i to be detected; detection task, otherwise the multi-rotor UAV does not perform tasks in the detection area A _i ;

Among them, 0,...N _A+1 represents the starting point, the area to be detected and the end point; t _i represents the time for the multi-rotor UAV to perform tasks on the detection area A _i according to the parallel scanning strategy; t _ij represents the multi-rotor without The flight time of the man-machine between the area A _i and A _j to be detected; _xi indicates the situation that the multi-rotor UAV completes the task in the area A _i to be detected. If _xi = 1, it means that the detection task is completed, otherwise the The multi-rotor UAV does not perform tasks in the detection area A _i ; y _ij indicates whether the multi-rotor UAV passes through the area A _i , A _j to be detected; if y _ij = 1, it means that the multi-rotor UAV passes through the area A _i to be detected ,A _j , otherwise the multi-rotor UAV does not pass through the area to be detected A _i ,A _j .

There are two fitness functions in the embodiment of the present invention. The first fitness function is formula (8), the larger the better, and it represents the total income of all visited regions to be detected, that is, it is related to the visited region and the area of the region. When the first fitness of multiple chromosomes is the same, that is, the total income of different allocation schemes is the same, but the time spent on each allocation scheme is different, so the calculation of the second fitness is required (as shown in formula (9) Shown), carry out secondary screening, so as to select the allocation scheme with the largest total income and the shortest time spent on the basis of the largest total income.

Due to the continuous iteration of the crossover mutation process, the parent population is continuously updated, thereby generating more new populations. It is understandable that this iterative cycle process can go on indefinitely, but a final result cannot be obtained in this way. Therefore, the present invention judges whether the current accumulated number of iterations has reached the threshold of iterations after each iteration, and the threshold can be set according to the actual situation. If it is judged that the threshold of the number of iterations has not been reached, the iterative process needs to be continued; if it is judged that the threshold of the number of iterations has been reached, the number of iterations at this time is considered sufficient, and the current optimal solution can be assigned as the task of this job result. Furthermore, the result can also be assigned to a corresponding multi-rotor UAV, so that the UAV can perform this operation task according to this result, achieve the purpose of this operation and maximize the area to be detected income.

In order to reflect the superiority of the method provided by the embodiment of the present invention, several specific examples are given below to describe in detail how to solve the UAV-O-OP model by using the genetic algorithm according to the above function settings, so as to obtain the final task assignment result.

Specifically, the genetic algorithm is implemented in the environment of MATLAB 2013 to solve the UAV-O-OP model, and experiments are carried out.

Assume that there is an unmanned aerial vehicle that performs tasks on five areas to be detected, and uses the genetic algorithm to obtain an allocation plan, where the crossover probability of the genetic algorithm is 0.9, the mutation probability is 0.5, the population size is 500, and the number of iterations for 100. The specific parameters involved in the experiment process are described as follows:

(1) UAV

The specific configuration of the UAV in this experiment is shown in Table 2. The speed of the UAV is 4m/s, the maximum detection radius is 5m, and the maximum endurance time is 1800s.

Table 2 UAV basic parameter configuration table

UAV parameters A₀\A_N+1 V R_D E. drone information (0,0) 4m/s 5m 1800s

(2) Area to be detected

There are five areas to be detected, as shown in Figure 6. The specific coordinates and benefits are shown in Table 3.

Table 3 Coordinate information of the area to be detected

coordinate lower left vertex upper left vertex upper right vertex lower right vertex income area 1 (100,100) (100,200) (200,200) (200,100) 0.9 area 2 (10,410) (10,560) (110,560) (110,410) 0.94 area 3 (350,10) (350,110) (540,110) (540,10) 0.87 area 4 (150,300) (150,400) (260,400) (260,300) 0.89 area 5 (350,350) (350,480) (450,480) (450,350) 0.97

The profit of the optimal solution obtained by using the genetic algorithm for the above scenario is 4.9420, and it has converged in the fourth generation, and the convergence speed is fast, as shown in Figure 7. The optimal allocation scheme that takes the shortest time in the case of the maximum benefit is shown in Table 4, and the shortest time spent is 1735.5s. Among all the regions to be detected, region 5 is not detected, and other regions are detected.

Table 4 Optimal Allocation Scheme

area 3 4 5 2 1 task execution 1 1 0 1 1 entry point 2 8 7 8 3

In the second aspect, an embodiment of the present invention also provides a UAV detection task allocation device. When a multi-rotor UAV performs multiple detection tasks on multiple rectangular areas to be detected, as shown in Figure 8, The devices include:

An information acquisition unit 201, configured to acquire area information to be detected and multi-rotor UAV information;

The initial solution acquisition unit 202 is used to obtain an initial solution that satisfies the preset UAV-O-OP model constraints, wherein the UAV-O-OP model is the total income obtained by the multi-rotor UAV in this detection mission The largest objective function; the constraints include the flight time constraints of the multi-rotor UAV;

The optimal solution calculation unit 203 is used to solve the UAV-O-OP model based on the initial solution using a preset genetic algorithm to obtain an optimal solution, and use the optimal solution as the multi-rotor UAV pair multi-rotor Task assignment results of the area to be detected.

During specific implementation, it is characterized in that:

The objective function of the UAV-O-OP model is:

The constraints of the UAV-O-OP model are:

In the UAV-O-OP model, N _A represents the number of areas A _i to be detected; A ₀ , Represents the starting point and the end point of the multi-rotor UAV, and the starting point and the end point are the same point; S _i represents the area of the area A _i to be detected; P _i represents the income obtained by completing the task of the area A _i to be detected; t _i represents the time for the multi-rotor UAV to perform tasks in the detection area A _i according to the parallel scanning flight mode; t _ij represents the time for the multi-rotor UAV to fly between the areas A _i and A _j to be detected; The maximum flight time limit of the man-machine; u _i represents the position of the area A _i to be detected in the route; _xi represents the situation where the multi-rotor UAV completes the task in the area A _i to be detected, if _xi = 1, it means that the detection task is completed , otherwise the multi-rotor UAV does not perform tasks in the area to be detected A _i ; y _ij indicates whether the multi-rotor UAV passes through the area to be detected A _i , A _j , if y _ij = 1 means that the multi-rotor UAV passes through the area to be detected A _i , A _j , otherwise the multi-rotor UAV has not passed through the area to be detected A _i , A _j ;

Wherein, the parallel scanning flight mode is: enter the area to be detected from the first entry point on the first side in a direction perpendicular to the first side of the area to be detected, and the distance between the first entry point and the apex of the nearest area to be detected is The distance is the detection radius of the multi-rotor UAV, and the first side is any side of the area to be detected; within the area to be detected, it flies in a manner parallel to one side of the area to be detected.

During specific implementation, the initial solution obtaining unit 202 is further used to:

Encoding the information of the area to be detected and the information of the multi-rotor UAV, randomly generating a plurality of chromosomes;

Wherein, the first row of the plurality of chromosomes is a random full arrangement of the identification information of the region to be detected, the second row of the plurality of chromosomes indicates whether the multi-rotor UAV performs the task of the region to be detected, and the plurality of chromosomes The third row of the chromosome is a random combination of entry points of the multi-rotor UAV into the area to be explored.

During specific implementation, the optimal solution calculation unit is further configured to perform the following steps:

Step 1. Generate an initial parent population of a preset size according to the initial solution, and calculate the fitness of each chromosome in the population;

Step 2. Carry out crossover operation on the chromosomes in the parent population to obtain the first generation offspring population. The crossover step specifically includes:

Randomly select two crossover positions in the first chromosome, and then find the same gene in the first line of the first chromosome crossover position in the second chromosome; replace the crossover position genes of the first chromosome and the second chromosome, so as to obtain the first Three chromosomes and the fourth chromosome; judging whether the third chromosome and the fourth chromosome satisfy the preset constraint condition; if satisfied, replace the first chromosome and the second chromosome in the parent population; if not satisfied, then end the current operation;

Step 3, performing a mutation operation on the chromosomes in the first-generation offspring population to obtain the second-generation offspring population, and the variation steps specifically include:

Randomly select the fifth chromosome to perform the mutation operation. If the first row is mutated, the first row will be randomly arranged. If the second row is mutated, the mutation position will be determined, and the original non-multi-rotor UAV will perform the task. Become a multi-rotor UAV to perform tasks, or on the contrary, if the third line mutates, determine the position of its mutation, and replace the entry point at the original mutation position with the randomly generated entry point;

Step 4: Obtain the optimal solution in the second child population according to the fitness function, and combine the second child population with the parent population according to a preset ratio to form a new parent population;

Judging whether the number of overall loop iterations in the current steps 2, 3, and 4 reaches the preset value; if not, return to step 2, and perform step 2 with the new parent population as the current parent population; if so, execute Step five;

Step 5: End the iteration, and use the final optimal solution as the assignment result of this task.

During specific implementation, the fitness of the chromosome is:

Among them, N _A represents the number of the area A _i to be detected; S _i represents the area of the area A _i to be detected; P _{i represents} the income obtained by completing the task of the area A _i to be detected; detection task, otherwise the multi-rotor UAV does not perform tasks in the detection area A _i ;

Among them, 0,...N _A+1 represents the starting point, the area to be detected and the end point; t _i represents the time for the multi-rotor UAV to perform tasks on the detection area A _i according to the parallel scanning strategy; t _ij represents the multi-rotor without The flight time of the man-machine between the area A _i and A _j to be detected; _xi indicates the situation that the multi-rotor UAV completes the task in the area A _i to be detected. If _xi = 1, it means that the detection task is completed, otherwise the The multi-rotor UAV does not perform tasks in the detection area A _i ; y _ij indicates whether the multi-rotor UAV passes through the area A _i , A _j to be detected; if y _ij = 1, it means that the multi-rotor UAV passes through the area A _i to be detected ,A _j , otherwise the multi-rotor UAV does not pass through the area to be detected A _i ,A _j .

Since the device for allocating UAV detection tasks introduced in this embodiment is a device that can implement the method for allocating UAV detection tasks in the embodiments of the present invention, based on the UAV detection tasks introduced in the embodiments of the present invention For the method of distribution, those skilled in the art can understand the specific implementation of the device for the distribution of UAV detection tasks in this embodiment and its various variations, so how to implement this method for the device for distribution of UAV detection tasks here The method for allocating UAV detection tasks in the embodiment of the invention will not be described in detail again. As long as those skilled in the art implement the device used by the method for allocating UAV detection tasks in the embodiment of the present invention, they all fall within the scope of protection intended by this application.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure the understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, in order to streamline this disclosure and to facilitate an understanding of one or more of the various inventive aspects, various features of the invention are sometimes grouped together in a single embodiment, figure, or its description. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art can understand that the modules in the device in the embodiment can be adaptively changed and arranged in one or more devices different from the embodiment. Modules or units or components in the embodiments may be combined into one module or unit or component, and furthermore may be divided into a plurality of sub-modules or sub-units or sub-assemblies. All features disclosed in this specification (including accompanying claims, abstract and drawings) and any method or method so disclosed may be used in any combination, except that at least some of such features and/or processes or units are mutually exclusive. All processes or units of equipment are combined. Each feature disclosed in this specification (including accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will understand that although some embodiments herein include some features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of the invention. And form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.

Certain component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components in the gateway, proxy server, and system according to the embodiments of the present invention. The present invention can also be implemented as an apparatus or an apparatus program (for example, a computer program and a computer program product) for performing a part or all of the methods described herein. Such a program for realizing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet site, or provided on a carrier signal, or provided in any other form.

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 can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The use of the words first, second, and third, etc. does not indicate any order. These words can be interpreted as names.

Claims (8)

1. a kind of unmanned plane detection mission distribution method, which is characterized in that waited for using a frame multi-rotor unmanned aerial vehicle muti-piece rectangle Search coverage executes a variety of detection missions, which comprises

Obtain area information to be detected and multi-rotor unmanned aerial vehicle information；

Obtain the initial solution for meeting preset UAV-O-OP model constraint condition, wherein the UAV-O-OP model is more rotors Unmanned plane obtains the maximum objective function of total revenue in this detection mission；The constraint condition includes multi-rotor unmanned aerial vehicle institute The constraint of flight duration；

The objective function of the UAV-O-OP model are as follows:

The constraint condition of the UAV-O-OP model are as follows:

In UAV-O-OP model, N_AIndicate region A to be detected_iNumber；A₀,Indicate the starting point of multi-rotor unmanned aerial vehicle And terminal, the starting point and terminal are same point；S_iIndicate region A to be detected_iArea；P_iIt indicates to complete region to be detected A_iTask income obtained；t_iIndicate multi-rotor unmanned aerial vehicle to search coverage A_iIt executes and appoints according to parallel sweep flying method The time of business；t_ijIndicate multi-rotor unmanned aerial vehicle in region A to be detected_i,A_jBetween time for flying；E indicates multi-rotor unmanned aerial vehicle Maximum flight duration limitation；u_iIndicate region A to be detected_iPosition in route；x_iIndicate that multi-rotor unmanned aerial vehicle treats detecting area Domain A_iThe case where completion task, if x_i=1, then it represents that complete detection mission, otherwise multi-rotor unmanned aerial vehicle does not treat search coverage A_iExecution task；y_ijIndicate whether multi-rotor unmanned aerial vehicle passes through region A to be detected_i,A_jIf y_ij=1 indicates multi-rotor unmanned aerial vehicle By region A to be detected_i,A_j, otherwise the multi-rotor unmanned aerial vehicle does not pass through region A to be detected_i,A_j；

The initial solution is based on using preset genetic algorithm, optimal solution is obtained to the UAV-O-OP model solution, and most by this Excellent solution is as the multi-rotor unmanned aerial vehicle to the task allocation result in muti-piece region to be detected, comprising:

Step 1: generate the initial parent population of default scale according to the initial solution, and calculate in population every chromosome Fitness；

Step 2: carrying out crossover operation to chromosome in parent population obtains first generation progeny population, the step of intersection, has Body includes:

Two crossover locations in the first chromosome are randomly choosed, then look for intersecting position with the first chromosome in the second chromosome The identical gene of the first row set；The crossover location gene of the first chromosome and the second chromosome is replaced, to obtain Third chromosome and tetrasome；Judge whether the third chromosome and tetrasome meet the constraint article Part；If satisfied, then replacing the first chromosome and the second chromosome in the parent population；If not satisfied, then terminating current Operation；

Step 3: carrying out mutation operation to chromosome in first generation progeny population obtains second generation progeny population, the variation Step specifically includes:

It randomly chooses the 5th chromosome and carries out mutation operation, if the first row morphs, random fully intermeshing is carried out to the first row, If the second row morphs, definitive variation position, and by original no multi-rotor unmanned aerial vehicle execute task become to have more rotors without Man-machine execution task, or on the contrary, the position of its variation, and the inlet point that will be generated at random are determined if the third line morphs Replace the inlet point at former variable position；

Step 4: obtain the optimal solution in the second generation progeny population according to fitness function, and by the second generation filial generation Population combines to form new parent population according to preset ratio with the parent population；

Judge whether the number of the whole loop iteration of current procedures two, three, four reaches preset value；If it is not, then return step two, and Step 2 is executed using the new parent population as current parent population；If so, executing step 5；

Step 5: terminate iteration, and using the optimal solution finally obtained as the allocation result of this subtask.

2. according to the method described in claim 1, it is characterized by:

The parallel sweep flying method are as follows: with perpendicular to region first to be detected while direction from first while on first enter Point enters region to be detected, and first inlet point detects at a distance from nearest region vertex to be detected for multi-rotor unmanned aerial vehicle Radius, first side are any one side in region to be detected；It is used inside region to be detected and is parallel to region to be detected The mode on one side is flown.

3. the method according to claim 1, wherein the acquisition meets preset UAV-O-OP model constraint item The initial solution of part, comprising:

The area information to be detected, multi-rotor unmanned aerial vehicle information are encoded, generate a plurality of chromosome at random；

Wherein, the random fully intermeshing of the identification information in region to be detected described in the first behavior of a plurality of chromosome is described more Second row of chromosome indicates whether multi-rotor unmanned aerial vehicle executes region task to be detected, the third line of a plurality of chromosome Enter the random combine of the inlet point in region to be detected for multi-rotor unmanned aerial vehicle.

4. the method according to claim 1, wherein the fitness of the chromosome are as follows:

Wherein, N_AIndicate region A to be detected_iNumber；S_iIndicate region A to be detected_iArea；P_iIt indicates to complete region to be detected A_iTask income obtained；If x_i=1, then it represents that complete detection mission, otherwise the multi-rotor unmanned aerial vehicle is not to be detected Region A_iExecution task；

Wherein, 0, N_A+1Indicate starting point and ending point；t_iIndicate multi-rotor unmanned aerial vehicle to search coverage A_iAccording to parallel sweep plan Slightly execute the time of task；t_ijIndicate multi-rotor unmanned aerial vehicle in region A to be detected_i,A_jBetween time for flying；x_iIndicate more rotations Wing unmanned plane completes region A to be detected_iThe case where completion task, if x_i=1, then it represents that complete detection mission, otherwise more rotors Unmanned plane does not treat search coverage A_iExecution task；y_ijIndicate whether multi-rotor unmanned aerial vehicle passes through region A to be detected_i,A_jIf y_ij=1 indicates that multi-rotor unmanned aerial vehicle passes through region A to be detected_i,A_j, otherwise the multi-rotor unmanned aerial vehicle does not pass through region to be detected A_i,A_j。

5. a kind of unmanned plane detection mission distributor, which is characterized in that waited for using a frame multi-rotor unmanned aerial vehicle muti-piece rectangle Search coverage executes a variety of detection missions, and described device includes:

Information acquisition unit, for obtaining area information to be detected and multi-rotor unmanned aerial vehicle information；

Initial solution acquiring unit, for obtaining the initial solution for meeting preset UAV-O-OP model constraint condition, wherein described UAV-O-OP model is that multi-rotor unmanned aerial vehicle obtains the maximum objective function of total revenue in this detection mission；The constraint item Part includes the constraint of multi-rotor unmanned aerial vehicle institute flight duration；

The objective function of the UAV-O-OP model are as follows:

The constraint condition of the UAV-O-OP model are as follows:

In UAV-O-OP model, N_AIndicate region A to be detected_iNumber；A₀,Indicate the starting point of multi-rotor unmanned aerial vehicle And terminal, the starting point and terminal are same point；S_iIndicate region A to be detected_iArea；P_iIt indicates to complete region to be detected A_iTask income obtained；t_iIndicate multi-rotor unmanned aerial vehicle to search coverage A_iIt executes and appoints according to parallel sweep flying method The time of business；t_ijIndicate multi-rotor unmanned aerial vehicle in region A to be detected_i,A_jBetween time for flying；E indicates multi-rotor unmanned aerial vehicle Maximum flight duration limitation；u_iIndicate region A to be detected_iPosition in route；x_iIndicate that multi-rotor unmanned aerial vehicle treats detecting area Domain A_iThe case where completion task, if x_i=1, then it represents that complete detection mission, otherwise multi-rotor unmanned aerial vehicle does not treat search coverage A_iExecution task；y_ijIndicate whether multi-rotor unmanned aerial vehicle passes through region A to be detected_i,A_jIf y_ij=1 indicates multi-rotor unmanned aerial vehicle By region A to be detected_i,A_j, otherwise the multi-rotor unmanned aerial vehicle does not pass through region A to be detected_i,A_j；

Optimal solution computing unit, for being based on the initial solution to the UAV-O-OP model solution using preset genetic algorithm Optimal solution is obtained, and using the optimal solution as the multi-rotor unmanned aerial vehicle to the task allocation result in muti-piece region to be detected, comprising:

Step 1: generate the initial parent population of default scale according to the initial solution, and calculate in population every chromosome Fitness；

Step 2: carrying out crossover operation to chromosome in parent population obtains first generation progeny population, the step of intersection, has Body includes:

Two crossover locations in the first chromosome are randomly choosed, then look for intersecting position with the first chromosome in the second chromosome The identical gene of the first row set；The crossover location gene of the first chromosome and the second chromosome is replaced, to obtain Third chromosome and tetrasome；Judge whether the third chromosome and tetrasome meet the constraint article Part；If satisfied, then replacing the first chromosome and the second chromosome in the parent population；If not satisfied, then terminating current Operation；

Step 3: carrying out mutation operation to chromosome in first generation progeny population obtains second generation progeny population, the variation Step specifically includes:

It randomly chooses the 5th chromosome and carries out mutation operation, if the first row morphs, random fully intermeshing is carried out to the first row, If the second row morphs, definitive variation position, and by original no multi-rotor unmanned aerial vehicle execute task become to have more rotors without Man-machine execution task, or on the contrary, the position of its variation, and the inlet point that will be generated at random are determined if the third line morphs Replace the inlet point at former variable position；

Step 4: obtain the optimal solution in the second generation progeny population according to fitness function, and by the second generation filial generation Population combines to form new parent population according to preset ratio with the parent population；

Judge whether the number of the whole loop iteration of current procedures two, three, four reaches preset value；If it is not, then return step two, and Step 2 is executed using the new parent population as current parent population；If so, executing step 5；

Step 5: terminate iteration, and using the optimal solution finally obtained as the allocation result of this subtask.

6. device according to claim 5, it is characterised in that:

The parallel sweep flying method are as follows: with perpendicular to region first to be detected while direction from first while on first enter Point enters region to be detected, and first inlet point detects at a distance from nearest region vertex to be detected for multi-rotor unmanned aerial vehicle Radius, first side are any one side in region to be detected；It is used inside region to be detected and is parallel to region to be detected The mode on one side is flown.

7. device according to claim 5, which is characterized in that the initial solution acquiring unit is further used for:

The area information to be detected, multi-rotor unmanned aerial vehicle information are encoded, generate a plurality of chromosome at random；

Wherein, the random fully intermeshing of the identification information in region to be detected described in the first behavior of a plurality of chromosome is described more Second row of chromosome indicates whether multi-rotor unmanned aerial vehicle executes region task to be detected, the third line of a plurality of chromosome Enter the random combine of the inlet point in region to be detected for multi-rotor unmanned aerial vehicle.

8. device according to claim 5, which is characterized in that the fitness of the chromosome are as follows:

Wherein, N_AIndicate region A to be detected_iNumber；S_iIndicate region A to be detected_iArea；P_iIt indicates to complete region to be detected A_iTask income obtained；If x_i=1, then it represents that complete detection mission, otherwise the multi-rotor unmanned aerial vehicle is not to be detected Region A_iExecution task；

Wherein, 0, N_A+1Indicate starting point and ending point；t_iIndicate multi-rotor unmanned aerial vehicle to search coverage A_iAccording to parallel sweep plan Slightly execute the time of task；t_ijIndicate multi-rotor unmanned aerial vehicle in region A to be detected_i,A_jBetween time for flying；x_iIndicate more rotations Wing unmanned plane completes region A to be detected_iThe case where completion task, if x_i=1, then it represents that complete detection mission, otherwise more rotors Unmanned plane does not treat search coverage A_iExecution task；y_ijIndicate whether multi-rotor unmanned aerial vehicle passes through region A to be detected_i,A_jIf y_ij=1 indicates that multi-rotor unmanned aerial vehicle passes through region A to be detected_i,A_j, otherwise the multi-rotor unmanned aerial vehicle does not pass through region to be detected A_i,A_j。