An unmanned aerial vehicle flight task planning method and device with thermal stealth function

Abstract

The application discloses a kind of unmanned aerial vehicle flight task planning methods with heat stealth function, method includes: unmanned aerial vehicle state acquisition, obtain the information such as the initial resource, speed of unmanned aerial vehicle task weight in cluster, respectively calculate the flight time of each unmanned aerial vehicle, the task load of unmanned aerial vehicle, the path cost of unmanned aerial vehicle, finally optimize the path of each unmanned aerial vehicle in cluster by genetic algorithm.The method provided by the application comprehensively considers the self resource of unmanned aerial vehicle, stealth performance, the risk that possibly be detected by enemy, and is convenient to calculate, parameter is easy to measure or estimate, can quickly optimize the task planning of unmanned aerial vehicle, saves energy for unmanned aerial vehicle to execute various complex tasks, improves operating life and work efficiency and provides technical support.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicle task planning, in particular to an unmanned aerial vehicle flight task planning method and device with thermal stealth function. BACKGROUND

[0002] Unmanned aerial vehicle technology has been widely used in military, reconnaissance, logistics and other fields. With the development of technology, unmanned aerial vehicles with stealth capabilities are increasingly valued, especially in reducing the ability to be discovered by enemy radar or infrared detection systems during task execution. Traditional unmanned aerial vehicle task planning methods usually rely on fixed flight distances, task ranges and task restrictions, and cannot fully utilize the concealment advantages of unmanned aerial vehicles with thermal stealth function during task execution.

[0003] In the prior art, the planning of flight paths usually does not consider the dynamic relationship between the task execution time, task load and path optimization of each unmanned aerial vehicle in the unmanned aerial vehicle cluster, especially in the case of unmanned aerial vehicles with thermal stealth function. The relevance of these factors directly affects the execution effect and concealment of the task. Therefore, there is an urgent need for a task planning method that can comprehensively consider the task execution time, task load and flight path optimization of each unmanned aerial vehicle in the unmanned aerial vehicle cluster. SUMMARY

[0004] The purpose of the present application is to provide an unmanned aerial vehicle flight task planning method and device with thermal stealth function, which can comprehensively consider the stealth performance, task execution time and task load of the unmanned aerial vehicle during task execution, and further optimize the flight path of the unmanned aerial vehicle.

[0005] Technical solution: To achieve the above purpose, the technical solution adopted by the present application is:

[0006] An unmanned aerial vehicle flight task planning method with thermal stealth function, based on the thermal stealth characteristics of unmanned aerial vehicles, considering the path cost and risk function of unmanned aerial vehicles, improving the fitness function of genetic algorithm, and using the improved genetic algorithm to complete the optimization of the flight path of the cluster unmanned aerial vehicle. Wherein the improved fitness function F is:

[0007]

[0008] Wherein, J i is the total path cost of the ith unmanned aerial vehicle, D i (t) is the distance between the ith unmanned aerial vehicle and the enemy radar detection area at time t, and n is the number of unmanned aerial vehicles. The genetic algorithm path optimization steps are as follows:

[0009] (1) the path point coordinates of all individual unmanned aerial vehicles in the unmanned aerial vehicle group and the collection of distances of all individual unmanned aerial vehicles from enemy detection radars are coded into a gene sequence, an initial population is randomly generated, and an initial value k=1 of an evolution counter is set;

[0010] (2) the fitness function value of each individual is calculated according to the improved fitness function F;

[0011] (3) the population is selected, crossed and mutated according to the obtained fitness, to obtain a new generation population;

[0012] (4) k=k+1; it is judged whether k is less than the maximum evolution generation g, if yes, step (3) (4) is returned to for evolution, otherwise, step (5) is entered;

[0013] (5) the individual with the maximum fitness function in the population is found, the code is converted into the path point coordinates of the unmanned aerial vehicle, and the optimal path is constructed.

[0014] As a preferred scheme of the application, a mathematical model of path cost of the unmanned aerial vehicle is established considering the task execution time, task load and stealth performance of the unmanned aerial vehicle as follows:

[0015]

[0016] wherein, R i is the resource parameter of the i-th unmanned aerial vehicle, d i is the distance between the i-th unmanned aerial vehicle and the enemy detection radar, and α and β are weight coefficients, L i is the task load of the i-th unmanned aerial vehicle, and T i is the task execution time of the i-th unmanned aerial vehicle.

[0017] As a preferred scheme of the application, the task execution time calculation method of the unmanned aerial vehicle is as follows:

[0018]

[0019] wherein, P opt is the total length of the cluster path, v i (t) is the speed of the i-th unmanned aerial vehicle at t, D i (t) is the relative position of the i-th unmanned aerial vehicle and the enemy radar detection area at t, and k is a stealth weight coefficient.

[0020] As a preferred scheme of the application, the task load calculation method of the unmanned aerial vehicle is as follows:

[0021]

[0022] wherein, w i is the task weight of the i-th unmanned aerial vehicle, and f(Si ) = 1 - S i is a task execution efficiency correction function of the i-th UAV, S i is a thermal stealth state of the i-th UAV, when S i = 0, it means that the target temperature of the UAV is completely consistent with the ambient temperature, and the thermal stealth effect is the strongest; when S i = 1, it means that the target temperature and the ambient temperature are most different, and the thermal stealth effect is the worst.

[0023] Also provided is a UAV flight task planning device based on the method as described above, the device comprising:

[0024] a model construction module, configured to consider the task execution time, the task load and the stealth performance of the UAV, and establish a mathematical model of the path cost of the UAV;

[0025] a fitness function improvement module, configured to consider the path cost of the UAV and the distance of the UAV from the enemy detection radar, and improve the fitness function of the genetic algorithm;

[0026] a path planning module, configured to complete the optimization of the flight path of the UAV cluster by using the genetic algorithm with the improved fitness function.

[0027] Also provided is a computer readable storage medium storing one or more programs, the one or more programs including instructions that, when executed by a computing device, cause the computing device to perform the method as described above.

[0028] Also provided is an electronic device comprising one or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, and the one or more programs include instructions for performing the method as described above.

[0029] Beneficial effects: the UAV flight task planning method with thermal stealth function provided by the present application can effectively improve the concealment and task execution efficiency of the UAV cluster when performing tasks by calculating the path cost based on the task execution time and the task load and finally optimizing the path cost. Compared with the prior art, the present application can better adapt to the dynamic environmental factors in the UAV task planning, optimize the flight path, and maximize the stealth performance of the UAV. BRIEF DESCRIPTION OF DRAWINGS

[0030] Figure 1 is a flow chart of the method of the embodiment of the present application, showing each step of the UAV flight task planning. DETAILED DESCRIPTION

[0031] In order to make the content of the present application more clear, the present application will be described in detail below in combination with specific embodiments.

[0032] Engineering example: assume that there is a UAV cluster consisting of 3 UAVs with thermal stealth function, performing a reconnaissance task. The task requires the UAV to approach the target area as much as possible, while maintaining stealth during reconnaissance and saving resources (such as power) as much as possible.

[0033] Below, a flight task planning method for a UAV with thermal stealth function proposed by the present application will be adopted:

[0034] UAV parameters:

[0035] UAV 1: task weight W1 = 1.0, resource parameter R1 = 80 units, initial speed v1(t) = 10 m / s, initial value of stealth state: S1 = 0.85.

[0036] UAV 2: task weight W2 = 1.2, resource parameter R2 = 100 units, initial speed v2(t) = 12 m / s, initial value of stealth state: S2 = 0.90.

[0037] UAV 3: task weight W3 = 0.9, resource parameter R3 = 70 units, initial speed v3(t) = 8 m / s, initial value of stealth state: S3 = 0.80.

[0038] (1) Calculate the task execution time T of each UAV in the UAV cluster i

[0039]

[0040] Where v i (t) is the speed of the UAV; h i (t) is the path concealment, which is determined by the relative position of the UAV and the enemy radar detection area; k = 0.5.

[0041] Assume that the flight distance of the UAV cluster is 200 meters, and the path concealment functions of each UAV are h1(t) = 1.2, h2(t) = 1.0, and h3(t) = 1.5. We can calculate the flight time of each UAV:

[0042] UAV 1:

[0043]

[0044] Task execution time T1 = 16.00s.

[0045] UAV 2:

[0046]

[0047] Task execution time T1 = 18.87s.

[0048] UAV 3:

[0049]

[0050] Task execution time T3 = 22.86s.

[0051] (2) Calculate the task load of each UAV in the UAV cluster

[0052] According to the task execution time T calculated in the path optimization model i , we then calculate the task load L of each UAV in the UAV cluster:

[0053]

[0054] where w i is the task weight; T i is the task execution time; R i is the resource parameter of the UAV; f(S i , C i ) is the task efficiency correction function; γ = 0.8.

[0055] Assuming that the task efficiency correction function f(S i , C i ) = 1 = S i , the task load L i of each UAV is calculated as follows:

[0056] UAV 1:

[0057]

[0058] UAV 2:

[0059]

[0060] UAV 3:

[0061]

[0062] The task load L1 = 0.356, L2 = 0.288, L3 = 0.438 reflects the combination of resource consumption and task complexity of each UAV when performing the task.

[0063] (3) Calculate the path cost of each UAV in the UAV cluster

[0064]

[0065] where P i(t) is the stealth performance of the UAV i; d i (t) is the distance between the UAV and the target; a = 0.6; b = 0.4.

[0066] The path cost of each UAV is calculated:

[0067] UAV 1:

[0068]

[0069] UAV 2:

[0070]

[0071] UAV 3:

[0072]

[0073] (4) Optimize the flight path of each UAV in the UAV cluster.

[0074] The path is re-planned using a genetic algorithm to maximize the fitness function F, and the calculated value of the fitness function at this time is:

[0075]

[0076] Therefore, the genetic algorithm needs to be used to re-plan the path to obtain the maximum fitness, and the optimal path of the UAV is obtained.

[0077] Specifically, the genetic algorithm path optimization steps are as follows:

[0078] (1) Encode the path point coordinates of all individual UAVs in the UAV cluster and the distance from all individual UAVs to the enemy detection radar into a gene sequence, and randomly generate an initial population, while setting the initial value of the evolution counter k = 1;

[0079] (2) Calculate the fitness function value of each individual according to the improved fitness function F;

[0080] (3) Perform selection, crossover, and mutation operations on the population according to the obtained fitness to obtain a new generation of population;

[0081] (4) Let k = k + 1; judge whether k is less than the maximum evolution number g, if it satisfies, go to step (3) (4) to continue evolution, otherwise go to step (5);

[0082] Find the individual with the maximum fitness function in the population, convert the code to UAV path point coordinates, and construct the optimal path.

[0083] Obviously, the above embodiments are only examples for clearly illustrating the present application, and are not intended to limit the use modes. Based on the above description, those skilled in the art can make other different forms of changes or variations. Here, all the use modes do not need to be exhausted, and the obvious changes or variations derived therefrom are still within the protection scope of the present application.

[0084] The present application also provides a UAV flight task planning device based on the above method, the device comprising:

[0085] a model construction module for establishing a mathematical model of the path cost of the UAV by considering the task execution time, the task load and the stealth performance of the UAV;

[0086] a fitness function improvement module for improving the fitness function of the genetic algorithm by considering the path cost of the UAV and the distance of the UAV from the enemy detection radar;

[0087] a path planning module for optimizing the flight path of the cluster UAV by using the genetic algorithm with the improved fitness function.

[0088] The technical solution of the above UAV flight task planning device is similar to that of the above UAV flight task planning method, and will not be repeated here.

[0089] Based on the same technical solution, the present application also provides a computer readable storage medium storing one or more programs, the one or more programs comprising instructions, wherein the instructions, when executed by a computing device, cause the computing device to perform the UAV flight task planning method with the thermal stealth function as described above.

[0090] Based on the same technical solution, the present application also provides an electronic system comprising one or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, and the one or more programs comprise instructions for performing the UAV flight task planning method with the thermal stealth function as described above.

[0091] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

[0092] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart Figure 1 one or more functions specified in the flowchart or multiple flows and / or blocks. Figure 1 one or more functions specified in the flowchart or multiple flows and / or blocks.

[0093] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the Figure 1 one or more functions specified in the flowchart or multiple flows and / or blocks. Figure 1 one or more functions specified in the flowchart or multiple flows and / or blocks.

[0094] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart Figure 1 one or more functions specified in the flowchart or multiple flows and / or blocks. Figure 1 one or more functions specified in the flowchart or multiple flows and / or blocks.

Claims

1. A flight mission planning method for a UAV with thermal stealth function, characterized in that: Based on the thermal stealth characteristics of UAVs, the UAV path cost and the distance between the UAV and the enemy detection radar are considered, and the fitness function of the genetic algorithm is improved. The flight path of the swarm UAVs is optimized using the improved genetic algorithm. The improved fitness function F is: ， Among them, J i is the total path cost of the i-th UAV, D i (t) is the distance between the i-th UAV and the enemy radar detection area at time t, and n is the number of UAVs; Considering the mission execution time, mission load, and stealth performance of the UAV, the following mathematical model of the UAV's path cost is established: ， Among them, R i is the resource parameter of the i-th UAV, d i is the distance between the i-th UAV and the enemy detection radar, and is the weight coefficient, L i is the mission load of the i-th UAV, T i is the mission execution time of the i-th UAV; The calculation method of the UAV's mission execution time is: ， Among them, P opt is the total length of the cluster path, v i (t) is the speed of the i-th UAV at time t, and k is the stealth weight coefficient; The calculation method of the UAV's mission load is: ， Where w i is the mission weight of the i-th UAV, is the mission execution efficiency correction function of the i-th UAV, S i is the thermal stealth state of the i-th UAV.

2. The flight mission planning method according to claim 1, characterized in that: The steps to optimize the flight path of swarm drones using the improved genetic algorithm include: The path point coordinates of all individual drones in the drone swarm and the distances of all individual drones from the enemy detection radar are encoded into a gene sequence, and an initial population is randomly generated. At the same time, the initial value of the evolution counter k is set to 1; According to the improved fitness function F, calculate the fitness function value of each individual; According to the obtained fitness, the current population is selected, crossed, and mutated to obtain a new generation of population; Let k = k + 1; determine whether k is less than the maximum evolutionary generation g. If so, return to step (3); otherwise, proceed to step (5). Find the individual with the largest fitness function in the current population, convert the corresponding code of the individual into a drone path point, and thus generate the optimal path.

3. A UAV flight mission planning device based on the method according to any one of claims 1 to 2, characterized in that: The device comprises: The model building module is used to build a mathematical model of the UAV's path cost by considering the mission execution time, mission load, and UAV stealth performance; The fitness function improvement module is used to improve the fitness function of the genetic algorithm by considering the UAV path cost and the distance between the UAV and the enemy detection radar; The path planning module is used to optimize the flight path of cluster UAVs using a genetic algorithm with an improved fitness function.

4. A computer-readable storage medium storing one or more programs, wherein the one or more programs include instructions, characterized in that When the instructions are executed by a computing device, the computing device is caused to perform the method according to any one of claims 1 to 2.

5. An electronic device, characterized in that: The method comprises one or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and are configured to be executed by the one or more processors, and the one or more programs include instructions for executing the method according to any one of claims 1 to 2.

Images