Unmanned aerial vehicle task planning method and system based on comprehensive empowerment, and storage medium

Abstract

The application discloses a kind of unmanned plane task planning method, system and storage medium based on comprehensive empowerment.The method comprises: determining the site of task planning, obtaining the physical space distance between each site, obtaining the weather state expectation value of the way station in the task execution time period, the weather state expectation value of site is used as the weight factor of the physical space distance between two sites, the path cost between two sites is calculated, the path cost model is constructed, the path cost between any two sites is described in path length model, and then the total path cost model for calculating the planning path total cost is obtained, the total path cost model is solved, and the path with minimum total path cost is obtained.The influence of extreme and severe weather on unmanned plane task planning is avoided, and the safety, feasibility and applicability of unmanned plane path planning are improved.

Description

Technical Field

[0001] The present application relates to the technical field of UAV flight mission planning, and more specifically, to a UAV mission planning method, system, device and storage medium based on comprehensive empowerment. Background Art

[0002] As a new type of weapon, drones (UAVs) have attracted widespread attention from researchers both domestically and internationally due to their rapid deployment, portability, and mobile networking capabilities. UAV mission planning is a key technology for enabling efficient UAV mission execution and is a combinatorial optimization problem that seeks to solve extreme values ​​in discrete states.

[0003] In a typical drone path planning problem, the optimization goal is to minimize the overall path after traversing all stations. Since the drone's speed is constant, this also means minimizing the overall flight time. Current algorithms are divided into two phases. The first phase uses an exact algorithm, which is very time-consuming. The second phase uses an approximate algorithm to minimize the overall flight path.

[0004] However, the actual overall flight path is affected by many factors. In longer flight paths, such as when performing missions across cities, severe weather may cause damage during the mission and make it impossible to continue domestic missions. How to achieve more applicable and feasible drone mission planning is still an urgent problem that needs to be solved. Summary of the Invention

[0005] In response to at least one defect or improvement need in the prior art, the present invention provides a UAV mission planning method based on comprehensive empowerment, which can effectively solve the UAV mission planning problem under conditions where weather conditions are known and predictable.

[0006] To achieve the above objectives, according to a first aspect of the present invention, a method for UAV mission planning based on comprehensive weighting is provided, the method comprising:

[0007] Determine the departure and en route points of the mission, and obtain the physical distance between the points;

[0008] Obtaining expected weather conditions for the route sites during the mission execution period;

[0009] The expected value of the weather state of the station is used as a weight factor of the physical space distance between the two stations to calculate the path cost between the two stations and construct a path cost model. The path length model describes the path cost between any two stations;

[0010] Constructing a planned path total cost model for calculating the total cost of the planned path based on the path cost model;

[0011] The total path cost model is solved to obtain a path with the minimum total path cost.

[0012] Furthermore, obtaining the expected value of the weather conditions at the route site during the mission execution time period includes:

[0013] Get weather forecast information and record the weather status of the i-th station on the t-th day as q it , then the weather status q at the i-th station on day t+1 is i,t Expressed as:

[0014] q i,t+1 =q i,t ×p i,[t,t+1] .

[0015] Among them, p i,[t,t+1] represents the weather condition of the i-th station, and the probability of the weather state transition from the t-th day to the t+1-th day,

[0016] For the i-th station, the expected weather conditions in the next n days can be expressed as:

[0017]

[0018] Furthermore, obtaining the weather transition probability includes: setting the probability of good turning good from day t to day t+1 as p1, the probability of good turning bad as p2, the probability of bad turning good as p3, and the probability of bad turning bad as p4, so that p1+p2=1,p3+p4=1, and the transition probability matrix p i,[t,t+1] Expressed as:

[0019]

[0020] Furthermore, taking the expected value of the weather state of a site as a weight factor of the physical space distance between two sites is to take the expected value of the weather state of the arrival site between the two sites as the power exponent of the physical space distance between the two sites.

[0021] Furthermore, the total number of en route sites is denoted as m, the departure site is denoted as c, and the path cost model is denoted as G, which is expressed as:

[0022]

[0023]

[0024] Among them, T u is the preset adjustment factor, 0≤T u ≤1,g ij represents the physical distance between site i and site j, 1≤i≤m, or i=c, 1≤j≤m, or j=c, E jis the expected value of the weather state at station j.

[0025] Furthermore, the total cost of the planned path is the sum of the path costs between each pair of adjacent sites on the planned path.

[0026] Furthermore, the total cost of the planned path is expressed as:

[0027]

[0028] The order of the UAV visiting sites in the planned path is recorded as Route = {c, v1, v2, ..., v m ,c}, v1,v2,...,v m represents the sites visited in sequence, G[c,v1] is the path cost of v1 when going from the starting site c to the first site, G[v i ,v j ] for site v i With site v j Calculation of path cost between 1≤i≤m, 1≤j≤m, G[v m ,c] is from site v m The path cost to the starting station c.

[0029] Furthermore, solving the total path cost model includes:

[0030] Construct the discriminant function x(s i ,s j ), representing site s i To site j The UAV path situation is expressed as:

[0031]

[0032] All sites are visited and only visited once, which is expressed as:

[0033]

[0034]

[0035] The objective function of the path cost model optimization based on the impact of weather factors on mission planning is expressed as:

[0036]

[0037] Genetic algorithm is used to solve the problem and obtain the path with the minimum total path cost.

[0038] According to a second aspect of the present invention, there is also provided a UAV mission planning system based on comprehensive weighting, comprising:

[0039] The spatial distance acquisition module is used to determine the starting point and the intermediate points of the task and obtain the physical distance between the points;

[0040] The module for obtaining the expected value of weather conditions is used to obtain weather forecast information, construct a weather condition transition probability matrix, and obtain the expected value of weather conditions at the route sites during the mission execution period;

[0041] The path cost acquisition module uses the expected weather conditions of the station as the weight factor of the physical space distance between the two stations to calculate the path cost between the two stations. After building the path cost model, a total cost model for planning the path is constructed to calculate the total cost of the planned path.

[0042] The path cost solving module is used to obtain the path with the minimum total path cost by solving the total path cost model.

[0043] According to a third aspect of the present invention, a storage medium is provided, which stores a computer program executable by a processor, and when the computer program runs on the processor, the processor executes the steps of any one of the above methods.

[0044] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects compared with the prior art:

[0045] (1) The present invention provides a UAV mission planning method based on comprehensive empowerment, which comprehensively considers the path length and the weather conditions of the target site in advance, reduces the impact of adverse weather phenomena on UAV flight, and improves the safety and feasibility of long-distance flight missions on the basis of ensuring that the UAV executes the minimized path length, thereby achieving the effect of saving fuel consumption and completing the site visit mission safely and quickly.

[0046] (2) The present invention uses weather conditions as weight factors to construct a path cost matrix based on weather conditions and a path cost model based on comprehensive weather condition weighting, and uses algorithms such as genetic algorithms to solve the problem. The problem can be solved by simply constructing the corresponding fitness function and connecting the path cost matrix to the corresponding interface of the genetic algorithm. This is easy to implement and has strong feasibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1A flowchart of a UAV mission planning method based on comprehensive empowerment provided in an embodiment of the present application;

[0049] Figure 2 A schematic diagram of the coding sequence before crossover of individuals without gene conflict provided in the embodiments of the present application;

[0050] Figure 3 A schematic diagram of the coding sequence after crossover of individuals without gene conflict provided in the embodiments of the present application;

[0051] Figure 4 A schematic diagram of the coding sequence before crossover of individuals with gene conflicts provided in the embodiments of the present application;

[0052] Figure 5 A schematic diagram of the coding sequence after crossover of individuals with gene conflicts provided in the embodiments of the present application;

[0053] Figure 6 A schematic diagram of the coding sequence after individual crossover before the mutation operation provided in the embodiment of the present application;

[0054] Figure 7 A schematic diagram of the coding order of individuals after crossover after the mutation operation provided in the embodiment of the present application;

[0055] Figure 8 A schematic diagram of the structure of a UAV mission planning system based on comprehensive empowerment provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely for the purpose of explaining the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.

[0057] The terms "first," "second," "third," and so on in the specification and claims of this application and the accompanying drawings are used to distinguish different objects, not to describe a specific order. In addition, the terms "including" and "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or modules is not limited to the listed steps or modules, but may optionally include steps or modules not listed, or may optionally include other steps or modules inherent to the process, method, product, or apparatus.

[0058] like Figure 1 The embodiment of the present invention provides a method for planning a UAV mission based on comprehensive weighting, including:

[0059] S101, determine the departure site and en route sites of the task, and obtain the physical space distance between the sites.

[0060] The departure site is the starting site of the mission planning, and the en route sites are the sites that need to be visited during the mission planning.

[0061] The physical distance between sites refers to the physical distance between two adjacent sites in mission planning.

[0062] In a specific embodiment, the starting point and the intermediate points to be visited can be determined according to the task requirements, which is recorded as Route = {c, v1, v2, ..., v m}, the number of stations along the way is m, and the location of station i is l i =(x i ,y i ).

[0063] S102, obtaining expected values ​​of weather conditions at route sites during the mission execution period.

[0064] The expected value of weather conditions refers to the mathematical expectation of the probability that the weather forecast for a station will change between good and bad.

[0065] The weather expectation value can be obtained by classifying the weather conditions into two conditions, good or bad, based on the known weather forecast. Good weather means that the site can be visited, and bad weather means that the site cannot be visited. After calculating the probability of the weather conditions at the first moment switching between good and bad, the mathematical expectation of the weather conditions at the second moment is calculated. Any other method can also be used.

[0066] Furthermore, obtaining the expected value of the weather state includes obtaining weather forecast information, recording the weather state of the i-th station on the t-th day as q it , then the weather status q at the i-th station on day t+1 is i,j Expressed as:

[0067] q i,t+1 =q i,t ×p i,[t,t+1]

[0068] Among them, p i,[t,t+1] It represents the weather condition of the i-th station, and the probability of the weather state transition from the t-th day to the t+1-th day.

[0069] For the i-th station, the expected weather conditions in the next n days can be expressed as:

[0070]

[0071] Furthermore, when performing a mission, the drone needs to determine whether to go to the destination site based on the weather conditions at the destination site.

[0072] As an example, suppose the future weather conditions at each station are known. The weather forecast is divided into two categories: good and bad. The weather state is {0, 1}, where 0 represents good weather and the station is accessible, and 1 represents bad weather and the station is inaccessible. The probability of good turning good is p1, the probability of good turning bad is p2, the probability of bad turning good is p3, and the probability of bad turning bad is p4. Without loss of generality, we have p1 + p2 = 1, p3 + p4 = 1, and the transition probability matrix can be expressed as:

[0073]

[0074] In order to reflect the impact of weather conditions on path length, it is assumed that p1+p3>p2+p4.

[0075] Assume that the weather state of the i-th station on the j-th day is q ij , then the weather status of day j+1 can be expressed as:

[0076] q i,j+1 =q i,j ×p i,[j,j+1]

[0077] S103 , using the expected value of the weather status of the site as a weight factor of the physical space distance between the two sites, calculates the path cost between the two sites, and constructs a path cost model. The path length model describes the path cost between any two sites.

[0078] Using the expected weather conditions at a station as a weighting factor for the physical distance between two stations is like using the expected weather conditions for reaching the station between the two stations as a power exponent of the physical distance between the two stations. Weather affects the length of path planning. By using the expected weather conditions as a weighting factor for the physical distance between the two stations, the path cost is calculated. By calculating the optimal solution for this path cost, we can avoid situations where inclement weather could cause damage during mission execution and prevent the continuation of domestic missions, thereby improving the safety of UAV mission planning.

[0079] Furthermore, as an example, taking weather expectations as the weight factor of physical space distance, the power exponential method is used to construct a path length model based on weather influencing factors. The path cost model is denoted as G and is expressed as follows:

[0080]

[0081]

[0082] Among them, Tu is the preset adjustment factor, 0≤T u ≤1,g ij represents the physical distance between site i and site j, 1≤i≤m, or i=c, 1≤j≤m, or j=c, E j is the expected value of the weather state at station j.

[0083] Preferably, the power exponential method is used to establish the path cost model. This method uses the adjustment factor and weather expectation as negative exponentials to better reflect the impact of weather factors on the path cost while maintaining positive values ​​in the matrix G. Ensuring that the values ​​in the matrix G are positive improves feasibility.

[0084] Furthermore, the total cost of the planned path is the sum of the costs between each pair of adjacent sites on the planned path. As an example, when planning a mission, the drone starts from the starting site, visits all the sites along the way, and finally returns to the starting site. The order of the drone's visits is recorded as

[0085] Route={c,v1,v2,...,v m ,c}

[0086] After considering the impact of weather factors on path planning, when the drone departs from the freight station and heads to the first station, the path cost is calculated as G[c,v1], where v1 represents the number of the first station; when the drone returns to the freight station from the last station, the path cost is calculated as G[v m ,c], where v m Represents the number of the last visited site; site v i With site v j The path cost between i ,v j ].

[0087] S104: Constructing a planned path total cost model for calculating the planned path total cost according to the path cost model.

[0088] The total cost model of the planning path refers to the sum of the path costs between all adjacent sites in the planning task.

[0089] Furthermore, for UAV mission planning, the overall optimization goal is to minimize the path cost, that is, the calculation formula for the total cost of the planned path is:

[0090]

[0091] Among them, 1≤i≤m, 1≤j≤m.

[0092] Furthermore, constructing the total cost model of the planned path also includes: constructing the discriminant function x(s i ,s j ), representing site s i To site j The UAV path situation is expressed as:

[0093]

[0094] To ensure that all sites are visited and only visited once, it is necessary to meet the inflow and outflow balance, which can be expressed as:

[0095]

[0096]

[0097] Furthermore, the model optimization objective function of the total cost of the planned path is expressed as:

[0098]

[0099] S105 , solving the path total cost model to obtain a path with the minimum total path cost.

[0100] To obtain the path with the minimum total path cost, the total path cost model is solved by an algorithm to obtain the path solution with the minimum path cost. The solution can be solved by a genetic algorithm or any other algorithm.

[0101] Preferably, the total path cost model is solved using a genetic algorithm to obtain a path with the minimum total path cost.

[0102] The use of genetic algorithms also includes:

[0103] Step A1: Set parameter initialization to determine the number of sites m and location l, the initial population size n, the maximum number of iterations, and the crossover probability p. c , mutation probability p m .

[0104] Step A2: integer code the departure station and the intermediate stations, and construct the inter-station path cost matrix G according to the weather forecast and the distance between stations.

[0105] Step A3: randomly generate n individuals, each of which represents a path planning solution:

[0106] Plan={Route1,Route2,Route3,...,Route n}

[0107] Calculate the total path cost for each individual, expressed as:

[0108]

[0109] Construct a fitness function. The magnitude of this value reflects the probability that an individual is retained during the iteration process. It is calculated as the reciprocal of the path cost and is expressed as:

[0110] f = 1 / value

[0111] Step A4. According to the fitness value of each individual, use the roulette betting method to calculate the probability that an individual is selected. For the k-th individual, its probability of being selected is calculated as:

[0112]

[0113] Step A5, crossover operation. According to the crossover probability p c , calculate the number of individuals in the population that need to perform crossover, which is np c . Randomly select two individuals Route i and Route j from all individuals, and perform the following operations on them until all individuals to be crossed have completed the crossover operation. If np c is odd, do not operate on the last individual.

[0114] Step A5.1. Randomly generate two integers, a and b, within the range [1, m] such that a < b. Swap the stations within the range [a, b]. Since performing the crossover operation may cause gene conflicts in individuals, the encoding order of individuals without gene conflicts before crossover is as shown in Figure 2 , and the encoding order of individuals after crossover encoding is as shown in Figure 3 . If there are no gene conflicts, execute STEP5.3; otherwise, execute STEP5.2.

[0115] Step A5.2: The encoding order of individuals with gene conflicts before and after crossover is as shown in Figure 4 , Figure 5 . First, detect whether there are gene conflicts between the range [1, a] and [a, b], and then detect whether there are gene conflicts between the range [b, m] and [a, b]. Taking the latter as an example, in Figure 5 , after crossover, the 5th and 7th positions of Route1 are repeated. Record these two positions as p and q respectively. Replace the gene at the p position in Route2 with the gene at the q position in Route1, and repeat this process until there are no gene conflicts in the individual.

[0116] Step A5.3: Mutation operation. According to the mutation probability p m , calculate the number of individuals in the population that need to perform crossover, which is np m. For all individuals undergoing mutation, two integers, c and d, are randomly generated within the range of [1, m], satisfying c < d. The genes within the range of [c, d] are arranged in reverse order. The gene coding order of the individual before and after mutation is as Figure 6 、 Figure 7 shown.

[0117] Step A5.6: Calculate the fitness value of the newly generated individual. If the fitness value is greater than the fitness value of the individual in the original population, this individual will participate in the next iteration as an individual in the new population, and update the iteration count iteration.

[0118] Step A5.7: Repeat Step A5.4 to Step A5.6 until the iteration count reaches the set value, and select the individual with the maximum fitness value as the path planning solution.

[0119] Based on the same idea, one or more embodiments of this specification also provide a device and equipment corresponding to the above method.

[0120] Figure 8 FIG. is a schematic structural diagram of an unmanned aerial vehicle mission planning system based on comprehensive weighting provided by one or more embodiments of this specification. The device includes:

[0121] The space distance acquisition module 501 is used to determine the departure site and passing sites of the mission, and obtain the physical space distance between each site;

[0122] The weather state expectation acquisition module 502 is used to construct a weather condition transition probability matrix by obtaining weather forecast information, and obtain the weather state expectation of the passing sites during the mission execution period;

[0123] The path cost acquisition module 503 uses the weather state expectation of the site as a weight factor for the physical space distance between two sites, calculates the path cost between two sites, constructs a path cost model, and then constructs a total path cost model for calculating the total cost of the planned path;

[0124] The path cost solving module 504 is used to solve the total path cost model to obtain the path with the minimum total path cost.

[0125] The implementation principle and technical effect of the system of the present invention are similar to the above method, and will not be elaborated here.

[0126] The present application also provides a storage medium storing a computer program executable by a processor. When the computer program is executed on the processor, the processor is caused to perform any of the steps of the above-mentioned method for planning a UAV mission based on comprehensive empowerment. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a microdrive, a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0127] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0128] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0129] In the several embodiments provided in this application, it should be understood that the disclosed system can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of the modules is merely a logical function division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interface, and the indirect coupling or communication connection of the system or module can be electrical or other forms.

[0130] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected to achieve the purpose of this embodiment according to actual needs.

[0131] In addition, the functional modules in the various embodiments of the present application may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into a single module. The above-mentioned integrated modules may be implemented in the form of hardware or software functional modules.

[0132] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0133] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0134] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure herein, those skilled in the art will easily think of the implementation scheme of the present disclosure. This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art that are not recorded in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

[0135] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0136] It will be easily understood by those skilled in the art that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A UAV mission planning method based on comprehensive empowerment, characterized in that: include: Determine the departure and en route points of the mission, and obtain the physical distance between the points; Obtaining expected weather conditions for the route sites during the mission execution period; The expected value of the weather state of the station is used as a weight factor of the physical space distance between the two stations to calculate the path cost between the two stations and construct a path cost model. The path length model describes the path cost between any two stations; Constructing a planned path total cost model for calculating the total cost of the planned path based on the path cost model; Solving the total path cost model to obtain a path with the minimum total path cost; The total number of en route sites is denoted as m, the departure site is denoted as c, and the path cost model is denoted as G; The total cost of the planned path is the sum of the path costs between each pair of adjacent sites on the planned path; The total cost of the planned path is expressed as: Among them, the order in which the UAV visits the sites in the planned path is recorded as , Indicates the sites visited in sequence. From the departure point c When heading to the first station v A path cost of 1, For site With site Calculate the path cost between i ≤ m , 1≤ j ≤ m , From the site v m Go to the departure point c The path cost; Solving the total path cost model includes: Constructing the discriminant function , representing the site To the site The UAV path situation is expressed as: All sites are visited and only visited once, which is expressed as: The objective function for optimizing the path cost model based on the impact of weather factors on mission planning is expressed as: Genetic algorithm is used to solve the problem and obtain the path with the minimum total path cost.

2. The UAV mission planning method based on comprehensive weighting according to claim 1, characterized in that: Obtaining the expected weather conditions of the route sites during the mission execution period includes: Get weather forecast information and Day's The weather status of each station is recorded as , then Site No. Weather conditions of the day Expressed as: in, Indicates the The weather conditions of the stations are given by Day transfer to The weather transition probability of the day, For the For each site, in the future The expected weather conditions during the day can be expressed as: 。 3. The UAV mission planning method based on comprehensive weighting according to claim 2, characterized in that: The weather transition probability includes: The first Day to day The probability of the weather turning from good to good is recorded as , the probability of good turning bad is , the probability of bad turning to good is , the probability of bad turning bad is ,satisfy , the transition probability matrix Expressed as: 。 4. The method for UAV mission planning based on comprehensive weighting according to claim 1, characterized in that: The use of the expected value of the weather status of a site as a weight factor of the physical space distance between two sites is to use the expected value of the weather status of the arrival site between the two sites as a power exponent of the physical space distance between the two sites.

5. The method for UAV mission planning based on comprehensive weighting according to claim 4, characterized in that: The total number of stations along the way is recorded as m , and record the departure station as c , the path cost model is recorded as G, and the expression is: in, is the preset adjustment factor, , Representative Site and sites The physical distance between i ≤ m ,or i=c, 1≤ j ≤ m ,or j=c,E j It is a site Expected weather conditions 。 6. A UAV mission planning system based on comprehensive weighting based on the UAV mission planning method based on comprehensive weighting according to claim 1, characterized in that: include: The spatial distance acquisition module is used to determine the starting point and the intermediate points of the task and obtain the physical distance between the points; The module for obtaining the expected value of weather conditions is used to obtain weather forecast information, construct a weather condition transition probability matrix, and obtain the expected value of weather conditions at the route sites during the mission execution period; The path cost acquisition module uses the expected weather conditions of the station as the weight factor of the physical space distance between the two stations to calculate the path cost between the two stations. After building the path cost model, a total cost model for planning the path is constructed to calculate the total cost of the planned path. The path cost solving module is used to obtain the path with the minimum total path cost by solving the total path cost model.

7. A storage medium, characterized in that: The device stores a computer program, which enables the processor to execute the steps of the method according to any one of claims 1 to 5 when the computer program is run on the processor.

Images