Unmanned aerial vehicle track acquisition method based on rattan optimization algorithm and related product

Abstract

The invention provides an unmanned aerial vehicle track acquisition method based on a rattan optimization algorithm and a related product. The method comprises the following steps: acquiring a flight environment model of the unmanned aerial vehicle, determining a population search space of big rats according to the flight environment model, and initializing a big rats population in the population search space; then, a preset flight cost function is obtained, a hybrid big rattan optimization algorithm is adopted, optimization updating of set times is carried out on the big rattan population in the population search space according to the preset flight cost function, and optimization updating comprises updating of a detection stage on the big rattan population by adopting a chaos factor strategy; or updating the population of the rats in the development stage; and optimally adopting a preset flight cost function to obtain an optimal rattan individual in the rattan population so as to obtain an optimal track of the unmanned aerial vehicle. According to the technical scheme, the control reliability of the unmanned aerial vehicle can be improved.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle (UAV) flight control technology, and in particular to a UAV track acquisition method based on a large rat optimization algorithm and related products. Background Art

[0002] Multirotor drones, due to their low maintenance, simple operation, and high maneuverability, are widely used in a variety of fields, including urban patrols, traffic management, building inspections, and express delivery, and demand is rapidly growing. With technological advancements, urban drone operations will become increasingly intelligent in the future. Research on trajectory planning methods for drones in complex urban environments is crucial for designing stable and feasible trajectories, thereby improving the efficiency of drone mission execution.

[0003] UAV trajectory planning utilizes optimization algorithms to find the optimal path within the flight environment. Currently, these algorithms fall into two main categories: traditional optimization algorithms, which rely on gradients, derivatives, or analytical expressions for the objective function, gradually approaching the optimal solution using fixed rules (such as gradient descent and Newton's method). Intelligent optimization algorithms, on the other hand, simulate natural phenomena (such as biological and physical behavior) to search for the optimal solution and balance global exploration with local exploitation through random perturbations and adaptive strategies. Intelligent optimization algorithms are widely used in trajectory planning due to their advantages, such as flexible parameter settings and rapid convergence.

[0004] The Giant Rat Optimization Algorithm is a new intelligent optimization algorithm that simulates the foraging behavior of giant rats to search for the optimal solution. It also balances the exploration and exploitation phases of the optimization process, effectively preventing premature convergence. However, in environments with dense obstacles or complex terrain, such as in complex urban environments with numerous high-rise buildings, drones cannot be guaranteed to reach their designated target area stably, safely, and quickly. Summary of the Invention

[0005] The present invention provides a UAV track acquisition method and related products based on the Big Rat optimization algorithm, which are used to improve the safety and stability of UAV flight and ensure that the UAV can quickly reach the designated target area.

[0006] To achieve the above objectives, in a first aspect, the present invention provides a method for obtaining a UAV track based on a large rat optimization algorithm, comprising:

[0007] Obtaining environmental information of the city to be flown by the drone, and determining a population search space of giant rats based on the environmental information;

[0008] Obtaining a preset starting position and an ending position, as well as a preset number of track points, and initializing a population of giant rats in the population search space according to the starting position, the ending position, and the preset number;

[0009] Obtain a preset flight cost function, and adopt a hybrid giant rat optimization algorithm to optimize and update the giant rat population a set number of times in the population search space according to the preset flight cost function, wherein each optimization update includes:

[0010] Generate a random number within a preset value range and determine whether the random number is greater than a preset parameter value;

[0011] If so, a chaos factor strategy is used to update the population of giant vine rats in the detection phase;

[0012] If not, then the development stage of the said population of giant vine rats is updated;

[0013] The preset flight cost function is used to obtain the optimal giant rat individual in the giant rat population, and the optimal track of the UAV is obtained based on the optimal giant rat individual.

[0014] Furthermore, after the step of updating the population of giant vine rats in the detection phase by adopting the chaos factor strategy, or updating the population of giant vine rats in the development phase, the method further includes:

[0015] The Gaussian difference mutation strategy is used to update the giant rat population again.

[0016] Furthermore, the step of obtaining a preset flight cost function includes:

[0017] Obtaining a flight distance cost function, a flight altitude cost function, and a flight smoothness cost function of the UAV;

[0018] The flight distance cost function, the flight height cost function and the flight smoothness cost function are fused to obtain the preset flight cost function.

[0019] Furthermore, the step of initializing the population of giant rats in the population space according to the starting position, the end position and the preset number includes:

[0020] Obtaining the number of giant vine rat individuals in the giant vine rat population;

[0021] The track points of each of the giant vine rat individuals are randomly obtained in the population space to initialize the foraging path of each of the giant vine rat individuals.

[0022] Furthermore, the step of determining the population search space of the giant rat according to the environmental information includes:

[0023] A flight environment model of the UAV is constructed according to the environmental information, and the population search space is determined according to the flight environment model.

[0024] Furthermore, the step of constructing the flight environment model of the UAV according to the environmental information includes:

[0025] Acquire terrain information of the city to be flown, and location information and size information of each building in the city to be flown, based on the environmental information;

[0026] Constructing a three-dimensional map model of the city to be flown to based on the terrain information, and constructing a building model of the corresponding building based on each piece of size information;

[0027] The corresponding building model is loaded into the three-dimensional map model according to each piece of position information to obtain the flight environment model.

[0028] Furthermore, the step of loading the corresponding building model into the three-dimensional map model according to each piece of location information includes:

[0029] A threat area model is determined according to each of the building models, and the three-dimensional map model is modified using the threat area model to load the building model into the three-dimensional map model.

[0030] Furthermore, after the step of obtaining the optimal track of the UAV according to the optimal giant rat individual, the method further includes:

[0031] The optimal trajectory is drawn into a graph using a preset mapping software.

[0032] In a second aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the drone track acquisition method described in any one of the above items are implemented.

[0033] In a third aspect, the present invention further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of any of the above-described methods for obtaining the trajectory of a UAV.

[0034] The technical solution of the present invention uses a hybrid vine rat optimization algorithm to obtain the optimal flight path for drones. A chaotic factor is introduced during the detection phase of the hybrid vine rat optimization algorithm to leverage the dynamic properties of the chaotic system to improve the diversity and randomness of the search process. This allows the hybrid vine rat optimization algorithm to converge quickly, preventing the original vine rat optimization algorithm from becoming trapped in a local optimal solution within the population search space. Therefore, the technical solution of the present invention overcomes the difficulty of the original vine rat optimization algorithm in obtaining a global optimal solution. It can quickly obtain the optimal flight path for drones, ensure the stability and safety of drone flight, and enable drones to quickly reach their designated destinations.

[0035] Based on the following detailed description of specific embodiments of the present invention in conjunction with the accompanying drawings, those skilled in the art will become more aware of the above and other objects, advantages and features of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Hereinafter, some specific embodiments of the present invention will be described in detail in an exemplary and non-limiting manner with reference to the accompanying drawings. The same reference numerals in the accompanying drawings indicate the same or similar components or parts. It should be understood by those skilled in the art that these drawings are not necessarily drawn to scale. In the accompanying drawings:

[0037] Figure 1 is a schematic flow chart of a method for obtaining a UAV track based on a large rat optimization algorithm according to an embodiment of the present invention;

[0038] Figure 2 is a schematic flow chart of optimizing and updating the population of giant vine rats in a method for obtaining a track of a drone according to an embodiment of the present invention;

[0039] Figure 3 is a schematic flow chart of obtaining a flight environment model of a UAV in a method for obtaining a UAV track according to an embodiment of the present invention;

[0040] Figure 4 is a schematic flow chart of a method for obtaining a UAV track based on a large rat optimization algorithm according to another embodiment of the present invention;

[0041] Figure 5 is a schematic diagram of a computer program product according to one embodiment of the present invention; and

[0042] Figure 6 is a schematic diagram of a computer-readable storage medium according to one embodiment of the present invention. DETAILED DESCRIPTION

[0043] Refer to the following Figures 1 to 6To describe an embodiment of the present invention, a method for obtaining a UAV track based on the Big Rat optimization algorithm and related products. In the description of this embodiment, it should be understood that the terms "first" and "second" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features, that is, include one or more of the features. In the description of the present invention, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. When a feature "includes or contains" one or some of the features it covers, unless otherwise specifically described, this indicates that other features are not excluded and may further include other features.

[0044] See also Figure 1 , Figure 1 What is shown is a schematic flow chart of a method for obtaining a UAV track based on the Big Rat optimization algorithm according to an embodiment of the present invention. The method for obtaining a UAV track can ensure the accuracy and reliability of the obtained UAV flight track, thereby improving the safety of UAV flight control.

[0045] exist Figure 1 In the process shown, the UAV track acquisition method based on the Big Rat optimization algorithm of this embodiment includes the following steps:

[0046] Step S101: Obtaining environmental information of the city where the drone is to fly, and determining a population search space of giant rats based on the environmental information;

[0047] Step S102: obtaining a preset starting position and an end position, as well as a preset number of track points of the UAV, and initializing a population of giant vine rats in a population search space of giant vine rats according to the preset starting position and the end position and the preset number of track points;

[0048] Step S103: obtaining a preset flight cost function, and using a hybrid giant rat optimization algorithm to optimize and update the giant rat population in the population search space a set number of times according to the preset flight cost function;

[0049] Step S104: using a preset flight cost function to obtain the optimal individual of the giant rat in the giant rat population, and obtaining the optimal track of the UAV based on the optimal individual of the giant rat.

[0050] In the above step S101, in order to ensure the safety of the drone flying in the city to be flown, in the process of determining the population search space of giant vine rats, the flight threat area is first determined based on the buildings in the city to be flown, and the area outside the flight threat area is used as a safe flight area. The safe flight area is the search space of the giant vine rat population.

[0051] In the above step S102, the preset number of track points of the UAV is N, where the i-th track point is P i ; Assume the starting position of the drone flight is P0 and the end position is P N+1 , and the coordinates of the starting position P0 are (x0, y0, z0), and the end position P N+1 The coordinates of (x N+1 ,y N+1 ,z N+1 ). The route between the starting position P0 and the first track point P1 is the first track segment of the drone, and the i-1th track point P i-1 To the i-th track point P i The route between them is the i-th track segment of the UAV, and the N-th track point P N To the end position P N+1 The route between them is the N+1th track segment of the UAV.

[0052] In this embodiment, it is assumed that there are M giant rat individuals in the giant rat population. The method for initializing the giant rat population in the population search space includes: randomly selecting N track points of each giant rat individual in the population search space, and then constructing a foraging path for each giant rat individual according to the starting position and end position of the drone flight and the track points of each giant rat individual to initialize the giant rat population.

[0053] In step S103, the preset flight cost function can be a cost function set for the drone based on the drone's own mechanical constraints and relevant regulations for drone transportation management. In the hybrid giant rat optimization algorithm, the flight cost function can calculate the flight cost of each individual giant rat in the giant rat population, that is, the flight cost required for the drone to fly along the flight path determined by the track points of each individual giant rat.

[0054] In this embodiment, the method of optimizing and updating the giant rat population using the hybrid giant rat optimization algorithm is as follows: Figure 2 As shown, the following steps are included:

[0055] Step S201: Generate a random number within a preset value range, and determine whether the random number is greater than a preset parameter value;

[0056] If yes, execute step S202; if no, execute step S203;

[0057] Step S202: using a chaotic factor strategy to update the total population of giant rats in the detection phase;

[0058] Step S203: updating the population of giant vine rats in the development phase.

[0059] In the above step S201, the preset value interval is [0, 1], and the random number generated within the value interval is λ; let the preset parameter value be ρ, and the preset parameter value is preferably 0.5.

[0060] In the above step S202, let the i-th individual of the giant rat in the giant rat population be V i , and the coordinates of the jth track point of the i-th rat individual are (x i,j ,y i,j , z i,j ),but

[0061] V i =(x i,1 ,x i,2 ,……,x i,N ,y i,1 ,y i,2 ,……,y i,N ,z i,1 ,z i,1 ,……,z i,N )

[0062] The method of updating the detection phase of the giant rat individual using the chaos factor strategy includes:

[0063] First, the preset cost function is used to calculate the flight cost of each rat in the rat population, and the rat with the smallest flight cost is taken as the male rat, and the male rat is set as V k .

[0064] Then, the following calculation formula is used to update the detection phase of the i-th rat individual:

[0065] V′ i,j =q×{V i,j +C×(V k,j -r×V i,j )}

[0066] Among them, V i,j is the i-th rat individual V i The jth element in V′ i,j is the updated number of the i-th rat individual V after the detection phase i The jth element in V k,j This is a male giant rat V k The jth element of , q is the chaos factor, and

[0067] q=4×C×(1-C)

[0068]

[0069] Among them, C is a random number in [0,1], F() is the preset flight cost function, F(V k ) is the flight cost of the male giant rat, t is the number of times the current optimization is updated, T max To set the number of times.

[0070] In the above step S203, the formula used to update the population of giant rats in the development stage is:

[0071] V′ i,j =V i,j +C×(V k,j -μ×V w,j )

[0072] Among them, V w,j represents a random female giant rat individual V w The jth element in , the female giant rat individual is the giant rat individual in the giant rat population, excluding the male giant rat individual, and μ represents a random number obtained in the value range [1,4].

[0073] In step S104, a preset flight cost function is used to calculate the flight cost of each individual rat in the rat population, and the rat with the lowest flight cost is selected as the optimal rat. The position of each trackpoint within the optimal rat is then obtained, and the optimal trajectory of the drone is constructed based on the starting and ending positions of the drone's flight and the position of each trackpoint within the optimal rat.

[0074] Based on the above, this embodiment uses a hybrid rat optimization algorithm to obtain the optimal flight path for the drone. A chaotic factor is introduced during the detection phase of the hybrid rat optimization algorithm to leverage the dynamic performance of the chaotic system to improve the diversity and randomness of the search process, enabling the hybrid rat optimization algorithm to converge quickly and preventing the original rat optimization algorithm from falling into a local optimal solution within the population search space. Therefore, the technical solution of this embodiment overcomes the problem of the original rat optimization algorithm's difficulty in obtaining a global optimal solution, enabling the drone's optimal flight path to be quickly obtained, ensuring the stability and safety of the drone's flight, and enabling the drone to quickly reach its designated destination.

[0075] In some embodiments of the present invention, in step S103, each time the hybrid giant rat optimization algorithm is used to optimize and update the giant rat population, after the chaotic factor strategy is used to update the giant rat population in the detection phase, or after the giant rat population is updated in the development phase, the method further includes:

[0076] The Gaussian difference mutation strategy is used to update the position of the rat population again. The update formula is:

[0077]

[0078] Among them, V” i,j is the i-th individual V” in the population of giant rats after the position is updated using the Gaussian difference mutation strategy i The jth element in V' k,j Before the Gaussian difference mutation strategy is used to update the position, the male giant rat individual V' in the giant rat population is k The jth element in V' w,j Before the Gaussian difference mutation strategy is used to update the position, a random female giant rat individual V' in the giant rat population w The jth element in ;

[0079] p1 and p2 are weight coefficients, f1 and f2 are random variables with mean 0, variance 1 and Gaussian distribution, and

[0080] β=2×r×μ-r

[0081] In this embodiment, the Gaussian difference mutation strategy is used to update the position of the giant rat population, which can avoid the hybrid giant rat optimization algorithm from falling into local optimality in the later stage, thereby improving the accuracy and reliability of obtaining the optimal flight trajectory of the drone.

[0082] In some embodiments of the present invention, the step of obtaining a preset flight cost function includes:

[0083] Obtain the UAV's flight distance cost function, flight altitude cost function, and flight smoothness cost function;

[0084] The flight distance cost function, the flight altitude cost function and the flight smoothness cost function are fused to obtain a preset flight cost function.

[0085] In this embodiment, let the flight path be L, and the flight distance cost function of the flight path L be F d (L), then

[0086]

[0087] in, is the length of the m+1th track segment in the flight track L, which is the length of the mth track point P m and the m+1th track point P m+1 The Euclidean distance between .

[0088] Assume that the flight altitude cost function of flight path L is F h ,but

[0089]

[0090] where z i represents the altitude of the ith track point of the flight track L, and

[0091]

[0092] Assume that the flight smoothing function of the flight path L is F s ,but

[0093]

[0094] Where Φ is the maximum turning angle in the flight path, θ i is the turning angle of the UAV at the i-th track point in the flight track L, a i is the vector of the i-th track segment in the flight track L, |a i | is vector a i length.

[0095] Assume the flight cost of flight path L is F(L), then

[0096] F(L)=α d F d (L)+α h F h (L)+α s F s (L)

[0097] Among them, α d , α h and α s are the distance cost weight, height cost weight and smoothness cost weight respectively, and α d +α h +α s =1.

[0098] The preset flight cost function in this embodiment comprehensively considers the flight length, flight altitude and flight smoothness of the drone, thereby improving the accuracy of the drone flight cost evaluation and thus ensuring the accuracy and reliability of obtaining the drone's optimal trajectory.

[0099] In some embodiments of the present invention, the step of initializing a population of giant rats in a population search space according to a starting position, an ending position, and a preset number of track points includes:

[0100] The initial position of the track point of each individual giant rat is randomly obtained in the population search space, and then the giant rat population is initialized according to the initial position of the track point of each individual giant rat using a reverse learning strategy.

[0101] In this embodiment, it is assumed that after obtaining the initial position of the track point of each individual rat, the i-th rat is The i-th individual of the giant rat The i-th element in is but

[0102]

[0103] Among them, rand is a random value in the interval [0,1], UB is the upper limit of the population search space, and UL is the lower limit of the population search space.

[0104] In this embodiment, it is assumed that the reverse learning strategy is adopted to initialize the giant rat population according to the initial position of the track point of each giant rat individual, and the i-th giant rat individual in the giant rat population is And the i-th rat individual The jth element of but

[0105]

[0106] Here, rand′ is a random value in the interval [0,1].

[0107] In this embodiment, the initial position of the track point of each giant rat individual is randomly obtained in the population search space, and the giant rat population is initialized according to the initial position using a reverse learning strategy, which can improve the diversity of the giant rat population and achieve the purpose of improving the quality of the giant rat population.

[0108] In some embodiments of the present invention, the method of determining the population search space of giant rats based on the environmental information of the city to be flown in step S101 includes:

[0109] A flight environment model of the UAV is constructed based on the environmental information of the city to be flown, and the population search space of the giant rat is determined based on the flight environment model.

[0110] In this embodiment, flight threat areas that pose a threat to the drone's flight can be identified in the drone's flight environment model, and the drone's flight safety area can be obtained by avoiding these flight threat areas, and the safe flight area can be used as the population search space of giant vine rats.

[0111] In this embodiment, the population search space of giant vine rats is determined from the flight environment model of the UAV, which can improve the convenience of obtaining the population search space and improve the accuracy of the population search space.

[0112] In some embodiments of the present invention, a method for constructing a flight environment model of a UAV based on environmental information of a city to be flown is as follows: Figure 3 As shown, the following steps are included:

[0113] Step S301: obtaining the terrain information of the city to be flown, as well as the location and size information of each building in the city to be flown, based on the environmental information of the city to be flown;

[0114] Step S302: constructing a three-dimensional map model of the city to be flown based on the terrain information of the city to be flown, and constructing a building model of each building based on its size information;

[0115] Step S303: Loading the corresponding building model of each location information into the three-dimensional map model to obtain a flight environment model.

[0116] In this embodiment, in the three-dimensional map model constructed based on the terrain information of the city to be flown, the height coordinate z(x,y) of the point projected on the horizontal plane is

[0117]

[0118] Among them, a, b, c, d, e, f and g are all constant coefficients, which can be set according to the terrain information of the city to be flown.

[0119] In the above step S302, a rectangular parallelepiped model can be used as the architectural model of the building, that is, the number of rectangular parallelepiped models is first set according to the number of buildings so that each building corresponds to a rectangular parallelepiped model; then, the length, height and width of the corresponding rectangular parallelepiped model are set according to the size information of each building to generate the architectural model of each building.

[0120] In some embodiments of the present invention, a method for loading a building model into a three-dimensional map model includes:

[0121] A threat area model is determined according to each building model, and the three-dimensional map model is modified according to the threat area model to load the building model into the three-dimensional map model.

[0122] In this embodiment, the projection coordinates of the center of the i-th building model on the horizontal plane are (x oi ,y oi ), height h i , the height of the reference terrain is h0, the height of the position whose projection coordinates on the horizontal plane are (x, y) is h(x, y), then

[0123]

[0124] Among them, a i and b i are the slopes of the i-th building model along the horizontal and vertical axes, and a i and b i The values ​​of

[0125] Assume that in the flight environment model, the height of the position with the projection coordinate (x, y) on the horizontal plane is z′(x, y), then

[0126] z′(x,y)=max[z(x,y),h(x,y)]

[0127] In this embodiment, a threat area model is determined based on a building model, and the building model is loaded into a three-dimensional map model of the city to be flown to obtain a flight environment model, which can ensure the safety and reliability of the flight environment model.

[0128] In some embodiments of the present invention, the method for obtaining the track of a UAV based on the Big Rat optimization algorithm is as follows: Figure 5 As shown, after obtaining the optimal track of the UAV according to the optimal giant rat individual in the above step S104, the following steps are also included:

[0129] Step S105: Use preset mapping software to draw the optimal trajectory of the UAV into a map.

[0130] In this embodiment, the preset mapping software may be Matlab. After the obtained optimal track is input into the Matlab software, the Matlab software may draw the optimal track into a graph according to the position of each track point in the optimal track.

[0131] In this embodiment, after the optimal trajectory of the drone is obtained, the optimal trajectory is also plotted into a graph so that the user can observe the optimal trajectory, thereby improving the safety and reliability of the drone control.

[0132] The flowcharts provided in this embodiment are not intended to indicate that the operations of the method will be performed in any particular order, or that all operations of the method are included in all cases. In addition, each of the above methods may include additional operations. Additional changes may be made to the above method within the scope of the technical ideas provided by the method of this embodiment.

[0133] It should be understood that in some embodiments, each part can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system.

[0134] This embodiment also provides a computer program product 10 , a computer-readable storage medium 20 , and a computer device 30 . Figure 5 is a schematic diagram of a computer program product 10 according to one embodiment of the present invention, Figure 6Schematic diagram of a computer-readable storage medium 20 according to one embodiment of the present invention. Computer program product 10 includes a computer program 11. When executed by processor 32, computer program 11 implements the steps of any of the aforementioned methods for acquiring drone tracks based on the Big Rat optimization algorithm. Computer-readable storage medium 20 stores computer program 11. When executed by processor 32, computer program 11 implements the steps of any of the aforementioned methods for acquiring drone tracks based on the Big Rat optimization algorithm.

[0135] The computer program 11 for performing the operations of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, configuration data for an integrated circuit, or source code or object code written in any combination of one or more programming languages ​​and procedural programming languages. The computer program 11 may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer may be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, to perform various aspects of the present invention, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may execute computer-readable program instructions by utilizing state information of the computer-readable program instructions to personalize the electronic circuit.

[0136] In the description of this embodiment, the computer program product 10 is a related product including the computer program 11 .

[0137] For the purposes of the description of this embodiment, the computer-readable storage medium 20 is a tangible device capable of retaining and storing the computer program 11, and can be any device that can contain, store, communicate, propagate, or use the computer program 11 for an instruction execution system, apparatus, or device, or in conjunction with such an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable storage medium 20 include the following: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, and any suitable combination of the foregoing.

[0138] At this point, those skilled in the art will recognize that, although a number of exemplary embodiments of the present invention have been shown and described in detail herein, many other variations or modifications consistent with the principles of the present invention may be directly determined or derived from the disclosure of the present invention without departing from the spirit and scope of the present invention. Therefore, the scope of the present invention should be understood and deemed to cover all such other variations or modifications.

Claims

1. A method for obtaining the track of an unmanned aerial vehicle based on the optimization algorithm of the giant rat, characterized in that: include: Obtaining environmental information of the city to be flown by the drone, and determining a population search space of giant rats based on the environmental information; Obtaining a preset starting position and an ending position, as well as a preset number of track points, and initializing a population of giant rats in the population search space according to the starting position, the ending position, and the preset number; Obtain a preset flight cost function, and adopt a hybrid giant rat optimization algorithm to optimize and update the giant rat population a set number of times in the population search space according to the preset flight cost function, wherein each optimization update includes: Generate a random number within a preset value range and determine whether the random number is greater than a preset parameter value; If so, a chaos factor strategy is used to update the population of giant vine rats in the detection phase; If not, then the development stage of the said population of giant vine rats is updated; The preset flight cost function is used to obtain the optimal giant rat individual in the giant rat population, and the optimal track of the UAV is obtained based on the optimal giant rat individual.

2. The method for obtaining the track of an unmanned aerial vehicle according to claim 1, wherein: After the step of updating the population of giant vine rats in the detection phase by adopting the chaos factor strategy, or updating the population of giant vine rats in the development phase, the method further includes: The Gaussian difference mutation strategy is used to update the giant rat population again.

3. The method for obtaining the track of an unmanned aerial vehicle according to claim 1, wherein: The step of obtaining a preset flight cost function includes: Obtaining a flight distance cost function, a flight altitude cost function, and a flight smoothness cost function of the UAV; The flight distance cost function, the flight height cost function and the flight smoothness cost function are fused to obtain the preset flight cost function.

4. The method for obtaining the track of an unmanned aerial vehicle according to claim 1, wherein: The step of initializing the population of giant rats in the population space according to the starting position, the end position and the preset number includes: Obtaining the number of giant vine rat individuals in the giant vine rat population; The track points of each of the giant vine rat individuals are randomly obtained in the population space to initialize the foraging path of each of the giant vine rat individuals.

5. The method for obtaining the track of an unmanned aerial vehicle according to claim 1, wherein: The step of determining the population search space of giant rats according to the environmental information comprises: A flight environment model of the UAV is constructed according to the environmental information, and the population search space is determined according to the flight environment model.

6. The method for obtaining the track of an unmanned aerial vehicle according to claim 5, wherein: The step of constructing a flight environment model of the UAV according to the environmental information includes: Acquire terrain information of the city to be flown, and location information and size information of each building in the city to be flown, based on the environmental information; Constructing a three-dimensional map model of the city to be flown to based on the terrain information, and constructing a building model of the corresponding building based on each piece of size information; The corresponding building model is loaded into the three-dimensional map model according to each piece of position information to obtain the flight environment model.

7. The method for obtaining the track of an unmanned aerial vehicle according to claim 6, wherein: The step of loading the corresponding building model into the three-dimensional map model according to each piece of position information comprises: A threat area model is determined according to each of the building models, and the three-dimensional map model is modified using the threat area model to load the building model into the three-dimensional map model.

8. The method for obtaining the track of an unmanned aerial vehicle according to claim 1, wherein: After the step of obtaining the optimal track of the UAV according to the optimal giant rat individual, the method further includes: using preset mapping software to draw the optimal track into a map.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the drone track acquisition method according to any one of claims 1 to 8 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method for obtaining the track of a drone according to any one of claims 1 to 8 are implemented.

Images