An unmanned aerial vehicle three-dimensional path planning method and system based on a meta-heuristic algorithm of a competitive search strategy

Abstract

The application provides a UAV three-dimensional path planning method and system based on a meta-heuristic algorithm of a competitive search strategy, aiming to solve the efficient and safe path planning problem of a UAV in a complex environment. The method constructs a UAV flight environment, determines the flight starting point and ending point, and constructs the constraint conditions of the path planning problem based on this. The constraint conditions include the flight path length of the UAV, the flight height fluctuation, the turning angle, and the obstacle and terrain constraints, to ensure that the path planning meets the safety and feasibility requirements of actual flight. The optimal UAV path is obtained by minimizing the cost function through an optimized meta-heuristic algorithm based on the competitive search strategy. Experimental results show that the method provided by the application can quickly generate a flight path with short flight distance and high smoothness.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of unmanned aerial vehicle three-dimensional path planning, and particularly relates to an unmanned aerial vehicle three-dimensional path planning method and system based on a meta-heuristic algorithm of a competitive search strategy. BACKGROUND

[0002] With the development of unmanned aerial vehicle technology and the continuous expansion of application fields, unmanned aerial vehicle path planning has become an important research field. In many fields such as military reconnaissance, environmental monitoring, and logistics distribution, unmanned aerial vehicles need to perform effective path planning in complex environments to ensure the smooth completion of tasks. Traditional path planning methods, such as A* algorithm and Dijkstra algorithm, can provide effective paths in some cases, but when faced with complex and variable environments, they often fail to adapt. Especially in three-dimensional space, these algorithms are easily limited by local optimal solutions when dealing with path optimization problems under multiple constraints, and the computational cost is high.

[0003] In recent years, heuristic algorithms such as particle swarm optimization (PSO) and genetic algorithm (GA) have been widely used in path planning problems. These algorithms simulate the group behavior in nature and have good global search ability and robustness. However, these algorithms still have low efficiency when dealing with high-dimensional, multi-constrained unmanned aerial vehicle path planning problems.

[0004] However, traditional path planning methods and existing heuristic algorithms in unmanned aerial vehicle path planning have the problems of easily falling into local optimal solutions, slow convergence speed, and poor globality, and cannot find a reasonable unmanned aerial vehicle path. SUMMARY

[0005] The purpose of the present application is to overcome the defects of the prior art that easily fall into local optimal solutions, slow convergence speed, and poor globality.

[0006] In order to achieve the above purpose, the present application proposes an unmanned aerial vehicle three-dimensional path planning method based on a meta-heuristic algorithm of a competitive search strategy, comprising:

[0007] Constructing unmanned aerial vehicle flight task constraint conditions, including path length constraint, turning angle constraint, flight height fluctuation constraint, and terrain constraint;

[0008] Establishing an unmanned aerial vehicle flight task cost function according to the unmanned aerial vehicle flight task constraint conditions;

[0009] Solving the unmanned aerial vehicle flight task cost function of the three-dimensional path planning problem by using an optimized meta-heuristic algorithm based on a competitive search strategy to obtain the path result of the unmanned aerial vehicle path planning.

[0010] As an improvement of the above method, the unmanned aerial vehicle flight task constraint condition comprises:

[0011] The path length constraint is:

[0012]

[0013] Wherein, J length represents the unmanned aerial vehicle path constraint; n represents the total number of nodes in the path; P i =(x i ,y i ,z i ) represents the position of the unmanned aerial vehicle at the i th path point in the three-dimensional space;

[0014] The turning angle constraint is:

[0015]

[0016] Wherein, J turn represents the unmanned aerial vehicle turning angle constraint; And respectively represent the vectors of adjacent path segments; And respectively represent the modulus of the vectors; α i represents the turning angle constraint variable of the unmanned aerial vehicle at the path point i; α max represents the maximum turning angle;

[0017] The flight height fluctuation constraint is:

[0018]

[0019] Wherein, J height represents the unmanned aerial vehicle flight height fluctuation constraint;

[0020] Terrain constraint:

[0021]

[0022] Wherein, z(x i ,y i ) represents the terrain height at (x i ,y i ), h min represents the minimum flight height; t i represents an intermediate variable.

[0023] As an improvement of the above method, the unmanned aerial vehicle path planning problem cost function is:

[0024] F=λ1J length +λ2J turn +λ3J height +λ4Jterrain

[0025] wherein, denotes the weight coefficient, and their sum is 1.

[0026] As an improvement of the above method, the optimized meta-heuristic algorithm based on competition search strategy comprises:

[0027] A random reverse learning strategy is introduced in the initialization stage to improve the population diversity; the search behavior of individuals in the exploration stage is updated through the step micro flight strategy; and the precision of the solution is prompted by incorporating the competition search strategy.

[0028] As an improvement of the above method, the random reverse learning strategy formula is as follows:

[0029]

[0030] wherein, RA denotes a random number between 0 and 1; X i denotes the i-th individual in the current population; X i ∈[LB i ,UB i ], LB i and UB i denote the upper and lower bounds of the i-th individual in the current population search; denotes the opposite of X i .

[0031] As an improvement of the above method, the step micro flight strategy formula is as follows:

[0032] step ~ |step| -1-β

[0033]

[0034] wherein, step denotes the step length of the step micro flight process at the step step, which follows a power law distribution, step denotes the length of the step micro flight; β ∈ (0, 2]; u and v both belong to the normal distribution, σ v = 1, and Γ denotes the Gamma function.

[0035] As an improvement of the above method, the mathematical formula of the competition search strategy is as follows:

[0036] Xnew j = RA*X RP

[0037] wherein, Xnew j denotes the j-th dimension of the generated new solution; X RPrepresents a certain dimension randomly selected in the current solution X; RA represents a random number between 0 and 1.

[0038] The application also provides a UAV three-dimensional path planning system based on a meta-heuristic algorithm of a contest search strategy, which is realized based on the above method.

[0039] A constraint condition module is configured to construct UAV flight task constraint conditions, including path length constraints, turning angle constraints, flight height fluctuation constraints and terrain constraints.

[0040] A cost function module is configured to establish a UAV flight task cost function according to the UAV flight task constraint conditions.

[0041] A planning path module is configured to solve the UAV flight task cost function of the three-dimensional path planning problem by using an optimized meta-heuristic algorithm of a contest search strategy, so as to obtain a path result of UAV path planning.

[0042] Compared with the prior art, the application has the following advantages:

[0043] First, the cost function is established according to the flight constraints of multiple UAVs in a flight task, and the UAV path planning problem is converted into a problem of finding the minimum value of the cost function that meets the UAV flight task constraints. Second, in order to improve population diversity, a random reverse learning strategy is introduced, and the behavior in the exploration stage is updated through the pull micro flight strategy to improve the convergence speed. Finally, in order to improve the accuracy and global performance of the solution, the contest search strategy is integrated. Through multiple experiments in a three-dimensional simulation environment, the experimental results show that the method provided by the application can quickly generate a flight path with short flight distance and high smoothness. BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1 Fig. 1 shows a flowchart of a UAV three-dimensional path planning method based on a meta-heuristic algorithm of a contest search strategy;

[0045] Figure 2 Fig. 3 shows a schematic diagram of environment modeling;

[0046] Figure 3 Fig. 5 shows a comparison diagram of UAV three-dimensional paths of the meta-heuristic algorithm of the contest search strategy and the original algorithm;

[0047] Figure 4 Fig. 6 shows a comparison diagram of convergence curves of the meta-heuristic algorithm of the contest search strategy and the original algorithm. DETAILED DESCRIPTION

[0048] The technical solutions of the application will be described in detail below with reference to the accompanying drawings.

[0049] Embodiment 1

[0050] As shown in the accompanying drawings, Figure 1 the present application proposes a UAV three-dimensional path planning method based on a meta-heuristic algorithm of a competitive search strategy, comprising the following steps:

[0051] Step 1: Constructing a UAV flight environment, obtaining the starting point and the end point position of the UAV flight;

[0052] Step 2: Constructing the UAV flight task constraint condition, the UAV flight task constraint condition including the path length constraint, the turning angle constraint, the flight height fluctuation constraint and the terrain constraint;

[0053] The UAV flight task constraint condition calculation formula includes:

[0054] Path length constraint:

[0055]

[0056] Turning angle constraint:

[0057]

[0058] Flight height fluctuation constraint:

[0059]

[0060] Terrain constraint:

[0061]

[0062] Wherein, n is the total number of nodes in the path, P i =(x i ,y i ,z i ) represents the position of the i-th path point of the UAV in the three-dimensional space, and are the adjacent path vectors, and represent the vector length, α i is the turning angle constraint variable of the UAV at the path point i, α max a represents the maximum turning angle, z(x i ,y i ) represents the terrain height at x i ,y i , and h min represents the minimum flight height.

[0063] Step 3: Establishing a UAV flight task cost function according to the UAV flight task constraint condition;

[0064] The cost function of the UAV path planning problem comprises:

[0065] F = λ1J length + λ2J turn + λ3J height + λ4J terrain

[0066] wherein J length , J turn , H height and J terrain represent the UAV path constraint, the turning angle constraint, the height constraint and the terrain constraint respectively, λ1, λ2, λ3 and λ4 represent the weight coefficients, and the sum of them is 1.

[0067] Step 4: A meta-heuristic algorithm based on the competitive search strategy is used to solve the flight task cost function of the UAV three-dimensional path planning problem, and the path result of the UAV path planning is obtained.

[0068] The meta-heuristic algorithm based on the competitive search strategy comprises:

[0069] In the initialization stage, a random reverse learning strategy is used to generate an initialized population, and the population diversity is improved by introducing the random reverse learning strategy; the search behavior of the individuals in the exploration stage is updated by using the step flight strategy to improve the convergence speed; and the competitive search strategy is integrated into the development stage of the algorithm to improve the solution accuracy and the global performance. Among them,

[0070] The formula of the random reverse learning strategy is:

[0071]

[0072] wherein RA represents a random number between 0 and 1, X i represents the ith individual in the current population, X∈[LB,UB], LB and UB are the upper and lower bounds of the search, is the opposite of X i .

[0073] The calculation formula of the step flight strategy comprises:

[0074] step ~ | step | -1-β

[0075]

[0076] wherein step represents the step length of the step flight process, step represents the length of the step flight, β∈(0,2], μ and υ belong to the normal distribution, σ ν= 1, and Γ is the Gamma function.

[0077] The mathematical formula of the competition search strategy is:

[0078] Xnew j = RA*X RP

[0079] wherein Xnew j represents the jth dimension of the generated new solution, X RP represents a randomly selected dimension in the current solution X, X j represents the jth dimension of the current solution.

[0080] In order to better illustrate the improvement of the meta-heuristic algorithm of the competition search strategy adopted by the present application, the meta-heuristic algorithm of the original competition search strategy is introduced as follows.

[0081] The meta-heuristic algorithm of the original competition search strategy is a group-based heuristic algorithm, which is inspired by the group behavior in nature, simulates the characteristics of the group behavior in nature to solve problems, and can improve the search efficiency through group cooperation and information sharing. The algorithm finds the optimal solution through the following steps:

[0082] 1) initialize the population;

[0083] 2) calculate the numerical value of all individuals according to the cost function;

[0084] 3) perform boundary check on all individuals;

[0085] 4) update the individual position;

[0086] 5) update the global optimal individual and its cost function value;

[0087] 6) go back to step 2) to start repeating until the stop rule is met or the maximum number of iterations is reached. The original algorithm solves the problem through two stages, exploration and development.

[0088] In the exploration stage of the original algorithm, the position of the individual is updated by the following formula:

[0089] x i,j,newP1 = x i,j + RA·(PZ j -I·x i,j )

[0090] wherein x i,j,newP1 represents the jth dimension value of the individual i in the exploration stage, x i,jrepresents the jth dimension value of the ith individual, i is between 1 and N (population quantity), j is between 1 and D (decision variable number), RA represents a random number between 0 and 1, PZ represents the optimal individual, PZ j represents the jth dimension of PZ, I is a random number in the set {1,2}.

[0091] The position of the individual in the development stage is updated by the following formula:

[0092]

[0093] Wherein, x i,j,newP2 represents the jth dimension value of the individual i in the development stage, R represents a constant, here 0.1 is taken, Max_Its represents the maximum iteration number, t represents the current iteration number, AZ represents the current individual state, AZ j represents the jth dimension value of AZ, Ps is a random number belonging to [0,1].

[0094] Compared with other algorithms, the original algorithm has the characteristics of few parameters and high simplicity, but it also has the problem of being easy to fall into local optimal solution. Therefore, the meta-heuristic algorithm based on the competition search strategy is proposed to improve the original algorithm and improve the optimization ability of the algorithm, and the main improvements are as follows:

[0095] 1) In the initialization stage, the random reverse learning strategy is used to generate the initialization population, and the basic idea of random reverse learning is to improve the search efficiency of the solution and improve the population diversity by considering the original solution and the opposite solution with randomness in space at the same time.

[0096] The specific mathematical formula of random reverse learning is:

[0097]

[0098] Wherein, x i,j represents the jth dimension value of the ith individual in the current population, LB i and UB i are the upper and lower bounds of the search region, is the opposite of x i,j .

[0099] 2) In the exploration stage, the pull micro flight is used, and the ability of the algorithm to explore the position search space is increased by means of the nonlinear step and the occasional long jump, which helps to avoid the algorithm searching to the local optimal solution too early. The search behavior in the exploration stage is updated by the pull micro flight strategy, so as to improve the overall convergence speed. The specific mathematical formula of the pull micro flight strategy is:

[0100] x i,j,newP1 =x i,j +RA·(PZj I x i,j )+0.01 x Levy (step)

[0101] 3) The competition search strategy has good randomness and combines the advantages of exploration and development, so the first half of the iteration in the algorithm development stage is integrated into the competition search strategy to improve the solution accuracy and improve the global performance. The specific mathematical definition of the competition search strategy is:

[0102] x i,j,newP2 = RA x X RP

[0103] Wherein, X RP represents a randomly selected dimension in the current solution X.

[0104] As Figure 2 shown, the embodiment constructs a mountain three-dimensional scene full of obstacles, and the scene size is set to 100*100*5km.

[0105] In this embodiment, the meta-heuristic algorithm of the competition search strategy and the original algorithm are compared, and the simulation results are as shown in Figures 3-4 From Fig. 3, it can be seen that although both algorithms can find a collision-free path in the scene, the path trajectory planned by the meta-heuristic algorithm of the competition search strategy is smoother, has smaller height fluctuation and is more suitable as a UAV flight path. Figure 4 The iteration curve of the fitness value of the two algorithms is shown in the figure, from which it can be seen that the convergence speed of the meta-heuristic algorithm of the competition search strategy is faster, and the solution accuracy is higher, so the path planning effect of the meta-heuristic algorithm of the competition search strategy is better than that of the original algorithm.

[0106] The experimental results show that the present application has effectiveness in UAV three-dimensional path planning, and compared with the original algorithm, the present application has better convergence, solution accuracy and globality.

[0107] Embodiment 2

[0108] The application also provides a UAV three-dimensional path planning system based on the meta-heuristic algorithm of the competition search strategy, which is realized based on the above method, and the system comprises:

[0109] A constraint condition module is constructed for constructing UAV flight task constraint conditions, including path length constraint, turning angle constraint, flight height fluctuation constraint and terrain constraint;

[0110] A cost function module is established for establishing a UAV flight task cost function according to the UAV flight task constraint conditions;

[0111] The computing planning path module is configured to solve the UAV flight task cost function of the three-dimensional path planning problem by using an optimized meta-heuristic algorithm based on a competitive search strategy, to obtain a path result of UAV path planning.

[0112] The present application can also provide a computer device, comprising: at least one processor, a memory, at least one network interface and a user interface. The various components in the device are coupled together by a bus system. It can be understood that the bus system is used to realize the connection communication between the components. In addition to including a data bus, the bus system also includes a power bus, a control bus and a status signal bus.

[0113] The user interface can include a display, a keyboard or a pointing device. For example, a mouse, a trackball, a touchpad or a touch screen, etc.

[0114] It can be understood that the memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. The non-volatile memory can be a read-only memory (Read-Only Memory, ROM), a programmable read-only memory (Programmable ROM, PROM), an erasable programmable read-only memory (Erasable PROM, EPROM), an electrically erasable programmable read-only memory (Electrically EPROM, EEPROM) or a flash memory. The volatile memory can be a random access memory (Random Access Memory, RAM) used as an external cache. By way of example and not limitation, many forms of RAM can be used, such as static random access memory (Static RAM, SRAM), dynamic random access memory (Dynamic RAM, DRAM), synchronous dynamic random access memory (Synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (Double Data Rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (Enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (Synchlink DRAM, SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DRRAM). The memory described herein is intended to include, but not limited to, these and any other suitable types of memory.

[0115] In some embodiments, the memory stores elements, executable modules or data structures, or a subset thereof, or an extended set thereof: an operating system and an application program.

[0116] The operating system includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services and processing hardware-based tasks. The application programs include various application programs, such as a media player (Media Player), a browser (Browser), and the like, for implementing various application services. The program for implementing the method of the embodiments of the present disclosure can be included in the application program.

[0117] In the above-described embodiments, the processor can be configured to, by invoking the program or the instruction stored in the memory, specifically, the program or the instruction stored in the application program:

[0118] perform the steps of the above-described method.

[0119] The above-described method can be applied to the processor or implemented by the processor. The processor can be an integrated circuit chip having a signal processing capability. In the implementation process, the steps of the above-described method can be completed by hardware integrated logic circuits in the processor or by the form of instructions in software. The processor described above can be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The above-described methods, steps and logical block diagrams can be implemented or executed by the processor. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the above-described method in combination with the above-described disclosure can be directly embodied as a hardware code processor to execute, or a combination of hardware and software modules in the code processor to execute. The software module can be located in the random access memory, the flash memory, the read-only memory, the programmable read-only memory or the electrically erasable programmable memory, the register or other mature storage mediums in the art. The storage medium is located in the storage memory, and the processor reads the information in the storage memory to complete the steps of the above-described method in combination with the hardware thereof.

[0120] It can be understood that the embodiments described in the present application can be realized by hardware, software, firmware, middleware, microcode or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), general purpose processors, controllers, micro-controllers, microprocessors, other electronic units for executing the functions described in the present application, or a combination thereof.

[0121] For software implementation, the present application can be implemented by executing the functional modules (such as processes, functions, etc.) described in the present application. The software code can be stored in a memory and executed by a processor. The memory can be implemented in the processor or outside the processor.

[0122] The present application also provides a non-volatile storage medium for storing a computer program. When the computer program is executed by a processor, each step of the above method embodiments can be implemented.

[0123] Finally, it should be pointed out that the above embodiments are only used to illustrate the technical solutions of the present application and not to limit. Although the present application is described in detail with reference to the embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the present application, and they should be covered in the scope of the claims of the present application.

Claims

1. A three-dimensional path planning method for unmanned aerial vehicles based on a meta-heuristic algorithm using a competitive search strategy, comprising: Construct UAV flight mission constraints, including path length constraints, turning angle constraints, flight altitude fluctuation constraints, and terrain constraints; Establishing a UAV flight mission cost function based on the UAV flight mission constraints; An optimized meta-heuristic algorithm based on a competitive search strategy is used to solve the UAV flight mission cost function of the three-dimensional path planning problem, and a path result of the UAV path planning is obtained; The optimized meta-heuristic algorithm based on the competitive search strategy includes: In the initialization phase, a random reverse learning strategy is introduced to improve population diversity; the search behavior of individuals in the exploration phase is updated through a micro-flight strategy; and a competitive search strategy is incorporated to improve the accuracy of the solution. The micro-flight strategy formula is as follows: Pull micro (step) ~ |step| -1-β Among them, step represents the step length of the step in the micro-flight process, which follows the power law distribution, and step represents the length of the micro-flight; β∈(0,2]; μ and υ both belong to the normal distribution. σ v =1, Γ represents the Gamma function.

2. The method for three-dimensional path planning of an unmanned aerial vehicle based on a meta-heuristic algorithm of a competitive search strategy according to claim 1 is characterized in that: The UAV flight mission constraints include: The path length constraint is: Among them, J length represents the UAV path constraint; n represents the total number of nodes in the path; P i =(x i ,y i ,z i ) represents the position of the i-th path point of the UAV in three-dimensional space; The turning angle constraint is: Among them, J turn Indicates the turning angle constraint of the drone; and Respectively represent the vectors of adjacent path segments; and Respectively represent the modulus of the vector; α i Represents the turning angle constraint variable of the UAV at path point i; α max Indicates the maximum turning angle; The flight altitude fluctuation constraint is: Among them, J height Represents the UAV flight altitude fluctuation constraint; Terrain constraints: Among them, z(x i ,y i ) means (x i ,y i ) at the terrain height, h min Indicates the minimum flight altitude; t i Represents an intermediate variable.

3. The method for three-dimensional path planning of an unmanned aerial vehicle based on a meta-heuristic algorithm of a competitive search strategy according to claim 2, characterized in that: The cost function of the UAV path planning problem is: F=λ1J length +λ2J turn +λ3J height +λ4J terrain Among them, λ1, λ2, λ3 and λ4 represent weight coefficients, and their sum is 1.

4. The method for three-dimensional path planning of an unmanned aerial vehicle based on a meta-heuristic algorithm of a competitive search strategy according to claim 1, characterized in that: The random reverse learning strategy formula is as follows: Among them, RA represents a random number between 0 and 1; X k represents the kth individual in the current population; X k ∈[LB k ,UB k ], LB k and UB k Indicates the upper and lower bounds of the search for the kth individual in the current population; Represents X k The opposite of.

5. The method for three-dimensional path planning of an unmanned aerial vehicle based on a meta-heuristic algorithm of a competitive search strategy according to claim 1, characterized in that: The mathematical formula of the contention search strategy is as follows: Xnew m =RA*X RP Among them, Xnew m Indicates the mth dimension of generating a new solution; X RP Represents a randomly selected dimension in the current solution X; RA represents a random number between 0 and 1.

6. A three-dimensional path planning system for unmanned aerial vehicles based on a metaheuristic algorithm with a competitive search strategy, implemented based on the method of any one of claims 1 to 5, characterized in that: The system comprises: The constraint condition module is used to construct the UAV flight mission constraint conditions, including path length constraint, turning angle constraint, flight altitude fluctuation constraint and terrain constraint; Establishing a cost function module, for establishing a UAV flight mission cost function according to the UAV flight mission constraints; and The calculation and planning path module is used to solve the UAV flight mission cost function of the three-dimensional path planning problem by adopting an optimized meta-heuristic algorithm based on a competitive search strategy to obtain the path result of the UAV path planning.

Images