An unmanned aerial vehicle path planning method and system based on a hybrid swarm intelligence algorithm

Abstract

The application discloses a kind of unmanned aerial vehicle path planning method and system based on hybrid swarm intelligence algorithm, and is related to unmanned aerial vehicle planning technical field.The method comprises: obtaining target task information;The target task information includes including departure location and end position;Utilize hybrid swarm intelligence algorithm, path planning is carried out to the target task information, and the optimal path of unmanned aerial vehicle is determined;The hybrid swarm intelligence algorithm includes improved particle swarm algorithm and sparrow search algorithm;The improved particle swarm algorithm is constructed according to particle swarm algorithm and adaptive t distribution variation operator.The application can improve the speed and accuracy of unmanned aerial vehicle path planning.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) planning technology, and in particular to a UAV trajectory planning method and system based on a hybrid swarm intelligence algorithm. Background Technology

[0002] As drones first emerged, their initial applications were primarily in military reconnaissance. With the continuous development of modern automatic control technology, the evolution of artificial intelligence, and the increasing maturity of sensor data fusion processing technology, drone control technology has also begun to flourish rapidly, gradually entering the public eye. With the advancement of science and technology, drones are now in large-scale use, requiring them to quickly, accurately, and effectively find the optimal flight path between the starting point and the target point within their flight area to efficiently complete designated tasks and ensure their own safety.

[0003] Unmanned aerial vehicle (UAV) trajectory planning is computationally complex, with numerous constraints and significant ambiguity. Traditional trajectory search algorithms fall short in both optimality and real-time performance, requiring urgent improvement in both theory and application. Among existing UAV flight path planning methods, mainstream approaches exhibit varying performance: early genetic algorithms face difficulties in dynamically correcting chromosome encoding lengths due to the uncertainty of trajectory length; neural networks can help address terrain following and obstacle avoidance challenges, but lack maneuverability under external environmental threats; intelligent swarm optimization methods offer better accuracy, but computational time is long, requiring a processor. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for UAV trajectory planning based on a hybrid swarm intelligence algorithm, which can improve the speed and accuracy of UAV trajectory planning.

[0005] To achieve the above objectives, the present invention provides the following solution:

[0006] A method for UAV trajectory planning based on a hybrid swarm intelligence algorithm includes:

[0007] Obtain target task information; the target task information includes the start position and the end position.

[0008] A hybrid swarm intelligence algorithm is used to plan the trajectory of the target mission information and determine the optimal trajectory of the UAV. The hybrid swarm intelligence algorithm includes an improved particle swarm algorithm and a sparrow search algorithm. The improved particle swarm algorithm is constructed based on the particle swarm algorithm and the adaptive t-distribution mutation operator.

[0009] Optionally, before using a hybrid swarm intelligence algorithm to plan the trajectory of the target task information and determine the optimal trajectory of the UAV, the method further includes:

[0010] Construct a flight environment function; the flight environment function is used to describe the terrain and topography of the UAV's flight environment.

[0011] Optionally, the step of using a hybrid swarm intelligence algorithm to plan the trajectory of the target task information and determine the optimal trajectory of the UAV specifically includes:

[0012] Set the algorithm parameters; the algorithm parameters include the maximum number of iterations and the dynamic probability;

[0013] Based on the sparrow search algorithm and the target task information, the trajectory planning of the first generation population is performed to determine the individual optimal solution and the global optimal solution for the current iteration number;

[0014] Determine whether the current iteration count has reached the maximum iteration count;

[0015] If so, the globally optimal solution will be output as the optimal flight path of the UAV;

[0016] If not, the improved particle swarm optimization algorithm and the dynamic probability are used to mutate and update the initial population, and then the next iteration is performed.

[0017] Optionally, the step of planning the trajectory of the initial population based on the sparrow search algorithm and the target task information to determine the individual optimal solution and the global optimal solution for the current iteration number specifically includes:

[0018] Using the sparrow search algorithm, trajectory planning is performed on the initial population of the target task information to determine the position and velocity of each particle in the initial population;

[0019] The individual optimal solution and the global optimal solution for the current iteration number are determined based on the position and velocity of each particle.

[0020] Optionally, the step of using the improved particle swarm optimization algorithm and the dynamic probability to mutate and update the initial population specifically includes:

[0021] Based on the individual optimal solution and the global optimal solution at the current iteration number, the population is iterated to generate a new particle swarm and random numbers;

[0022] The new particle swarm is subjected to an adaptive t-distribution mutation operator operation based on the random number and the dynamic probability, and the mutated result is updated as the individual optimal solution and the global optimal solution for the next iteration.

[0023] This invention also provides a UAV trajectory planning system based on a hybrid swarm intelligence algorithm, comprising:

[0024] The task determination module is used to obtain target task information; the target task information includes the start position and the end position.

[0025] The trajectory planning module is used to plan the trajectory of the target mission information using a hybrid swarm intelligence algorithm to determine the optimal trajectory of the UAV; the hybrid swarm intelligence algorithm includes an improved particle swarm algorithm and a sparrow search algorithm; the improved particle swarm algorithm is constructed based on the particle swarm algorithm and the adaptive t-distribution mutation operator.

[0026] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0027] This invention discloses a method and system for UAV trajectory planning based on a hybrid swarm intelligence algorithm. The method includes using a hybrid swarm intelligence algorithm to plan the trajectory of the target task information and determine the optimal trajectory of the UAV. The hybrid swarm intelligence algorithm includes an improved particle swarm algorithm and a sparrow search algorithm. Furthermore, an improved particle swarm algorithm is constructed by combining an adaptive t-distribution mutation operator with the traditional particle swarm algorithm. This allows the hybrid swarm intelligence algorithm to inherit the advantages of the improved particle swarm algorithm in terms of trajectory cost, convergence accuracy, and stability, while also accelerating the convergence speed to a certain extent, achieving a balance between the two and improving the speed and accuracy of UAV trajectory planning. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 This is a flowchart illustrating the UAV trajectory planning method of the present invention;

[0030] Figure 2 This is a flowchart illustrating the hybrid swarm intelligence algorithm in this embodiment;

[0031] Figure 3 This is a three-dimensional front view of the trajectory planning result of the hybrid algorithm in this embodiment;

[0032] Figure 4 This is a top-grid view of the trajectory planning results of the hybrid algorithm in this embodiment;

[0033] Figure 5 This is a top-view contour line view of the trajectory planning result of the hybrid algorithm in this embodiment;

[0034] Figure 6 This is a schematic diagram of the fitness function of the hybrid algorithm trajectory planning results in this embodiment;

[0035] Figure 7This is a structural block diagram of the UAV trajectory planning system of the present invention. Detailed Implementation

[0036] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0037] The purpose of this invention is to provide a method and system for UAV trajectory planning based on a hybrid swarm intelligence algorithm, which can improve the speed and accuracy of UAV trajectory planning.

[0038] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0039] like Figure 1 As shown, this invention provides a UAV trajectory planning method based on a hybrid swarm intelligence algorithm, comprising:

[0040] Step 100: Obtain target task information; the target task information includes the starting position and the ending position.

[0041] Step 200: Using a hybrid swarm intelligence algorithm, perform trajectory planning on the target task information to determine the optimal trajectory of the UAV; the hybrid swarm intelligence algorithm includes an improved particle swarm algorithm and a sparrow search algorithm; the improved particle swarm algorithm is constructed based on the particle swarm algorithm and the adaptive t-distribution mutation operator.

[0042] Before step 200, the method further includes: constructing a flight environment function; the flight environment function is used to describe the terrain and topography of the UAV's flight environment.

[0043] As one specific implementation of step 200, the steps include:

[0044] The first step is to set the algorithm parameters; these parameters include the maximum number of iterations and the dynamic probability.

[0045] The second step involves planning the trajectory of the initial population based on the sparrow search algorithm and the target task information, determining the individual optimal solution and the global optimal solution for the current iteration number; specifically including:

[0046] Using the sparrow search algorithm, trajectory planning is performed on the initial population of the target task information to determine the position and velocity of each particle in the initial population; based on the position and velocity of each particle, the individual optimal solution and the global optimal solution for the current iteration number are determined.

[0047] The third step is to determine whether the current iteration count has reached the maximum iteration count.

[0048] If so, the globally optimal solution will be output as the optimal flight path of the UAV;

[0049] If not, the improved particle swarm optimization algorithm and the dynamic probability are used to mutate and update the initial population, and then the next iteration is performed. Specifically, this includes:

[0050] Population iteration is performed based on the individual optimal solution and the global optimal solution of the current iteration number to generate a new particle swarm and a random number; an adaptive t-distribution mutation operator operation is performed on the new particle swarm based on the random number and the dynamic probability, and the mutated result is updated to the individual optimal solution and the global optimal solution for the next iteration.

[0051] Based on the above technical solution, the following embodiments are provided.

[0052] This embodiment discloses a UAV trajectory planning method that initializes a particle swarm optimization (PSO) algorithm using a sparrow search algorithm. The convergence speed of the sparrow search algorithm is used to compensate for the shortcomings of the PSO algorithm, improving the generation of the initial population and producing a reasonable and uniform initial population distribution, thus enhancing stability. This algorithm inherits the advantages of the improved PSO algorithm in terms of trajectory cost, convergence accuracy, and stability, while further accelerating the convergence speed to a certain extent, achieving a balance between the two. The hybrid algorithm was then used to complete 30 independent trajectory planning runs to verify the effectiveness.

[0053] Let the random number be rand, and the dynamic selection probability be p. The Sparrow Search Algorithm-Particle Swarm Optimization algorithm flow is as follows: Figure 2 As shown.

[0054] The above algorithm flow is simulated:

[0055] Set the objective function as the trajectory cost function:

[0056] J cost =w1L path +w2h height +w3J turn (1)

[0057] Among them, J cost It is the total cost function, w i The parameters i = 1, 2, 3 represent the weights of each cost function, and the maximum track length is L. path The maximum turning angle is J turn h height Let be the standard deviation cost function for height, and satisfy:

[0058]

[0059] By effectively processing the total cost function, a track consisting of line segments is obtained. The resulting path is then used to smooth the track.

[0060] The flight environment function expression is:

[0061]

[0062] Where (x, y) are the coordinates of a point on the terrain on the horizontal plane, and z is the altitude corresponding to point (x, y). In the formula, a, b, c, d, e, f, and g are constant coefficients; by changing the values ​​of these parameters, different terrain features can be obtained. A mountain model is superimposed on this baseline terrain information. The mathematical expression for the mountain model is:

[0063]

[0064] Among them, h0 and h i These represent the baseline terrain and the height of the th peak, respectively. oi y oi ) represents the center coordinates of the i-th mountain peak, a i and b i and are the slopes of the i-th mountain peak along the x-axis and y-axis, respectively.

[0065] The starting point of the trajectory is set to (10, 90), and the z-axis coordinate of the starting point is generated by interpolation; the ending point of the trajectory is set to (130, 25), and the z-axis coordinate of the ending point is also generated by interpolation. The population size is 50, the maximum number of iterations is 300, and the trajectory planning experiment of the hybrid algorithm is started.

[0066] The Sparrow Search algorithm was used to conduct 30 independent and repeated experiments under the same conditions, and the best trajectory from the 30 experiments was displayed. Figures 3-6 This represents the trajectory planning result of the hybrid algorithm. Among them, Figure 3 This indicates how the planned flight path is presented in the three-dimensional terrain. Figure 4 This represents the flight path in the grid top view. Figure 5 This indicates that the flight path is presented in a top-down view with contour lines. Figure 6 This represents the relationship between the number of iterations and the objective function.

[0067] Based on the above experiments, the results are shown in Tables 1 and 2. Table 1 records the experimental data of the track cost values ​​in 30 independent repeated experiments of the hybrid algorithm, and Table 2 records the experimental data of the convergence algebra in the hybrid algorithm.

[0068] Table 1. Value of track data in 30 independent repeated experiments using the hybrid algorithm.

[0069]

[0070] Table 2. 30 independent repeated experiments of the hybrid algorithm (convergence algebra)

[0071]

[0072]

[0073] In the simulation experiment of the particle swarm optimization-sparrow search hybrid algorithm for trajectory planning, the mean trajectory cost was 70.72348, the minimum was 67.3259, the maximum was 79.3464, the standard deviation was 4.04691, and the mean convergence algebraic number was 52.03333. The statistical comparison results are shown in Table 3.

[0074] Table 3 Statistical Comparison of Results

[0075]

[0076] The experimental results show that the hybrid algorithm improves the mean and standard deviation of some track cycle values, in exchange for a significant increase in the mean of convergence algebra. Compared with the standard particle swarm optimization algorithm, the mean of track cycle values ​​is reduced by 3.48%, the standard deviation is increased by 8.37%, and the mean of convergence algebra is advanced by 58.62%.

[0077] Therefore, it can be seen that this embodiment has the following beneficial effects:

[0078] The improved Particle Swarm Optimization (PSO) algorithm offers improvements in trajectory cost, convergence accuracy, and result stability, but its convergence generation (convergence speed) increases (slows down). The Sparrow Search algorithm, on the other hand, can compensate for the lower convergence speed of trajectory planning compared to the PSO algorithm. Therefore, the two algorithms are combined. Based on the theory of PSO, the initial population has a crucial impact on algorithm performance. For PSO, a more uniform initial population is beneficial for rapid global search. Besides the parameters that need to be set, the randomly generated first-generation particle population plays a vital role in initializing the population. If the first-generation particles are relatively evenly distributed, the convergence speed and stability of planning the optimal trajectory are significantly improved. This paper combines the improved PSO algorithm and the Sparrow Search algorithm, using the initial population of the Sparrow Search algorithm instead of the initial population of the improved PSO algorithm. The subsequent steps are largely the same as those for the improved PSO algorithm.

[0079] like Figure 7 As shown, the present invention also provides a UAV trajectory planning system based on a hybrid swarm intelligence algorithm, comprising:

[0080] The task determination module is used to obtain target task information; the target task information includes the start position and the end position.

[0081] The trajectory planning module is used to plan the trajectory of the target mission information using a hybrid swarm intelligence algorithm to determine the optimal trajectory of the UAV; the hybrid swarm intelligence algorithm includes an improved particle swarm algorithm and a sparrow search algorithm; the improved particle swarm algorithm is constructed based on the particle swarm algorithm and the adaptive t-distribution mutation operator.

[0082] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0083] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for UAV trajectory planning based on a hybrid swarm intelligence algorithm, characterized in that, include: Obtain target task information; The target task information includes the start location and the destination location; A hybrid swarm intelligence algorithm is used to plan the trajectory of the target task information and determine the optimal trajectory of the UAV; the hybrid swarm intelligence algorithm includes an improved particle swarm algorithm and a sparrow search algorithm; the improved particle swarm algorithm is constructed based on the particle swarm algorithm and the adaptive t-distribution mutation operator; The process of using a hybrid swarm intelligence algorithm to plan the trajectory of the target mission information and determine the optimal trajectory of the UAV specifically includes: Set the algorithm parameters; the algorithm parameters include the maximum number of iterations and the dynamic probability; Based on the sparrow search algorithm and the target task information, the trajectory planning of the first generation population is performed to determine the individual optimal solution and the global optimal solution for the current iteration number; Determine whether the current iteration count has reached the maximum iteration count; If so, the globally optimal solution will be output as the optimal flight path of the UAV; If not, the improved particle swarm optimization algorithm and the dynamic probability are used to mutate and update the first generation population, and then the next iteration is performed. The step of planning the trajectory of the initial population based on the sparrow search algorithm and the target task information to determine the individual optimal solution and the global optimal solution for the current iteration number specifically includes: Using the sparrow search algorithm, trajectory planning is performed on the initial population of the target task information to determine the position and velocity of each particle in the initial population; The individual optimal solution and the global optimal solution for the current iteration number are determined based on the position and velocity of each particle. The process of using the improved particle swarm optimization algorithm and the dynamic probability to mutate and update the initial population specifically includes: Based on the individual optimal solution and the global optimal solution at the current iteration number, the population is iterated to generate a new particle swarm and random numbers; The new particle swarm is subjected to an adaptive t-distribution mutation operator operation based on the random number and the dynamic probability, and the mutated result is updated as the individual optimal solution and the global optimal solution for the next iteration.

2. The UAV trajectory planning method based on a hybrid swarm intelligence algorithm according to claim 1, characterized in that, Before using a hybrid swarm intelligence algorithm to plan the trajectory of the target mission information and determine the optimal trajectory of the UAV, the method further includes: Construct a flight environment function; the flight environment function is used to describe the terrain and topography of the UAV's flight environment.

3. A UAV trajectory planning system based on a hybrid swarm intelligence algorithm, using the method described in any one of claims 1-2, characterized in that, include: The task determination module is used to obtain target task information; The target task information includes the start location and the destination location; The trajectory planning module is used to plan the trajectory of the target mission information using a hybrid swarm intelligence algorithm to determine the optimal trajectory of the UAV; the hybrid swarm intelligence algorithm includes an improved particle swarm algorithm and a sparrow search algorithm; the improved particle swarm algorithm is constructed based on the particle swarm algorithm and the adaptive t-distribution mutation operator.

Images