Unmanned aerial vehicle path planning method based on hippo state optimization particle swarm algorithm

Abstract

The application provides a kind of unmanned aerial vehicle path planning method based on hippo state optimization particle swarm algorithm, comprising: obtaining the coordinates of static obstacles, and modeling the environment by grid method;Initialize particle swarm, establish global path optimization function with the shortest travel path and no collision with obstacles as the target;Optimize particle swarm algorithm through hippo state mechanism, get improved particle swarm algorithm, solve global path optimization function through improved particle swarm algorithm, get global planning path.The unmanned aerial vehicle path planning method based on hippo state optimization particle swarm algorithm provided by the application optimizes the traditional particle swarm algorithm by combining the hippo state mechanism, realizes the adaptive adjustment of algorithm parameters, improves the convergence speed and global search ability of path planning, and improves the accuracy and efficiency of path planning.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) path planning technology, and in particular to a UAV path planning method based on the Hippo State Optimization Particle Swarm Optimization algorithm. Background Technology

[0002] With the increasing application of drones in military, agriculture, logistics, environmental monitoring, disaster relief, and other fields, achieving autonomous path planning for drones has become a key research topic. Path planning aims to find the optimal path for a drone from its starting point to its destination, enabling it to avoid obstacles, reduce energy consumption, shorten flight time, and ensure flight safety. Current technologies used for drone path planning mainly include classical algorithms such as A*, Dijkstra's algorithm, and D* algorithm, which determine the optimal path through graph search and path optimization; and intelligent optimization algorithms such as genetic algorithms, ant colony algorithms, and particle swarm optimization algorithms, which search for optimal solutions by simulating natural evolution and group behavior.

[0003] Among these intelligent optimization algorithms, Particle Swarm Optimization (PSO) is a swarm intelligence-based optimization algorithm inspired by the collective behavior of flocks of birds or schools of fish in nature. The basic idea of ​​PSO is to represent the solution space of the optimization problem using the motion of a swarm of particles in the search space. Each particle represents a possible solution, and the particle gradually approaches the optimal solution by adjusting its velocity and position. The particle's velocity update depends on its own historical best position and the swarm's historical best position, and is also influenced by inertia weights and learning factors. As iterations proceed, the particle swarm gradually converges to the optimal solution under the guidance of the globally optimal position. However, the application of PSO in UAV path planning still faces some challenges. Specifically, PSO is prone to getting trapped in local optima, resulting in a planned path that is not globally optimal, and the UAV's flight distance is relatively long, affecting mission efficiency and energy consumption. Summary of the Invention

[0004] In view of this, the present invention provides a UAV path planning method based on the hippo state optimization particle swarm algorithm to solve the problems existing in the prior art.

[0005] This invention provides a UAV path planning method based on the hippo state optimization particle swarm algorithm, comprising:

[0006] Obtain the coordinates of static obstacles and model the environment using a grid method;

[0007] Initialize the particle swarm and establish a global path optimization function with the goal of minimizing the travel path and avoiding collisions with obstacles;

[0008] The particle swarm optimization algorithm is optimized by using the hippo state mechanism to obtain an improved particle swarm optimization algorithm. The global path optimization function is solved by the improved particle swarm optimization algorithm to obtain the global planning path.

[0009] Preferably, obtaining the coordinates of static obstacles and performing environmental modeling using the grid method includes the following steps:

[0010] Collect information on all static obstacles in the flight environment using sensors or pre-drawn maps, and record the coordinates of each obstacle;

[0011] The entire map is divided into uniform grids, with each grid cell representing an independent spatial region. A two-dimensional array representing the map is created, with all initial values ​​set to 0. Then, each grid cell in the map is traversed, and the grid cell is checked to see if it contains an obstacle. If it contains an obstacle, it is marked as 1; otherwise, it is marked as 0.

[0012] Further optimization involves initializing the particle swarm by randomly generating the initial positions and velocities of the particles, with each particle in the swarm representing a possible path solution.

[0013] Further optimization yields the following global path optimization function:

[0014]

[0015] Among them, L path It is the total length of the path; P smoothness It is a path smoothness penalty; n B E(1) represents the number of nodes that pass through obstacles in the path; E(2) and E(3) represent the number of rows and columns of the map, respectively.

[0016] Where, n B The calculation formula is as follows:

[0017]

[0018] In the formula, As an indicator function, when node (x i ,y i When located inside an obstacle, otherwise n represents the total number of nodes in the path;

[0019] L path The calculation formula is as follows:

[0020]

[0021] In the formula, x i The x-coordinate of the i-th node in the path is represented by the x-coordinate, and the y-coordinate by the y-coordinate. iThis represents the y-coordinate of the i-th node in the path, and n represents the total number of nodes in the path.

[0022] P smoothness The calculation formula is as follows:

[0023]

[0024] In the formula, θ i It is the direction angle of the i-th segment in the path, calculated using the formula: θ i =atan2(y i+1 -y i ,x i+1 -x i ), where n represents the total number of nodes in the path.

[0025] Further optimization involves using a hippo state mechanism to refine the particle swarm optimization algorithm, resulting in an improved algorithm. Solving the global path optimization function using this improved algorithm yields the global path planning, comprising the following steps:

[0026] The path quality of each particle is evaluated using a global path optimization function, and the fitness value is calculated.

[0027] Based on the particle's fitness value, the particles are divided into three states using the hippopotamus state mechanism, and the inertial weight and acceleration constant of the particles in each state are dynamically adjusted. The three states are in water, on the shore, and on land.

[0028] The velocity and position of particles are iteratively updated based on the inertial weights and acceleration constants adjusted according to the hippo mechanism to obtain the globally optimal path.

[0029] Further optimization yields the following inertial weights and acceleration constants for particles in each state:

[0030] In water:

[0031] w = w max ;

[0032] c1 = c 1max ;

[0033] c2 = c 2max ;

[0034] On the shore:

[0035]

[0036] On land:

[0037] w = w min ;

[0038] c1 = c 1min ;

[0039] c2 = c 2min ;

[0040] Where w represents the adjusted inertia weight, and c1 and c2 represent the adjusted acceleration constants, w max and w min These represent the maximum and minimum values ​​of the inertia weight, respectively; c 1max and c 1min These represent the maximum and minimum values ​​of the individual acceleration constant, respectively; c 2max and c 2min These represent the maximum and minimum values ​​of the population acceleration constant, respectively.

[0041] Further optimization yields the following formula for updating the particle's position:

[0042]

[0043] in, represents the velocity of particle i at time t+1; w represents the inertial weight. c1 and c2 represent the velocity of particle i at time t; c1 and c2 represent the acceleration constants; v1 and v2 represent random numbers in the range [0,1]; p i x represents the optimal position of particle i; i (t) represents the position of particle i at time t; g represents the global optimal position; This indicates the position of particle i at time t+1; This represents the position of particle i at time t.

[0044] Further optimization involves applying the following formula to the boundary conditions of the particle positions in each iteration:

[0045] p i,j =max(min(p) i,j U bj ),L bj );

[0046] Where p(i,j) is the coordinate component of particle i in the j-th dimension; U bj It is the upper boundary of the j-th dimension; L bj It is the lower boundary of the j-th dimension.

[0047] Further optimization involves using Bézier curves to smooth the path during path generation, ensuring its naturalness and continuity.

[0048] This invention provides a UAV path planning method based on the Hippo State Optimization Particle Swarm Optimization (PSO) algorithm. It introduces a Hippo State mechanism to improve the PSO algorithm and combines this mechanism with a global path optimization function. This overcomes the shortcomings of traditional PSO algorithms, such as improper parameter selection and poor path planning performance, and obtains an optimal path suitable for UAV flight. Through the Hippo State mechanism, the inertia weight and acceleration constant are dynamically adjusted based on the particle fitness value, achieving adaptive parameter adjustment. This allows the algorithm to dynamically optimize under different states, improving the accuracy and efficiency of path planning. The planned path has a shorter travel distance, avoids obstacle collisions, is suitable for actual UAV flight, and meets the high real-time requirements of UAV path planning.

[0049] The UAV path planning method based on the hippo state optimization particle swarm algorithm provided by this invention improves the particle swarm algorithm by introducing the hippo state mechanism, realizing adaptive adjustment of path planning parameters, and improving search efficiency and convergence speed. Combined with the global path optimization function, the algorithm can dynamically optimize the path, avoid obstacles, and generate the shortest and safest path, meeting the actual flight requirements of UAVs, and has significant technical advantages and effects. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0051] Figure 1 This is a flowchart of the UAV path planning method based on the hippo state optimization particle swarm algorithm provided by the present invention;

[0052] Figure 2a This is the final roadmap of the improved particle swarm optimization algorithm in this embodiment of the invention;

[0053] Figure 2b This is the final roadmap of the traditional particle swarm algorithm in this embodiment of the invention. Detailed Implementation

[0054] The present invention will be further described below with reference to specific embodiments.

[0055] like Figure 1 As shown, this invention provides a UAV path planning method based on the hippopotamus state optimization particle swarm algorithm, including the following steps:

[0056] S1. Obtain the coordinates of static obstacles and perform environmental modeling using the grid method;

[0057] The specific steps are as follows:

[0058] First, information on all static obstacles in the flight environment is collected using sensors (such as lidar and cameras) or pre-drawn maps, and the coordinates and shape parameters of each obstacle are recorded. For example, for a rectangular obstacle, its vertex coordinates are recorded.

[0059] Next, the entire flight area is divided into uniform grid cells, each grid cell representing an independent spatial region. A two-dimensional array G representing the map is created, with all initial values ​​set to 0, indicating that all regions are passable. Then, each grid cell in the map is traversed, and it is checked whether the cell contains obstacles. If the grid cell contains obstacles, it is marked as 1, indicating that the region is impassable; otherwise, it is marked as 0.

[0060] S2. Initialize the particle swarm and establish a global path optimization function with the goal of minimizing the travel path and avoiding collisions with obstacles;

[0061] In improving the particle swarm optimization algorithm, the first step is to initialize the particle swarm. The initialization process involves randomly generating the initial positions and velocities of the particles. Each particle's position is initialized within the boundaries of the search space. By randomly generating particle positions, particles can cover different regions of the search space, thus ensuring diversity in the path optimization process. For each particle's position x... i Randomly generate its initial coordinates (x, y) in two-dimensional space. i ,y i The initial velocity v of these particles i They will also be randomly assigned, and the initial particle swarm will provide the basis for the subsequent path optimization process.

[0062] Each particle's position represents a possible path, and path generation and optimization are accomplished with each iteration through position updates. Specifically, the particle's position is adjusted in each iteration, tending towards a better solution (i.e., a shorter path and a path that avoids obstacles). Each particle generates a path by updating its position, and the particle's fitness function is evaluated based on path length, obstacle avoidance capability, and smoothness. After multiple iterations, the particle's position is continuously adjusted until a globally optimal path is found.

[0063] The following describes the process of constructing a global path optimization function.

[0064] Traverse each node x in the path i Check each node x i Is it located inside an obstacle? Specifically, for each node x i If (x i ,y iIf a node is located within an obstacle (i.e., its corresponding position value on map G is 1), then the node is recorded as having passed through the obstacle. The number of nodes n that pass through obstacles along the path is counted. B The number of nodes n that pass through obstacles in the path B The calculation formula is as follows:

[0065]

[0066] Where, Ⅱ is the indicator function, when node (x i ,y i If the path is located inside an obstacle, Ⅱ = 1; otherwise, Ⅱ = 0. n represents the total number of nodes in the path.

[0067] For paths without obstacles, a smooth, continuous path is generated, and the total path length is calculated to prioritize shorter and safer paths during path optimization. The formula for calculating the total path length is as follows:

[0068]

[0069] Where, x i The x-coordinate of the i-th node in the path is represented by the x-coordinate, and the y-coordinate by the y-coordinate. i This represents the y-coordinate of the i-th node in the path.

[0070] The path smoothness penalty is calculated based on the angle change between adjacent path segments. A larger angle change indicates a sharp turn. The formula for calculating the path smoothness penalty is as follows:

[0071]

[0072] Where, θ i It is the direction angle of the i-th segment in the path, calculated using the formula: θ i =atan2(y i+1 -y i ,x i+1 -x i );

[0073] For paths that pass through obstacles, a larger fitness value is set as a penalty to avoid selecting these paths during path optimization. The specific formula is as follows:

[0074] f x =E(1)×E(2)×n B ;

[0075] Where E(1) and E(2) represent the number of rows and columns of the map, respectively, and n B It is the number of nodes that pass through obstacles in the path.

[0076] The final global path optimization function f is obtained by combining the cases of no obstacles and obstacles. x :

[0077]

[0078] Among them, L path It is the length of the path; P smoothness It is a path smoothness penalty; n B E is the number of nodes that pass through obstacles in the path; E(1) and E(2) represent the number of rows and columns of the map, respectively, and are used to severely penalize paths that cross obstacles.

[0079] S3. Optimize the particle swarm optimization algorithm through the hippo state mechanism to obtain an improved particle swarm optimization algorithm. Solve the global path optimization function through the improved particle swarm optimization algorithm to obtain the global planning path.

[0080] First, the path quality of each particle is evaluated through a global path optimization function, and the fitness value is calculated to guide the search direction of the particle swarm.

[0081] The inertia weight w and acceleration constants c1 and c2 are dynamically adjusted based on the particle's fitness value. The specific steps are as follows:

[0082] The hippopotamus state mechanism categorizes particles into three states based on their fitness values ​​and dynamically adjusts the inertia weight *w* and acceleration constants *c1* and *c2* for each state to improve the algorithm's search efficiency and convergence speed. The three states are: in water, on shore, and on land. For particles with low fitness values ​​(in water), their inertia weight and acceleration constant are set to larger values ​​to increase their search range and randomness; for particles with medium fitness values ​​(on shore), their inertia weight and acceleration constant are set to medium values ​​to balance global and local searches; and for particles with high fitness values ​​(on land), their inertia weight and acceleration constant are set to smaller values ​​for more refined local searches. The specific adjustment formulas are as follows:

[0083] In water (particles with lower fitness values ​​exhibit greater randomness):

[0084]

[0085] On the shore (particles with moderate fitness and moderate randomness):

[0086]

[0087] On land (particles with higher fitness values ​​have less randomness):

[0088] w = w min ;

[0089]

[0090]

[0091] Among them, w max and w min These represent the maximum and minimum values ​​of the inertia weight, respectively; c 1max and c 1min These represent the maximum and minimum values ​​of the individual acceleration constant, respectively; c 2max and c 2min These represent the maximum and minimum values ​​of the population acceleration constant, respectively.

[0092] In each iteration, the particle's position and velocity are updated based on the inertia weights and acceleration constants adjusted according to the hippo mechanism. The particle's position update formula is as follows:

[0093]

[0094] in, represents the velocity of particle i at time t+1; w represents the inertial weight, used to balance the particle's search capability and convergence capability; c1 and c2 represent the velocity of particle i at time t; c1 and c2 represent acceleration constants, used to adjust the acceleration of the particle moving towards its individual optimal position and the global optimal position; v1 and v2 represent random numbers in the range [0,1], increasing the randomness and diversity of the algorithm; p i x represents the optimal position of particle i; i (t) represents the position of particle i at time t; g represents the global optimal position. This indicates the position of particle i at time t+1; This represents the position of particle i at time t.

[0095] To ensure that the updated particle positions are within the defined boundary range, the particle positions need to be constrained using a boundary treatment formula, which is as follows:

[0096] p i,j =max(min(p) i,j U bj ),L bj );

[0097] Where p(i,j) is the coordinate component of particle i in the j-th dimension; U bj It is the upper boundary of the j-th dimension; L bj It is the lower boundary of the j-th dimension.

[0098] During path generation, the generated path is further optimized to improve its smoothness and continuity. Specifically, the connection between adjacent nodes is checked for freedom; if obstacles exist between adjacent nodes, new intermediate nodes are inserted into the path to avoid them. Then, Bézier curves are used to further smooth the path, ensuring its naturalness and continuity. During Bézier curve generation, control points p0 and p1 are used to calculate the Bézier curve, using the following formula:

[0099] bezierCurve(t)=(1-t)·p0+t·p1;

[0100] Where t is a parameter ranging from [0,1]; p0 and p1 are the coordinates of two control points, respectively. The generated Bézier curve calculates the corresponding coordinates at each value of t, forming a smooth curve.

[0101] Through multiple iterations, the particle's velocity and position are continuously updated, the path is optimized, and the algorithm gradually approaches the optimal solution. To ensure that the algorithm converges within a reasonable time, a maximum number of iterations and a fitness value change threshold are set as termination conditions. When the preset number of iterations is reached or the fitness value change is lower than the set threshold, the algorithm terminates and outputs the current optimal path.

[0102] In a specific implementation of this invention, completing the task means finding a path with the shortest travel distance and without collisions with obstacles. The above steps enable UAV path planning based on an improved particle swarm optimization algorithm.

[0103] In a grid map where obstacles account for 27%, the path planning performance of the traditional particle swarm optimization (PSO) algorithm and the improved PSO algorithm are compared. The number of participating populations is set to 50, and the number of iterations is 200. Given the initial and final positions of the UAV, the optimal path for each step is continuously calculated using the method described in this invention, ultimately finding a path with the shortest travel distance and no collisions with obstacles. The improved PSO algorithm has the same settings as the traditional PSO algorithm. After multiple simulation experiments, the simulation results are shown in the comparison... Figure 2a , Figure 2b In complex environments, the optimal path length searched by the traditional particle swarm optimization algorithm is 40.9, while the optimal path length searched by the improved particle swarm optimization algorithm is 32.6, a reduction of 20.2%. Comparing the paths planned by the traditional and improved particle swarm optimization algorithms, the improved algorithm improves the search efficiency, indicating that the improved particle swarm optimization algorithm has significant advantages in convergence speed and optimization ability.

[0104] It should be noted that the purpose of disclosing the embodiments is to help further understand the present invention; however, those skilled in the art will understand that various substitutions and modifications are possible without departing from the spirit and scope of the present invention and the appended claims. Therefore, the present invention should not be limited to the content disclosed in the embodiments, and the scope of protection of the present invention is defined by the scope of the claims.

Claims

1. A method for UAV path planning based on the hippopotamus state optimization particle swarm optimization algorithm, characterized in that, include: Obtain the coordinates of static obstacles and model the environment using a grid method; Initialize the particle swarm and establish a global path optimization function with the goal of minimizing the travel path and avoiding collisions with obstacles; The particle swarm optimization algorithm is optimized by the hippo state mechanism to obtain an improved particle swarm optimization algorithm. The global path optimization function is solved by the improved particle swarm optimization algorithm to obtain the global planning path. The global path optimization function is as follows: ； in, It is the total length of the path; It is a penalty for the smoothness of the path; It is the number of nodes that pass through obstacles in the path; and These represent the number of rows and columns of the map, respectively. in, The calculation formula is as follows: ； In the formula, For indicator functions, when node When inside an obstacle, =1, otherwise =0, This represents the total number of nodes in the path; The calculation formula is as follows: ； In the formula, This represents the coordinates of the nth node in the path on the x-axis. This represents the y-coordinate of the nth node in the path. This represents the total number of nodes in the path; The calculation formula is as follows: ； In the formula, It is the first in the path The direction angle of the segment is calculated using the following formula: , This represents the total number of nodes in the path; The process involves optimizing the particle swarm optimization algorithm using the hippo state mechanism to obtain an improved particle swarm optimization algorithm. Solving the global path optimization function using this improved algorithm yields the global planning path, which includes the following steps: The path quality of each particle is evaluated using a global path optimization function, and the fitness value is calculated. Based on the fitness value of the particles, the particles are divided into three states using the hippo state mechanism, and the inertia weight and acceleration constant of the particles in each state are dynamically adjusted. The three states are in water, on the shore, and on land. In water, the particles with lower fitness values ​​are corresponding to particles with medium fitness values, on the shore, the particles with higher fitness values ​​are corresponding to particles with higher fitness values. The velocity and position of the particles are iteratively updated based on the inertial weights and acceleration constants adjusted according to the hippo mechanism to obtain the globally optimal path; The inertial weight and acceleration constant of the particle in each state are as follows: In water: ； ； ； On the shore: ； ； ； On land: ； ； ； in, This represents the adjusted inertia weight. and This represents the adjusted acceleration constant. and These represent the maximum and minimum values ​​of the inertia weight, respectively. and These represent the maximum and minimum values ​​of the individual acceleration constant, respectively. and These represent the maximum and minimum values ​​of the population acceleration constant, respectively.

2. The UAV path planning method based on the hippo state optimization particle swarm algorithm according to claim 1, characterized in that: Obtaining the coordinates of static obstacles and modeling the environment using the grid method involves the following steps: Collect information on all static obstacles in the flight environment using sensors or pre-drawn maps, and record the coordinates of each obstacle; The entire map is divided into uniform grids, with each grid cell representing an independent spatial region. A two-dimensional array representing the map is created, with all initial values ​​set to 0. Then, each grid cell in the map is traversed, and the grid cell is checked to see if it contains an obstacle. If it contains an obstacle, it is marked as 1; otherwise, it is marked as 0.

3. The UAV path planning method based on the hippo state optimization particle swarm algorithm according to claim 1, characterized in that: The initialization of the particle swarm includes randomly generating the initial positions and velocities of the particles, with each particle in the swarm representing a possible path solution.

4. The UAV path planning method based on the hippo state optimization particle swarm algorithm according to claim 1, characterized in that: The particle position update formula is as follows: ； ； in, Represents particles exist The speed of time; Indicates inertia weight; Represents particles exist The speed of time; and Indicates the acceleration constant; and Represents a random number in the range [0,1]. Represents particles The optimal position of an individual; Indicates the globally optimal position; Represents particles exist The position at that moment; Represents particles exist The location at any given moment.

5. The UAV path planning method based on the hippo state optimization particle swarm algorithm according to claim 1, characterized in that: In each iteration, the particle's position is boundary-processed using the following formula: ； in, It is a particle No. Coordinate components in a dimension; It is the first The upper boundary of the dimension; It is the first The lower bound of the dimension.

6. The UAV path planning method based on the hippo state optimization particle swarm algorithm according to claim 1, characterized in that: During path generation, Bézier curves are used to further smooth the path, ensuring its naturalness and continuity.

Images