CN-121977573-A - Low-altitude airspace aircraft three-dimensional path planning method based on enhanced particle swarm optimization

CN121977573ACN 121977573 ACN121977573 ACN 121977573ACN-121977573-A

Abstract

The invention relates to the technical field of aircraft path planning, and provides a low-altitude airspace aircraft three-dimensional path planning method based on enhanced particle swarm optimization, which comprises the steps of modeling a low-altitude airspace environment to obtain a low-altitude airspace environment model; the method comprises the steps of constructing a fitness function, adopting an enhanced particle swarm optimization algorithm to iteratively solve a global optimal solution vector in a feasible space of a low-altitude airspace environment model, wherein in the iteration process, inertia weight is gradually reduced, individual learning factors are gradually reduced, global learning factors are gradually increased, when a swarm tends to converge, local disturbance is applied to a plurality of particle positions with better performance by taking the global optimal position as a center, when the integral swarm detects stagnation for the first time, random disturbance update is carried out on partial particle speeds, and if continuous repeated iteration still detects stagnation, fine adjustment and boundary correction are carried out on the particle positions. The aircraft path planning method can rapidly and accurately plan the optimal flight path.

Inventors

WANG CHUANYUN
CHEN XIPEI
Sun Enyan
WANG LINLIN
GAO JIAN
ZHANG YAJUAN

Assignees

沈阳航空航天大学

Dates

Publication Date: 20260505
Application Date: 20260213

Claims (10)

1. The low-altitude airspace aircraft three-dimensional path planning method based on enhanced particle swarm optimization is characterized by comprising the following steps of: modeling a low-altitude airspace environment to obtain a low-altitude airspace environment model; Constructing an adaptability function for evaluating the comprehensive cost of the path; The method comprises the steps of adopting an enhanced particle swarm optimization algorithm to iteratively solve a global optimal solution vector in a feasible space of a low-altitude airspace environment model, gradually reducing inertia weight, gradually reducing individual learning factors and gradually increasing global learning factors in an iterative process, applying local disturbance to a plurality of particle positions with better performance by taking a global optimal position as a center when a group tends to converge, judging that the group falls into a stagnation state when the overall convergence speed of the group is slowed down or the change of the particle positions tends to be stable, randomly disturbing and updating part of particle speeds if stagnation is detected for the first time, slightly adjusting the particle positions and carrying out boundary correction if stagnation is still detected for a plurality of continuous iterations, and enabling the position vector of each particle in the particle swarm to represent the code of one flight path.
2. The method for planning a three-dimensional path of a low-altitude airspace aircraft based on enhanced particle swarm optimization according to claim 1, wherein the low-altitude airspace environment modeling comprises three-dimensional terrain modeling and static obstacle modeling.
3. The method for three-dimensional path planning of low-altitude airspace aircraft based on enhanced particle swarm optimization according to claim 1, wherein the fitness function The formula of (2) is as follows: ; In the formula, Representing the cost of the path length, The cost of path smoothness is represented by the number of paths, Representing the cost of the fly height, Represents the collision prevention cost of the obstacle, 、、、 Respectively, weight coefficients.
4. The three-dimensional path planning method of the low-altitude airspace aircraft based on the enhanced particle swarm optimization according to claim 1, wherein the specific steps of adopting the enhanced particle swarm optimization algorithm to iteratively solve the global optimal solution vector in the feasible space of the low-altitude airspace environment model are as follows: initializing an include Particle swarm of each particle, carrying out fitness evaluation on each particle by utilizing the fitness function, and taking the position vector of each particle as the initial individual optimal solution vector Taking the position vector of the fitness optimal particle in the particle swarm as an initial global optimal solution vector , wherein, Indicating the particle swarm size; Iteratively updating each particle in the particle swarm to obtain a globally optimal solution vector, wherein The steps of the second iteration are as follows: Updating the velocity and position of the particles, wherein the inertial weights Individual learning factors Global learning factors The formula of (2) is as follows: ; ; ; In the formula, For the current number of iterations, Is the maximum iteration number; For adjusting the coefficient; 、 the upper and lower limit values of the inertial weight are respectively, For the individual learning factor upper limit value, Is a global learning factor lower limit; Calculating group velocity variance And compares it with a preset population convergence threshold Comparing if In the current global optimum position A local disturbance is applied to a plurality of particles with better performance for the center, and a disturbance model is as follows: ; Wherein, the Is the first The original position vector of the individual particles, Is the first The new position vector of each particle after the disturbance, For a uniform random vector within the interval [ -1,1], Gradually reducing the current disturbance intensity along with the iteration progress; Calculating normalized group velocity variance And compares it with a preset stall awareness threshold Comparing if Judging that the group falls into a stagnation state, if stagnation is detected for the first time, carrying out random disturbance update on part of particle speeds, and if stagnation is still detected for a plurality of continuous iterations, carrying out slight adjustment on particle positions and carrying out boundary correction.
5. The method for three-dimensional path planning of low-altitude airspace aircraft based on enhanced particle swarm optimization according to claim 4, wherein the particle swarm is initialized by a continuous domain ant colony algorithm.
6. The method for three-dimensional path planning of low-altitude airspace aircraft based on enhanced particle swarm optimization according to claim 4, wherein the current disturbance intensity is as follows The formula of (2) is as follows: ; In the formula, And (3) with The upper and lower limits of the disturbance intensity respectively, For the current number of iterations, Is the maximum number of iterations.
7. The method for three-dimensional path planning of low-altitude airspace aircraft based on enhanced particle swarm optimization according to claim 4, which is characterized in that for the first aspect The formula for disturbance update of the velocity of individual particles is as follows: ; Wherein, the Is the first The original velocity vector of the individual particles, Is the first The new velocity vector of each particle after the disturbance, In order to be able to adapt the intensity of the velocity disturbance, For a random vector uniformly distributed in the interval [ -1,1], Is the first Maximum speed vector allowed by each particle.
8. The method for three-dimensional path planning of low-altitude airspace aircraft based on enhanced particle swarm optimization according to claim 4, which is characterized in that for the first aspect The formula for performing the slight adjustment of the positions of the individual particles is as follows: ; Wherein, the Is the first The original position vector of the individual particles, Is the first The new position vector of each particle after the disturbance, For a uniform random vector within the interval [ -1,1], In order to be the intensity of the position disturbance, And (3) with An upper boundary vector and a lower boundary vector of the search space, respectively.
9. The three-dimensional path planning method of the low-altitude airspace aircraft based on the enhanced particle swarm optimization according to claim 4, wherein the formula for carrying out boundary correction on the particles is as follows: ; Wherein, the Is the first The new position vector of each particle after the disturbance, Is the first The position vector after the correction of the individual particles, And (3) with An upper boundary vector and a lower boundary vector of the search space, respectively.
10. The method for planning the three-dimensional path of the low-altitude airspace aircraft based on the enhanced particle swarm optimization according to claim 1, which is characterized by further comprising the step of smoothing discrete waypoints corresponding to the globally optimal solution vector by adopting a Bezier curve to obtain a continuous smooth flight path.

Description

Low-altitude airspace aircraft three-dimensional path planning method based on enhanced particle swarm optimization Technical Field The invention relates to the technical field of autonomous navigation of low-altitude aircrafts, in particular to a three-dimensional path planning method of a low-altitude airspace aircrafts based on enhanced particle swarm optimization, which can be widely applied to autonomous path planning of low-altitude aircrafts in a complex low-altitude space domain, and intelligent flight decision and path optimization in low-altitude economy related scenes. Background Along with the rapid development of low-altitude aircrafts, low-altitude aircrafts and related autonomous systems in low-altitude economic scenes such as logistics distribution, inspection and monitoring, emergency rescue and the like, a path planning technology in a low-altitude airspace environment becomes a key link for realizing safe flight and efficient operation. The objective of low-altitude path planning is to search for an optimal or suboptimal feasible flight path from a starting point to a target point in a known or partially known low-altitude environment, wherein the path needs to simultaneously meet multiple constraint conditions such as terrain and obstacle avoidance, flight smoothness, path length, energy consumption and the like. The traditional deterministic programming algorithm (such as an A-based algorithm, a Dijkstra algorithm and the like) has higher calculation efficiency in a low-dimensional and regularized environment, but is easy to suffer from the limitations of calculated explosion, poor path quality and the like when facing the problems of complex low-altitude environment, dense obstacle, high search space dimension and the like. In recent years, population intelligent optimization algorithms (such as Particle Swarm Optimization (PSO), genetic Algorithm (GA), ant colony Algorithm (ACO) and the like) are gradually applied to the field of low-altitude aircraft path planning by virtue of global searching capability and self-adaptive characteristics. However, the standard particle swarm optimization algorithm still has a plurality of defects under the low-altitude complex airspace condition, namely, the algorithm is easy to fall into local optimum in a multi-constraint environment and lacks an effective global jump-out mechanism, secondly, the population diversity is rapidly reduced along with the advancement of an iteration process, early ripening convergence and search capacity decline are easy to be caused, thirdly, the feasibility and the distribution uniformity of an initial path are difficult to ensure in a traditional random initialization mode, the initial solution quality is low, and fourthly, the local search capacity is limited, so that the high-quality low-altitude flight path is difficult to be further refined and optimized. Therefore, the novel path planning method for the low-altitude airspace environment is provided, the global exploration capacity and the local development capacity in the path optimizing process are considered, and the high-precision and high-stability path planning under the low-altitude complex environment is realized, so that the problem to be solved is urgent. Disclosure of Invention In view of the above, the invention provides a low-altitude airspace aircraft three-dimensional path planning method based on enhanced particle swarm optimization, which aims to solve the problems existing in the prior art. The invention provides a low-altitude airspace aircraft three-dimensional path planning method based on enhanced particle swarm optimization, which comprises the following steps: modeling a low-altitude airspace environment to obtain a low-altitude airspace environment model; Constructing an adaptability function for evaluating the comprehensive cost of the path; The method comprises the steps of adopting an enhanced particle swarm optimization algorithm to iteratively solve a global optimal solution vector in a feasible space of a low-altitude airspace environment model, gradually reducing inertia weight, gradually reducing individual learning factors and gradually increasing global learning factors in an iterative process, applying local disturbance to a plurality of particle positions with better performance by taking a global optimal position as a center when a group tends to converge, judging that the group falls into a stagnation state when the overall convergence speed of the group is slowed down or the change of the particle positions tends to be stable, randomly disturbing and updating part of particle speeds if stagnation is detected for the first time, slightly adjusting the particle positions and carrying out boundary correction if stagnation is still detected for a plurality of continuous iterations, and enabling the position vector of each particle in the particle swarm to represent the code of one flight path. Preferably, the low-altitude airsp