CN115202394A - Unmanned aerial vehicle full-coverage path planning method based on improved genetic algorithm - Google Patents
Unmanned aerial vehicle full-coverage path planning method based on improved genetic algorithm Download PDFInfo
- Publication number
- CN115202394A CN115202394A CN202210826983.9A CN202210826983A CN115202394A CN 115202394 A CN115202394 A CN 115202394A CN 202210826983 A CN202210826983 A CN 202210826983A CN 115202394 A CN115202394 A CN 115202394A
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- flight
- genetic algorithm
- grid
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention relates to the technical field of unmanned aerial vehicles, in particular to an unmanned aerial vehicle full coverage path planning method based on an improved genetic algorithm, which comprises the following steps: scanning an environment map to acquire basic information; converting the longitude and latitude coordinates into grid point coordinates by using a grid method, defining the grid height as the maximum value of the grid cataract obstacle height, and establishing a three-dimensional model of the unmanned aerial vehicle full-coverage flight environment; respectively introducing a flight path distance cost function and a flight path direction cost function, and optimizing the cruising ability of the unmanned aerial vehicle in full-coverage flight; improving genetic algorithm training; converting the obtained traversal sequence into longitude and latitude coordinates, inputting the longitude and latitude coordinates into a control program of the unmanned aerial vehicle, and realizing the planning of the flight full-coverage path of the unmanned aerial vehicle; the invention utilizes the grid method to carry out unmanned plane flight environment modeling, applies the improved genetic algorithm to unmanned plane flight path planning, improves the convergence speed, enhances the global optimization capability and reduces the flight time and energy consumption.
Description
Technical Field
The invention relates to the technical field of unmanned aerial vehicles, in particular to an unmanned aerial vehicle full coverage path planning method based on an improved genetic algorithm.
Background
With the improvement of electronic technology and intelligence level, the problem of full coverage path planning of unmanned aerial vehicles has become an important research topic in the current society. The unmanned aerial vehicle plays an important role in military affairs, has a huge application prospect in life and business of people, and has an auxiliary role in the aspects of epidemic prevention and control, forest fire monitoring, immovable cultural heritage protection and the like. In many application scenes of the unmanned aerial vehicle, the sensing and obstacle avoidance technology of the unmanned aerial vehicle is a necessary link for automatic and intelligent realization, and the obstacle avoidance technology of the unmanned aerial vehicle can be divided into three stages: sensing obstacles, bypassing obstacles and scene models. The first two stages are to finish automatic identification, suspension and obstacle avoidance, and the third stage is to scan the target environment, establish a three-dimensional stereogram and plan an optimal route from the perspective of the whole situation.
The early full coverage path planning algorithm mainly uses a random search coverage strategy, which is easy to implement, but has the problems of high time overhead, low map coverage rate, weak intellectualization and the like. The research of the modern full coverage path algorithm has respective advantages in a specific environment, but when facing a more complex flight environment of the unmanned aerial vehicle, the method also has self problems, such as long algorithm convergence time, weak global performance, large calculation amount, low search efficiency and the like, and still has great improvement and promotion space. A chinese patent application with application number CN202010312645.4 discloses a method for planning a full-coverage path of an unmanned aerial vehicle, which comprises the following steps: determining a coverage type flight range to be carried out by the unmanned aerial vehicle, and selecting a plurality of boundary points at the peripheral edge of the path planning range; acquiring longitude and latitude coordinates of the boundary points, and converting the longitude and latitude coordinates into horizontal and vertical coordinates with equal unit length; taking a connecting line between the boundary point and the central point of the coverage type flight range, and performing spiral cruise on the connecting line by the unmanned aerial vehicle until all ranges are completely covered; or connecting lines through two adjacent boundary points to obtain the transverse movement length of the selected range, connecting lines of the equally divided points and the boundary points on the transverse movement length to obtain intersection points, and connecting the intersection points to perform S-shaped cruising till all ranges are covered; the coordinates of each point connected in sequence are taken out, stored and sent to a controller of the unmanned aerial vehicle, so that the full-coverage type path planning of the unmanned aerial vehicle is realized, and the problems of complexity, large error and low precision of the full-coverage path planning of the existing unmanned aerial vehicle are solved.
However, in the process of implementing the specific embodiment of the present invention, the inventor of the present application finds that the unmanned aerial vehicle full coverage path planning method has the following several defects: (1) The unmanned aerial vehicle full-coverage path planning method is a path planning method applied to a two-dimensional environment, and cannot be well adapted to full-coverage path planning of an unmanned aerial vehicle in a complex three-dimensional environment; (2) The unmanned aerial vehicle full-coverage path planning method only considers the cost and the cost brought by the path, but does not consider the cost and the cost brought by the direction; (2) The unmanned aerial vehicle full-coverage path planning method adopts a traditional genetic algorithm, is low in convergence speed and is easy to fall into a local optimal solution. Therefore, an unmanned aerial vehicle full-coverage path planning method based on an improved genetic algorithm is provided to solve the technical problems.
Disclosure of Invention
Aiming at the problems, the invention provides an unmanned aerial vehicle full coverage path planning method based on an improved genetic algorithm, which improves the convergence rate, enhances the global optimization capability, reduces the flight time and energy consumption, and enables the traversal coverage environment required by the actual flight of the unmanned aerial vehicle to be suitable for the complex three-dimensional environment.
In order to solve the technical problems, the invention is realized by the following technical scheme:
the invention relates to an unmanned aerial vehicle full coverage path planning method based on an improved genetic algorithm, which comprises the following steps:
s1, determining an overlay type flight range to be carried out by an unmanned aerial vehicle, and scanning a map of the overlay type flight range to obtain basic information;
s2, transforming longitude and latitude coordinates in the basic information obtained by scanning into grid point coordinates by using a grid method, defining the grid height as the maximum value of the height of the grid cataract obstacle, and establishing a three-dimensional model of the full-coverage flight environment of the unmanned aerial vehicle;
s3, respectively introducing a flight path distance cost function and a flight path direction cost function, and optimizing the cruising ability of the unmanned aerial vehicle in full-coverage flight;
s4, improving the genetic algorithm training, which mainly comprises the following steps:
s41, encoding a traversal sequence;
s42, introducing a greedy algorithm to determine an initialization population and calculating the fitness;
s43, adopting a non-playback selection mode when selecting excellent genes so as to improve the replication probability of other genes;
s44, improving a gene crossing mode to ensure that each node in the three-dimensional model only traverses once;
s45, introducing a flight route direction cost function to enable the variation process of the genetic algorithm to advance towards the direction of the optimal solution;
s46, after continuous multiple iterations, judging whether the population optimal adaptive value changes, and if the population optimal adaptive value does not change, increasing the transformation probability to jump out a local optimal solution;
and S5, converting the traversal sequence obtained by the training of the improved genetic algorithm into longitude and latitude coordinates, inputting the longitude and latitude coordinates into a control program of the unmanned aerial vehicle, and executing the unmanned aerial vehicle according to the control program to realize the planning of the flight full-coverage path of the unmanned aerial vehicle.
As a preferred technical scheme of the invention, the establishment of the three-dimensional model of the full-coverage flight environment of the unmanned aerial vehicle comprises the following steps:
s21, dividing the flight environment of the unmanned aerial vehicle into a plurality of cubes to represent the fluctuation of the ground and the positions of obstacles;
s22, abstracting the height of the highest obstacle in the grids into the height of a grid cube, and enabling each grid to be presented in the form of coordinate points (x, y, z);
s23, if the height of the obstacle in the grid is smaller than or equal to the set height h, the obstacle is a point accessible to the unmanned aerial vehicle in a default mode, and if the obstacle with the height larger than h exists in the grid, the obstacle is a point inaccessible to the unmanned aerial vehicle in a default mode.
As a preferred embodiment of the present invention, whether the obstacle can be accessed by the drone in step S23 is represented by a variable o, which is defined according to the following formula:
as a preferred technical solution of the present invention, the flight path distance cost function is defined according to the following formula:
wherein, dist ij Representing the distance cost between two nodes, d ij When the path between two points has an obstacle, the heights of all the obstacles are stored in a set H, and the unmanned aerial vehicle can set the initial height H from the set height H 0 Ascending to max (H) in situ, then going to the target point, and finally descending to the initial set height H 0 。
As a preferred technical solution of the present invention, the flight path direction cost function is defined according to the following formula:
wherein, delta theta (x,y) Is the angle difference between the current moving direction and the next moving direction of the unmanned aerial vehicle, delta theta (x,y) The larger the value of (a), the larger the direction of change of the corresponding unmanned aerial vehicleThe greater the cost incurred;
the difference angle delta theta (x,y) Specifically defined according to the following formula:
Δθ＝|θ n -θ p |＝
|a tan 2(y n -y p ,x n -x p )-a tan 2(y p -y b ,x p -x b )|
wherein, theta n Is the angle theta between the straight line formed by the next state point and the current node and the abscissa p Forming an angle between the current node and the previous covered node, (x) n ,y n ) As a target position coordinate point, (x) p ,y p ) As the current position coordinate point, (x) b ,y b ) For the coordinate point of the previous position, the cost consumed by the similarity between the moving direction of the next step and the original moving direction is relatively smaller.
As a preferred technical solution of the present invention, the specific manner of determining the initialization population by introducing the greedy algorithm is as follows: after the initial coordinate points are selected randomly, a greedy algorithm is used for solving a better traversal sequence as a population gene.
As a preferred technical scheme of the invention, the specific mode for improving the gene crossing mode is as follows: firstly, a section of continuous gene is taken from the father generation sequence, and then the gene different from the continuous gene is taken from the mother generation sequence in sequence and added into the offspring sequence.
As a preferred technical solution of the present invention, the specific manner of introducing the flight route direction cost function in step S45 is as follows: after a replaced gene is randomly selected, the directional cost value of other genes to the gene is calculated, and the gene with the minimum cost loss is selected for exchange.
As a preferred embodiment of the present invention, the step S46 of increasing the transformation probability to jump out the local optimal solution is implemented by using a dynamic variation rate, where the dynamic variation rate is defined by the following formula:
wherein M is p Representing the probability of genetic algorithm variation, if the current optimal fitness value of the genetic algorithm is not changed after more than 10 iterations, dynamically improving the probability of variation, and increasing P for each iteration on the original probability a Until the mutation probability is 1, when the optimal solution is updated, M p And the initial value is restored again, and the diversity of the population genes is increased by introducing the dynamic variation rate, and simultaneously, the retention of individual excellent genes is prevented from being influenced by the excessively high variation probability.
The invention has the following beneficial effects:
1. according to the invention, the grid method is utilized to carry out unmanned aerial vehicle flight environment modeling, the unmanned aerial vehicle flight environment is mapped by the grid method, and models are constructed by cubes with different heights, so that the traversal coverage environment required by the actual flight of the unmanned aerial vehicle can adapt to a complex three-dimensional environment.
2. The invention applies the improved genetic algorithm to the flight path planning of the unmanned aerial vehicle, and effectively combines the flight path distance cost function and the flight path direction cost function, thereby improving the convergence rate, enhancing the global optimization capability and reducing the flight time and energy consumption.
Of course, it is not necessary for any product in which the invention is practiced to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is an obstacle crossing flight diagram of an unmanned aerial vehicle in the invention.
Fig. 2 is a diagram of the directional cost function difference in the present invention.
FIG. 3 is a flow chart of the basic genetic algorithm of the present invention.
FIG. 4 is a schematic cross-flow diagram of the present invention.
FIG. 5 is a flow chart of the improved genetic algorithm of the present invention.
Fig. 6 is a flow chart of the overall scheme of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
1. Grid method environment modeling
The problem of studying path planning is to select a suitable method to model the environment map. Common three-dimensional environment modeling methods include: geometric modeling, topological modeling, and grid modeling. In consideration of the actual terrain condition and the calculation efficiency of unmanned aerial vehicle coverage traversal, the invention applies the grid method to the simulation of the environment map, and divides the flight environment of the unmanned aerial vehicle into a plurality of cubes so as to represent the fluctuation of the ground and the positions of the obstacles.
The unmanned aerial vehicle flight environment is divided into 81 grids, the size of each grid is 10 x 10m, and for the convenience of calculation and research, the height of the highest obstacle in the grids is abstracted into the height of a grid cube, and each grid is presented in the form of coordinate points (x, y, z). The goal of drone full coverage path planning is to go from a starting location back to the starting location after traversing all coverable grids (i.e., all accessible points) and minimize the flight cost of the drone, which can be analogized to the traveler problem (TSP).
Considering the specific requirements of the unmanned aerial vehicle on the flying height in the application scenes of cruising, scanning, pesticide spraying and the like, the invention makes the following settings. And if the height of the obstacle in the grid is less than or equal to the set height h, defaulting the obstacle to be a unmanned aerial vehicle accessible point, and if the obstacle with the height greater than h exists in the grid, considering the obstacle to be an unmanned aerial vehicle inaccessible point. The variable o is used to represent whether the grid can be accessed and the following formula definition is made:
2. flight path distance cost function
One of the problems faced by drones in practical applications is poor endurance, and therefore flight energy consumption is considered when researching drone path planning. The primary index for determining the energy consumption of the unmanned aerial vehicle is the range distance after path planning, and the following definitions are made:
wherein dist ij Represents the distance cost between two nodes, d ij When the path between two points has an obstacle, the heights of all the obstacles are stored in a set H, and the unmanned aerial vehicle can set the initial height H from the set height H 0 Ascending to max (H) in situ, then going to the target point, and finally descending to the initial set height H 0 As shown in fig. 1.
3. Flight path direction cost function
Proved that the energy consumption brought by the unmanned aerial vehicle when turning is higher than that of the straight line without changing the direction. In order to evaluate the advantages and disadvantages of the unmanned aerial vehicle path planning, a direction cost function, namely the consumption caused by the course change of the unmanned aerial vehicle, is introduced on the basis of considering the shortest overall flight length, and the following definitions are made:
Δθ＝|θ n -θ p |＝
|a tan 2(y n -y p ,x n -x p )-a tan 2(y p -y b ,x p -x b )|
wherein, theta n Is the angle theta between the straight line formed by the next state point and the current node and the abscissa p Forming an included angle between the current node and the previous covered node (x) n ,y n ) As a target position coordinate point, (x) p ,y p ) As the current position coordinate point, (x) b ,y b ) For the coordinate point of the previous position, the cost consumed by the next motion direction is relatively smaller as the motion direction is more similar to the original motion direction, and the direction cost function difference value graph is shown in fig. 2.
4. Method steps of genetic algorithm
Genetic Algorithm (GA) is an algorithm that iteratively calculates the process of natural evolution based on natural selection and genetic mechanisms to obtain the best results. The basic operation steps of the genetic algorithm are as follows:
1) Determining the size of the population scale, the iteration times and the gene variation probability;
2) Initializing a population (initializing a traversal sequence of grid nodes of the unmanned aerial vehicle);
3) Calculating the individual fitness of the population;
when calculating the population fitness value, the three-dimensional moving distance consumption is considered, and the reciprocal of the distance of complete coverage is taken as the fitness value, as follows:
4) Selecting an individual for retention;
5) Selecting individuals for mutation;
6) Setting a termination condition; it should be noted here that the termination condition in fig. 3 is that the maximum number of iterations or the optimal value specified initially is not changed, specifically: (1) completing a preset evolutionary algebra; (2) The best individual in the population has no improvement or the average fitness has substantially no improvement over successive generations.
FIG. 3 is a flow chart of a basic genetic algorithm. When the basic genetic algorithm is used for solving, the height of the obstacles passing between adjacent nodes in the path sequence is comprehensively considered, so that the algorithm preferentially selects the obstacle on the paths with the obstacles and the paths without the obstacles, but the paths with the obstacles are not completely abandoned, and the shortest path crossing the obstacles for the minimum times is found based on the method. However, the basic genetic algorithm has some defects, such as too low convergence rate and easy falling into local optimal solution. In order to solve the problems, the invention provides five corresponding optimization strategies on the basis of a basic algorithm.
1) Determining initial generation population by introducing greedy algorithm
In the basic genetic algorithm, the gene sequences of the initial generation population are randomly generated, so that the initial generation population has low adaptive value and is difficult to quickly converge. The method introduces a greedy algorithm for determining the initial generation population gene sequence, namely, after an initial coordinate point is randomly selected, a better traversal sequence is solved by using the greedy algorithm to serve as the population gene.
2) Using selection without putting back
In basic genetic algorithms, screening of individuals is often performed using a method with put-back. Individuals with a higher fitness value are easier to screen, while individuals with a lower fitness value are selected with a probability of approaching 0 after multiple iterations.
The traditional selection method easily causes the algorithm to trap in the local optimal solution in the solving process. Therefore, when selecting excellent genes, a method without putting back is adopted, the replication probability of other genes is improved, and a new cross method is introduced.
3) Improved gene crossing pattern
And when the cross problem is considered, the requirements of the lowest repetition rate and the highest coverage rate in the full coverage path planning are met. If each node is traversed only once, the traditional crossing mode which is easy to generate repeated points cannot be relied on. Therefore, the present invention introduces an improved gene crossing method, which considers that a continuous gene is first taken from a parent generation sequence, and then a gene different from the continuous gene is sequentially taken from the parent generation sequence and added into a offspring sequence, as shown in FIG. 4.
4) Introducing a directional cost function
Because the variation mode set by the basic genetic algorithm is to randomly exchange the position sequence of two access nodes, the path cost is increased with a certain probability, and a direction cost function is introduced. After a replaced gene is randomly selected, the directional cost value of other genes to the gene is calculated, and the gene with the minimum cost loss is selected for exchange. The mutation process of the genetic algorithm can be made to advance towards the direction of the optimal solution by introducing the directional cost function.
5) Using dynamic variation rate
In order to avoid the algorithm from falling into the local optimum, after continuous iteration for multiple times, if the population optimum adaptive value is not changed, the variation probability is increased to a certain extent to jump out the local optimum solution.
Wherein M is p Representing the probability of genetic algorithm variation, if the current optimal fitness value of the genetic algorithm is not changed after more than 10 iterations, dynamically improving the probability of variation, and increasing P for each iteration on the original probability a Until the mutation probability is 1, when the optimal solution is updated, M p And the initial value is restored again, and the diversity of the population genes is increased by introducing the dynamic mutation rate, and meanwhile, the influence of the overhigh mutation probability on the reservation of the excellent genes of the individuals is avoided. The flow chart of the improved genetic algorithm is shown in fig. 5, and the termination condition in fig. 5 is the same as that in fig. 3, in order to achieve the initial specified maximum iteration number or optimal value, specifically: (1) completing a preset evolutionary algebra; (2) The best individual in the population has no improvement or the average fitness has substantially no improvement over successive generations.
Finally, the obtained traversal sequence obtained by algorithm training is converted into longitude and latitude coordinates to be input into a program for controlling the unmanned aerial vehicle to fly, so that the overall scheme design of the unmanned aerial vehicle flying full coverage path planning is realized, the overall scheme flow chart is shown in fig. 6, the termination condition in fig. 5 is the same as that in fig. 3, and in order to achieve the initially specified maximum iteration times or optimal value, the method specifically comprises the following steps: (1) completing a preset evolutionary algebra; (2) The best individual in the population has no improvement or the average fitness has substantially no improvement over successive generations.
In the description herein, references to the description of "one embodiment," "an example," "a specific example" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (9)
1. An unmanned aerial vehicle full coverage path planning method based on an improved genetic algorithm is characterized in that: the method comprises the following steps:
s1, determining an overlay type flight range to be carried out by an unmanned aerial vehicle, and scanning a map of the overlay type flight range to obtain basic information;
s2, transforming longitude and latitude coordinates in the basic information obtained by scanning into grid point coordinates by using a grid method, defining the grid height as the maximum value of the height of the grid cataract obstacle, and establishing a three-dimensional model of the full-coverage flight environment of the unmanned aerial vehicle;
s3, respectively introducing a flight path distance cost function and a flight path direction cost function, and optimizing the cruising ability of the unmanned aerial vehicle in full-coverage flight;
s4, improving the genetic algorithm training, which mainly comprises the following steps:
s41, encoding a traversal sequence;
s42, introducing a greedy algorithm to determine an initialization population and calculating the fitness;
s43, adopting a non-playback selection mode when selecting excellent genes so as to improve the replication probability of other genes;
s44, improving a gene crossing mode to ensure that each node in the three-dimensional model only traverses once;
s45, introducing a flight route direction cost function to enable the variation process of the genetic algorithm to advance towards the direction of the optimal solution;
s46, after continuous multiple iterations, judging whether the optimal adaptation value of the population changes, and if the optimal adaptation value of the population does not change, increasing the transformation probability to jump out of the local optimal solution;
and S5, converting the traversal sequence obtained by the training of the improved genetic algorithm into longitude and latitude coordinates, inputting the longitude and latitude coordinates into a control program of the unmanned aerial vehicle, and executing the unmanned aerial vehicle according to the control program to realize the planning of the flight full-coverage path of the unmanned aerial vehicle.
2. The unmanned aerial vehicle full-coverage path planning method based on the improved genetic algorithm as claimed in claim 1, wherein the establishing of the three-dimensional model of the unmanned aerial vehicle full-coverage flight environment comprises the following steps:
s21, dividing the flight environment of the unmanned aerial vehicle into a plurality of cubes to represent the fluctuation of the ground and the positions of obstacles;
s22, abstracting the height of the highest obstacle in the grids into the height of a grid cube, and enabling each grid to be presented in the form of coordinate points (x, y, z);
s23, if the height of the obstacle in the grid is smaller than or equal to the set height h, the obstacle is a point accessible to the unmanned aerial vehicle in a default mode, and if the obstacle with the height larger than h exists in the grid, the obstacle is a point inaccessible to the unmanned aerial vehicle in a default mode.
3. The method for unmanned aerial vehicle full coverage path planning based on improved genetic algorithm as claimed in claim 2, wherein whether the obstacle can be accessed by the unmanned aerial vehicle in step S23 is represented by using a variable o, the variable o is defined according to the following formula:
4. the unmanned aerial vehicle full coverage path planning method based on the improved genetic algorithm, according to claim 1, wherein the flight path distance cost function is defined according to the following formula:
wherein, dist ij Representing the distance cost between two nodes, d ij When the path between the two points has an obstacle, the heights of all the obstacles are stored in a set H, and the unmanned aerial vehicle sets the initial height H from the set 0 Ascending to max (H) in situ, then going to the target point, and finally descending to the initial set height H 0 。
5. The unmanned aerial vehicle full coverage path planning method based on the improved genetic algorithm, according to claim 1, wherein the flight route direction cost function is defined according to the following formula:
wherein, delta theta (x,y) Is the angle difference between the current moving direction and the next moving direction of the unmanned aerial vehicle, delta theta (x,y) The larger the value of (a), the larger the direction of the corresponding unmanned aerial vehicle is changed, the larger the consumption caused by the direction change of the corresponding unmanned aerial vehicle is;
the difference angle delta theta (x,y) Specifically defined according to the following formula:
Δθ＝|θ n -θ p |＝
|atan2(y n -y p ,x n -x p )-atan2(y p -y b ,x p -x b )|
wherein, theta n Is the angle theta between the straight line formed by the next state point and the current node and the abscissa p Forming an angle between the current node and the previous covered node, (x) n ,y n ) As a target position coordinate point, (x) p ,y p ) As the current position coordinate point, (x) b ,y b ) For the coordinate point of the previous position, the more similar the direction of the next movement to the original movement direction, the less the cost is consumed.
6. The unmanned aerial vehicle full coverage path planning method based on the improved genetic algorithm, according to claim 1, is characterized in that the specific manner of determining the initialized population by introducing the greedy algorithm is as follows: after the initial coordinate points are randomly selected, a better traversal sequence is solved by a greedy algorithm to serve as a population gene.
7. The unmanned aerial vehicle full coverage path planning method based on the improved genetic algorithm as claimed in claim 1, wherein the specific way of improving the gene crossing mode is: first, a continuous gene is taken from the father generation sequence, and then the gene different from the continuous gene is taken from the mother generation sequence in sequence and added into the filial generation sequence.
8. The unmanned aerial vehicle full coverage path planning method based on the improved genetic algorithm as claimed in claim 1, wherein the specific manner of introducing the flight route direction cost function in step S45 is as follows: after a replaced gene is randomly selected, the directional cost value of other genes to the gene is calculated, and the gene with the minimum cost loss is selected for exchange.
9. The unmanned aerial vehicle full coverage path planning method based on the improved genetic algorithm as claimed in claim 1, wherein the step S46 of increasing the transformation probability to jump out the local optimal solution is implemented by using a dynamic variation rate, the dynamic variation rate being defined by the following formula:
wherein M is p Representing the probability of genetic algorithm variation, if the current optimal fitness value of the genetic algorithm is not changed after more than 10 iterations, dynamically improving the probability of variation, and increasing P for each iteration on the original probability a Until the mutation probability is 1, when the optimal solution is updated, M p And the initial value is restored again, and the diversity of the population genes is increased by introducing the dynamic mutation rate, and meanwhile, the influence of the overhigh mutation probability on the reservation of the excellent genes of the individuals is avoided.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210826983.9A CN115202394A (en) | 2022-07-13 | 2022-07-13 | Unmanned aerial vehicle full-coverage path planning method based on improved genetic algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210826983.9A CN115202394A (en) | 2022-07-13 | 2022-07-13 | Unmanned aerial vehicle full-coverage path planning method based on improved genetic algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115202394A true CN115202394A (en) | 2022-10-18 |
Family
ID=83580192
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210826983.9A Pending CN115202394A (en) | 2022-07-13 | 2022-07-13 | Unmanned aerial vehicle full-coverage path planning method based on improved genetic algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115202394A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115826591A (en) * | 2023-02-23 | 2023-03-21 | 中国人民解放军海军工程大学 | Multi-target point path planning method based on neural network estimation path cost |
| CN116149374A (en) * | 2023-04-19 | 2023-05-23 | 南京信息工程大学 | Multi-unmanned aerial vehicle coverage path planning method |
| CN116400740A (en) * | 2023-06-06 | 2023-07-07 | 成都时代星光科技有限公司 | Intelligent unmanned aerial vehicle trend processing method, system and medium in full blind area environment |
| CN116820140A (en) * | 2023-08-30 | 2023-09-29 | 兰笺(苏州)科技有限公司 | Path planning method and device for unmanned operation equipment |
-
2022
- 2022-07-13 CN CN202210826983.9A patent/CN115202394A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115826591A (en) * | 2023-02-23 | 2023-03-21 | 中国人民解放军海军工程大学 | Multi-target point path planning method based on neural network estimation path cost |
| CN116149374A (en) * | 2023-04-19 | 2023-05-23 | 南京信息工程大学 | Multi-unmanned aerial vehicle coverage path planning method |
| CN116149374B (en) * | 2023-04-19 | 2023-07-21 | 南京信息工程大学 | Multi-unmanned aerial vehicle coverage path planning method |
| CN116400740A (en) * | 2023-06-06 | 2023-07-07 | 成都时代星光科技有限公司 | Intelligent unmanned aerial vehicle trend processing method, system and medium in full blind area environment |
| CN116400740B (en) * | 2023-06-06 | 2023-09-08 | 成都时代星光科技有限公司 | Intelligent unmanned aerial vehicle trend processing method, system and medium in full blind area environment |
| CN116820140A (en) * | 2023-08-30 | 2023-09-29 | 兰笺(苏州)科技有限公司 | Path planning method and device for unmanned operation equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115202394A (en) | Unmanned aerial vehicle full-coverage path planning method based on improved genetic algorithm | |
| CN110470301B (en) | Unmanned aerial vehicle path planning method under multi-dynamic task target point | |
| CN110544296B (en) | Intelligent planning method for three-dimensional global track of unmanned aerial vehicle in uncertain enemy threat environment | |
| CN110488859B (en) | Unmanned aerial vehicle route planning method based on improved Q-learning algorithm | |
| Obayashi et al. | Multi-objective design exploration for aerodynamic configurations | |
| CN112082552A (en) | Unmanned aerial vehicle flight path planning method based on improved hybrid particle swarm optimization algorithm | |
| CN107807665B (en) | Unmanned aerial vehicle formation detection task cooperative allocation method and device | |
| CN109945881A (en) | A kind of method for planning path for mobile robot of ant group algorithm | |
| CN108388250B (en) | Water surface unmanned ship path planning method based on self-adaptive cuckoo search algorithm | |
| CN112462803B (en) | Unmanned aerial vehicle path planning method based on improved NSGA-II | |
| CN107229287A (en) | A kind of unmanned plane global path planning method based on Genetic Ant algorithm | |
| CN109931943B (en) | Unmanned ship global path planning method and electronic equipment | |
| CN110986960B (en) | Unmanned aerial vehicle flight path planning method based on improved clustering algorithm | |
| CN113671985A (en) | Staged multi-base unmanned aerial vehicle task allocation and flight path planning method | |
| CN109269502A (en) | A kind of no-manned plane three-dimensional Route planner based on more stragetic innovation particle swarm algorithms | |
| CN111813144B (en) | Multi-unmanned aerial vehicle collaborative route planning method based on improved flocks of sheep algorithm | |
| CN113848919A (en) | Ant colony algorithm-based indoor AGV path planning method | |
| CN112000126A (en) | Whale algorithm-based multi-unmanned-aerial-vehicle collaborative searching multi-dynamic-target method | |
| Zhao et al. | Learning transformer-based cooperation for networked traffic signal control | |
| CN114815801A (en) | Adaptive environment path planning method based on strategy-value network and MCTS | |
| CN112034880A (en) | Novel multi-unmanned aerial vehicle collaborative route planning method | |
| CN115185297A (en) | Unmanned aerial vehicle cluster distributed cooperative target searching method | |
| CN115951682A (en) | Constraint four-target AUV global path planning method under condition of considering ocean current existence | |
| CN114399045A (en) | Flower pollination optimization method based on nonlinear cross-generation differential evolution and implementation system | |
| CN114237282A (en) | Intelligent unmanned aerial vehicle flight path planning method for intelligent industrial park monitoring |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |