CN113495573A - Ground unmanned platform path planning method based on improved global drosophila algorithm - Google Patents
Ground unmanned platform path planning method based on improved global drosophila algorithm Download PDFInfo
- Publication number
- CN113495573A CN113495573A CN202110875618.2A CN202110875618A CN113495573A CN 113495573 A CN113495573 A CN 113495573A CN 202110875618 A CN202110875618 A CN 202110875618A CN 113495573 A CN113495573 A CN 113495573A
- Authority
- CN
- China
- Prior art keywords
- individual
- drosophila
- unmanned platform
- fruit fly
- ground unmanned
- 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
Abstract
The invention discloses a ground unmanned platform path planning method based on an improved global drosophila algorithm, which comprises the following steps: the method comprises the steps of obtaining an objective function of ground unmanned platform path planning, randomly generating individual fruit fly positions within a set search range, substituting each individual fruit fly position into the objective function to obtain an adaptability value of each individual fruit fly, determining that fruit fly populations gather to the position of the optimal individual fruit fly according to the adaptability value, carrying out flight search on common fruit flies according to a self-adaptive flight radius, carrying out flight search on elaiopsis pungens according to the flight radius, and determining the optimal path of the ground unmanned platform. The method can remarkably improve the effect of planning the path of the ground unmanned platform.
Description
Technical Field
The invention relates to the technical field of path planning, in particular to a ground unmanned platform path planning method based on an improved global drosophila algorithm.
Background
The ground unmanned platform is an important class of ground professional vehicles, and is increasingly widely applied to the fields of industry, military affairs, traffic, logistics, service and the like. For many ground unmanned platforms, the ability to autonomously move is a prerequisite for their performance of a prescribed task, and to be able to autonomously move, the ability to plan a movement path is necessary. That is, path planning is one of the keys of ground unmanned platform technology. The path planning of the ground unmanned platform means that after sensing the surrounding environment, an optimal moving path from a starting point to a terminal point can be planned by self, and the optimal path can meet the requirements of shortest moving path, shortest time consumption, minimum energy consumption and the like. In other words, the path planning problem can be regarded as a complex optimization problem with constraints.
The drosophila optimization algorithm is a novel bionic optimization algorithm for simulating foraging behavior of drosophila, and can be applied to the path planning problem of the ground unmanned platform. However, the drosophila optimization algorithm has the defects of non-uniform solution generation mode, fixed individual flight radius of drosophila, easy falling into local optimum and the like, and often cannot achieve ideal path planning effect when the ground unmanned platform path planning is carried out.
1. The candidate solution is obtained by the reciprocal of the distance between the position of the drosophila individual and the origin of coordinates, and the distance cannot be negative, so that the candidate solution cannot appear in a negative value range, the uniformity of the solution is greatly reduced, and the solution is extremely easy to converge on the origin of coordinates finally;
2. the flight radius of the individual fruit flies is set to be a constant at the beginning, the flight radius cannot change along with the increase of the iteration times, and if the constant is set unreasonably, the algorithm is easy to fall into local optimization or the searching capacity of the algorithm is reduced;
3. in real fruit fly foraging, individual flies jump within a small area near the food in the hope of finding a more precise location of the food, and this real foraging behavior is not simulated in the fruit fly algorithm.
The above 3 disadvantages result in that the optimal path planning effect cannot be achieved when the drosophila algorithm is adopted to perform the path planning of the ground unmanned platform.
Disclosure of Invention
The embodiment of the invention provides a ground unmanned platform path planning method based on an improved global drosophila algorithm, which comprises the following steps:
acquiring a target function of the ground unmanned platform path planning;
randomly generating individual positions of the drosophila within a set search range;
substituting the position of each individual fruit fly into a target function to obtain the fitness value of each individual fruit fly;
according to the fitness value, determining that the fruit fly population is gathered to the position where the optimal fruit fly individual is located;
carrying out flight search on the common fruit flies according to the self-adaptive flight radius, and carrying out flight search on the elaeagnus pungens according to the flight radius;
and determining the optimal path of the ground unmanned platform.
Further, obtaining an objective function of the ground unmanned platform path planning includes:
modeling a ground unmanned platform working environment to obtain a moving area map;
performing rasterization processing on the moving area map;
and determining an objective function based on the moving area map after the rasterization processing.
Further, the objective function includes: the objective function with the shortest moving path, or the objective function with the shortest consumed time, or the objective function with the least consumed energy.
Further, parameter settings are included, including Popsize, maximum, SR, frmax, γ, δ, wherein,
popsize represents the number of individual Drosophila;
maximer represents the condition for iteration to stop;
SR represents a population search radius;
frmax represents the upper limit of the individual flying radius of the fruit fly;
gamma represents the percentage of the number of Elite fruit flies in the fruit fly population;
the value of gamma is generally 5 to 10 percent;
the value of delta is within the range of 5-10.
6. Further, the set search range is a region of the range of the positive and negative population search radii SR, and the population search radii SR are determined according to the constraint conditions of the objective function.
Further, randomly generating the individual positions of the drosophila within the set search range comprises:
Xi＝rand(-SR,SR)
wherein, XiIndicating individual positions of drosophila.
Further, the fitness value of each individual drosophila includes:
Smelli＝function(Xi)
Smellithe fitness value of each individual drosophila was expressed.
Further, according to the fitness value, determining that the fruit fly population is gathered to the position where the optimal fruit fly individual is located comprises the following steps:
recording the fitness value and the position of the optimal drosophila individual in the current iteration:
[bestSmell,Xb]＝max(Smelli)
wherein, XbThe position of the optimal fruit fly individual is shown, and bestsmlell shows the fitness value of the optimal fruit fly individual;
recording the largest bestSmell in the previous iteration, and then gathering the fruit fly population to the position of the optimal fruit fly individual obtained in the current iteration;
wherein, X \uaxisAnd (4) representing the aggregation coordinates of the positions of the individual drosophila.
Further, the formula for searching the flying of the common fruit flies according to the self-adaptive flying radius comprises the following steps:
wherein fr represents the flight radius of the common fruit fly, iter represents the current iteration number, and XiIndicating the new position of the fruit fly.
Further, the flight search formula of the elaiopsis elite flies according to the flight radius comprises the following steps:
wherein ffr represents the flying radius of Elaphanita elite, XjIndicating the new location of the elaeagnus elite flies.
The embodiment of the invention provides a ground unmanned platform path planning method based on an improved global drosophila algorithm, which has the following beneficial effects compared with the prior art:
1. will improve S in the Global Drosophila AlgorithmiBecome Xi. By this improvement, uniformity of the way the solution is generated is achieved.
2. The individual fixed flight radius of the drosophila is changed into the self-adaptive flight radius, through the improvement, the balance of the searching capability of the algorithm in the early and later stages is realized, the algorithm is ensured to be capable of carrying out global search in the early stage, and the algorithm is capable of carrying out local search in the later stage.
3. A small amount of Elaphanita elite flies are introduced and kept unchanged in initial flight radius, and through the improvement, the algorithm can search with a larger flight radius in the later period, so that the algorithm is ensured to have the capability of jumping out of local optimum.
Drawings
Fig. 1 is a flow chart of path planning of an improved global drosophila algorithm in a ground unmanned platform path planning method based on the improved global drosophila algorithm provided by the embodiment of the invention;
fig. 2 is a moving path diagram of a drosophila algorithm and an improved global drosophila algorithm in the ground unmanned platform path planning method based on the improved global drosophila algorithm provided by the embodiment of the invention, wherein Start and End respectively represent a Start point and an End point of a moving path of the ground unmanned platform, and black squares represent obstacles;
fig. 3 is an iterative process curve in the ground unmanned platform path planning method based on the improved global drosophila algorithm according to the embodiment of the present 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.
Referring to fig. 1 to 3, an embodiment of the present invention provides a ground unmanned platform path planning method based on an improved global drosophila algorithm, including:
and acquiring an objective function of the ground unmanned platform path planning.
And randomly generating individual positions of the drosophila within a set search range.
Substituting the position of each individual fruit fly into a target function to obtain the fitness value of each individual fruit fly;
and determining that the fruit fly population is gathered to the position of the optimal fruit fly individual according to the fitness value.
And carrying out flight search on the common fruit flies according to the self-adaptive flight radius, and carrying out flight search on the elaeagnus pungens according to the flight radius.
And determining the optimal path of the ground unmanned platform.
The following are specific examples:
the Fruit Fly algorithm (FOA) mainly comprises the following steps:
(1) and setting related parameters. The method mainly comprises the following steps: size of Drosophila population (i.e., number of Drosophila individuals) Popsize; maximum number of iterations (i.e., a condition under which the iteration stops) maximer; a population search radius SR; the individual flying radius fr of the fruit flies; an initial position radius LR; the initial center positions (X _ axis, Y _ axis) of the population are randomly initialized between (-LR, LR).
(2) A search is started. Each individual fruit fly randomly flies around to search for food according to the flying radius fr within the sight range of the individual fruit fly.
Wherein, Xi,YiAnd the coordinates of the position of the individual drosophila are shown.
(3) Calculating a food concentration determination value SiThe value is the reciprocal of the distance value between the position of the individual fruit fly and the origin of coordinates.
Wherein Dist represents the distance between the position of the individual drosophila and the origin of coordinates.
(4) Calculating the fitness value Smell of individual fruit fliesi. The value is obtained by mixing SiAnd substituting the fitness function into the fitness function to obtain the fitness function.
Smelli＝function(Si) (3)
(5) Information is recorded. Record Smell in the current iterationiThe fitness value and the position coordinate of the largest individual fruit fly;
[bestSmell,Xb,Yb]＝max(Smelli) (4)
wherein bestsell and Xb,YbRespectively representing Smell in the current iterationiThe fitness value of the largest individual fruit fly and the position coordinate of the individual fruit fly.
(6) And (4) aggregating the population. Recording the largest bestSmell in the previous iteration, and then gathering the fruit fly population to the position of the optimal fruit fly individual obtained in the current iteration;
(7) and (5) repeatedly executing the steps (2) to (6), stopping the algorithm after the maximum iteration number maxim is reached, and outputting an optimal result.
The foregoing is the basic steps of an FOA, and an Improved Global drosophila Optimization Algorithm (IGFOA) is proposed and used for ground unmanned platform path planning for several problems existing in the FOA, where the flow of the IGFOA-based ground unmanned platform path planning method is shown in fig. 1, and the specific steps are as follows:
(1) and modeling the ground unmanned platform working environment to obtain a moving area map and performing grid processing on the map.
(2) Establishing an objective function funtion (which can be set to be shortest in moving path, shortest in time consumption, least in energy consumption and the like according to actual needs) of the ground unmanned platform path planning, and simultaneously setting corresponding constraint conditions and the number D of key nodes of the path.
(3) And setting parameters, which mainly comprises: size of Drosophila population (i.e., number of Drosophila individuals) Popsize; maximum number of iterations (i.e., a condition under which the iteration stops) maximer; the population search radius SR (obtained from the constraint); the upper limit frmax of the individual flying radius of the fruit flies; the number of Elite fruit flies is the percentage gamma of the number of fruit fly populations.
It should be noted that, through test and comparison, the value of γ is usually preferably 5% to 10%.
(4) Randomly generated location of individual Drosophila within the search range (-SR, SR):
Xi＝rand(-SR,SR) (6)
wherein, XiIndicating individual positions of drosophila.
(5) Placing each individual fruit fly at the position XiSubstituting into the fitness function to obtain the fitness value of each individual fruit fly:
Smelli＝function(Xi) (7)
Smellithe fitness value of each individual drosophila was expressed.
In addition, X isiIs in the search range (-SR, SR)) The internal random generation is obtained, which shows that the internal random generation is uniformly distributed in positive and negative value domains, and is used for S in the FOA step (4)iReplacement is carried out, and the method is more reasonable.
(6) Recording the fitness value and the position of the optimal drosophila individual in the current iteration:
[bestSmell,Xb]＝max(Smelli) (8)
wherein, XbThe position of the optimal fruit fly individual is shown, and bestsmlell shows the fitness value of the optimal fruit fly individual.
(7) Recording the largest bestSmell in the previous iteration, and then gathering the fruit fly population to the position of the optimal fruit fly individual obtained in the current iteration;
wherein, X \uaxisAnd (4) representing the aggregation coordinates of the positions of the individual drosophila.
(8) The common fruit flies and the Elaphe odorata flies respectively carry out flight search according to the self-adaptive flight radius shown in the formula (10) and the flight radius shown in the formula (11):
wherein fr represents the flight radius of the common fruit fly, iter represents the current iteration number, and XiIndicating the new position of the fruit fly.
Wherein ffr represents the flying radius of Elaphanita elite, XjIndicating the new location of the elaeagnus elite flies.
It should be noted that, for a common fruit fly, the calculation formula of the adaptive flight radius fr in the formula (10) is a modification of the gaussian-plus-square distribution, where frmax determines the upper limit height of the distribution, maximer/δ determines the amplitude of the distribution, and after test comparison, the value of δ is preferably in the range of 5-10. The slope of fr is changed according to the principle that the slope is reduced firstly and then is reduced secondly, so that the drosophila individuals can be searched globally at the initial stage and searched locally at the later stage, and the searching precision is improved; for Elaphanita elite fruit flies, the value ffr in the formula (11) is the upper limit frmax of the flight radius, and the upper limit frmax is not affected by the iteration number, so that the algorithm has the capability of jumping out of the local optimum in the later period.
(9) And (5) repeating the steps (5) to (8), stopping the algorithm after the maximum iteration number Maxiter is reached, and outputting the optimal moving path of the ground unmanned platform.
And (3) establishing a 10 multiplied by 10 grid matrix for the ground unmanned platform to move by taking MATLAB as a simulation platform, and analyzing the FOA method and the IGFOA method by taking the shortest moving distance as a target. The parameters in the FOA algorithm are: popsize ═ 30, maximer ═ 100, SR ═ 10, fr ═ SR/10, LR ═ SR; the parameters in the IGFOA algorithm are: popsize ═ 30, maximer ═ 100, SR ═ 10; frmax is SR/5, γ is 5%, δ is 8. The simulation environment and the movement paths obtained by the two methods are shown in fig. 2 (Start and End represent the Start point and the End point of the movement path of the ground unmanned platform, respectively, and the black square represents an obstacle), and fig. 3 is an iterative process curve.
It can be seen from fig. 2 that the ground unmanned platform moving path obtained by the FOA is longer than that of the IGFOA, the path is roundabout, and the path obtained by the IGFOA is reasonable. Further analyzing the results in fig. 2 and fig. 3, it can be seen that when the FOA algorithm is used, the shortest path length obtained after the algorithm iterates 31 times is 19.301; when the IGFOA algorithm is adopted, the shortest path length obtained by the algorithm after iteration is carried out for 19 times is 12.296, and it can be seen that the IGFOA algorithm designed in the text has higher convergence speed and convergence accuracy, and the FOA is trapped in a local optimum condition. Simulation results show that in the same environment, IGFOA realizes the uniform distribution of generated solutions, balances the front and back search capability of the algorithm, enhances the local optimal jumping-out capability, obtains the optimal moving path from the starting point to the end point of the ground unmanned platform, and verifies the effectiveness of the algorithm.
Although the embodiments of the present invention have been disclosed in the foregoing for illustrative purposes, those skilled in the art will appreciate that various modifications, additions and substitutions are possible, without departing from the scope and spirit of the invention as disclosed in the accompanying drawings.
Claims (10)
1. A ground unmanned platform path planning method based on an improved global drosophila algorithm is characterized by comprising the following steps:
acquiring a target function of the ground unmanned platform path planning;
randomly generating individual positions of the drosophila within a set search range;
substituting the position of each individual fruit fly into a target function to obtain the fitness value of each individual fruit fly;
according to the fitness value, determining that the fruit fly population is gathered to the position where the optimal fruit fly individual is located;
carrying out flight search on the common fruit flies according to the self-adaptive flight radius, and carrying out flight search on the elaeagnus pungens according to the flight radius;
and determining the optimal path of the ground unmanned platform.
2. The ground unmanned platform path planning method based on the improved global drosophila algorithm as claimed in claim 1, wherein the obtaining of the objective function of the ground unmanned platform path planning comprises:
modeling a ground unmanned platform working environment to obtain a moving area map;
performing rasterization processing on the moving area map;
and determining an objective function based on the moving area map after the rasterization processing.
3. The ground unmanned platform path planning method based on the improved global drosophila algorithm as claimed in claim 1, wherein the objective function comprises: the objective function with the shortest moving path, or the objective function with the shortest consumed time, or the objective function with the least consumed energy.
4. The ground unmanned platform path planning method based on the improved global drosophila algorithm as claimed in claim 1, further comprising parameter settings, wherein the parameters comprise Popsize, Maxiter, SR, frmax, γ, δ, and wherein,
popsize represents the number of individual Drosophila;
maximer represents the condition for iteration to stop;
SR represents a population search radius;
frmax represents the upper limit of the individual flying radius of the fruit fly;
gamma represents the percentage of the number of Elite fruit flies in the fruit fly population;
the value of gamma is generally 5 to 10 percent;
the value of delta is within the range of 5-10.
5. The ground unmanned platform path planning method based on the improved global drosophila algorithm as claimed in claim 1, wherein the set search range is a region with a range of positive and negative population search radii SR, namely the search range is-SR to SR, and the population search radius SR is determined according to the constraint condition of the objective function.
6. The ground unmanned platform path planning method based on the improved global drosophila algorithm as claimed in claim 1, wherein the randomly generating individual drosophila positions within the set search range comprises:
Xi＝rand(-SR,SR)
wherein, XiIndicating individual positions of drosophila.
7. The ground unmanned platform path planning method based on the improved global drosophila algorithm as claimed in claim 6, wherein the fitness value of each drosophila individual comprises:
Smelli＝function(Xi)
Smellithe fitness value of each individual drosophila was expressed.
8. The ground unmanned platform path planning method based on the improved global drosophila algorithm of claim 7, wherein the determining that the drosophila population is gathered to the position where the optimal drosophila individual is located according to the fitness value comprises:
recording the fitness value and the position of the optimal drosophila individual in the current iteration:
[bestSmell,Xb]＝max(Smelli)
wherein, XbThe position of the optimal fruit fly individual is shown, and bestsmlell shows the fitness value of the optimal fruit fly individual;
recording the largest bestSmell in the previous iteration, and then gathering the fruit fly population to the position of the optimal fruit fly individual obtained in the current iteration;
wherein, X_axisAnd (4) representing the aggregation coordinates of the positions of the individual drosophila.
9. The ground unmanned platform path planning method based on the improved global drosophila algorithm as claimed in claim 8, wherein the flying search formula of the common drosophila according to the adaptive flying radius comprises:
wherein fr represents the flight radius of the common fruit fly, iter represents the current iteration number, and XiIndicating the new position of the fruit fly.
10. The ground unmanned platform path planning method based on the improved global drosophila algorithm of claim 8, wherein the flying search formula of the elargosophila elite according to the flying radius comprises:
wherein ffr represents the flying radius of Elaphanita elite, XjIndicating the new location of the elaeagnus elite flies.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110875618.2A CN113495573A (en) | 2021-07-30 | 2021-07-30 | Ground unmanned platform path planning method based on improved global drosophila algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110875618.2A CN113495573A (en) | 2021-07-30 | 2021-07-30 | Ground unmanned platform path planning method based on improved global drosophila algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113495573A true CN113495573A (en) | 2021-10-12 |
Family
ID=77996851
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110875618.2A Pending CN113495573A (en) | 2021-07-30 | 2021-07-30 | Ground unmanned platform path planning method based on improved global drosophila algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113495573A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110802601A (en) * | 2019-11-29 | 2020-02-18 | 北京理工大学 | Robot path planning method based on fruit fly optimization algorithm |
| CN110986958A (en) * | 2019-12-24 | 2020-04-10 | 北京工业大学 | Multi-unmanned aerial vehicle collaborative path planning method based on multi-population collaborative drosophila optimization |
| CN113031578A (en) * | 2019-12-24 | 2021-06-25 | 牟茹月 | Sweeping robot sweeping walking path planning method based on genetic algorithm |
-
2021
- 2021-07-30 CN CN202110875618.2A patent/CN113495573A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110802601A (en) * | 2019-11-29 | 2020-02-18 | 北京理工大学 | Robot path planning method based on fruit fly optimization algorithm |
| CN110986958A (en) * | 2019-12-24 | 2020-04-10 | 北京工业大学 | Multi-unmanned aerial vehicle collaborative path planning method based on multi-population collaborative drosophila optimization |
| CN113031578A (en) * | 2019-12-24 | 2021-06-25 | 牟茹月 | Sweeping robot sweeping walking path planning method based on genetic algorithm |
Non-Patent Citations (4)
| Title |
|---|
| 孔卫东等: "改进果蝇算法的爬行机器人足端轨迹规划", 《合肥工业大学学报(自然科学版)》 * |
| 毛正阳等: "基于果蝇优化算法的月球车全局路径规划", 《电子设计工程》 * |
| 毛正阳等: "应用改进果蝇优化算法的月面巡视器路径规划", 《中国空间科学技术》 * |
| 程小洪: "基于改进果蝇优化算法的汽车饰件焊接路径规划", 《中国优秀博硕士学位论文全文数据库(硕士) 工程科技Ⅱ辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110608743B (en) | Multi-unmanned aerial vehicle collaborative route planning method based on multi-population chaotic grayling algorithm | |
| CN107169608B (en) | Distribution method and device for multiple unmanned aerial vehicles to execute multiple tasks | |
| CN107103164B (en) | Distribution method and device for unmanned aerial vehicle to execute multiple tasks | |
| CN106529674B (en) | Multiple no-manned plane cooperates with mine to target assignment method | |
| Stonedahl et al. | Finding forms of flocking: Evolutionary search in abm parameter-spaces | |
| Jain et al. | MVO-based path planning scheme with coordination of UAVs in 3-D environment | |
| CN110489340B (en) | Game map balance testing method, device, equipment and storage medium | |
| CN108211362B (en) | Non-player character combat strategy learning method based on deep Q learning network | |
| CN102901500A (en) | Aircraft optimal path determination method based on mixed probability A star and agent | |
| CN107392388A (en) | A kind of method for planning no-manned plane three-dimensional flight path using artificial fish-swarm algorithm is improved | |
| Stephenson et al. | Procedural generation of complex stable structures for angry birds levels | |
| Lei et al. | Improved artificial bee colony algorithm and its application in data clustering | |
| CN109541960B (en) | System and method for aircraft digital battlefield confrontation | |
| CN112469050B (en) | WSN three-dimensional coverage enhancement method based on improved wolf optimizer | |
| CN109269502A (en) | A kind of no-manned plane three-dimensional Route planner based on more stragetic innovation particle swarm algorithms | |
| CN114415663A (en) | Path planning method and system based on deep reinforcement learning | |
| Virtanen et al. | Decision theoretical approach to pilot simulation | |
| CN112329327A (en) | Hardware-aware liquid state machine network generation method and system | |
| CN111832135A (en) | Pressure container structure optimization method based on improved Harris eagle optimization algorithm | |
| CN115420294A (en) | Unmanned aerial vehicle path planning method and system based on improved artificial bee colony algorithm | |
| CN114611801A (en) | Traveler problem solving method based on improved whale optimization algorithm | |
| CN116225066A (en) | Unmanned aerial vehicle path optimization method based on chaotic mapping pely optimization algorithm | |
| CN112666981A (en) | Unmanned aerial vehicle cluster dynamic route planning method based on dynamic group learning of original pigeon group | |
| CN115983130A (en) | Global optimal solution searching method based on improved particle swarm optimization algorithm | |
| Hu et al. | LCAHA: A hybrid artificial hummingbird algorithm with multi-strategy for engineering applications |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211012 |