CN106979784A - Non-linear trajectory planning based on mixing dove group's algorithm - Google Patents
Non-linear trajectory planning based on mixing dove group's algorithm Download PDFInfo
- Publication number
- CN106979784A CN106979784A CN201710155141.4A CN201710155141A CN106979784A CN 106979784 A CN106979784 A CN 106979784A CN 201710155141 A CN201710155141 A CN 201710155141A CN 106979784 A CN106979784 A CN 106979784A
- Authority
- CN
- China
- Prior art keywords
- algorithm
- population
- matrix
- mixing
- threat
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Abstract
The invention discloses a kind of non-linear path planning method based on mixing dove group's algorithm, belong to single unmanned air vehicle technique field.Including following content：Determine flight range and barrier；Initialize various parameters；Population initial state value is generated with random interval method；In map and compass operator, the thought being combined using particle cluster algorithm self-teaching and social learning, with inertial matrix and with formula of the inertial matrix in self and social learning's factor of varies with cosine, the position of Population Regeneration and speed；Reach after the circulation upper limit, into terrestrial reference operator, dove group is ranked up by fitness value, and records center position；The population quantity of this iteration is calculated using the damping matrix in varies with cosine；More new position and speed；Export optimal trajectory.The invention improves the precision of algorithm, obtains optimal solution or the closely suboptimal solution of optimal solution, while improving the stability of algorithm and the speed of trajectory planning.
Description
Technical field
The present invention relates to a kind of non-linear path planning method based on mixing dove group's algorithm, belong to unmanned aerial vehicle flight path planning
Technical field.
Background technology
Unmanned plane（Unmanned Aerial Vehicle,UAV）It is the weaponry of the current research of people both at home and abroad, tool
There are the functions such as automatic lifting stick, automatic Pilot, self-navigation, be adapted to replace people to complete special in the environment of dangerous, the severe and limit
Fixed work and task, then suffer from being widely applied in fields such as military affairs, business, Aero-Space.Wherein trajectory planning is
One of core in unmanned plane task grouping.The purpose of trajectory planning is under conditions of restriction（Avoid threatening and no-fly
Area, fuel oil is most saved, shortest path etc.）, the optimal or closely optimal suboptimum that selection one reaches task place from starting point
Path.At present, existing more path planning method, can substantially be divided into two major classes：
1st, deterministic parameters calculation method method.Such as A* algorithms：Heuristic search A* algorithm advantages are convergences compared with quick with computing by force
Deng, have the disadvantage that it can be only generated a flight path, it is unsuitable to need the mission requirements of a plurality of reference track；
2nd, stochastic search optimization algorithm, including ant group algorithm, genetic algorithm, particle cluster algorithm etc..This kind of algorithm is simulation nature
The material change procedure on boundary, and biological activity and evolutionary process.Ant group algorithm is by the information interchange of ant and cooperated
Carry out realizing route search, with dynamic characteristic, compare the polytropy for adapting to threatening environment；Genetic algorithm be based on natural selection and
The searching method of gene genetic principle, is not constrained by search space, it is not required that the continuity and derivative of majorized function are present
Etc. condition, and there is concurrency, be relatively adapted to the trajectory planning problem of much complex constraint and fuzzy message.Particle cluster algorithm
It is by cooperating between individual, while it is optimal that search is completed using the self-teaching of organism and the thought of social learning
Solution, the algorithm implements very simple, also there is preferable of overall importance and locality, therefore in path planning method by widely
Use.Although possessing the intelligent algorithms such as the genetic algorithm and ant group algorithm of random feature generally has preferable drawn game of overall importance
Portion's property, can also overcome the limitation of deterministic algorithm to generate multiple solutions, but amount of calculation is larger, and convergence rate is slower, it is difficult to meet
Engineering is actually needed
In order to overcome the shortcoming of the above method, constantly there are some new natural heuristics to propose.Such as Duan H, et al. propose
A kind of new Swarm Intelligence Algorithm --- dove group's algorithm carries out the trajectory planning of unmanned plane, referring to Duan H, Qiao P.
Pigeon-inspired optimization: a new swarm intelligence optimizer for air
robot path planning[J]. International Journal of Intelligent Computing and
Cybernetics, 2014, 7(1):24-37.Zhang B et al. carry out the three of unmanned plane with dove group's algorithm of predation escape
Path planning is tieed up, referring to Zhang B, Duan H. Predator-Prey Pigeon-Inspired Optimization
for UAV Three-Dimensional Path Planning[M]// Advances in Swarm Intelligence.
2014:96-105.Dove group's algorithm is easily realized, and most significant advantage is fast convergence rate, is relatively adapted to engineer applied.But
There is also the shortcoming for being absorbed in local optimum for basic dove group algorithm.
The content of the invention
The purpose of the present invention is slow and the problem of be easily absorbed in local optimum to solve unmanned aerial vehicle flight path planning speed, it is proposed that
A kind of non-linear path planning method based on mixing dove group's algorithm.
The purpose of the present invention is achieved through the following technical solutions：
1）The two-dimentional planning space that UAV flight environment of vehicle is planned is expressed as geometric space region：
；
2）The primary condition for setting unmanned aerial vehicle flight path to plan, including starting point, target point, threat distribution.By in aerial mission
Threat modeling：The threat indexes such as the geographical position of threat, coverage, threat level are converted into discretization planning space
Matrix information；
3）The various parameters of initialization algorithm, such as population quantity, map and compass operator maximum iteration, terrestrial reference operator
Maximum iteration etc..The abscissa in flight range is subjected to equidistant discretization simultaneously, that is, determines flight track point
Abscissa matrix；
4）The position of initial population is generated with random interval method, and randomly generates the initial position of dove group；
5）Pass through object function（WhereinFor different cost functions,For the weight coefficient of each cost function,For the number of cost function）The cost value in every initial air route is calculated, and records out initial global optimum air route and each
The optimal air line of individual；
6）Circulate, with reference to self-teaching in particle cluster algorithm and the thought of social learning, pass through into map and compass operator
The position of below equation Population Regeneration and speed：
,
Wherein,Value in inertial matrix, matrix byProduce；Self-teaching
The factor；The team learning factor；For 0 to 1 it
Between random number,For current iteration number of times；The maximum iteration of map and compass operator,ForBar air route；
For individual optimal trajectory；For current global optimum's flight path；
7）The cost value of every flight path is calculated, and records global optimum's flight path of this iteration and the optimal trajectory of each individual；
8）Judge whether iterations reaches the maximum iteration of the operator, if reaching, end loop, calculated into terrestrial reference
Son, otherwise repeat step 6）To step 8）；
9）It is every air route by being ranked up in proper order from small to large according to the cost value of object function into terrestrial reference operator；
10）Use formula：Calculate the population quantity of this iteration；WhereinIt is damping matrix,
Value in matrix（Scope is between 0.8 to 1）By formulaProduce；For population number
Amount；For current iteration number of times；It is the maximum iteration of terrestrial reference operator；
11）Utilize formula：The center of the population of this iteration is calculated, whereinFor the center of this iteration；It isThe fitness value of individual, here,ForThe target function value of individual；For current iteration number of times；
12）Utilize formula：, the position of Population Regeneration.Wherein
For the random number between 0 to 1；
13）The cost value of every flight path is calculated, and records global optimum's flight path of this iteration；
14）Judge whether iterations reaches the maximum iteration of operator, reach, terminate the circulation, otherwise repeat step 9）
To step 14）；
15）Export optimal trajectory.
Brief description of the drawings
Fig. 1 is the FB(flow block) of experimental procedure of the present invention.
Fig. 2 is the exemplary plot that unmanned plane threat radar is calculated.
Fig. 3 is the route map planned for unmanned plane.
Fig. 4 is the change curve of fitness value during trajectory planning.
Embodiment
With reference to embodiment, the present invention is described in further detail：
1）The two-dimentional planning space that UAV flight environment of vehicle is planned is expressed as geometric space region,
And determine the origin coordinates point start of flight（startx,starty）, target point target（targetx,targety）；
2）By the threat modeling in aerial mission：The threat indexes such as the geographical position of threat, coverage, threat level are turned
The matrix information of discretization planning space is turned to, threat radar is primarily referred to as here, with oneThe matrix that row four is arranged is stored
Threat information, whereinThe number threatened is represented, first row represents the abscissa threatened, and secondary series represents the ordinate threatened,
3rd row represent the radius threatened, and the 4th row represent the grade threatened；
3）The various parameters of initialization algorithm, such as population quantity, map and compass operator maximum iteration, terrestrial reference operator
Maximum iteration etc..The abscissa in flight range is subjected to equidistant discretization simultaneously, that is, determines flight track point
Abscissa matrix.The number of track points is also the Spatial Dimension of planning；
4）The position of initial population is generated with random interval method, i.e., is divided into the ordinate of flight rangeIndividual minizone, it is raw
Into oneMatrix, whereinEvery a line be allEach ginseng of individual minizone random alignment, then each individual
Number is generated at random in minizone respectively.So initial individuals will be evenly distributed in whole solution space, it is ensured that initial
More rich pattern is contained in colony, enhances the possibility that search converges on globe optimum；
5）Pass through object function（WhereinFor different cost functions,For the power system of each cost function
Number, and；For the number of cost function）Calculate the cost value in every initial air route.Each cost function contains
Justice and calculation formula are as follows：
：Cost is threatened, if the flight path section of flight is not in threat range, then this sectionIt is zero；If the boat of flight
Mark section is in threat range, in order to simplify calculating, and each flight path section is equally divided into ten points by we, and such as Fig. 2, then compartment of terrain take
Wherein five points are calculated, then simplified threat calculation formula carries out as follows：
。
WhereinFor flight path sectionLength（I.e.Individual track points are arrivedThe length of track points）；For correspondence threaten etc.
Level；For the number of threat；It is 1/10 point to the of flight path sectionThe distance at threat center；
：Fuel penalty, intermediate fuel oil cost of the present invention is directly influenceed by path length, here with relative path length come table
Show, calculation formula is as follows：, whereinFor track points number；
：Hard-over cost, noteIf maximum allowable corner is, then corner is worked asWhen,；OtherwiseFor a very big cost value；
：Minimum flight path length cost.Remember that minimum flight path is, theSection flight path length be, then whenWhen,, otherwise；
6）Pass through fitness valueFind out and record initial global optimum air routeWith each individual optimal air line, fitness value is bigger herein, and flight path is more excellent.Fitness calculation formula is as follows：.Wherein
Represent theThe flight path cost value of bar flight path, i.e. step 5）In object function,It is the constant of a very little；
7）It is optimal using individual in map and compass operatorAnd global optimum, pass through below equation Population Regeneration
Position and speed：
Wherein,For inertial matrix, value in matrix byProduce；Self-teaching
The factor；Social learning's factor；For 0 to 1 it
Between random number,For current iteration number of times；The maximum iteration of map and compass operator,ForBar air route；
For individual optimal trajectory；For individual optimal trajectory；
8）The speed after updating and position are judged whether in the range of prior agreement, if so, into next step；Otherwise in regulation
A value is randomly generated in the range of ground and is assigned to it；
9）In order that UAV does not fly towards starting point direction, strictly to controlIf be unsatisfactory for, calculated with below equation, whereinIt must set up,For the random number between 0 to 1,
10）Found out by fitness value and record global optimum's flight path and individual optimal trajectory；
11）Judge whether to reach maximum iteration, if so, into terrestrial reference operator, otherwise repeating step 7）To step
11）；
12）Into terrestrial reference operator, calculate ideal adaptation angle value and individual is ranked up, fitness value is bigger（That is target function value
It is smaller）Position is more forward；
13）Utilize formula：The population quantity of this iteration is calculated, whereinIt is damping moment
Value in battle array, matrix（Scope is between 0.8 to 1）By formulaProduce,For population
Quantity,For current iteration number of times,It is the maximum iteration of terrestrial reference operator；
14）Utilize formula：The center of the population of this iteration is calculated, whereinFor
The center of this iteration,It isThe fitness value of individual, here,
ForThe target function value of individual, is current iteration number of times；
15）Utilize formula：, the position of Population Regeneration.WhereinFor
Random number between 0 to 1；
16）Perform step 8）With step 9）；
17）Judge whether to reach maximum iteration, if so, end loop, into next step, otherwise repeats step 12）
To step 17）；
18）Found out by fitness value and record global optimum's flight path and individual optimal trajectory；
19）Export global optimum's flight path.
The effect of the present invention can be further illustrated by following emulation：
Simulated conditions and emulation content：The map size of procedure simulation is, totally 6 threaten point, and coordinate is respectively（9,
25）,（9,50）,（29,28）,（44,15）,（49,45）,（59,45）；It is respectively 8,8,8.5,12,10,7 to threaten radius；Threaten
Grade is respectively 4,4,5,4,5,5, and the point coordinates that sets out is（1,1）；Coordinate of ground point is（65,65）；Hard-over is 600, most
Small flight path length isProgram population quantity is 50；Map and compass operator maximum iteration are 100, and terrestrial reference operator is most
Big iterations is 50.The time for cooking up flight path is 12.8941s.
Claims (7)
1. in a kind of non-linear path planning method based on mixing dove group's algorithm, it is characterised in that comprise the following steps：
Step 1：It is determined that two-dimentional flight environment of vehicle, by single UAV（Unmanned Aerial Vehicle）The two dimension rule of flight environment of vehicle
It is ensemble space region to draw space representation；
Step 2：The primary condition for setting unmanned aerial vehicle flight path to plan, including starting point, target point, threat distribution, specific embodiment party
Method is as follows：
First, according to starting point and the position of target point, the abscissa in flight range is subjected to equidistant discretization, that is, determined
The abscissa matrix of flight track point；Then, by the threat modeling in aerial mission：By the geographical position of threat, influence model
Enclose, the threat index such as threat level is converted into the matrix information of discretization planning space；
Step 3：Initialization mixing dove group algorithm various parameters, including inertial matrix, damping matrix, population quantity, map and
Compass operator maximum iteration, maximum iteration of terrestrial reference operator etc.；
Step 4：The original state of population is generated by random interval method；
Step 5：In map and compass operator, position and speed using equation below Population Regeneration：
Wherein,It is inertial matrix；It is the self-teaching factor；It is social learning's factor；For between 0 to 1 with
Machine number,For current iteration number of times；It is the maximum iteration of map and compass operator,ForBar air route；To be individual
Body optimal trajectory；For current global optimum's flight path；
Step 6：The fitness value of every flight path is calculated according to the value of object function, and records optimal trajectory；
Step 7：Terminate after map and compass operator, in terrestrial reference operator, descending sort is carried out to population according to fitness value；
Step 8：Calculate quantity and the center of this iteration population, and more new position and speed；
Step 9：After end loop, optimal trajectory is exported.
2. according to claims 1 based on mixing dove group algorithm, it is characterised in that：The generation of inertial matrix in step 3
Mode is as follows：
；
The generating mode of damping matrix：
,
Wherein,For current iteration number of times；It is the maximum iteration of map and compass operator；Be terrestrial reference operator most
Big iterations.
3. according to claims 1 based on mixing dove group algorithm, it is characterised in that：Random interval method refers in step 4：
The ordinate of flight range is divided intoIndividual minizone, generates oneMatrix, whereinEvery a line be allIndividual minizone random alignment, then each the parameters of individual are generated at random in minizone respectively, and such initial individuals will
It can be evenly distributed in whole solution space, it is ensured that initial population contains more rich pattern, enhance search and converge on entirely
The possibility of office's optimum point.
4. according to claims 1 based on mixing dove group algorithmic method, it is characterised in that：Self-teaching in step 5
The factorGenerate formula：
；
Social learning's factorGenerate formula：
,
Wherein,For current iteration number of times；For inertial matrix.
5. according to claims 1 based on mixing dove group algorithm, it is characterised in that：Object function refers in step 6, whereinFor different cost functions,For the weight coefficient of each cost function, and；For generation
The number of valency function, hereinFor 4；
：Threat radar cost, calculation formula：, when not epoch in threat range
Valency is 0；
：Fuel penalty, calculation formula；
：Hard-over cost, is that cost is 0 when meeting hard-over, is otherwise a very big value；
：Minimum flight path length cost, cost is 0 when the condition is satisfied, otherwise。
6. according to claims 1 based on mixing dove group algorithm, it is characterised in that：Flight path fitness value is in step 6
Refer to。
7. the non-linear path planning method based on mixing dove group's algorithm according to claims 1, it is characterised in that：Step
Population quantity in rapid 8 refers to,；Center refers to：；
More new formula refers to：, wherein,For current iteration number of times；It is
Damping matrix；For fitness value；For population quantity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710155141.4A CN106979784B (en) | 2017-03-16 | 2017-03-16 | Non-linear track planning based on hybrid pigeon swarm algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710155141.4A CN106979784B (en) | 2017-03-16 | 2017-03-16 | Non-linear track planning based on hybrid pigeon swarm algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106979784A true CN106979784A (en) | 2017-07-25 |
| CN106979784B CN106979784B (en) | 2020-01-03 |
Family
ID=59339543
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710155141.4A Expired - Fee Related CN106979784B (en) | 2017-03-16 | 2017-03-16 | Non-linear track planning based on hybrid pigeon swarm algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106979784B (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108151746A (en) * | 2017-12-27 | 2018-06-12 | 中国人民解放军国防科技大学 | Improved label real-time airway re-planning method based on multi-resolution situation mapping |
| CN108829131A (en) * | 2018-06-12 | 2018-11-16 | 北京航空航天大学 | A kind of unmanned plane cluster avoidance method based on the dove group's optimization of multiple target TSP question |
| CN108919641A (en) * | 2018-06-21 | 2018-11-30 | 山东科技大学 | A kind of unmanned aerial vehicle flight path planing method based on improvement cup ascidian algorithm |
| CN109357678A (en) * | 2018-10-16 | 2019-02-19 | 北京航空航天大学 | A kind of multiple no-manned plane paths planning method based on heterogeneousization dove colony optimization algorithm |
| CN109657778A (en) * | 2018-11-20 | 2019-04-19 | 北京工业大学 | A kind of adaptive dove group optimizing method based on improved global optimum on multiple populations |
| CN109991976A (en) * | 2019-03-01 | 2019-07-09 | 江苏理工学院 | A method of the unmanned vehicle based on standard particle group's algorithm evades dynamic vehicle |
| TWI676003B (en) * | 2018-05-22 | 2019-11-01 | 旻新科技股份有限公司 | Method for planning unmanned aerial vehicle path by using bird flight path |
| CN110597280A (en) * | 2019-09-04 | 2019-12-20 | 中国航空工业集团公司沈阳飞机设计研究所 | Method for re-planning aircraft route |
| CN110749325A (en) * | 2019-11-29 | 2020-02-04 | 北京京东乾石科技有限公司 | Flight path planning method and device |
| CN110926477A (en) * | 2019-12-17 | 2020-03-27 | 湘潭大学 | Unmanned aerial vehicle route planning and obstacle avoidance method |
| CN111024085A (en) * | 2019-12-18 | 2020-04-17 | 四川大学 | Unmanned aerial vehicle track planning method with end point direction and time constraints |
| CN111089593A (en) * | 2019-12-24 | 2020-05-01 | 山东科技大学 | Robot path planning method based on pigeon swarm algorithm |
| CN111158395A (en) * | 2020-01-13 | 2020-05-15 | 哈尔滨工程大学 | Multi-unmanned aerial vehicle tight formation control method based on pigeon swarm optimization |
| CN111210454A (en) * | 2020-01-09 | 2020-05-29 | 山东科技大学 | Otsu image segmentation method based on parallel pigeon swarm algorithm |
| CN111829509A (en) * | 2020-07-20 | 2020-10-27 | 深圳名仕堂贸易有限公司 | New energy automobile positioning method and positioning device |
| CN112666981A (en) * | 2021-01-04 | 2021-04-16 | 北京航空航天大学 | Unmanned aerial vehicle cluster dynamic route planning method based on dynamic group learning of original pigeon group |
| CN113175930A (en) * | 2021-03-22 | 2021-07-27 | 西安理工大学 | Multi-unmanned aerial vehicle collaborative track planning method based on MMEA |
| CN113885320A (en) * | 2021-09-26 | 2022-01-04 | 北京航空航天大学 | Aircraft random robust control method based on mixed quantum pigeon swarm optimization |
| CN114372603A (en) * | 2020-11-13 | 2022-04-19 | 北京航空航天大学 | Pigeon-group-imitated multi-learning-intelligence unmanned target drone collaborative route dynamic planning method |
| CN114397818A (en) * | 2022-01-04 | 2022-04-26 | 南京航空航天大学 | MAPIO-based spacecraft cluster orbit reconstruction path planning method |
| CN115877853A (en) * | 2023-03-03 | 2023-03-31 | 天津牛磨王科技有限公司 | Intelligent storage flow path planning system and method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971180A (en) * | 2014-05-09 | 2014-08-06 | 北京航空航天大学 | Continuous optimization problem solving method based on pigeon-inspired optimization |
| CN105929848A (en) * | 2016-06-28 | 2016-09-07 | 南京邮电大学 | Track planning method for multi-unmanned plane system in three-dimensional environment |
| CN106441308A (en) * | 2016-11-10 | 2017-02-22 | 沈阳航空航天大学 | Unmanned aerial vehicle path planning method based on adaptive weight pigeon flock algorithm |
-
2017
- 2017-03-16 CN CN201710155141.4A patent/CN106979784B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971180A (en) * | 2014-05-09 | 2014-08-06 | 北京航空航天大学 | Continuous optimization problem solving method based on pigeon-inspired optimization |
| CN105929848A (en) * | 2016-06-28 | 2016-09-07 | 南京邮电大学 | Track planning method for multi-unmanned plane system in three-dimensional environment |
| CN106441308A (en) * | 2016-11-10 | 2017-02-22 | 沈阳航空航天大学 | Unmanned aerial vehicle path planning method based on adaptive weight pigeon flock algorithm |
Non-Patent Citations (2)
| Title |
|---|
| BO ZHANG 等: "Predator-Prey Pigeon-Inspired Optimization for UAV Three-Dimensional Path Planning", 《ICSI 2014，PART Ⅱ》 * |
| 温雅 等: "一种带交叉因子的双向寻优粒子群优化算法", 《计算机应用研究》 * |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108151746A (en) * | 2017-12-27 | 2018-06-12 | 中国人民解放军国防科技大学 | Improved label real-time airway re-planning method based on multi-resolution situation mapping |
| TWI676003B (en) * | 2018-05-22 | 2019-11-01 | 旻新科技股份有限公司 | Method for planning unmanned aerial vehicle path by using bird flight path |
| CN108829131A (en) * | 2018-06-12 | 2018-11-16 | 北京航空航天大学 | A kind of unmanned plane cluster avoidance method based on the dove group's optimization of multiple target TSP question |
| CN108919641A (en) * | 2018-06-21 | 2018-11-30 | 山东科技大学 | A kind of unmanned aerial vehicle flight path planing method based on improvement cup ascidian algorithm |
| CN108919641B (en) * | 2018-06-21 | 2021-02-09 | 山东科技大学 | Unmanned aerial vehicle flight path planning method based on improved goblet sea squirt algorithm |
| CN109357678B (en) * | 2018-10-16 | 2020-10-13 | 北京航空航天大学 | Multi-unmanned aerial vehicle path planning method based on heterogeneous pigeon swarm optimization algorithm |
| CN109357678A (en) * | 2018-10-16 | 2019-02-19 | 北京航空航天大学 | A kind of multiple no-manned plane paths planning method based on heterogeneousization dove colony optimization algorithm |
| CN109657778A (en) * | 2018-11-20 | 2019-04-19 | 北京工业大学 | A kind of adaptive dove group optimizing method based on improved global optimum on multiple populations |
| CN109657778B (en) * | 2018-11-20 | 2022-02-15 | 北京工业大学 | Improved multi-swarm global optimal-based adaptive pigeon swarm optimization method |
| CN109991976A (en) * | 2019-03-01 | 2019-07-09 | 江苏理工学院 | A method of the unmanned vehicle based on standard particle group's algorithm evades dynamic vehicle |
| CN110597280A (en) * | 2019-09-04 | 2019-12-20 | 中国航空工业集团公司沈阳飞机设计研究所 | Method for re-planning aircraft route |
| CN110749325A (en) * | 2019-11-29 | 2020-02-04 | 北京京东乾石科技有限公司 | Flight path planning method and device |
| CN110749325B (en) * | 2019-11-29 | 2021-11-02 | 北京京东乾石科技有限公司 | Flight path planning method and device |
| CN110926477A (en) * | 2019-12-17 | 2020-03-27 | 湘潭大学 | Unmanned aerial vehicle route planning and obstacle avoidance method |
| CN111024085A (en) * | 2019-12-18 | 2020-04-17 | 四川大学 | Unmanned aerial vehicle track planning method with end point direction and time constraints |
| CN111024085B (en) * | 2019-12-18 | 2020-10-16 | 四川大学 | Unmanned aerial vehicle track planning method with end point direction and time constraints |
| CN111089593A (en) * | 2019-12-24 | 2020-05-01 | 山东科技大学 | Robot path planning method based on pigeon swarm algorithm |
| CN111210454B (en) * | 2020-01-09 | 2023-04-07 | 山东科技大学 | Otsu image segmentation method based on parallel pigeon swarm algorithm |
| CN111210454A (en) * | 2020-01-09 | 2020-05-29 | 山东科技大学 | Otsu image segmentation method based on parallel pigeon swarm algorithm |
| CN111158395A (en) * | 2020-01-13 | 2020-05-15 | 哈尔滨工程大学 | Multi-unmanned aerial vehicle tight formation control method based on pigeon swarm optimization |
| CN111158395B (en) * | 2020-01-13 | 2021-05-14 | 哈尔滨工程大学 | Multi-unmanned aerial vehicle tight formation control method based on pigeon swarm optimization |
| CN111829509A (en) * | 2020-07-20 | 2020-10-27 | 深圳名仕堂贸易有限公司 | New energy automobile positioning method and positioning device |
| CN111829509B (en) * | 2020-07-20 | 2021-09-03 | 泉州森泸玩具有限公司 | New energy automobile positioning method and positioning device |
| CN114372603A (en) * | 2020-11-13 | 2022-04-19 | 北京航空航天大学 | Pigeon-group-imitated multi-learning-intelligence unmanned target drone collaborative route dynamic planning method |
| CN112666981A (en) * | 2021-01-04 | 2021-04-16 | 北京航空航天大学 | Unmanned aerial vehicle cluster dynamic route planning method based on dynamic group learning of original pigeon group |
| CN113175930A (en) * | 2021-03-22 | 2021-07-27 | 西安理工大学 | Multi-unmanned aerial vehicle collaborative track planning method based on MMEA |
| CN113175930B (en) * | 2021-03-22 | 2024-04-30 | 西安理工大学 | MMEA-based multi-unmanned aerial vehicle collaborative track planning method |
| CN113885320A (en) * | 2021-09-26 | 2022-01-04 | 北京航空航天大学 | Aircraft random robust control method based on mixed quantum pigeon swarm optimization |
| CN113885320B (en) * | 2021-09-26 | 2024-02-23 | 北京航空航天大学 | Aircraft random robust control method based on mixed quantum pigeon swarm optimization |
| CN114397818B (en) * | 2022-01-04 | 2023-11-07 | 南京航空航天大学 | Spacecraft cluster orbit reconstruction path planning method based on MAPIO |
| CN114397818A (en) * | 2022-01-04 | 2022-04-26 | 南京航空航天大学 | MAPIO-based spacecraft cluster orbit reconstruction path planning method |
| CN115877853A (en) * | 2023-03-03 | 2023-03-31 | 天津牛磨王科技有限公司 | Intelligent storage flow path planning system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106979784B (en) | 2020-01-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106979784A (en) | Non-linear trajectory planning based on mixing dove group's algorithm | |
| CN107622327B (en) | Multi-unmanned aerial vehicle flight path planning method based on culture ant colony search mechanism | |
| CN110488859B (en) | Unmanned aerial vehicle route planning method based on improved Q-learning algorithm | |
| Zhu et al. | A novel algorithm of multi-AUVs task assignment and path planning based on biologically inspired neural network map | |
| Zhou et al. | An improved flower pollination algorithm for optimal unmanned undersea vehicle path planning problem | |
| CN104503464B (en) | Computer-based convex polygon field unmanned aerial vehicle spraying operation route planning method | |
| Chen et al. | A workload balanced algorithm for task assignment and path planning of inhomogeneous autonomous underwater vehicle system | |
| CN110766254A (en) | Multi-unmanned aerial vehicle cooperative task allocation method based on improved genetic algorithm | |
| CN108919641A (en) | A kind of unmanned aerial vehicle flight path planing method based on improvement cup ascidian algorithm | |
| CN103471592A (en) | Multi-unmanned aerial vehicle route planning method based on bee colony collaborative foraging algorithm | |
| CN106705970A (en) | Multi-UAV(Unmanned Aerial Vehicle) cooperation path planning method based on ant colony algorithm | |
| CN105892480A (en) | Self-organizing method for cooperative scouting and hitting task of heterogeneous multi-unmanned-aerial-vehicle system | |
| CN109917811A (en) | Unmanned aerial vehicle cluster cooperative obstacle avoidance-reconstruction processing method | |
| CN105841702A (en) | Method for planning routes of multi-unmanned aerial vehicles based on particle swarm optimization algorithm | |
| CN107063255A (en) | A kind of three-dimensional Route planner based on improvement drosophila optimized algorithm | |
| Duan et al. | Optimal formation reconfiguration control of multiple UCAVs using improved particle swarm optimization | |
| Cheng et al. | Path planning based on immune genetic algorithm for UAV | |
| CN113268087A (en) | Flight path planning method for cooperative work of multiple unmanned aerial vehicles based on improved ant colony algorithm in multi-constraint complex environment | |
| Yu et al. | Balanced multi-region coverage path planning for unmanned aerial vehicles | |
| Cheng et al. | Survey of cooperative path planning for multiple unmanned aerial vehicles | |
| Wu et al. | Based on improved bio-inspired model for path planning by multi-AUV | |
| Qiannan et al. | Path planning of UAVs formation based on improved ant colony optimization algorithm | |
| Yu et al. | UAV path planning using GSO-DE algorithm | |
| Chen et al. | Multi-robot task allocation based on the modified particle swarm optimization algorithm | |
| Wang | Optimize 2-D path planning of mobile robot by using ACO with guidance factor |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200103 Termination date: 20210316 |