CN107063255A - A kind of three-dimensional Route planner based on improvement drosophila optimized algorithm - Google Patents
A kind of three-dimensional Route planner based on improvement drosophila optimized algorithm Download PDFInfo
- Publication number
- CN107063255A CN107063255A CN201710014194.4A CN201710014194A CN107063255A CN 107063255 A CN107063255 A CN 107063255A CN 201710014194 A CN201710014194 A CN 201710014194A CN 107063255 A CN107063255 A CN 107063255A
- Authority
- CN
- China
- Prior art keywords
- axis
- formula
- unmanned plane
- drosophila
- air route
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The present invention discloses a kind of three-dimensional Route planner, using by making improvement to original drosophila optimized algorithm, for the no-manned plane three-dimensional routeing under solving complexity physical features environment and battlefield threat situation, it is that unmanned plane calculates the three-dimensional flight route of optimal or suboptimum on the premise of considering complicated situation with unmanned plane performance constraints.
Description
Technical field
The invention belongs to robotic technology field, more particularly to a kind of three-dimensional air route rule based on improvement drosophila optimized algorithm
The method of drawing.
Background technology
Routeing is the key components of unmanned plane autonomous control, and the target of Route Planning Algorithm is for unmanned plane
Optimal or suboptimum flight path is calculated, this flight path can make unmanned plane avoid complicated terrain obstruction and the anti-enemy that dashes forward
Weapon is threatened, and self is survived while target point is reached with the shorter time.No-manned plane three-dimensional routeing problem belongs to many
Target, the complicated optimum problem of multiple constraint, generally with following features：1) index for evaluating air route performance is a lot, the mesh of composition
Scalar functions are difficult to calculate；2) battlefield surroundings situation complexity and dynamic change；3) unmanned plane self performance constraints is more；4) thing
First known information content is not complete, and may change；5) optimized variable is more, and search space often has the spy that dimension explodes
Point；6) airborne equipment is limited, it is allowed to which the information content of storage is less and airborne computer calculating speed is limited.Therefore, unmanned plane
One key challenge of routeing is how the Various Complex constraint that processing unmanned plane own physical characteristic is brought, and overcomes change
The dimension explosion issues that excessively bring are measured, and quickly draws meet various restrictive conditions and performance indications connect within a short period of time
Nearly optimal air route.
Traditional planning algorithm and intelligent planning can be substantially divided into by solving the method for Path Planning for Unmanned Aircraft Vehicle problem both at home and abroad
Algorithm.Wherein, traditional planning algorithm is had dynamic programming, the method based on figure by representative of Voronoi diagram, calculated with A stars
Method is method based on grid of representative etc.；Intelligent planning method have neural net method, artificial potential field, evolutionary computation and
Swarm intelligence method etc..The characteristics of these planning algorithms and from the point of view of the requirement of routeing problem, with evolutionary computation and colony
Intelligence is the artificial intelligence technology of representative, it has also become solve the development trend of Path Planning for Unmanned Aircraft Vehicle problem, including genetic algorithm
(genetic algorithm, GA), particle swarm optimization (particle swarm optimization, PSO), ant group optimization are calculated
Method (ant colony optimization, ACO), artificial bee colony algorithm (artificial bee colony, ABC), differential
Evolution algorithm (differential evolution, DE), universal gravitation algorithm (gravitational search
Algorithm, GSA), intelligent water drop algorithm (intelligent water drops, IWD), biogeography optimization
(biogeography-based optimization, BBO) and Memetic algorithms etc..Although these routeing technologies are just
Further develop to intelligent, practical direction, but still problems are individually present.For example, A star algorithms search space demand
It is too big, calculate overlong time；Neural network algorithm convergence rate is slow, and obtained air route may be locally optimal solution rather than the overall situation
It is optimal；The convergence rate of Artificial Potential Field Method all has larger uncertainty, and convergence rate is influenceed larger by terrain profile；Evolve
Calculate and the control parameter of swarm intelligence method be difficult to select, performance is unstable, randomness is stronger, easily occur Premature Convergence and
Stagnation behavior.Therefore, existing method could not really effectively from practical significance solve no-manned plane three-dimensional routeing ask
Topic is, it is necessary to further develop more superior planing method
Drosophila optimized algorithm (Fruit fly optimization algorithm, FOA) is a kind of to be looked for food row based on drosophila
For heuristic Global Optimization Algorithm For Analysis.Drosophila is in sensory perception, especially smell and visually, better than other species.Drosophila
Olfactory organ can be good at collecting various smells in air, or even the food source beyond great distances can be smelt.When
Drosophila can use the organs of vision of acumen to find the particular location of food and the aggregation position of companion behind food position,
And flown to towards the direction.It is simpler the step of drosophila optimized algorithm compared with other Swarm Intelligence Algorithms, in programming only
Need seldom program statement that core algorithm program just can be depicted.But original drosophila optimized algorithm has coded system
Applicability limitation is more, easily the shortcomings of sink into local optimum, therefore solving the problems, such as three-dimensional routeing using drosophila optimized algorithm
When need to be improved primal algorithm.The present invention is directed to unmanned plane own characteristic, changes to original drosophila optimized algorithm
On the basis of entering, the computational methods designed for solving no-manned plane three-dimensional routeing problem.With existing Route planner phase
Than method proposed by the invention is simpler efficiently, calculating speed is fast.Compared with original drosophila optimized algorithm, the present invention is carried
The method gone out is more stablized, and obtained air route has more excellent cost value.This method is to solve unmanned plane under complicated situation of battlefield
The effective technical way of three-dimensional routeing, can also be applied to the technologies such as ground robot path planning, Urban Traffic Planning neck
Domain.
The content of the invention
It is an object of the invention to provide a kind of based on the three-dimensional Route planner for improving drosophila optimized algorithm, considering multiple
It is that unmanned plane calculates the three-dimensional flight route of optimal or suboptimum on the premise of miscellaneous situation and unmanned plane performance constraints.
To achieve the above object, the present invention is adopted the following technical scheme that：
A kind of three-dimensional Route planner based on improvement drosophila optimized algorithm, it is first determined unmanned plane during flying task is believed
Breath, including starting point coordinate (xS,yS,zS)TWith terminal point coordinate (xT,yT,zT)T, task map boundary line is, it is necessary to the air route control cooked up
System point number n；Determine enemy's terrestrial weapon information, including threat types (radar, guided missile, antiaircraft gun), weapon position (xthreat j,
ythreat j)T, and respective threat range；Setting improves the relevant parameter of drosophila algorithm, including maximum iteration Gmax, smell
Feel searching times Mosp, and mutation probability Pm, it comprises the following steps：
Step one：If iterations NC=1, random initializtion phase angle vector thetaaxis=[θaxis,1,Λ,θaxis,D], its
In per one-dimensional phase angle value all in [- pi/2, pi/2], and D=3n, and set corresponding initial flavor concentration decision content
Smellaxis=+∞；
Step 2：The search radius of drosophila is calculated according to equation below
Step 3：Drosophila smell search operation is performed, i=1, j=1 is made；
Step 4：A real number r is randomly generated on 0 to 1 intervaljIf, rj<Pm, then five are gone to step；If rj≥Pm, then turn
Step 6；
Step 5：Mutation operation is performed, that is, is calculatedWherein random (-
RNC,RNC) it is-RNCTo RNCThe real number randomly generated on interval；Go to step 7；
Step 6：Mutation operation is not performed, that is, is calculated
Step 7：The flavor concentration decision content for calculating this smell search is as follows
Wherein, Smax,jAnd Smin,jThe respectively up-and-down boundary of search space；
Step 8：J=j+1 is made, if j≤D, step 5 is gone to, otherwise, goes to step 10；
Step 9：Utilize air route beginning and end, and vector [Si,j,Si,n+j,Si,2n+j] the complete air route of generation
PUAV,i；
Step 10：Calculate the flavor concentration value (costs of flight routes value) of air route curve
Step 11：I=i+1 is made, if i≤Mosp, then j=1 is made, and go to step 4；Otherwise, step 12 is gone to；
Step 12：The operation of drosophila visual search is performed, the individual with minimum flavor concentration value, the i.e. individual is selected
Call number is
Step 13：IfCompare ΘaxisWith more excellent flavor concentration value, then drosophila flies to the position using vision,
EvenAnd
Step 14：Iterations NC=NC+1 is updated, if iterations NC≤Gmax, then step 2 is gone to；If iteration time
Number NC ＞ Gmax, then by ΘaxisBe converted to Saxis=[Saxis,1,Saxis,2,Λ,Saxis,D], and then generation unmanned plane during flying air route,
And export final program results.
Preferably, using phase angle coded system to the position of drosophila, that is, use phase angle vector thetaaxis=
[θaxis,1,θaxis,2,Λ,θaxis,D] the location of drosophila is represented, per the phase angle on one-dimensional in interval [- pi/2, pi/2]
On.Use Smin,The up-and-down boundary of planning space is represented, using the dullness from phase angle space to air route search space
Mapping relations, to the flavor concentration decision content S of drosophila positionaxis=[Saxis,1,Saxis,2,Λ,Saxis,D] calculated：
Saxis=((Smax-Smin)sinΘaxis+Smax+Smin,)/2 (3)
Preferably, generating the mode in unmanned plane air route described in step 9 and step 14, it is described in detail and counted
Calculation mode is as follows：
If concentration decision content vector in drosophila position is [S1,S2,Λ,SD], determined using the vector as control point w1,
w2,…,wn, wherein the three-dimensional coordinate at each control point is wj=(Xj,Yj,Zj)T=(Sj,Sn+j,S2n+j)T.In addition, taking task to rise
Point is control point w0, terminal is control point wn+1。
Unmanned plane air route is expressed as to the set P of N+2 discrete pointUAV:{p0,p1,p2,Λ,pN,pN+1, wherein p0And pN+1
Task Origin And Destination, and each way point p are represented respectivelykThree-dimensional coordinate be (xk,yk,zk)T.Utilize control point wi, i=
1,2 ..., n+2, calculate way point pkThe mode of coordinate is as follows：
In formula, Bi,K(k) it is the air route function of flexure, is determined by following formula：
And
In formula, K is the order in air route, characterizes the smoothness in air route；Parameter k changes to n-K+ with fixed step-length from 0
3。
Preferably, the costs of flight routes value J (P described in step 10UAV), it is considered to air route length, flying height, enemy
Weapon threat, map limitation, turning angle limitation, limitation of climbing/glide, landform limitation etc., its calculating process is as follows：
In formula, fi, i=1,2, Λ, 7 be respectively air route length cost JL, flying height cost JH, threaten cost JT, task
Map overflows cost Jmap, turning cost Jturn, climb/glide cost JS, landform cost Jter。
Wherein,
JLIt is the length of whole piece flight route, is calculated by following formula：
And
JHFor the integration of flying height down an airway, calculated by following formula：
Wherein
In formula, zpFor way point p absolute altitude, Hter(zp) for the ground level below way point p.
JTIt is summation of each air route section by enemy's threat degree, is calculated by following formula：
In formula, Pj,kBe j-th of terrestrial weapon to air route section pkpk+1The threat probabilities caused, calculation is as follows：
If terrestrial weapon is radar, threat probabilities are as follows
In formula,For the intrinsic parameter of radar, RRmaxFor the maximum detectable range of radar.The radar cross section of unmanned plane
RCS depends on unmanned plane relative to the orientation of radar, is calculated by following formula：
In formula, αz=sin ψe, βz=cos ψe, αφ=sin φe, βφ=cos φe, wherein ψeFor the unmanned plane direction of motion with
Angle between its position vector relative to radar, φe=φ-arctan (tan θ/sin ψ) and φ, θ, ψ are respectively nobody
The position of machine is relative to the roll angle of radar, the elevation angle, azimuth.
If terrestrial weapon is surface-to-air ballistic missile, threat probabilities are as follows
In formula, RMmaxFor the maximum strike scope of surface-to-air ballistic missile, d is distance of the unmanned plane to Missile Center.
If terrestrial weapon is antiaircraft gun, threat probabilities are as follows
In formula, RGAnd RGmaxRespectively effective strike scope of antiaircraft gun and maximum hit scope, and d is unmanned plane and anti-outage
Horizontal range between big gun.
JmapCost is overflowed for task map, is calculated by following formula：
And
In formula,WithThe respectively minimum and maximum abscissa of task map, andWithIt is respectively then to appoint
The minimum and maximum ordinate of business map.
JturnFor air route turning cost, calculated by following formula：
And
In formula,Represent in way point pkThe turning angle at place,
And nmaxOverloaded for unmanned plane maximum transversal, V is unmanned plane during flying speed, and g is acceleration of gravity.
JSFor cost of climbing/glide, calculated by following formula：
And
In formula,
JterFor landform cost, calculated by following formula：
And
In formula, HsafeFor minimum safe flight altitude of the unmanned plane away from ground, Hter(xk,yk) it is at k-th of way point
Ground level.
The present invention's is beneficial as follows：
The present invention proposes a kind of based on the three-dimensional Route planner for improving drosophila optimized algorithm, this method control parameter
Few, simpler and be easily achieved, no matter using which kind of programming language, core algorithm program all only needs the code statements of minority
Just desired calculating can be completed.Variation is introduced in the smell search procedure of drosophila and adapts to operation, is conducive to drosophila from optimal
Outstanding element is inherited in body solution.Meanwhile, drosophila smell hunting zone is set in the algorithm is gradually contracted with the progress of iteration
It is small, so as to improve convergence of algorithm ability.Proposed by the invention is this based on the three-dimensional air route rule for improving drosophila optimized algorithm
The method of drawing adds the diversity of air route search, has both improved convergence of algorithm speed, overcomes again and sinks into lacking for local optimum
Point, improves the probability for obtaining optimal air line solution.The unmanned function that the Route planner makes breaks through the threat of enemy's terrestrial weapon,
Task terminal can be reached with the short period while meeting and itself being limited with environment.The present invention can efficiently solve unmanned plane
Three-dimensional routeing problem, it can also be used to other multidimensional function optimization problems.
Brief description of the drawings
Fig. 1 is phase angle mapping function curve；
The curve that Fig. 2 drosophila smell hunting zones change with iterations；
Fig. 3 improves the flow chart of drosophila optimized algorithm；
The 3-D view in the unmanned plane during flying air route that Fig. 4 institute's extracting methods of the present invention are obtained；
The top view in the unmanned plane during flying air route that Fig. 5 institute's extracting methods of the present invention are obtained；
The height in the unmanned plane during flying air route that Fig. 6 institute's extracting methods of the present invention are obtained with air route length change curve；
The costs of flight routes evolution curve of Fig. 7 institute's extracting methods of the present invention and the contrast of original drosophila algorithm；
Label and symbol description are as follows in figure：
The flavor concentration decision content of S --- drosophila
θ --- phase angle
Gmax--- maximum iteration
NC --- currently calculate iteration
RNC--- the drosophila smell search radius of the NC times calculating iteration
I --- ith smell is searched for
J --- the variable of jth dimension
D --- dimension
Rand --- the random number on 0 to 1 interval
Pm--- mutation probability
Θaxis--- drosophila position
--- the position that the smell of drosophila ith is searched in NC iterative calculation
--- the jth dimension component for the flavor concentration decision content that the smell of drosophila ith is searched in NC iterative calculation
Smellaxis--- the flavor concentration value of drosophila position
--- the flavor concentration value that the smell of drosophila ith is searched in NC iterative calculation
Mosp--- drosophila maximum smell searching times
Embodiment
The embodiment of the present invention provide it is a kind of based on improve drosophila optimized algorithm three-dimensional Route planner, using by pair
Original drosophila optimized algorithm makes improvement, for the no-manned plane three-dimensional air route under solving complexity physical features environment and battlefield threat situation
Planning, its step is as follows.
Preparation work：
Determine unmanned plane during flying mission bit stream, including starting point coordinate (xS,yS,zS)TWith terminal point coordinate (xT,yT,zT)T, task
Map boundary line is, it is necessary to the air route control point number n cooked up；
Determine enemy's terrestrial weapon information, including threat types (radar, guided missile, antiaircraft gun), weapon position (xthreat j,
ythreat j)T, and respective threat range.
Setting improves the relevant parameter of drosophila algorithm, including maximum iteration Gmax, smell searching times Mosp, Yi Jibian
Different probability Pm。
Step one：If iterations NC=1, random initializtion phase angle vector thetaaxis=[θaxis,1,Λ,θaxis,D], its
In per one-dimensional phase angle value all in [- pi/2, pi/2], and D=3n, and set corresponding initial flavor concentration decision content
Smellaxis=+∞.
Step 2：The search radius of drosophila is calculated according to equation below
Step 3：Drosophila smell search operation is performed, i=1, j=1 is made.
Step 4：A real number r is randomly generated on 0 to 1 intervaljIf, rj<Pm, then five are gone to step；If rj≥Pm, then turn
Step 6.
Step 5：Mutation operation is performed, that is, is calculatedWherein random (-
RNC,RNC) it is-RNCTo RNCThe real number randomly generated on interval；Go to step 7.
Step 6：Mutation operation is not performed, that is, is calculated
Step 7：The flavor concentration decision content for calculating this smell search is as follows
Wherein, Smax,jAnd Smin,jThe respectively up-and-down boundary of search space.
Step 8：J=j+1 is made, if j≤D, step 5 is gone to, otherwise, goes to step 10.
Step 9：Utilize air route beginning and end, and vector [Si,j,Si,n+j,Si,2n+j] the complete air route of generation
PUAV,i。
Step 10：Calculate the flavor concentration value (costs of flight routes value) of air route curve
Step 11：I=i+1 is made, if i≤Mosp, then j=1 is made, and go to step 4；Otherwise, step 12 is gone to.
Step 12：The operation of drosophila visual search is performed, the individual with minimum flavor concentration value, the i.e. individual is selected
Call number is
Step 13：IfCompare ΘaxisWith more excellent flavor concentration value, then drosophila flies to the position using vision,
EvenAnd
Step 14：Iterations NC=NC+1 is updated, if iterations NC≤Gmax, then step 2 is gone to；If iteration time
Number NC ＞ Gmax, then by ΘaxisBe converted to Saxis=[Saxis,1,Saxis,2,Λ,Saxis,D], and then generation unmanned plane during flying air route,
And export final program results.
Wherein, phase angle coded system is used to the position of drosophila in above-mentioned algorithm steps, i.e., with phase angle vector
Θaxis=[θaxi,s1,θaxi,s2,Λ,θaxi,sD] represent the location of drosophila, per the phase angle on one-dimensional interval [-
Pi/2, pi/2] on.Use Smin,Represent planning space up-and-down boundary, using shown in accompanying drawing 1 from phase angle space to
The Monotone Mappings relation of air route search space, to the flavor concentration decision content S of drosophila positionaxis=[Saxis,1,Saxis,2,Λ,
Saxis,D] calculated：
Saxis=((Smax-Smin)sinΘaxis+Smax+Smin,)/2 (22)
Wherein, the random initializtion described in step one, refers to the initial phase in algorithm, by the phase angle of drosophila
Θaxis=[θaxi,s1,θaxi,s2,Λ,θaxi,sD] random value on [- pi/2, pi/2], calculated according to the following formula：
θaxis,j=random (- pi/2, pi/2), j=1,2, Λ, D (23)
Random () in formula is represented in interval according to the random real number for being uniformly distributed selection.
Wherein, the search radius R of the drosophila described in step 2NC, it is gradually reduced with the increase of iterations, such as accompanying drawing
Shown in 2.
Wherein, the mode in unmanned plane air route is generated described in step 9 and step 14, it is described in detail and calculating side
Formula is as follows：
The drosophila position concentration decision content vector that note algorithm is obtained is [S1,S2,Λ,SD], determined using the vector as control
Make point w1,w2,…,wn, wherein the three-dimensional coordinate at each control point is wj=(Xj,Yj,Zj)T=(Sj,Sn+j,S2n+j)T.In addition, taking
Task starting point is control point w0, terminal is control point wn+1。
Unmanned plane air route is expressed as to the set P of N+2 discrete pointUAV:{p0,p1,p2,Λ,pN,pN+1, wherein p0And pN+1
Task Origin And Destination, and each way point p are represented respectivelykThree-dimensional coordinate be (xk,yk,zk)T.Utilize control point wi, i
=1,2 ..., n+2 calculate way point pkThe mode of coordinate is as follows：
In formula, Bi,K(k) it is the air route function of flexure, is determined by following formula：
And
In formula, K is the order in air route, characterizes the smoothness in air route；Parameter k changes to n-K+ with fixed step-length from 0
3。
Wherein, the costs of flight routes value J (P described in step 10UAV), it is considered to air route length, flying height, enemy weapon
Threat, map limitation, turning angle limitation, limitation of climbing/glide, landform limitation etc., its calculating process is as follows：
In formula, fi, i=1,2, Λ, 7 be respectively air route length cost JL, flying height cost JH, threaten cost JT, task
Map overflows cost Jmap, turning cost Jturn, climb/glide cost JS, landform cost Jter。
Wherein,
JLIt is the length of whole piece flight route, is calculated by following formula：
And
JHFor the integration of flying height down an airway, calculated by following formula：
Wherein
In formula, zpFor way point p absolute altitude, Hter(zp) for the ground level below way point p.
JTIt is summation of each air route section by enemy's threat degree, is calculated by following formula：
In formula, Pj,kBe j-th of terrestrial weapon to air route section pkpk+1The threat probabilities caused, calculation is as follows：
If terrestrial weapon is radar, threat probabilities are as follows
In formula,For the intrinsic parameter of radar, RRmaxFor the maximum detectable range of radar.The radar cross section of unmanned plane
RCS depends on unmanned plane relative to the orientation of radar, is calculated by following formula：
In formula, αz=sin ψe, βz=cos ψe, αφ=sin φe, βφ=cos φe, wherein ψeFor the unmanned plane direction of motion with
Angle between its position vector relative to radar, φe=φ-arctan (tan θ/sin ψ) and φ, θ, ψ are respectively nobody
The position of machine is relative to the roll angle of radar, the elevation angle, azimuth.
If terrestrial weapon is surface-to-air ballistic missile, threat probabilities are as follows
In formula, RMmaxFor the maximum strike scope of surface-to-air ballistic missile, d is distance of the unmanned plane to Missile Center.
If terrestrial weapon is antiaircraft gun, threat probabilities are as follows
In formula, RGAnd RGmaxRespectively effective strike scope of antiaircraft gun and maximum hit scope, and d is unmanned plane and anti-outage
Horizontal range between big gun.
JmapCost is overflowed for task map, is calculated by following formula：
And
In formula,WithThe respectively minimum and maximum abscissa of task map, andWithIt is respectively then to appoint
The minimum and maximum ordinate of business map.
JturnFor air route turning cost, calculated by following formula：
And
In formula,Represent in way point pkThe turning angle at place,
And nmaxOverloaded for unmanned plane maximum transversal, V is unmanned plane during flying speed, and g is acceleration of gravity.
JSFor cost of climbing/glide, calculated by following formula：
And
In formula,
JterFor landform cost, calculated by following formula：
And
In formula, HsafeFor minimum safe flight altitude of the unmanned plane away from ground, Hter(xk,yk) it is at k-th of way point
Ground level.
Carried below by an instantiation description present invention based on the three-dimensional routeing for improving drosophila optimized algorithm
The embodiment of method, and verify the performance of institute's extracting method of the present invention.Software for calculation used in example is MATLAB 2009a, specifically
As shown in Figure 3, detailed implementation steps are following (long measure in step is km) for implementing procedure.
Determine unmanned plane during flying mission bit stream：Starting point coordinate (5,10, zS) and terminal point coordinate (85,85, zT), task map
Border is, it is necessary to the air route control point number n=5 cooked up, z thereinSAnd zTGround level respectively at beginning and end.
Determine enemy's terrestrial weapon information：Archibald weapon position coordinates (45,45), threat range 9；Two missile armament positions
It is respectively (35,70) and (20,41) to put coordinate, and threat range is 8；Two radar site coordinates be respectively (40,25) and
(75,60), threat range is 15.
Setting improves the relevant parameter of drosophila algorithm：Maximum iteration Gmax=400, smell searching times Mosp=40,
Mutation probability Pm=0.9.
Step one：If iterations NC=1, according to formula θaxis,j=random (- pi/2, pi/2), j=1,2, Λ, D with
Machine generates initial phase angle vector thetaaxis=[θaxis,1,Λ,θaxis,D] so that every one-dimensional phase angle value in vector is all
In [- pi/2, pi/2], and vector dimension D=3n=15, and set corresponding initial flavor concentration decision content Smellaxis=+
∞。
Step 2：The search radius of drosophila is calculated according to equation below
Step 3：Drosophila smell search operation is performed, i=1, j=1 is made.
Step 4：A real number r is randomly generated on 0 to 1 intervaljIf, rj<Pm, then five are gone to step；If rj≥Pm, then turn
Step 6.
Step 5：Mutation operation is performed, that is, is calculatedWherein random (-
RNC,RNC) it is-RNCTo RNCThe real number randomly generated on interval；Go to step 7.
Step 6：Mutation operation is not performed, that is, is calculated
Step 7：The flavor concentration decision content for calculating this smell search is as follows
Wherein, Smax,jAnd Smin,jThe respectively up-and-down boundary of task map.
Step 8：J=j+1 is made, if j≤D, step 5 is gone to, otherwise, goes to step 10.
Step 9：Make w0Coordinate is air route starting point coordinate, i.e. w0=(X0,Y0,Z0)=(xS,yS,zS),
wn+1Coordinate is air route terminal point coordinate, i.e. wn+1=(Xn+1,Yn+1,Zn+1)=(xT,yT,zT),
wjCoordinate is
Utilize point range w0,w1,w2,…,wn+1, way point p is calculated by following formulakThree-dimensional coordinate (xk,yk,
zk)T,
In formula, K=3, parameter k is taken to change to n-K+3 from 0 with fixed step-length, and
And
Knot (i)=0, if i ＜ K
Knot (i)=i-K+1, if K≤i≤n+1
Knot (i)=n-K+3, if n ＜ i-1
By above-mentioned calculating, complete unmanned plane air route point sequence P is drawnUAV,j:{p0,p1,p2,Λ,pN,pN+1}。
Step 10：Calculate air route curve PUAV,iCosts of flight routes value, and as vector [Si,j,Si,n+j,Si,2n+j]
Flavor concentration valuePenalty C=10000 is taken, the calculation of costs of flight routes is as follows：
By following formula calculate the length cost J in air routeL：
And
The flying height cost J in air route is calculated by following formulaH：
Wherein
In formula, zpFor way point p absolute altitude, Hter(zp) for the ground level below way point p.
Summation J of each air route section by enemy's threat degree is calculated by following formulaT：
In formula, nT=5 be the number that terrestrial weapon is threatened, Pj,1And Pj,2Be two radar weapons to air route section pkpk+1Cause
Threat probabilities, calculation is as follows：
In formula, k=1,2,For the intrinsic parameter of radar, RkmaxFor the maximum detectable range of radar, and
In formula, αz=sin ψe, βz=cos ψe, αφ=sin φe, βφ=cos φe, wherein ψeFor the unmanned plane direction of motion with
Angle between its position vector relative to radar, φe=φ-arctan (tan θ/sin ψ) and φ, θ, ψ are respectively nobody
The position of machine is relative to the roll angle of radar, the elevation angle, azimuth.
Pj,3And Pj,4Be two missile armaments to air route section pkpk+1The threat probabilities caused, calculation is as follows：
In formula, k=3,4, RkmaxFor the maximum strike scope of surface-to-air ballistic missile, d is distance of the unmanned plane to Missile Center.
Pj,5Archibald weapon is to air route section pkpk+1The threat probabilities caused, calculation is as follows：
In formula, k=5, RkAnd RkmaxRespectively effective strike scope of antiaircraft gun and maximum hit scope, and d is unmanned plane and anti-
Horizontal range between outage big gun.
The task map for calculating air route by following formula overflows cost Jmap,：
And
In formula,WithThe respectively minimum and maximum abscissa of task map, andWithIt is respectively then to appoint
The minimum and maximum ordinate of business map.
Air route turning cost J is calculated by following formulaturn：
And
In formula,Represent in way point pkThe turning angle at place,
And nxam=5, V=200m/s, g=9.8.
The cost J that climbs/glide in air route is calculated by following formulaS：
And
In formula,
Pass through the landform cost J in following formula air routeter：
And
In formula, Hsafe=0.03km, Hter(xk,yk) for the ground level at k-th way point, pass through the ground of task map
Graphic data is obtained.
Comprehensive costs of flight routes value above, calculates PUAV,iTotal cost it is as follows：
J(PUAV,i)=JL+JH+JT+Jmap+Jturn+JS+Jter
Step 11：I=i+1 is made, if i≤Mosp, then j=1 is made, and go to step 4；Otherwise, step 12 is gone to.
Step 12：The operation of drosophila visual search is performed, the individual with minimum flavor concentration value, the i.e. individual is selected
Call number is
Step 13：IfCompare ΘaxisWith more excellent flavor concentration value, then drosophila flies to the position using vision,
I.e.And
Step 14：Iterations NC=NC+1 is updated, if iterations NC≤Gmax, then step 2 is gone to；If iteration time
Number NC ＞ Gmax, then by ΘaxisBe converted to Saxis=[Saxis,1,Saxis,2,Λ,Saxis,D], and then generation unmanned plane during flying air route,
And export final program results.
Accompanying drawing 4 shows the 3 D stereo view in the unmanned plane air route obtained by above-mentioned calculation procedure, and accompanying drawing 5 is for nobody
The top view in machine air route, wherein concentric circles are the threat range of enemy's terrestrial weapon, and accompanying drawing 6 is obtained air route height with boat
The situation of change of road length.As can be seen that the present invention carries the air route that algorithm obtains and successfully got around owns from result figure
Threaten, be that unmanned plane cooks up a smooth effective flight path.Accompanying drawing 7 is obtained optimal air line cost in calculating process
The improvements drosophila algorithm that is carried of the present invention and original drosophila algorithm have been carried out pair in the curve that value changes with iterations, figure
Than showing that the present invention puies forward convergence of algorithm speed, is superior to primal algorithm on optimization ability.
It is unmanned plane battlefield routeing that the present invention, which carries the three-dimensional Route planner based on improvement drosophila optimized algorithm,
Problem provides solution, while also providing very effective approach for high-dimensional function optimization problem, can be widely applied to
Robot, Aeronautics and Astronautics, industrial production etc. are related to the field of high-dimensional function optimization problem.
Claims (4)
1. it is a kind of based on the three-dimensional Route planner for improving drosophila optimized algorithm, it is characterised in that to determine that unmanned plane flies first
Row mission bit stream, including starting point coordinate (xS,yS,zS)TWith terminal point coordinate (xT,yT,zT)T, task map boundary line is, it is necessary to cook up
Air route control point number n；Determine enemy's terrestrial weapon information, including threat types (radar, guided missile, antiaircraft gun), weapon position
(xthreat j,ythreat j)T, and respective threat range；Setting improves the relevant parameter of drosophila algorithm, including greatest iteration
Number of times Gmax, smell searching times Mosp, and mutation probability Pm, it comprises the following steps：
Step one：If iterations NC=1, random initializtion phase angle vector thetaaxis=[θaxis,1,Λ,θaxis,D], wherein often
One-dimensional phase angle value sets corresponding initial flavor concentration decision content Smell all in [- pi/2, pi/2], and D=3naxis
=+∞；
Step 2：The search radius of drosophila is calculated according to equation below
Step 3：Drosophila smell search operation is performed, i=1, j=1 is made；
Step 4：A real number r is randomly generated on 0 to 1 intervaljIf, rj<Pm, then five are gone to step；If rj≥Pm, then go to step
Six；
Step 5：Mutation operation is performed, that is, is calculatedWherein random (- RNC,RNC)
For-RNCTo RNCThe real number randomly generated on interval；Go to step 7；
Step 6：Mutation operation is not performed, that is, is calculated
Step 7：The flavor concentration decision content for calculating this smell search is as follows
Wherein, Smax,jAnd Smin,jThe respectively up-and-down boundary of search space；
Step 8：J=j+1 is made, if j≤D, step 5 is gone to, otherwise, goes to step 10；
Step 9：Utilize air route beginning and end, and vector [Si,j,Si,n+j,Si,2n+j] the complete air route P of generationUAV,i；
Step 10：Calculate the flavor concentration value (costs of flight routes value) of air route curve
Step 11：I=i+1 is made, if i≤Mosp, then j=1 is made, and go to step 4；Otherwise, step 12 is gone to；
Step 12：The operation of drosophila visual search is performed, the individual with minimum flavor concentration value, the i.e. individual index is selected
Number it is
Step 13：IfCompare ΘaxisWith more excellent flavor concentration value, then drosophila flies to the position using vision, evenAnd
Step 14：Iterations NC=NC+1 is updated, if iterations NC≤Gmax, then step 2 is gone to；If iterations NC
＞ Gmax, then by ΘaxisBe converted to Saxis=[Saxis,1,Saxis,2,Λ,Saxis,D], and then unmanned plane during flying air route is generated, and it is defeated
Go out final program results.
2. it is as claimed in claim 1 based on the three-dimensional Route planner for improving drosophila optimized algorithm, it is characterised in that to fruit
The position of fly uses phase angle coded system, that is, uses phase angle vector thetaaxis=[θaxis,1,θaxis,2,Λ,θaxis,D] come
The location of drosophila is represented, per the phase angle on one-dimensional on interval [- pi/2, pi/2].WithRepresent rule
The up-and-down boundary in space is drawn, using the Monotone Mappings relation from phase angle space to air route search space, to the taste of drosophila position
Road concentration decision content Saxis=[Saxis,1,Saxis,2,Λ,Saxis,D] calculated：
Saxis=((Smax-Smin)sinΘaxis+Smax+Smin,)/2 (3)。.
3. it is as claimed in claim 1 based on the three-dimensional Route planner for improving drosophila optimized algorithm, it is characterised in that in step
Rapid nine and step 14 described in generation unmanned plane air route mode, it is described in detail and calculation is as follows：
If concentration decision content vector in drosophila position is [S1,S2,Λ,SD], determined using the vector as control point w1,w2,…,
wn, wherein the three-dimensional coordinate at each control point is wj=(Xj,Yj,Zj)T=(Sj,Sn+j,S2n+j)T.In addition, taking task starting point to be control
Make point w0, terminal is control point wn+1。
Unmanned plane air route is expressed as to the set P of N+2 discrete pointUAV:{p0,p1,p2,Λ,pN,pN+1, wherein p0And pN+1Respectively
Expression task Origin And Destination, and each way point pkThree-dimensional coordinate be (xk,yk,zk)T.Utilize control point wi, i=1,
2 ..., n+2, calculate way point pkThe mode of coordinate is as follows：
In formula, Bi,K(k) it is the air route function of flexure, is determined by following formula：
And k=n-K+3
And
In formula, K is the order in air route, characterizes the smoothness in air route；Parameter k changes to n-K+3 with fixed step-length from 0.
4. it is as claimed in claim 1 based on the three-dimensional Route planner for improving drosophila optimized algorithm, it is characterised in that in step
Costs of flight routes value J (P described in rapid tenUAV), it is considered to air route length, flying height, enemy weapon are threatened, map is limited, turned
Angle limitation, limitation of climbing/glide, landform limitation etc., its calculating process is as follows：
In formula, fi, i=1,2, Λ, 7 be respectively air route length cost JL, flying height cost JH, threaten cost JT, task map
Overflow cost Jmap, turning cost Jturn, climb/glide cost JS, landform cost Jter。
Wherein,
JLIt is the length of whole piece flight route, is calculated by following formula：
And
JHFor the integration of flying height down an airway, calculated by following formula：
Wherein
In formula, zpFor way point p absolute altitude, Hter(zp) for the ground level below way point p.
JTIt is summation of each air route section by enemy's threat degree, is calculated by following formula：
In formula, Pj,kBe j-th of terrestrial weapon to air route section pkpk+1The threat probabilities caused, calculation is as follows：
If terrestrial weapon is radar, threat probabilities are as follows
In formula,For the intrinsic parameter of radar, RRmaxFor the maximum detectable range of radar.The radar cross section RCS of unmanned plane depends on
In orientation of the unmanned plane relative to radar, calculated by following formula：
In formula, αz=sin ψe, βz=cos ψe, αφ=sin φe, βφ=cos φe, wherein ψeFor the unmanned plane direction of motion and its phase
For the angle between the position vector of radar, φe=φ-arctan (tan θ/sin ψ) and φ, θ, ψ are respectively unmanned plane
Position is relative to the roll angle of radar, the elevation angle, azimuth.
If terrestrial weapon is surface-to-air ballistic missile, threat probabilities are as follows
In formula, RMmaxFor the maximum strike scope of surface-to-air ballistic missile, d is distance of the unmanned plane to Missile Center.
If terrestrial weapon is antiaircraft gun, threat probabilities are as follows
In formula, RGAnd RGmaxRespectively effective strike scope of antiaircraft gun and maximum strike scope, d be unmanned plane and antiaircraft gun it
Between horizontal range.
JmapCost is overflowed for task map, is calculated by following formula：
And
In formula,WithThe respectively minimum and maximum abscissa of task map, andWithIt is respectively then task
The minimum and maximum ordinate of figure.
JturnFor air route turning cost, calculated by following formula：
And
In formula,Represent in way point pkThe turning angle at place,And
nmxaOverloaded for unmanned plane maximum transversal, V is unmanned plane during flying speed, and g is acceleration of gravity.
JSFor cost of climbing/glide, calculated by following formula：
And
In formula,
JterFor landform cost, calculated by following formula：
And
In formula, HsafeFor minimum safe flight altitude of the unmanned plane away from ground, Hter(xk,yk) for the ground at k-th way point
Highly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710014194.4A CN107063255B (en) | 2017-01-09 | 2017-01-09 | Three-dimensional route planning method based on improved drosophila optimization algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710014194.4A CN107063255B (en) | 2017-01-09 | 2017-01-09 | Three-dimensional route planning method based on improved drosophila optimization algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107063255A true CN107063255A (en) | 2017-08-18 |
| CN107063255B CN107063255B (en) | 2020-10-30 |
Family
ID=59624505
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710014194.4A Active CN107063255B (en) | 2017-01-09 | 2017-01-09 | Three-dimensional route planning method based on improved drosophila optimization algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107063255B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108387232A (en) * | 2018-01-30 | 2018-08-10 | 河北科技大学 | The flying object path planning method of evolution algorithm based on Artificial Potential Field |
| CN109541960A (en) * | 2017-09-21 | 2019-03-29 | 成都紫瑞青云航空宇航技术有限公司 | A kind of system and method for the confrontation of aircraft digital battlefield |
| CN109901402A (en) * | 2019-04-08 | 2019-06-18 | 哈尔滨工程大学 | A kind of autonomous underwater robot path following method based on course smoothing technique |
| CN109947136A (en) * | 2019-02-28 | 2019-06-28 | 清华大学 | A kind of collaboration actively perceive method towards unmanned plane group target searching |
| CN110084390A (en) * | 2019-03-26 | 2019-08-02 | 河南科技学院 | A kind of more vehicles collaboration share-car method for optimizing route based on modified drosophila algorithm |
| CN110544157A (en) * | 2019-09-04 | 2019-12-06 | 北京三快在线科技有限公司 | riding position recommendation method and device, electronic equipment and storage medium |
| CN110836670A (en) * | 2019-11-14 | 2020-02-25 | 北京工业大学 | Mixed firework particle swarm cooperation method for solving unmanned aerial vehicle constrained route planning |
| CN110930772A (en) * | 2019-12-05 | 2020-03-27 | 中国航空工业集团公司沈阳飞机设计研究所 | Multi-aircraft collaborative route planning method |
| 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 |
| 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 |
| CN111047019A (en) * | 2018-10-12 | 2020-04-21 | 兰州交通大学 | Construction algorithm of network weighted Voronoi graph |
| CN111256681A (en) * | 2020-05-07 | 2020-06-09 | 北京航空航天大学 | Unmanned aerial vehicle group path planning method |
| CN112327939A (en) * | 2020-10-15 | 2021-02-05 | 广东工业大学 | High-rise fire-fighting multi-unmanned aerial vehicle collaborative path planning method in urban block environment |
| CN113495564A (en) * | 2021-07-30 | 2021-10-12 | 中国人民解放军陆军装甲兵学院 | Ground unmanned platform path planning method based on evolutionary drosophila algorithm |
| CN113551682A (en) * | 2021-07-19 | 2021-10-26 | 大连理工大学 | Path planning method of amphibious unmanned war chariot considering influence of terrain and topography |
| CN115440091A (en) * | 2022-11-03 | 2022-12-06 | 成都沃飞天驭科技有限公司 | Method and device for displaying route switching views, aircraft and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102506863A (en) * | 2011-11-07 | 2012-06-20 | 北京航空航天大学 | Universal gravitation search-based unmanned plane air route planning method |
| CN105841702A (en) * | 2016-03-10 | 2016-08-10 | 赛度科技（北京）有限责任公司 | Method for planning routes of multi-unmanned aerial vehicles based on particle swarm optimization algorithm |
| CN105972185A (en) * | 2016-07-10 | 2016-09-28 | 北京工业大学 | Calculation method for working tooth profile of cycloidal gear based on fruit fly optimization algorithm |
-
2017
- 2017-01-09 CN CN201710014194.4A patent/CN107063255B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102506863A (en) * | 2011-11-07 | 2012-06-20 | 北京航空航天大学 | Universal gravitation search-based unmanned plane air route planning method |
| CN105841702A (en) * | 2016-03-10 | 2016-08-10 | 赛度科技（北京）有限责任公司 | Method for planning routes of multi-unmanned aerial vehicles based on particle swarm optimization algorithm |
| CN105972185A (en) * | 2016-07-10 | 2016-09-28 | 北京工业大学 | Calculation method for working tooth profile of cycloidal gear based on fruit fly optimization algorithm |
Non-Patent Citations (4)
| Title |
|---|
| EVA BESADA-PORTAS 等: "On the performance comparison of multi-objective evolutionary UAV path planners", 《INFORMATION SCIENCES》 * |
| MUNAN LI: "Three-Dimensional Path Planning of Robots in Virtual Situations Based on an Improved Fruit Fly Optimization Algorithm", 《ADVANCES IN MECHANICAL ENGINEERING》 * |
| 左岑: "基于果蝇优化算法的最短路径路由优化", 《山东农业大学学报(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》 * |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109541960A (en) * | 2017-09-21 | 2019-03-29 | 成都紫瑞青云航空宇航技术有限公司 | A kind of system and method for the confrontation of aircraft digital battlefield |
| CN108387232A (en) * | 2018-01-30 | 2018-08-10 | 河北科技大学 | The flying object path planning method of evolution algorithm based on Artificial Potential Field |
| CN108387232B (en) * | 2018-01-30 | 2021-08-03 | 河北科技大学 | Flight object track planning method based on artificial potential field evolution algorithm |
| CN111047019B (en) * | 2018-10-12 | 2022-09-23 | 兰州交通大学 | Network weighting Voronoi diagram construction method based on improved pulse coupling neural network |
| CN111047019A (en) * | 2018-10-12 | 2020-04-21 | 兰州交通大学 | Construction algorithm of network weighted Voronoi graph |
| CN109947136B (en) * | 2019-02-28 | 2020-07-10 | 清华大学 | Collaborative active sensing method for unmanned aerial vehicle group rapid target search |
| CN109947136A (en) * | 2019-02-28 | 2019-06-28 | 清华大学 | A kind of collaboration actively perceive method towards unmanned plane group target searching |
| CN110084390A (en) * | 2019-03-26 | 2019-08-02 | 河南科技学院 | A kind of more vehicles collaboration share-car method for optimizing route based on modified drosophila algorithm |
| CN110084390B (en) * | 2019-03-26 | 2024-01-12 | 河南科技学院 | Multi-vehicle collaborative carpooling path optimization method based on improved drosophila algorithm |
| CN109901402A (en) * | 2019-04-08 | 2019-06-18 | 哈尔滨工程大学 | A kind of autonomous underwater robot path following method based on course smoothing technique |
| CN109901402B (en) * | 2019-04-08 | 2021-10-29 | 哈尔滨工程大学 | Autonomous underwater robot path tracking method based on course smoothing technology |
| CN110544157A (en) * | 2019-09-04 | 2019-12-06 | 北京三快在线科技有限公司 | riding position recommendation method and device, electronic equipment and storage medium |
| CN110836670A (en) * | 2019-11-14 | 2020-02-25 | 北京工业大学 | Mixed firework particle swarm cooperation method for solving unmanned aerial vehicle constrained route planning |
| CN110836670B (en) * | 2019-11-14 | 2021-08-20 | 北京工业大学 | Mixed firework particle swarm cooperation method for solving unmanned aerial vehicle constrained route planning |
| CN110930772A (en) * | 2019-12-05 | 2020-03-27 | 中国航空工业集团公司沈阳飞机设计研究所 | Multi-aircraft collaborative route planning 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 |
| 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 |
| CN110986958B (en) * | 2019-12-24 | 2021-11-26 | 北京工业大学 | Multi-unmanned aerial vehicle collaborative path planning method based on multi-population collaborative drosophila optimization |
| CN111256681A (en) * | 2020-05-07 | 2020-06-09 | 北京航空航天大学 | Unmanned aerial vehicle group path planning method |
| CN111256681B (en) * | 2020-05-07 | 2020-08-11 | 北京航空航天大学 | Unmanned aerial vehicle group path planning method |
| CN112327939A (en) * | 2020-10-15 | 2021-02-05 | 广东工业大学 | High-rise fire-fighting multi-unmanned aerial vehicle collaborative path planning method in urban block environment |
| CN112327939B (en) * | 2020-10-15 | 2024-04-12 | 广东工业大学 | Collaborative path planning method for high-rise fire-fighting multiple unmanned aerial vehicles in city block environment |
| CN113551682A (en) * | 2021-07-19 | 2021-10-26 | 大连理工大学 | Path planning method of amphibious unmanned war chariot considering influence of terrain and topography |
| CN113495564A (en) * | 2021-07-30 | 2021-10-12 | 中国人民解放军陆军装甲兵学院 | Ground unmanned platform path planning method based on evolutionary drosophila algorithm |
| CN115440091A (en) * | 2022-11-03 | 2022-12-06 | 成都沃飞天驭科技有限公司 | Method and device for displaying route switching views, aircraft and storage medium |
| CN115440091B (en) * | 2022-11-03 | 2023-07-04 | 成都沃飞天驭科技有限公司 | Course switching view display method and device, aircraft and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107063255B (en) | 2020-10-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107063255A (en) | A kind of three-dimensional Route planner based on improvement drosophila optimized algorithm | |
| Huang et al. | UAV path planning based on particle swarm optimization with global best path competition | |
| CN111240353B (en) | Unmanned aerial vehicle collaborative air combat decision method based on genetic fuzzy tree | |
| CN110031004B (en) | Static and dynamic path planning method for unmanned aerial vehicle based on digital map | |
| Zhang et al. | Three-dimensional path planning for uninhabited combat aerial vehicle based on predator-prey pigeon-inspired optimization in dynamic environment | |
| CN109144102A (en) | A kind of Path Planning for UAV based on improvement bat algorithm | |
| Zhang et al. | UAV path planning method based on ant colony optimization | |
| CN109631900A (en) | A kind of no-manned plane three-dimensional track multi-objective particle swarm Global Planning | |
| CN106705970A (en) | Multi-UAV(Unmanned Aerial Vehicle) cooperation path planning method based on ant colony algorithm | |
| CN113791634A (en) | Multi-aircraft air combat decision method based on multi-agent reinforcement learning | |
| CN104317305B (en) | A kind of front flight path of penetrating threatened towards complicated battlefield determines method | |
| CN102880186A (en) | Flight path planning method based on sparse A* algorithm and genetic algorithm | |
| CN112666981B (en) | Unmanned aerial vehicle cluster dynamic route planning method based on dynamic group learning of original pigeon group | |
| CN110928329A (en) | Multi-aircraft track planning method based on deep Q learning algorithm | |
| CN110986958B (en) | Multi-unmanned aerial vehicle collaborative path planning method based on multi-population collaborative drosophila optimization | |
| Lei et al. | Path planning for unmanned air vehicles using an improved artificial bee colony algorithm | |
| CN114330115B (en) | Neural network air combat maneuver decision-making method based on particle swarm search | |
| CN112733251B (en) | Collaborative flight path planning method for multiple unmanned aerial vehicles | |
| CN113625569B (en) | Small unmanned aerial vehicle prevention and control decision method and system based on hybrid decision model | |
| CN113052289B (en) | Method for selecting cluster hitting position of unmanned ship based on game theory | |
| CN111121784B (en) | Unmanned reconnaissance aircraft route planning method | |
| Ma et al. | Chaotic random opposition-based learning and Cauchy mutation improved moth-flame optimization algorithm for intelligent route planning of multiple UAVs | |
| CN112305913A (en) | Multi-UUV collaborative dynamic maneuver decision method based on intuitive fuzzy game | |
| CN113741186B (en) | Double-aircraft air combat decision-making method based on near-end strategy optimization | |
| CN116400737B (en) | Safety path planning system based on ant colony algorithm |
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 |