CN117193004A - Unmanned aerial vehicle three-dimensional path planning method based on improved symbiotic particle swarm algorithm - Google Patents
Unmanned aerial vehicle three-dimensional path planning method based on improved symbiotic particle swarm algorithm Download PDFInfo
- Publication number
- CN117193004A CN117193004A CN202311265147.9A CN202311265147A CN117193004A CN 117193004 A CN117193004 A CN 117193004A CN 202311265147 A CN202311265147 A CN 202311265147A CN 117193004 A CN117193004 A CN 117193004A
- Authority
- CN
- China
- Prior art keywords
- aerial vehicle
- unmanned aerial
- particle swarm
- path
- flight
- 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
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 90
- 239000002245 particle Substances 0.000 title claims abstract description 80
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000009499 grossing Methods 0.000 claims abstract description 16
- 230000008901 benefit Effects 0.000 claims abstract description 7
- 230000006870 function Effects 0.000 claims description 56
- 230000009194 climbing Effects 0.000 claims description 15
- 238000005457 optimization Methods 0.000 claims description 15
- 230000031068 symbiosis, encompassing mutualism through parasitism Effects 0.000 claims description 9
- 238000012876 topography Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 7
- 238000010845 search algorithm Methods 0.000 claims description 5
- 230000009286 beneficial effect Effects 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 3
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 230000015654 memory Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000013370 mutualism Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses an unmanned aerial vehicle three-dimensional path planning method based on an improved symbiotic particle swarm algorithm, which comprises the following steps: constructing a task space model of the unmanned aerial vehicle according to the flight environment of the unmanned aerial vehicle; designing a cost function of unmanned aerial vehicle flight based on the task space model; the particle swarm algorithm is improved, and an improved symbiotic particle swarm algorithm is obtained; taking the cost function as an adaptability function of population individuals in the improved symbiotic particle swarm algorithm, and outputting control points of unmanned aerial vehicle paths based on the improved symbiotic particle swarm algorithm according to the set starting point and the set end point of unmanned aerial vehicle flight; and carrying out smoothing treatment on control points of the unmanned aerial vehicle path output by the improved symbiotic particle swarm algorithm, and obtaining track points of the actual flight of the unmanned aerial vehicle to obtain a three-dimensional path planning result of the unmanned aerial vehicle. The three-dimensional path planning method for the unmanned aerial vehicle has the advantages of being high in precision, high in speed and good in planned path effect, is suitable for actual flight of the unmanned aerial vehicle, and can meet the requirement of high real-time performance of the unmanned aerial vehicle path planning.
Description
Technical Field
The invention relates to the technical field of unmanned aerial vehicle path planning, in particular to an unmanned aerial vehicle three-dimensional path planning method based on an improved symbiotic particle swarm algorithm.
Background
With the continuous development of unmanned aerial vehicle technology, unmanned aerial vehicle path planning has become an important component part of unmanned aerial vehicle research field, and has already exerted great potential in military and civil fields. Unmanned plane path planning refers to planning an optimal path from a starting point to a target point rapidly and safely under the condition of meeting various targets and constraints in a target area. Common path planning algorithms are divided into classical algorithms and intelligent optimization algorithms, wherein the classical algorithms comprise an A-algorithm, a fast search random tree algorithm, an artificial potential field algorithm and the like, and the intelligent optimization algorithms comprise a genetic algorithm, a particle swarm algorithm, an ant colony algorithm and the like. The particle swarm algorithm is used as an algorithm based on population evolution, has stronger optimization capability compared with other algorithms, has fewer parameters, is convenient to adjust, and is easy to combine with other methods, so that the particle swarm algorithm is widely applied to path planning. However, the particle swarm algorithm also has some drawbacks, such as insufficient convergence accuracy and easy sinking to local optima.
Disclosure of Invention
The invention provides an unmanned aerial vehicle three-dimensional path planning method based on an improved symbiotic particle swarm algorithm, which aims to solve the technical problems that the existing unmanned aerial vehicle path planning method is insufficient in convergence precision and prone to being in local optimum.
In order to solve the technical problems, the invention provides the following technical scheme:
in one aspect, the invention provides an unmanned aerial vehicle three-dimensional path planning method based on an improved symbiotic particle swarm algorithm, which comprises the following steps:
constructing a task space model of the unmanned aerial vehicle according to the flight environment of the unmanned aerial vehicle;
designing a cost function of unmanned aerial vehicle flight based on the task space model;
the particle swarm algorithm is improved, and an improved symbiotic particle swarm algorithm is obtained;
setting a starting point and an ending point of a flight path of the unmanned aerial vehicle, taking the cost function as an fitness function of population individuals in the improved symbiotic particle swarm algorithm, and outputting control points of the unmanned aerial vehicle path based on the improved symbiotic particle swarm algorithm according to the set starting point and ending point of the flight of the unmanned aerial vehicle;
and performing smoothing treatment on control points of the unmanned aerial vehicle path output by the improved symbiotic particle swarm algorithm to obtain track points of the actual flight of the unmanned aerial vehicle, and obtaining a three-dimensional path planning result of the unmanned aerial vehicle.
Further, constructing a task space model of the unmanned aerial vehicle according to a flight environment of the unmanned aerial vehicle, including:
firstly initializing the terrain size, and then modeling the original terrain to obtain an original terrain model:
wherein z is 1 (x, y) is the terrain height corresponding to the point with coordinates (x, y); a, b, c, d, e and f are topography coefficients for controlling the degree of relief of the landform, different topography coefficients combining to simulate different topography features;
peak center coordinates, height, and slope are then defined to determine a peak model:
wherein z is 2 (x, y) is the peak height corresponding to the point with coordinates (x, y); n is the total number of peaks; h (i) is the height of the ith peak; x is x 0 (i)，y 0 (i) Respectively the horizontal and vertical coordinate values of the central coordinates of i peaks in the horizontal plane and x sl (i) And y sl (i) Slope parameters of the ith peak along the x-axis and y-axis directions respectively;
finally, combining the original terrain model and the mountain peak model to obtain an elevation matrix of the three-dimensional mountain terrain:
z(x,y)＝max[z 1 (x,y),z 2 (x,y)]
wherein z (x, y) is the height of the three-dimensional mountain terrain corresponding to the point with coordinates (x, y); max is the maximum function.
Further, designing a cost function of unmanned aerial vehicle flight, comprising:
and designing a cost function of flight distance, flight height and path smoothness of the unmanned aerial vehicle, and constraint conditions of no collision, minimum flight height, maximum pitching angle and maximum horizontal angle.
Further, the flight distance cost refers to the flight path length, and the flight distance cost function is expressed as:
wherein C is length Is the flight distance cost; x is x j ,y j ,z j Three-dimensional coordinate values of the jth path point; x is x j+1 ,y j+1 ,z j+1 Three-dimensional coordinate values of the j+1th path point; s is the total number of path points-1;
the flying height cost refers to the variation of the flying height of the unmanned plane, and the flying height cost function is expressed as:
wherein C is height Is the path height cost; z j The height of the jth path point; z j+1 The height of the j+1th path point;
the path smoothing cost designation is the angle between the legs, and the path smoothing cost function is expressed as:
wherein C is smooth The cost is smoothed for the path;is the j-th vector of the navigation segment; />Is the j+1th vector of the navigation segment;
a collision-free constraint refers to the inability of the flight trajectory to collide with an obstacle, expressed as:
wherein C is collision Cost for path collision; q (Q) col,j The collision constraint violation amount for the jth path point; k (k) col Violation coefficients for collision constraints;
the minimum fly height constraint refers to the minimum height that the drone can fly, expressed as:
wherein C is minf Is the minimum fly height cost; q (Q) minf,j The minimum flying height constraint violation amount for the jth path point; k (k) minf Violation coefficients for minimum fly height constraints; z (x) j ,y j ) Is of the coordinates (x j ,y j ) The height corresponding to the point of (2); z min Is the minimum flying safety height;
the maximum flying height constraint refers to the maximum height that the drone can fly, expressed as:
wherein C is maxf Is the maximum flying height cost; q (Q) maxf,j Constraint violation amount for maximum flying height of jth path point; k (k) maxf Violation coefficients for maximum flight altitude constraints; z max Is the maximum flying height;
the maximum horizontal turning angle constraint refers to the maximum horizontal turning angle of the unmanned aerial vehicle, which is expressed as:
wherein C is hor Is the cost of the maximum horizontal turning angle; q (Q) hor,j Constraint violation amount for the maximum horizontal turning angle of the jth horizontal turning angle; k (k) hor A violation coefficient for the maximum horizontal turning angle constraint; alpha j Is the j-th horizontal turning angle; alpha max Is the maximum horizontal turning angle; x is x j-1 ,y j-1 ,z j-1 Three-dimensional coordinate values of the j-1 th path point;
the maximum pitch angle constraint refers to the maximum vertical turning angle of the drone, which is expressed as:
wherein C is ver The maximum vertical climbing angle cost is set; q (Q) ver,j Constraint violation amount for the maximum vertical climbing angle of the jth vertical climbing angle; k (k) ver Constraint violation coefficients are the maximum vertical climbing angle; beta j Is the j-th vertical climbing angle; beta max Is the maximum vertical climb angle.
Further, the cost function of unmanned aerial vehicle flight is expressed as:
C all ＝k 1 ·C length +k 2 ·C height +k 3 ·C smooth +C constraint
C constraint ＝C collision +C minf +C maxf +C hor +C ver
wherein C is all A cost function for unmanned aerial vehicle flight; c (C) constraint Is the constraint cost; k (k) 1 For the distance cost weight, k 2 Is a high cost weight, k 3 The cost weights are smoothed for the path.
Further, the particle swarm algorithm is improved to obtain an improved symbiotic particle swarm algorithm, which comprises the following steps:
and (3) introducing a sine and cosine model to improve the particle swarm algorithm, and combining an improved mutually beneficial symbiotic stage of the symbiotic search algorithm with the improved particle swarm algorithm to obtain the improved symbiotic particle swarm algorithm.
Further, outputting control points of the unmanned aerial vehicle path based on the improved symbiotic particle swarm algorithm comprises:
setting all parameters of an improved symbiotic particle swarm algorithm, including a maximum iteration number, a maximum individual factor and a maximum inertia weight; then randomly initializing an algorithm population in a solution space and calculating an fitness function corresponding to an individual; the population refers to a set of individuals containing a series of path control points, each individual is a candidate solution, and represents all the control points of one unmanned plane path; the individual merits are evaluated by using a fitness function; then, the population enters an 'improved symbiosis' stage of an algorithm, and the population is optimized;
X ij_new ＝X i +r·(X best -MV·BF)
f＝C all
wherein X is ij_new To "improve symbiosis" stage X i By X j New individuals are produced, r is [0,1]Random values within the range; x is X best The optimal position of all the individuals at present; MV is a reciprocal vector; BF is a benefit factor, and 1 or 2 is randomly selected; f is the fitness function of the algorithm; c (C) all A final cost function for unmanned aerial vehicle flight; x is X i Is the ith individual in the population; x is X j For the jth individual in the population, i+.j;
then calculate the fitness function of the new individual if it is better than X i Is to replace father X with the individual i And entering the next stage, otherwise, reserving a parent and removing a child;
next, the "modified particle swarm" phase is entered to continue optimization:
V inew ＝w·V i +c 1 ·r·(X ipbest -X i )+k SC
X inew ＝X i +V inew
wherein V is i For the speed of the ith individual, X i Is the i-th individual location, where the location is the individual itself; v (V) inew And X inew Respectively V i And X i Is a progeny of (a); w is inertial weight; c 1 Is a learning factor; x is X ipbest The optimal location found for the current individual; k (k) SC Is a sine and cosine component; r is R 1 Is the attenuation coefficient; r is R 2 And R is 3 Is a random number; t is the current iteration number; t is the maximum number of iterations; w (w) max And w min Maximum and minimum values of inertial weights; c 1max And c 1min Maximum and minimum values of learning factors;
then, calculate the newly generated individual X inew If the fitness function of (2) is better than X i Is to replace father X with the individual i And enter the next iteration, and at the same time, also will V inew Substitute V i Otherwise, reserving the parent and removing the offspring; finally, update X ipbest The method comprises the steps of carrying out a first treatment on the surface of the After traversing all individuals, updating w and c 1 、R 1 And X best ；
The two phases of improving symbiosis and improving particle swarm are repeatedly iterated, when the maximum iteration number is reached, the iteration is stopped, and X is the time best Namely a series of control points of the optimal flight path of the unmanned aerial vehicle.
Further, performing smoothing processing on control points of the unmanned aerial vehicle path output by the improved symbiotic particle swarm algorithm, and obtaining a flight path point of the unmanned aerial vehicle in actual flight to obtain a three-dimensional path planning result of the unmanned aerial vehicle, wherein the method comprises the following steps:
and performing smoothing treatment on the control points output by the improved symbiotic particle swarm algorithm by using a cubic B spline curve to obtain the track points of the actual flight of the unmanned aerial vehicle, thereby obtaining the three-dimensional path planning result of the unmanned aerial vehicle.
In yet another aspect, the present invention also provides an electronic device including a processor and a memory; wherein the memory stores at least one instruction that is loaded and executed by the processor to implement the above-described method.
In yet another aspect, the present invention also provides a computer readable storage medium having at least one instruction stored therein, the instruction being loaded and executed by a processor to implement the above method.
The technical scheme provided by the invention has the beneficial effects that at least:
the invention introduces a sine and cosine model to improve a particle swarm algorithm, combines an improved mutualism phase of a symbiotic search algorithm with the improved particle swarm algorithm, and further provides an unmanned aerial vehicle three-dimensional path planning method based on the improved mutualism particle swarm algorithm, and an optimal path suitable for unmanned aerial vehicle flight is obtained on the basis of overcoming the defects of an original particle swarm algorithm. The method has the advantages of high precision, high speed and good planned path effect, is suitable for the actual flight of the unmanned aerial vehicle, and can meet the requirement of high real-time performance of unmanned aerial vehicle path planning.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of an execution flow of an unmanned aerial vehicle three-dimensional path planning method based on an improved symbiotic particle swarm algorithm according to an embodiment of the present invention;
fig. 2 is a flowchart of an improved symbiotic particle swarm algorithm provided by an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings.
First embodiment
The embodiment provides an unmanned aerial vehicle three-dimensional path planning method based on an improved symbiotic particle swarm algorithm, which can be realized by electronic equipment, and the execution flow of the method is shown in a figure 1, and comprises the following steps:
s1, constructing a task space model of the unmanned aerial vehicle according to the flight environment of the unmanned aerial vehicle;
it should be noted that, in this embodiment, the mountain model is modeled, and the following procedure is adopted:
firstly initializing the terrain size, and then modeling the original terrain to obtain an original terrain model:
wherein z is 1 (x, y) is the terrain height corresponding to the point with coordinates (x, y); a, b, c, d, e and f are topography coefficients for controlling the degree of relief of the landform, different topography coefficient combinations can simulate different topography features;
peak center coordinates, height, and slope are then defined to determine a peak model:
wherein z is 2 (x, y) is the peak height corresponding to the point with coordinates (x, y); n is the total number of peaks; h (i) is the height of the ith peak; x is x 0 (i)，y 0 (i) Respectively the horizontal and vertical coordinate values of the central coordinates of i peaks in the horizontal plane and x sl (i) And y sl (i) Slope parameters of the ith peak along the x-axis and y-axis directions respectively;
finally, combining the original terrain model and the mountain peak model to obtain an elevation matrix of the three-dimensional mountain terrain:
z(x,y)＝max[z 1 (x,y),z 2 (x,y)]
wherein z (x, y) is the height of the three-dimensional mountain terrain corresponding to the point with coordinates (x, y); max is the maximum function.
In addition, it should be noted that, the elevation matrix of other terrains may also be directly applied to the following three-dimensional path planning method of the unmanned aerial vehicle, which is not limited in this embodiment.
S2, designing a cost function of unmanned aerial vehicle flight based on the task space model, and converting a path planning problem into an optimization problem;
it should be noted that, in designing the cost function, various factors are considered in the present embodiment, including the flight distance, the flight height, the cost function of the path smoothing, and the limiting conditions of no collision, minimum flight height, maximum pitch angle, and maximum horizontal angle. I.e. the total cost function is:
C all ＝k 1 ·C length +k 2 ·C height +k 3 ·C smooth +C constraint
C constraint ＝C collision +C minf +C maxf +C hor +C ver
wherein C is all A cost function for unmanned aerial vehicle flight; c (C) constraint Is the constraint cost; k (k) 1 For the distance cost weight, k 2 Is a high cost weight, k 3 The cost weights are smoothed for the path.
The flight distance cost refers to the flight path length, and the flight distance cost function is expressed as:
wherein C is length Is the flight distance cost; x is x j ,y j ,z j Three-dimensional coordinate values of the jth path point; x is x j+1 ,y j+1 ,z j+1 Three-dimensional coordinate values of the j+1th path point; s is the total number of path points-1;
the flying height cost refers to the variation of the flying height of the unmanned plane, and the flying height cost function is expressed as:
wherein C is height Is the path height cost; z j The height of the jth path point; z j+1 The height of the j+1th path point;
the path smoothing cost designation is the angle between the legs, and the path smoothing cost function is expressed as:
wherein C is smooth The cost is smoothed for the path;for the j-th leg vector (x j+1 -x j ,y j+1 -y j ,z j+1 -z j )；/>Is the j+1th vector of the navigation segment;
a collision-free constraint refers to the inability of the flight trajectory to collide with an obstacle, expressed as:
wherein C is collision Cost for path collision; q (Q) col,j Is the j-th path point (x j ,y j ,z j ) Is a collision constraint violation amount; k (k) col Violation coefficients for collision constraints;
the minimum fly height constraint refers to the minimum height that the drone can fly, expressed as:
wherein C is minf Is the minimum fly height cost; q (Q) minf,j The minimum flying height constraint violation amount for the jth path point; k (k) minf Violation coefficients for minimum fly height constraints; z (x) j ,y j ) Is of the coordinates (x j ,y j ) The height corresponding to the point of (2); z min Is the minimum flying safety height;
the maximum flying height constraint refers to the maximum height that the drone can fly, expressed as:
wherein C is maxf Is the maximum flying height cost; q (Q) maxf,j Is the j-th path point (x j ,y j ,z j ) Is a maximum flying height constraint violation amount; k (k) maxf Violation coefficients for maximum flight altitude constraints; z max Is the maximum flying height;
the maximum horizontal turning angle constraint refers to the maximum horizontal turning angle of the unmanned aerial vehicle, which is expressed as:
wherein C is hor Is the cost of the maximum horizontal turning angle; q (Q) hor,j Constraint violation amount for the maximum horizontal turning angle of the jth horizontal turning angle; k (k) hor A violation coefficient for the maximum horizontal turning angle constraint; alpha j Is the j-th horizontal turning angle; alpha max Is the maximum horizontal turning angle; x is x j-1 ,y j-1 ,z j-1 Three-dimensional coordinate values of the j-1 th path point;
the maximum pitch angle constraint refers to the maximum vertical turning angle of the drone, which is expressed as:
wherein C is ver The maximum vertical climbing angle cost is set; q (Q) ver,j Constraint violation amount for the maximum vertical climbing angle of the jth vertical climbing angle; k (k) ver Constraint violation coefficients are the maximum vertical climbing angle; beta j Is the j-th vertical climbing angle; beta max Is the maximum vertical climb angle.
S3, improving a particle swarm algorithm to obtain an improved symbiotic particle swarm algorithm;
specifically, the method for improving the particle swarm algorithm in this embodiment is as follows: and (3) introducing a sine and cosine model to improve the particle swarm optimization, and combining an improved mutually beneficial symbiotic stage of the symbiotic search algorithm with the improved particle swarm optimization, so as to obtain the improved symbiotic particle swarm optimization.
S4, setting a starting point and an ending point of a flight path of the unmanned aerial vehicle, taking the cost function as an fitness function of population individuals in the improved symbiotic particle swarm algorithm, and outputting a control point of the unmanned aerial vehicle path based on the improved symbiotic particle swarm algorithm according to the set starting point and ending point of the flight of the unmanned aerial vehicle;
specifically, after setting the start point and the end point of the unmanned aerial vehicle flight path, a flow of outputting the control point of the unmanned aerial vehicle path based on the improved symbiotic particle swarm algorithm is shown in fig. 2, and includes:
setting all parameters of an improved symbiotic particle swarm algorithm, including a maximum iteration number, a maximum individual factor, a maximum inertia weight and the like; then randomly initializing an algorithm population in a solution space and calculating an fitness function corresponding to an individual; the population refers to a set of individuals containing a series of path control points, each individual is a candidate solution, and represents all the control points of one unmanned plane path; the individual's merits are evaluated using fitness functions (cost functions); then, the population enters an 'improved symbiosis' stage of an algorithm, and the population is optimized;
X ij_new ＝X i +r·(X best -MV·BF)
f＝C all
wherein X is ij_new To "improve symbiosis" stage X i By X j New individuals are produced, r is [0,1]Random values within the range; x is X best The optimal position of all the individuals at present; MV is a reciprocal vector; BF is a benefit factor, and 1 or 2 is randomly selected; f is the fitness function of the algorithm; c (C) all A final cost function for unmanned aerial vehicle flight; x is X i Is the ith individual in the population; x is X j For the jth individual in the population, i+.j;
then calculate the fitness function of the new individual if it is better than X i Is to replace father X with the individual i And entering the next stage, otherwise, reserving the parent and removing the offspring;
next, the "modified particle swarm" phase is entered to continue optimization:
V inew ＝w·V i +c 1 ·r·(X ipbest -X i )+k SC
X inew ＝X i +V inew
wherein r is [0,1 ]]Random values within the range; v (V) i For the speed of the ith individual, X i Is the i-th individual location, where the location is the individual itself; v (V) inew And X inew Respectively V i And X i Is a progeny of (a); w is inertial weight; c 1 Is a learning factor; x is X ipbest The optimal location found for the current individual; k (k) SC Is a sine and cosine component; r is R 1 Is the attenuation coefficient; r is R 2 And R is 3 Is a random number; t is the current iteration number; t is the maximum number of iterations; w (w) max And w min Maximum and minimum values of inertial weights; c 1max And c 1min Maximum and minimum values of learning factors;
then, calculate the newly generated individual X inew If the fitness function of (2) is better than X i Is to replace father X with the individual i And enter the next iteration, and at the same time, also will V inew Substitute V i Otherwise, reserving the parent and removing the offspring; finally, update X ipbest The method comprises the steps of carrying out a first treatment on the surface of the After traversing all individuals, updating w and c 1 、R 1 And X best ；
The two phases of improving symbiosis and improving particle swarm are repeatedly iterated, when the maximum iteration number is reached, the iteration is stopped, and X is the time best Namely a series of control points of the optimal flight path of the unmanned aerial vehicle.
S5, performing smoothing treatment on control points of the unmanned aerial vehicle path output by the improved symbiotic particle swarm algorithm, and obtaining a flight path point of the unmanned aerial vehicle in actual flight to obtain a three-dimensional path planning result of the unmanned aerial vehicle;
it should be noted that, the output result of the algorithm is a series of path control points, which is not suitable for unmanned aerial vehicle flight. In order to adapt the planned path to the unmanned aerial vehicle flight, the present embodiment applies a cubic B-spline curve to the path control points for path optimization. Namely: inputting the control points output by the algorithm into a cubic B spline calculation model, and smoothing the control points output by the improved symbiotic particle swarm algorithm by using a cubic B spline curve to obtain a series of flight path points of the actual flight of the unmanned aerial vehicle, wherein the flight path points can be applied to the flight of the unmanned aerial vehicle.
In summary, the present embodiment introduces a sine and cosine model to improve the particle swarm optimization, combines the improved reciprocal symbiotic phase of the symbiotic search algorithm with the improved particle swarm optimization, and further provides an unmanned aerial vehicle three-dimensional path planning method based on the improved symbiotic particle swarm optimization, which obtains an optimal path suitable for unmanned aerial vehicle flight on the basis of overcoming the defects of the original particle swarm optimization. The method has the advantages of high precision, high speed and good planned path effect, is suitable for the actual flight of the unmanned aerial vehicle, and can meet the requirement of high real-time performance of unmanned aerial vehicle path planning.
Second embodiment
The embodiment provides an electronic device, which comprises a processor and a memory; wherein the memory stores at least one instruction that is loaded and executed by the processor to implement the method of the first embodiment.
The electronic device may vary considerably in configuration or performance and may include one or more processors (central processing units, CPU) and one or more memories having at least one instruction stored therein that is loaded by the processors and performs the methods described above.
Third embodiment
The present embodiment provides a computer-readable storage medium having stored therein at least one instruction that is loaded and executed by a processor to implement the method of the first embodiment described above. The computer readable storage medium may be, among other things, ROM, random access memory, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. The instructions stored therein may be loaded by a processor in the terminal and perform the methods described above.
Furthermore, it should be noted that the present invention can be provided as a method, an apparatus, or a computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the invention may take the form of a computer program product on one or more computer-usable storage media having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
It is finally pointed out that the above description of the preferred embodiments of the invention, it being understood that although preferred embodiments of the invention have been described, it will be obvious to those skilled in the art that, once the basic inventive concepts of the invention are known, several modifications and adaptations can be made without departing from the principles of the invention, and these modifications and adaptations are intended to be within the scope of the invention. It is therefore intended that the following claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Claims (8)
1. The unmanned aerial vehicle three-dimensional path planning method based on the improved symbiotic particle swarm algorithm is characterized by comprising the following steps of:
constructing a task space model of the unmanned aerial vehicle according to the flight environment of the unmanned aerial vehicle;
designing a cost function of unmanned aerial vehicle flight based on the task space model;
the particle swarm algorithm is improved, and an improved symbiotic particle swarm algorithm is obtained;
setting a starting point and an ending point of a flight path of the unmanned aerial vehicle, taking the cost function as an fitness function of population individuals in the improved symbiotic particle swarm algorithm, and outputting control points of the unmanned aerial vehicle path based on the improved symbiotic particle swarm algorithm according to the set starting point and ending point of the flight of the unmanned aerial vehicle;
and performing smoothing treatment on control points of the unmanned aerial vehicle path output by the improved symbiotic particle swarm algorithm to obtain track points of the actual flight of the unmanned aerial vehicle, and obtaining a three-dimensional path planning result of the unmanned aerial vehicle.
2. The unmanned aerial vehicle three-dimensional path planning method based on the improved symbiotic particle swarm algorithm of claim 1, wherein constructing a task space model of the unmanned aerial vehicle according to the flight environment of the unmanned aerial vehicle comprises:
firstly initializing the terrain size, and then modeling the original terrain to obtain an original terrain model:
wherein z is 1 (x, y) is the terrain height corresponding to the point with coordinates (x, y); a, b, c, d, e and f are topography coefficients for controlling the degree of relief of the landform, different topography coefficients combining to simulate different topography features;
peak center coordinates, height, and slope are then defined to determine a peak model:
wherein z is 2 (x, y) is the peak height corresponding to the point with coordinates (x, y); n is the total number of peaks; h (i) is the height of the ith peak; x is x 0 (i)，y 0 (i) Respectively the horizontal and vertical coordinate values of the central coordinates of i peaks in the horizontal plane and x sl (i) And y sl (i) Slope parameters of the ith peak along the x-axis and y-axis directions respectively;
finally, combining the original terrain model and the mountain peak model to obtain an elevation matrix of the three-dimensional mountain terrain:
z(x,y)＝max[z 1 (x,y),z 2 (x,y)]
wherein z (x, y) is the height of the three-dimensional mountain terrain corresponding to the point with coordinates (x, y); max is the maximum function.
3. The unmanned aerial vehicle three-dimensional path planning method based on the improved symbiotic particle swarm algorithm of claim 1, wherein designing the cost function of unmanned aerial vehicle flight comprises:
and designing a cost function of flight distance, flight height and path smoothness of the unmanned aerial vehicle, and constraint conditions of no collision, minimum flight height, maximum pitching angle and maximum horizontal angle.
4. A method for three-dimensional path planning for unmanned aerial vehicle based on improved symbiotic particle swarm algorithm according to claim 3, wherein the flight distance cost is the flight path length, and the flight distance cost function is expressed as:
wherein C is length Is the flight distance cost; x is x j ,y j ,z j Three-dimensional coordinate values of the jth path point; x is x j+1 ,y j+1 ,z j+1 Three-dimensional coordinate values of the j+1th path point; s is the sum of the path pointsNumber-1;
the flying height cost refers to the variation of the flying height of the unmanned plane, and the flying height cost function is expressed as:
wherein C is height Is the path height cost; z j The height of the jth path point; z j+1 The height of the j+1th path point;
the path smoothing cost designation is the angle between the legs, and the path smoothing cost function is expressed as:
wherein C is smooth The cost is smoothed for the path;is the j-th vector of the navigation segment; />Is the j+1th vector of the navigation segment;
a collision-free constraint refers to the inability of the flight trajectory to collide with an obstacle, expressed as:
wherein C is collision Cost for path collision; q (Q) col,j The collision constraint violation amount for the jth path point; k (k) col Violation coefficients for collision constraints;
the minimum fly height constraint refers to the minimum height that the drone can fly, expressed as:
wherein C is minf Is the minimum fly height cost; q (Q) minf,j The minimum flying height constraint violation amount for the jth path point; k (k) minf Violation coefficients for minimum fly height constraints; z (x) j ,y j ) Is of the coordinates (x j ,y j ) The height corresponding to the point of (2); z min Is the minimum flying safety height;
the maximum flying height constraint refers to the maximum height that the drone can fly, expressed as:
wherein C is maxf Is the maximum flying height cost; q (Q) maxf,j Constraint violation amount for maximum flying height of jth path point; k (k) maxf Violation coefficients for maximum flight altitude constraints; z max Is the maximum flying height;
the maximum horizontal turning angle constraint refers to the maximum horizontal turning angle of the unmanned aerial vehicle, which is expressed as:
wherein C is hor Is the cost of the maximum horizontal turning angle; q (Q) hor,j Constraint violation amount for the maximum horizontal turning angle of the jth horizontal turning angle; k (k) hor A violation coefficient for the maximum horizontal turning angle constraint; alpha j Is the j-th horizontal turning angle; alpha max Is the maximum horizontal turning angle; x is x j-1 ,y j-1 ,z j-1 Three-dimensional coordinate values of the j-1 th path point;
the maximum pitch angle constraint refers to the maximum vertical turning angle of the drone, which is expressed as:
wherein C is ver The maximum vertical climbing angle cost is set; q (Q) ver,j Constraint violation amount for the maximum vertical climbing angle of the jth vertical climbing angle; k (k) ver Constraint violation coefficients are the maximum vertical climbing angle; beta j Is the j-th vertical climbing angle; beta max Is the maximum vertical climb angle.
5. The unmanned aerial vehicle three-dimensional path planning method based on the improved symbiotic particle swarm algorithm of claim 4, wherein the cost function of unmanned aerial vehicle flight is expressed as:
C all ＝k 1 ·C length +k 2 ·C height +k 3 ·C smooth +C constraint
C constraint ＝C collision +C minf +C maxf +C hor +C ver
wherein C is all A cost function for unmanned aerial vehicle flight; c (C) constraint Is the constraint cost; k (k) 1 For the distance cost weight, k 2 Is a high cost weight, k 3 The cost weights are smoothed for the path.
6. The unmanned aerial vehicle three-dimensional path planning method based on the improved symbiotic particle swarm algorithm of claim 1, wherein the improvement of the particle swarm algorithm results in the improved symbiotic particle swarm algorithm, comprising:
and (3) introducing a sine and cosine model to improve the particle swarm algorithm, and combining an improved mutually beneficial symbiotic stage of the symbiotic search algorithm with the improved particle swarm algorithm to obtain the improved symbiotic particle swarm algorithm.
7. The unmanned aerial vehicle three-dimensional path planning method based on the improved symbiotic particle swarm algorithm of claim 6, wherein outputting control points of unmanned aerial vehicle paths based on the improved symbiotic particle swarm algorithm comprises:
setting all parameters of the improved symbiotic particle swarm algorithm, including: maximum iteration number, maximum individual factor and maximum inertial weight; then randomly initializing an algorithm population in a solution space and calculating an fitness function corresponding to an individual; the population refers to a set of individuals containing a series of path control points, each individual is a candidate solution, and represents all the control points of one unmanned plane path; the individual merits are evaluated by using a fitness function; then, the population enters an 'improved symbiosis' stage of an algorithm, and the population is optimized;
X ij_new ＝X i +r·(X best -MV·BF)
f＝C all
wherein X is ij_new To "improve symbiosis" stage X i By X j New individuals are produced, r is [0,1]Random values within the range; x is X best The optimal position of all the individuals at present; MV is a reciprocal vector; BF is a benefit factor, and 1 or 2 is randomly selected; f is the fitness function of the algorithm; c (C) all A final cost function for unmanned aerial vehicle flight; x is X i Is the ith individual in the population; x is X j For the jth individual in the population, i+.j;
then calculate the fitness function of the new individual if it is better than X i Is to replace father X with the individual i And entering the next stage, otherwise, reserving the parent and removing the offspring;
next, the "modified particle swarm" phase is entered to continue optimization:
V inew ＝w·V i +c 1 ·r·(X ipbest -X i )+k SC
X inew ＝X i +V inew
wherein V is i For the speed of the ith individual, X i Is the i-th individual location, where the location is the individual itself; v (V) inew And X inew Respectively V i And X i Is a progeny of (a); w is inertial weight; c 1 Is a learning factor; x is X ipbest The optimal location found for the current individual; k (k) SC Is a sine and cosine component; r is R 1 Is the attenuation coefficient; r is R 2 And R is 3 Is a random number; t is the current iteration number; t is the maximum number of iterations; w (w) max And w min Maximum and minimum values of inertial weights; c 1max And c 1min Maximum and minimum values of learning factors;
then, calculate the newly generated individual X inew If the fitness function of (2) is better than X i Is to replace father X with the individual i And enter the next iteration, and at the same time, also will V inew Substitute V i Otherwise, reserving the parent and removing the offspring; finally, update X ipbest The method comprises the steps of carrying out a first treatment on the surface of the After traversing all individuals, updating w and c 1 、R 1 And X best ；
The two phases of improving symbiosis and improving particle swarm are repeatedly iterated, when the maximum iteration number is reached, the iteration is stopped, and X is the time best Namely a series of control points of the optimal flight path of the unmanned aerial vehicle.
8. The unmanned aerial vehicle three-dimensional path planning method based on the improved symbiotic particle swarm algorithm according to claim 1, wherein the method is characterized in that control points of the unmanned aerial vehicle path output by the improved symbiotic particle swarm algorithm are subjected to smoothing processing, track points of actual flight of the unmanned aerial vehicle are obtained, and unmanned aerial vehicle three-dimensional path planning results are obtained, and the method comprises the following steps:
and performing smoothing treatment on the control points output by the improved symbiotic particle swarm algorithm by using a cubic B spline curve to obtain the track points of the actual flight of the unmanned aerial vehicle, thereby obtaining the three-dimensional path planning result of the unmanned aerial vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311265147.9A CN117193004A (en) | 2023-09-27 | 2023-09-27 | Unmanned aerial vehicle three-dimensional path planning method based on improved symbiotic particle swarm algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311265147.9A CN117193004A (en) | 2023-09-27 | 2023-09-27 | Unmanned aerial vehicle three-dimensional path planning method based on improved symbiotic particle swarm algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117193004A true CN117193004A (en) | 2023-12-08 |
Family
ID=89005237
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311265147.9A Pending CN117193004A (en) | 2023-09-27 | 2023-09-27 | Unmanned aerial vehicle three-dimensional path planning method based on improved symbiotic particle swarm algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117193004A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118089742A (en) * | 2024-04-23 | 2024-05-28 | 广东电网有限责任公司云浮供电局 | Unmanned aerial vehicle route determining method and device for electric power inspection and electronic equipment |
-
2023
- 2023-09-27 CN CN202311265147.9A patent/CN117193004A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118089742A (en) * | 2024-04-23 | 2024-05-28 | 广东电网有限责任公司云浮供电局 | Unmanned aerial vehicle route determining method and device for electric power inspection and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gao et al. | Gradient-based online safe trajectory generation for quadrotor flight in complex environments | |
| CN107356254B (en) | Particle swarm optimization method suitable for geomagnetic-assisted navigation track planning | |
| CN109357678B (en) | Multi-unmanned aerial vehicle path planning method based on heterogeneous pigeon swarm optimization algorithm | |
| CN110181508A (en) | Underwater robot three-dimensional Route planner and system | |
| CN117193004A (en) | Unmanned aerial vehicle three-dimensional path planning method based on improved symbiotic particle swarm algorithm | |
| CN113848919A (en) | Ant colony algorithm-based indoor AGV path planning method | |
| CN111307153B (en) | Multi-AUV task allocation and path planning method based on hexagonal grid map | |
| CN116225066A (en) | Unmanned aerial vehicle path optimization method based on chaotic mapping pely optimization algorithm | |
| CN102324041B (en) | Pixel classification method, joint body gesture recognition method and mouse instruction generating method | |
| CN111626500A (en) | Path planning method based on improved artificial bee colony algorithm | |
| Xu et al. | Heuristic and random search algorithm in optimization of route planning for Robot’s geomagnetic navigation | |
| CN113253744B (en) | Multi-robot collaborative trajectory planning method and device, electronic equipment and storage medium | |
| CN114895707B (en) | Agricultural unmanned aerial vehicle path planning method and system based on variable frequency bat algorithm | |
| CN114721429A (en) | Three-dimensional unmanned aerial vehicle track planning method and device based on improved differential evolution algorithm | |
| CN115903888A (en) | Rotor unmanned aerial vehicle autonomous path planning method based on longicorn swarm algorithm | |
| CN116880561A (en) | Optimization method and system based on improved particle swarm unmanned aerial vehicle path planning safety enhancement | |
| Kareem et al. | Planning the Optimal 3D Quadcopter Trajectory Using a Delivery System-Based Hybrid Algorithm. | |
| CN115143970A (en) | Obstacle avoidance method and system of underwater vehicle based on threat degree evaluation | |
| CN114777789A (en) | Three-dimensional obstacle avoidance airway planning method based on spherical vector pigeon group algorithm | |
| Short et al. | Abio-inspiredalgorithminimage-based pathplanning and localization using visual features and maps | |
| Zhang et al. | UAV path planning based on receding horizon control with adaptive strategy | |
| Ghnatios et al. | Optimal velocity planning based on the solution of the Euler-Lagrange equations with a neural network based velocity regression | |
| CN116400737B (en) | Safety path planning system based on ant colony algorithm | |
| Zeng et al. | An Indoor 2D LiDAR SLAM and Localization Method Based on Artificial Landmark Assistance | |
| Bouraine et al. | NDT-PSO, a new NDT based SLAM approach using particle swarm optimization |
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 |