CN115540869A - Unmanned aerial vehicle 3D path planning method based on improved Hui wolf algorithm - Google Patents
Unmanned aerial vehicle 3D path planning method based on improved Hui wolf algorithm Download PDFInfo
- Publication number
- CN115540869A CN115540869A CN202211146728.6A CN202211146728A CN115540869A CN 115540869 A CN115540869 A CN 115540869A CN 202211146728 A CN202211146728 A CN 202211146728A CN 115540869 A CN115540869 A CN 115540869A
- Authority
- CN
- China
- Prior art keywords
- wolf
- unmanned aerial
- aerial vehicle
- ith
- radar
- 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
- 241000282461 Canis lupus Species 0.000 title claims abstract description 178
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000005457 optimization Methods 0.000 claims abstract description 9
- 238000011156 evaluation Methods 0.000 claims abstract description 4
- 230000008859 change Effects 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 9
- 230000009191 jumping Effects 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 7
- 230000007246 mechanism Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000005295 random walk Methods 0.000 claims description 6
- 230000003247 decreasing effect Effects 0.000 claims description 4
- 235000007164 Oryza sativa Nutrition 0.000 claims description 3
- 235000009566 rice Nutrition 0.000 claims description 3
- 230000003068 static effect Effects 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims description 2
- 240000007594 Oryza sativa Species 0.000 claims 1
- 108010040933 progressin Proteins 0.000 claims 1
- 230000008713 feedback mechanism Effects 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 33
- 230000009471 action Effects 0.000 description 3
- 230000002787 reinforcement Effects 0.000 description 3
- 241000209094 Oryza Species 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 241000282421 Canidae Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
- G05D1/106—Change initiated in response to external conditions, e.g. avoidance of elevated terrain or of no-fly zones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Aviation & Aerospace Engineering (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses an unmanned aerial vehicle 3D path planning method based on an improved wolf algorithm, which comprises the following steps: s1: constructing a task space model according to the track environment of the unmanned aerial vehicle, and determining a starting point and an ending point of the unmanned aerial vehicle; s2: constructing a cost function of the unmanned aerial vehicle path according to the planned performance evaluation index requirements; s3: constructing a track set of the unmanned aerial vehicle according to the grey wolf population idea; s4: carrying out three-dimensional path planning on the unmanned aerial vehicle according to an improved wolf algorithm to obtain optimal wolf parameters; s5: and constructing a route according to the terrain value and the optimal wolf parameters, and acquiring the optimal path of the unmanned aerial vehicle according to route points. The algorithm of the invention has simple structure and few parameters, has a convergence factor capable of self-adaptive adjustment and an information feedback mechanism, can not only realize multi-dimensional space search and route planning under different conditions, but also realize balance between local optimization and global search.
Description
Technical Field
The invention relates to the field of unmanned aerial vehicle path planning design, in particular to an unmanned aerial vehicle 3D path planning method based on an improved wolf algorithm.
Background
In the civil and military fields, an unmanned aerial vehicle usually needs to perform tasks at multiple target points, and finding an optimal path to traverse all the target points is a key technology of unmanned aerial vehicle application research, namely a path planning problem.
Path planning algorithms can be generally divided into three categories: 1) Numerical methods, such as methods of mixed integer programming; however, the numerical method usually needs to solve the problem of non-convex optimization, which not only needs special commercial software (such as CPLEX) but also takes a long time. 2) Reinforcement learning based algorithms; the principle of reinforcement learning is an algorithm that an agent selects an action by observing the current state and learns according to the obtained reward value. The core of reinforcement learning is discount reward, but because the form of discount reward is exponential discount, the form is decayed fast, and is more suitable for learning the optimal action in short time, and the discount coefficient needs to be increased when the action is learned for long time, but this will result in slow learning efficiency, because the trial-and-error step size increases with the step size of iteration, the number of trial-and-error times will increase exponentially, thereby affecting the convergence efficiency. 3) Algorithms based on biological elicitation, such as genetic algorithms, ant colony algorithms, particle swarm algorithms, and the like, are traditional biological elicitation algorithms. The algorithm has many parameters such as cross rate and variation rate in genetic algorithm due to the realization of operators, and the selection of the parameters may cause the problem that the solution is converged prematurely and is easy to fall into the local optimum.
Disclosure of Invention
In order to overcome the technical problems, the invention provides an unmanned aerial vehicle 3D path planning method based on an improved wolf algorithm, the algorithm is simple in structure and few in parameters, convergence factors and information feedback mechanisms capable of being adjusted in a self-adaptive mode exist, multi-dimensional space search and route planning under different conditions can be achieved, balance between local optimization and global search can be achieved, the problem that a traditional biological heuristic algorithm is prone to falling into a local optimal solution is solved, and optimal route search of an unmanned aerial vehicle is achieved.
The invention mainly adopts the technical scheme that:
an unmanned aerial vehicle 3D path planning method based on an improved wolf algorithm comprises the following specific steps:
s1: constructing a task space model according to the unmanned aerial vehicle track environment, obtaining a terrain value, initializing unmanned aerial vehicle parameters, and determining a starting point and an ending point of the unmanned aerial vehicle;
s2: constructing a cost function of the unmanned aerial vehicle path according to the planned performance evaluation index requirements;
s3: constructing a track set of the unmanned aerial vehicle according to the concept of the grey wolf population;
s4: carrying out three-dimensional path planning on the unmanned aerial vehicle according to an improved wolf algorithm to obtain optimal wolf parameters;
s5: and constructing an airway according to the terrain value obtained in the step S1 and the optimal wolf parameter obtained in the step S4, and obtaining an optimal path of the unmanned aerial vehicle according to the airway point.
Preferably, the specific construction method of the task space model in S1 is as follows:
s11: extracting information required by the unmanned aerial vehicle path planning process from a terrain model, and carrying out environment modeling according to an original terrain, a no-fly area and radar factors, wherein the original terrain model is shown as a formula (1):
extracting information required by the unmanned aerial vehicle path planning process from a terrain model, and carrying out environment modeling according to an original terrain, a no-fly area and radar factors, wherein the original terrain model is shown as a formula (1):
wherein x and y are coordinates of projection points of the task space model on a horizontal plane; z is a linear or branched member 1 The elevation values are corresponding to points on the horizontal plane; b 1 、b 2 、b 3 、b 4 、b 5 、b 6 、b 7 The constant coefficient is used for controlling the fluctuation of the reference terrain in the digital map;
for a natural mountain in a flight environment, a corresponding mountain obstacle model is constructed according to mountains, as shown in formula (2):
wherein Z is 2 (x, y) is the height of the natural mountain; (x) i ,y i ) Is the center coordinate of the ith peak; h is a total of i Height information indicating the ith peak, and controlling the height; x is the number of si And y si Attenuation and control slopes of the ith peak in the x-axis and y-axis, respectively, x si 、y si The larger the mountain, the flatter the mountain and conversely the steeper; n represents the total number of the peaks;
s12: generally, a radar interference area and a no-fly area are regarded as a threat area, wherein the no-fly area is modeled by a cylindrical model, and a no-fly area model is constructed, as shown in formula (3):
wherein L is i (x, y, z) denotes the ith no-fly zone, (x) i ,y i )、z i 、R Li Respectively the central coordinate, height and radius of the ith no-fly zone;
modeling a radar interference area by adopting a hemisphere model, and constructing a radar interference area model as shown in a formula (4):
wherein, W i (x, y, z) represents the detection area of the ith radar, (x) i ,y i ,z i ) Is the position of the ith radar, R Wi Is the detection radius of the ith radar.
Preferably, the specific construction method of the cost function in S2 is as follows:
s21: cost function f for constructing unmanned aerial vehicle path length cost L As shown in equation (5):
wherein, the unmanned aerial vehicle track comprises N nodes, (x) i ,y i ,z i ) And (x) i+1 ,y i+1 ,z i+1 ) Respectively representing the three-dimensional coordinates of the ith node and the adjacent next node;
s22: when the unmanned aerial vehicle enters a radar interference area, constructing a cost function f of radar threat cost R As shown in equations (6) and (7):
wherein S represents the number of radars, N represents the total number of unmanned aerial vehicle track nodes, and delta represents radar intensity and R Wk Represents the detection radius of the kth radar; d k,l Representing the distance between the ith track node and the kth radar center;
s23: when the flying height of the unmanned aerial vehicle is lower than the height of the obstacle and the distance from the center point of the obstacle is smaller than the radius of the obstacle, collision occurs, so that the flight path node and the obstacle need to keep a certain distance, and a cost function f of the cost of the no-fly area is constructed C As shown in equations (8) and (9):
wherein T represents the number of obstacles, and N represents the total number of unmanned aerial vehicle track nodes; c. C i,j Represents the horizontal distance from the ith obstacle to the jth track node, R obsi Denotes the radius of the obstacle i, z i Denotes the height value of the ith obstacle, z j Representing the height value of the jth track node;
s24: according to the track height change information structureCost function f for establishing height change cost H As shown in equation (10):
wherein N represents the total number of unmanned aerial vehicle track nodes, z j The height value of the jth track node is obtained;
s25: integrating and balancing 4 factors of path length, radar threat, no-fly zone and altitude change to model a fitness function, wherein the unmanned aerial vehicle cost function is shown in formulas (11) and (12):
F＝w 1 f L +w 2 f R +w 3 f C +w 4 f H (11)；
wherein F is a track total cost function; f. of L As a cost function of the path length cost, f R As a cost function of the radar threat cost, f C Cost function of the cost of the no-fly zone, f H A cost function that is a cost of altitude change; w is a g G =1,2,3,4 denotes the weight of each cost function.
Preferably, the specific construction method of the flight path set of the unmanned aerial vehicle in S3 is as follows:
if the number of wolf individuals in the population is m, the wolf individuals in the population represent X = { X = { (X) } i I =1,2, \ 8230;, m }, the location of the ith wolf in the search space is X i ＝(X i1 ,X i2 ,…,X in ) Representing the middle waypoint of a certain route except the starting point and the ending point, wherein the ith route point X of the Grey wolf is in Coordinate of (2) represents X in ＝(x in ,y in ,z in ) And connecting the middle flight path with the starting point and the ending point to form a complete flight path.
Preferably, in step S4, the three-dimensional path planning of the unmanned aerial vehicle includes the following specific steps:
s41: initializing a grey wolf algorithm parameter, grey wolf individual positions, population quantity, iteration times and weights of all cost functions, determining upper and lower search boundaries according to the task space model planned in the step S1, randomly initializing the grey wolf individual positions, and performing iterative search;
s42: performing boundary processing on the positions of all the wolf individuals, and adjusting the individuals beyond the boundary;
s43: calculating the fitness value of the current grey wolf individual according to a track total cost function F to obtain the first three-grade individuals with the best fitness in the current population, namely alpha wolf, beta wolf and delta wolf;
s44: judging whether the gray wolf individual fitness value is the first three-level individual, and jumping to S46 if the gray wolf individual fitness value is the first three-level individual; otherwise, jumping to S45;
s45: the positions of the other individuals omega wolfs are updated according to the positions of the first three grades of individuals, and the distance and the position between the grey wolf individual and the prey are updated as shown in formulas (13) and (14):
wherein t is the current iteration algebra,
represents the distance between the wolf individual and the prey,
the position of the prey of the t generation is shown,
the position of the individual of the t-th generation of the wolf is shown,
and
are coefficient vectors, and satisfy equations (15) and (16):
wherein, a is an improved gray wolf algorithm attenuation factor, and adopts a piecewise nonlinear form for attenuation, as shown in formula (17):
wherein max represents the maximum iteration times of the wolf pack, p is a decreasing index, and 0< -p is less than or equal to 1;
according to the distance between the omega wolf body and the prey and the position updating formula, the distance between the current omega wolf and the first three-grade wolf and the direction of moving towards the prey are obtained, as shown in the formulas (18), (19) and (20):
wherein, the first and the second end of the pipe are connected with each other,
respectively represent the positions of alpha wolf, beta wolf and delta wolf,
indicating the current location of the omega wolf,
respectively represent the advancing direction and the step length of the omega wolf to the alpha wolf, the beta wolf and the delta wolf,
respectively represent the distances between the alpha wolf, the beta wolf and the delta wolf and the current omega wolf,
representing the final position of the omega wolf in the iteration cycle, introducing static weighting in position updating, wherein the weights of the alpha wolf, the beta wolf and the delta wolf are respectively 6,4,2, the sum of the weights is equal to 12, and skipping to S48 after the position updating is finished;
s46: updating the positions of the alpha wolf, the beta wolf and the delta wolf according to the Laevir flight and random walk strategies, wherein the position updating is shown as a formula (21):
wherein x is i (t) denotes the ith solution, x, of the t-th generation j (t) and x k (t) two random solutions in the t generation, and ≧ represents point-to-point multiplication; o denotes a weight of the control step, and o =0.01 (x) i (t)-x b )，x b For the current optimal solution, levy (λ) represents a path obeying the rice distribution, and satisfies: levy-u = t -λ ，1<λ ≦ 3, ε is a scaling factor, ε ≦ U (0, 1); when the temperature is higher than the set temperature
When the Chinese wolf searches for prey, the Chinese wolf searches for prey globally, and the first three-level individuals update their positions according to the flight of Laiwei, when the Chinese wolf searches for prey
The gray wolf is caughtThe prey, namely local optimization, and the first three-level individuals update the positions thereof according to a random walk strategy;
s47: in order to ensure that the fitness of the obtained new solution is better than that of the original solution, the solution with better fitness is updated according to a greedy mechanism, and the position update is shown as a formula (22):
wherein x is i (t) denotes the ith original solution of the t-th generation, x i ' (t) is a new solution, and the fitness of the original solution and the fitness of the new solution are compared through a greedy mechanism so as to keep the solution with better fitness;
s48: calculating the fitness value to obtain an optimal individual, judging whether the maximum iteration times is reached, if the maximum iteration times is reached, ending the iteration and obtaining the parameters of the optimal wolf alpha; otherwise, jumping to S42 for next iteration.
Has the beneficial effects that: the invention provides a three-dimensional unmanned aerial vehicle path planning method based on an improved wolf optimization algorithm, which is used for carrying out three-dimensional path planning on an unmanned aerial vehicle by adopting the improved wolf optimization algorithm (IGWO), has few adjustment parameters and high convergence speed, can realize multi-dimensional space search and air route planning problems under different conditions, meets different constraint conditions and planning requirements, realizes the optimal air route search of the unmanned aerial vehicle, and can be widely applied to civil or military, inspection, air transportation goods and materials and other aspects.
Drawings
FIG. 1 is a flow chart of a three-dimensional unmanned aerial vehicle path planning method based on an improved Grey wolf algorithm of the present invention;
FIG. 2 is a flow chart of an algorithm for improving the Grey wolf algorithm in the present invention;
fig. 3 is a schematic diagram of a three-dimensional unmanned aerial vehicle path planning based on an improved wolf algorithm in the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. The following description of the embodiments is merely exemplary in nature and is in no way intended to limit the invention, its application, or uses.
It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. In contrast, when an element is referred to as being "directly on" another element, there are no intervening elements present. In contrast, when an element is referred to as being "directly connected" to another element, there are no intervening elements present. The terms "vertical," "horizontal," "left," "right," and the like are used herein for purposes of illustration only.
In the description of the present invention, it is to be understood that the terms "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "top," "bottom," "inner," "outer," and the like are used in the orientations and positional relationships indicated in the drawings, which are based on the orientation or positional relationship shown in the drawings, and are used for convenience of description and simplicity of description, but do not indicate or imply that the device or element so referred to must have a particular orientation, be constructed in a particular orientation, and be operated, and thus should not be construed as limiting the present invention.
An unmanned aerial vehicle 3D path planning method based on an improved wolf algorithm is shown in figure 1 and specifically comprises the following construction steps:
s1: the method comprises the following steps of constructing a task space model according to an unmanned aerial vehicle track environment, obtaining a terrain value, initializing unmanned aerial vehicle parameters, and determining an initial point and a termination point of the unmanned aerial vehicle, wherein the specific steps are as follows:
s11: extracting information required by the unmanned aerial vehicle path planning process from the terrain model, and carrying out environment modeling according to an original terrain, a no-fly area and radar factors, wherein the original terrain model is shown as a formula (1):
wherein x and y are coordinates of projection points of the task space model on a horizontal plane; z is a linear or branched member 1 The elevation values are corresponding to points on the horizontal plane; b is a mixture of 1 、b 2 、b 3 、b 4 、b 5 、b 6 、b 7 The constant coefficient is used for controlling the fluctuation of the reference terrain in the digital map;
for a natural mountain range higher in the flight environment, constructing a corresponding mountain obstacle model according to the mountain range, as shown in formula (2):
wherein, Z 2 (x, y) is the height of the natural mountain; (x) i ,y i ) Is the center coordinate of the ith peak; h is i Height information indicating the ith peak, and controlling the height; x is the number of si And y si Attenuation and control slopes of the ith peak in the x-axis and y-axis, respectively, x si 、y si The larger the mountain is, the flatter the mountain is, and conversely, the steeper the mountain is; n represents the total number of the peaks;
s12: generally, a radar interference area and a no-fly area are regarded as threat areas, the no-fly area is simulated by a cylinder, and a no-fly area model is constructed, as shown in formula (3):
wherein L is i (x, y, z) denotes the ith no-fly zone, (x) i ,y i )、z i 、R Li Respectively the central coordinate, height and radius of the ith no-fly zone;
modeling a radar interference area by adopting a hemisphere model, and constructing a radar interference area model as shown in a formula (4):
wherein, W i (x, y, z) represents the detection area of the ith radar, (x) i ,y i ,z i ) Is the position of the ith radar, R Wi Is the detection radius of the ith radar.
S2: the method comprises the following steps of constructing a path cost function of an unmanned aerial vehicle path according to the requirements of planned performance evaluation indexes:
s21: cost function f for constructing unmanned aerial vehicle path length cost L As shown in equation (5):
wherein, the unmanned aerial vehicle track comprises N nodes, (x) i ,y i ,z i ) And (x) i+1 ,y i+1 ,z i+1 ) Respectively representing the three-dimensional coordinates of the ith node and the adjacent next node;
s22: when the unmanned aerial vehicle enters a radar interference area, constructing a cost function f of radar threat cost R As shown in equations (6) and (7):
wherein S represents the number of radars, N represents the total number of unmanned aerial vehicle track nodes, and delta represents radar intensity and R Wk Represents the detection radius of the kth radar; d k,l Representing the distance between the ith track node and the kth radar center;
s23: when the flying height of the unmanned aerial vehicle is lower than the height of the obstacle and the distance from the center point of the obstacle is smaller than the radius of the obstacle, collision occurs, so that the flight path node and the obstacle need to keep a certain distance, and a cost function f of the cost of the no-fly area is constructed C As shown in equations (8) and (9):
wherein T represents the number of obstacles, and N represents the total number of unmanned aerial vehicle track nodes; c. C i,j Represents the horizontal distance, R, from the ith obstacle to the jth track node obsi Denotes the radius of the obstacle i, z i Denotes the height value of the ith obstacle, z j Representing the height value of the jth track node;
s24: constructing cost function f of altitude change cost according to flight path altitude change information H As shown in equation (10):
wherein N represents the total number of unmanned aerial vehicle track nodes, z j The height value of the jth track node is obtained;
s25: integrating and balancing 4 factors of path length, radar threat, flight forbidding area and altitude change to model a fitness function, wherein the unmanned aerial vehicle cost function is shown in formulas (11) and (12):
F＝w 1 f L +w 2 f R +w 3 f C +w 4 f H (11)；
wherein F is a track total cost function; f. of L As a cost function of the path length cost, f R As a cost function of the radar threat cost, f C Cost function of the cost of the no-fly zone, f H To change in heightCost function of cost; w is a g G =1,2,3,4 denotes the weight of each cost function.
S3: according to the grey wolf population thought, a track set of the unmanned aerial vehicle is constructed, and if the number of grey wolf individuals in the population is m, the grey wolf individuals in the population represent X = { X = (the number of the grey wolf individuals in the population is m) i I =1,2, \ 8230;, m }, the location of the ith wolf in the search space is X i ＝(X i1 ,X i2 ,…,X in ) Representing the middle waypoint of a certain route except the starting point and the ending point, wherein the ith route point X of the Grey wolf is the nth route point X in Coordinate of (2) represents X in ＝(x in ,y in ,z in ) And connecting the middle flight path with the starting point and the ending point to form a complete flight path.
S4: the method comprises the following steps of planning a three-dimensional path of the unmanned aerial vehicle according to an improved wolf algorithm to obtain an optimal wolf parameter, as shown in fig. 2, and specifically comprises the following steps:
s41: initializing the parameters of the grey wolf algorithm, the individual positions of the grey wolfs, the population number, the iteration times and the weight of each cost function, and determining the upper and lower search boundaries according to the task space model planned in the step S1, as shown in FIG. 3, the task space model of the embodiment is 100 x 10, so that the upper and lower search boundaries in three directions are respectively [0,100], [0,10], randomly initializing the individual positions of the grey wolfs and performing iterative search;
s42: in the invention, the adjustment of the individuals exceeding the boundary specifically means that when a variable (three-dimensional coordinate) in the individual position exceeds an upper boundary, the variable is directly set as the upper boundary; when the variable is smaller than the lower boundary, the variable is directly set as the lower boundary, which is the prior art and is not detailed;
s43: calculating the fitness value of the current wolf individual according to a track total cost function F to obtain the first three-grade individuals with the best fitness in the current population, namely alpha wolf, beta wolf and delta wolf (in the invention, the value of the track total cost function F is used as the fitness value of the wolf individual in the current population, the smaller the value is, the better the fitness is, and the first three with the lowest fitness are the best three);
s44: judging whether the grey wolf individual fitness value is the first three-level individual or not according to the grey wolf individual fitness value, and skipping to S46 if the grey wolf individual fitness value is the first three-level individual; otherwise, jumping to S45;
s45: the remaining individuals ω wolf update their own position according to the positions of the first three-level individuals, and the distance and position between the grey wolf individual and the prey are updated as shown in equations (13) and (14):
wherein t is the current iteration algebra,
represents the distance between the wolf individual and the prey,
the position of the prey of the t generation is shown,
represents the position of the t-th generation gray wolf individual,
and
are coefficient vectors, and satisfy equations (15) and (16):
wherein, the traditional grey wolfThe attenuation factor a of the algorithm decreases linearly from 2 to 0 as the number of iterations increases,
and
is [0,1 ]]And in the invention, a is an improved gray wolf algorithm attenuation factor, and attenuation is implemented in a piecewise nonlinear form, as shown in formula (17):
wherein max represents the maximum iteration times of the wolf pack, p is a decreasing index, and 0< -p is less than or equal to 1;
the distance between the current omega wolf and the first three-level wolf and the moving direction to the prey are obtained according to the formula of updating the distance and the position between the omega wolf individual and the prey, as shown in the formulas (18), (19) and (20):
wherein the content of the first and second substances,
respectively showing the positions of alpha wolf, beta wolf and delta wolf,
indicating the current location of the omega wolf,
respectively represent the advancing direction and the step length of the omega wolf to the alpha wolf, the beta wolf and the delta wolf,
respectively represent the distances between the alpha wolf, the beta wolf and the delta wolf and the current omega wolf,
representing the final position of the omega wolf in the iteration period, introducing static weighting in position updating, wherein the weights of the alpha wolf, the beta wolf and the delta wolf are respectively 6,4,2, the sum of the weights is equal to 12, and jumping to S48 after the position updating is finished;
s46: updating the positions of the alpha wolf, the beta wolf and the delta wolf according to the Laevir flight and random walk strategies, wherein the position updating is shown as a formula (21):
wherein x is i (t) denotes the ith solution, x, of the t-th generation j (t) and x k (t) two random solutions in the t generation, and ≧ represents point-to-point multiplication; o denotes a weight of the control step, and o =0.01 (x) i (t)-x b )，x b For the current optimal solution, levy (λ) represents a path that obeys the rice distribution, and satisfies: levy-u = t -λ ，1<λ ≦ 3, ε is a scaling factor, ε ≦ U (0, 1); when the temperature is higher than the set temperature
When the Chinese wolf searches for prey, the Chinese wolf searches for prey globally, and the first three-level individuals update their positions according to the flight of Laiwei, when the Chinese wolf searches for prey
In the process, the wolf catches the prey, namely local optimization is carried out, and the first three-level individuals update the positions of the wolf according to a random walk strategy; in the invention
The attenuation factor a is decreased along with the decrease of the attenuation factor a, the attenuation factor a is equal to 1 and is only an instant moment, the influence on the stages which are more than 1 and less than 1 is small, and the positions of the first three-level individual gray wolves are not updated when the attenuation factor a is equal to 1 by default;
s47: in order to ensure that the obtained new solution fitness is better than the original solution, and therefore, the solution with better fitness is updated according to the greedy mechanism, the position update is shown as a formula (22):
wherein x is i (t) denotes the ith original solution, x, of the t-th generation i ' (t) is a new solution, and the fitness of the original solution and the new solution is compared through a greedy mechanism so as to keep the solution with better fitness;
s48: continuously adopting a track total cost function F to calculate the fitness value of the wolf individual to obtain an optimal individual, judging whether the maximum iteration frequency is reached, if the maximum iteration frequency is reached, ending the iteration and obtaining the parameter of the optimal wolf alpha; otherwise, jumping to S42 for next iteration.
S5: and constructing an airway according to the parameters and the terrain values of the optimal wolf, and acquiring the optimal path of the unmanned aerial vehicle according to the airway points, wherein a schematic diagram of path planning is shown in fig. 3.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present specification describes embodiments, not every embodiment includes only a single embodiment, and such description is for clarity purposes only, and it is to be understood that all embodiments may be combined as appropriate by one of ordinary skill in the art to form other embodiments as will be apparent to those of skill in the art from the description herein.
Claims (5)
1. An unmanned aerial vehicle 3D path planning method based on an improved wolf algorithm is characterized by comprising the following steps:
s1: constructing a task space model according to the unmanned aerial vehicle track environment, obtaining a terrain value, initializing unmanned aerial vehicle parameters, and determining a starting point and an ending point of the unmanned aerial vehicle;
s2: constructing a cost function of the unmanned aerial vehicle path according to the planned performance evaluation index requirements;
s3: constructing a track set of the unmanned aerial vehicle according to the grey wolf population idea;
s4: carrying out three-dimensional path planning on the unmanned aerial vehicle according to an improved wolf algorithm to obtain optimal wolf parameters;
s5: and constructing an airway according to the terrain value obtained in the step S1 and the optimal wolf parameter obtained in the step S4, and obtaining an optimal path of the unmanned aerial vehicle according to the airway point.
2. The improved wolf algorithm-based unmanned aerial vehicle 3D path planning method according to claim 1, wherein the specific construction method of the task space model in S1 is as follows:
s11: extracting information required by the unmanned aerial vehicle path planning process from a terrain model, and carrying out environment modeling according to an original terrain, a no-fly area and radar factors, wherein the original terrain model is shown as a formula (1):
wherein x and y are coordinates of projection points of the task space model on a horizontal plane; z is a linear or branched member 1 The elevation values are corresponding to points on the horizontal plane; b 1 、b 2 、b 3 、b 4 、b 5 、b 6 、b 7 The constant coefficient is used for controlling the fluctuation of the reference terrain in the digital map;
for a natural mountain in a flight environment, a corresponding mountain obstacle model is constructed according to mountains, as shown in formula (2):
wherein Z is 2 (x, y) is the height of the natural mountain; (x) i ,y i ) Is the center coordinate of the ith peak; h is i Height information indicating the ith peak, and controlling the height; x is the number of si And y si Attenuation and control slopes of the ith peak in the x-axis and y-axis, respectively, x si 、y si The larger the mountain, the flatter the mountain and conversely the steeper; n represents the total number of the peaks;
s12: generally, a radar interference area and a no-fly area are regarded as a threat area, wherein the no-fly area is modeled by a cylindrical model, and a no-fly area model is constructed, as shown in formula (3):
wherein L is i (x, y, z) denotes the ith no-fly zone, (x) i ,y i )、z i 、R Li Respectively the central coordinate, height and radius of the ith no-fly zone;
modeling a radar interference area by adopting a hemisphere model, and constructing a radar interference area model as shown in a formula (4):
wherein, W i (x, y, z) represents the detection area of the ith radar, (x) i ,y i ,z i ) Is the position of the ith radar, R Wi Is the detection radius of the ith radar.
3. The improved grayish wolf algorithm-based unmanned aerial vehicle 3D path planning method according to claim 1 or 2, characterized in that the specific construction method of the cost function in S2 is as follows:
s21: cost function f for constructing unmanned aerial vehicle path length cost L As shown in equation (5):
wherein, the unmanned aerial vehicle track comprises N nodes, (x) i ,y i ,z i ) And (x) i+1 ,y i+1 ,z i+1 ) Respectively representing the three-dimensional coordinates of the ith node and the adjacent next node;
s22: when the unmanned aerial vehicle enters a radar interference area, constructing a cost function f of radar threat cost R As shown in equations (6) and (7):
wherein S represents the number of radars, N represents the total number of unmanned aerial vehicle track nodes, and delta represents radar intensity and R Wk Represents the detection radius of the kth radar; d k,l Representing the distance between the ith track node and the kth radar center;
s23: when the flying height of the unmanned aerial vehicle is lower than the height of the obstacle and the distance from the center point of the obstacle is smaller than the radius of the obstacle, collision occurs, so that a certain distance needs to be kept between a flight path node and the obstacle, and a cost function f of the cost of a no-fly area is constructed C As shown in equations (8) and (9):
wherein T represents the number of obstacles, and N represents the total number of unmanned aerial vehicle track nodes; c. C i,j Represents the horizontal distance, R, from the ith obstacle to the jth track node obsi Denotes the radius of the obstacle i, z i Denotes the height value of the ith obstacle, z j Representing the height value of the jth track node;
s24: constructing cost function f of altitude change cost according to flight path altitude change information H As shown in equation (10):
wherein N represents the total number of unmanned aerial vehicle track nodes, and z j The height value of the jth track node is obtained;
s25: integrating and balancing 4 factors of path length, radar threat, flight forbidding area and altitude change to model a fitness function, wherein the unmanned aerial vehicle cost function is shown in formulas (11) and (12):
F＝w 1 f L +w 2 f R +w 3 f C +w 4 f H (11)；
wherein F is a track total cost function; f. of L As a cost function of the path length cost, f R As a cost function of the radar threat cost, f C Cost function of the cost of the no-fly zone, f H A cost function that is a height change cost; w is a g G =1,2,3,4 denotes each cost functionThe weight of (c).
4. The improved graybee algorithm-based unmanned aerial vehicle 3D path planning method according to claim 1, wherein the specific construction method of the track set of the unmanned aerial vehicle in S3 is as follows:
if the number of wolf individuals in the population is m, the wolf individuals in the population represent X = { X = { (X) } i I =1,2, \ 8230;, m }, the location of the ith wolf in the search space is X i ＝(X i1 ,X i2 ,…,X in ) Representing the middle waypoint of a certain route except the starting point and the ending point, wherein the ith route point X of the Grey wolf is in Coordinate of (2) represents X in ＝(x in ,y in ,z in ) And connecting the middle flight path with the starting point and the ending point to form a complete flight path.
5. The improved wolf algorithm-based 3D path planning method for unmanned aerial vehicles according to claim 1, wherein in the step S4, the three-dimensional path planning of unmanned aerial vehicles comprises the following specific steps:
s41: initializing the grey wolf algorithm parameters, the grey wolf individual positions, the population number, the iteration times and the weight of each cost function, determining the upper and lower search boundaries according to the task space model planned in the step S1, randomly initializing the grey wolf individual positions, and performing iterative search;
s42: carrying out boundary processing on the positions of all the wolf individuals, and adjusting the individuals beyond the boundary;
s43: calculating the fitness value of the current grey wolf individual according to a track total cost function F to obtain the first three-grade individual alpha wolf, beta wolf and delta wolf with the best fitness in the current population;
s44: judging whether the gray wolf individual fitness value is the first three-level individual, and jumping to S46 if the gray wolf individual fitness value is the first three-level individual; otherwise, jumping to S45;
s45: the positions of the other individuals omega wolfs are updated according to the positions of the first three grades of individuals, and the distance and the position between the grey wolf individual and the prey are updated as shown in formulas (13) and (14):
wherein, t is the current iteration algebra,
represents the distance between the wolf individual and the prey,
the position of the prey of the t generation is shown,
the position of the individual of the t-th generation of the wolf is shown,
and
are coefficient vectors, and satisfy equations (15) and (16):
wherein, a is an improved gray wolf algorithm attenuation factor, and adopts a piecewise nonlinear form for attenuation, as shown in formula (17):
wherein max represents the maximum iteration times of the wolf pack, p is a decreasing index, and 0< -p is less than or equal to 1;
according to the distance between the omega wolf body and the prey and the position updating formula, the distance between the current omega wolf and the first three-grade wolf and the direction of moving towards the prey are obtained, as shown in the formulas (18), (19) and (20):
wherein the content of the first and second substances,
respectively showing the positions of alpha wolf, beta wolf and delta wolf,
indicating the current position of the omega wolf,
respectively represent the advancing direction and the step length of the omega wolf to the alpha wolf, the beta wolf and the delta wolf,
respectively represent the distances between the alpha wolf, the beta wolf and the delta wolf and the current omega wolf,
representing the final position of the omega wolf in the current iteration cycle, and introducing static weighting in the position updatingAt this time, the weights of the alpha wolf, the beta wolf and the delta wolf are respectively 6,4,2, the sum of the weights is equal to 12, and after the position updating is finished, the step is shifted to S48;
s46: updating the positions of the alpha wolf, the beta wolf and the delta wolf according to the Laevir flight and random walk strategies, wherein the position updating is shown as a formula (21):
wherein x is i (t) denotes the ith solution, x, of the t-th generation j (t) and x k (t) are two random solutions in the t-th generation,
representing point-to-point multiplication; o denotes the weight of the control step, and o =0.01 (x) i (t)-x b )，x b For the current optimal solution, levy (λ) represents a path that obeys the rice distribution, and satisfies: levy-u = t -λ ，1<λ ≦ 3, ε is a scaling factor, ε ≦ U (0, 1); when in use
When the wolf is in progress, the search for prey is carried out, i.e. global optimization is carried out, the first three-level individual updates the position of the wolf according to the Laevi flight, and when the wolf is in progress
In the process, the wolf catches the prey, namely local optimization is carried out, and the first three-level individuals update the positions of the wolf according to a random walk strategy;
s47: in order to ensure that the fitness of the obtained new solution is better than that of the original solution, the solution with better fitness is updated according to a greedy mechanism, and the position update is shown as a formula (22):
wherein x is i (t) denotes the ith original solution, x, of the t-th generation i ' (t) is a new solution, and the fitness of the original solution and the new solution is compared through a greedy mechanism so as to keep the solution with better fitness;
s48: calculating the fitness value to obtain an optimal individual, judging whether the maximum iteration times is reached, if the maximum iteration times is reached, ending the iteration and obtaining the parameters of the optimal wolf alpha; otherwise, jump to S42 for the next iteration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211146728.6A CN115540869A (en) | 2022-09-21 | 2022-09-21 | Unmanned aerial vehicle 3D path planning method based on improved Hui wolf algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211146728.6A CN115540869A (en) | 2022-09-21 | 2022-09-21 | Unmanned aerial vehicle 3D path planning method based on improved Hui wolf algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115540869A true CN115540869A (en) | 2022-12-30 |
Family
ID=84728072
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211146728.6A Pending CN115540869A (en) | 2022-09-21 | 2022-09-21 | Unmanned aerial vehicle 3D path planning method based on improved Hui wolf algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115540869A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116684960A (en) * | 2023-06-15 | 2023-09-01 | 哈尔滨工程大学 | Anchor node optimization method based on improved gray wolf optimization algorithm |
| CN116822357A (en) * | 2023-06-25 | 2023-09-29 | 成都飞机工业（集团）有限责任公司 | Photogrammetry station layout planning method based on improved wolf algorithm |
| CN117367434A (en) * | 2023-12-04 | 2024-01-09 | 上海伯镭智能科技有限公司 | Intelligent positioning method for mining area unmanned mine car |
| CN117914216A (en) * | 2024-01-16 | 2024-04-19 | 江苏和亿智能科技有限公司 | Energy-saving speed regulation control method for automatic frequency conversion equipment |
| CN117914216B (en) * | 2024-01-16 | 2024-06-25 | 江苏和亿智能科技有限公司 | Energy-saving speed regulation control method for automatic frequency conversion equipment |
-
2022
- 2022-09-21 CN CN202211146728.6A patent/CN115540869A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116684960A (en) * | 2023-06-15 | 2023-09-01 | 哈尔滨工程大学 | Anchor node optimization method based on improved gray wolf optimization algorithm |
| CN116822357A (en) * | 2023-06-25 | 2023-09-29 | 成都飞机工业（集团）有限责任公司 | Photogrammetry station layout planning method based on improved wolf algorithm |
| CN117367434A (en) * | 2023-12-04 | 2024-01-09 | 上海伯镭智能科技有限公司 | Intelligent positioning method for mining area unmanned mine car |
| CN117367434B (en) * | 2023-12-04 | 2024-02-23 | 上海伯镭智能科技有限公司 | Intelligent positioning method for mining area unmanned mine car |
| CN117914216A (en) * | 2024-01-16 | 2024-04-19 | 江苏和亿智能科技有限公司 | Energy-saving speed regulation control method for automatic frequency conversion equipment |
| CN117914216B (en) * | 2024-01-16 | 2024-06-25 | 江苏和亿智能科技有限公司 | Energy-saving speed regulation control method for automatic frequency conversion equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115540869A (en) | Unmanned aerial vehicle 3D path planning method based on improved Hui wolf algorithm | |
| Shao et al. | Efficient path planning for UAV formation via comprehensively improved particle swarm optimization | |
| Wu et al. | Distributed trajectory optimization for multiple solar-powered UAVs target tracking in urban environment by Adaptive Grasshopper Optimization Algorithm | |
| CN109144102B (en) | Unmanned aerial vehicle route planning method based on improved bat algorithm | |
| CN112230678B (en) | Three-dimensional unmanned aerial vehicle path planning method and system based on particle swarm optimization | |
| Huang et al. | Adaptive cylinder vector particle swarm optimization with differential evolution for UAV path planning | |
| Xu et al. | Optimized multi-UAV cooperative path planning under the complex confrontation environment | |
| Rezwan et al. | Artificial intelligence approaches for UAV navigation: Recent advances and future challenges | |
| Wang et al. | Three-dimensional path planning for UCAV using an improved bat algorithm | |
| Wu | A survey on population-based meta-heuristic algorithms for motion planning of aircraft | |
| CN112947592B (en) | Reentry vehicle trajectory planning method based on reinforcement learning | |
| Mou et al. | A modified ant optimization algorithm for path planning of UCAV | |
| CN108762296B (en) | Unmanned aerial vehicle deception route planning method based on ant colony algorithm | |
| CN111813144B (en) | Multi-unmanned aerial vehicle collaborative route planning method based on improved flocks of sheep algorithm | |
| CN110986960B (en) | Unmanned aerial vehicle flight path planning method based on improved clustering algorithm | |
| CN112484732B (en) | IB-ABC algorithm-based unmanned aerial vehicle flight path planning method | |
| CN114840020A (en) | Unmanned aerial vehicle flight path planning method based on improved whale algorithm | |
| CN109032167A (en) | Unmanned plane paths planning method based on Parallel Heuristic Algorithm | |
| CN114812564B (en) | Multi-target unmanned aerial vehicle path planning method based on urban dynamic space-time risk analysis | |
| Dai et al. | A novel whale optimization algorithm of path planning strategy for mobile robots | |
| CN113805609A (en) | Unmanned aerial vehicle group target searching method based on chaos lost pigeon group optimization mechanism | |
| CN115657721A (en) | Space environment unmanned aerial vehicle trajectory planning method based on improved ant colony algorithm | |
| CN116088576A (en) | Unmanned aerial vehicle three-dimensional path planning method based on improved whale algorithm | |
| CN113391633A (en) | Urban environment-oriented mobile robot fusion path planning method | |
| CN114967721A (en) | Unmanned aerial vehicle self-service path planning and obstacle avoidance strategy method based on DQ-CapsNet |
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 |