CN117308942A - Unmanned aerial vehicle path planning method based on enhanced type bata foraging optimization algorithm - Google Patents
Unmanned aerial vehicle path planning method based on enhanced type bata foraging optimization algorithm Download PDFInfo
- Publication number
- CN117308942A CN117308942A CN202310792476.2A CN202310792476A CN117308942A CN 117308942 A CN117308942 A CN 117308942A CN 202310792476 A CN202310792476 A CN 202310792476A CN 117308942 A CN117308942 A CN 117308942A
- Authority
- CN
- China
- Prior art keywords
- ray
- individual
- iteration
- value
- population
- 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 51
- 230000002431 foraging effect Effects 0.000 title claims abstract description 44
- 238000005457 optimization Methods 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 title claims abstract description 25
- 241001175904 Labeo bata Species 0.000 title claims abstract description 7
- 241000288673 Chiroptera Species 0.000 claims abstract description 14
- 230000000739 chaotic effect Effects 0.000 claims abstract description 12
- 230000008859 change Effects 0.000 claims abstract description 8
- 238000013507 mapping Methods 0.000 claims abstract description 7
- 241001331491 Myliobatis californica Species 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 230000004888 barrier function Effects 0.000 claims description 4
- 230000009191 jumping Effects 0.000 abstract description 3
- 238000011161 development Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 7
- 230000007246 mechanism Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 241000330899 Hepialus Species 0.000 description 3
- 241000544061 Cuculus canorus Species 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000009827 uniform distribution Methods 0.000 description 2
- 241000282461 Canis lupus Species 0.000 description 1
- 241000283153 Cetacea Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
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
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/933—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of aircraft or spacecraft
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an unmanned aerial vehicle path planning method based on an enhanced type bata foraging optimization algorithm, which comprises the following steps: establishing a three-dimensional map, and setting the number of individuals and the maximum iteration number contained in the ray population; generating an initial bate ray population by adopting a Tent chaotic map; and calculating the fitness function value of each individual in the initial population according to the fitness function formula. Iteratively updating the positions of the individual bats; updating the curve length of the current ray; according to the path length, the collision cost of the obstacle, the threat cost of the radar and the height change cost, calculating a fitness function value; and outputting a solution with the minimum fitness function value calculated by the algorithm as a result of unmanned plane path planning. According to the invention, the Tent chaotic mapping is introduced, so that the diversity of the population during initialization is improved; the local searching capability and the global searching capability of the algorithm are balanced by adopting a control parameter adjustment strategy; on the basis, levy flight strategies are added, and the ability of jumping out of local optimum is increased.
Description
Technical Field
The invention relates to the technical field of intelligent computation, in particular to an unmanned aerial vehicle path planning method based on a bats ray foraging optimization algorithm.
Background
With the continuous development of unmanned aerial vehicle technology, path planning research is particularly important. Through path planning, the unmanned aerial vehicle can realize the optimal navigation path under certain conditions, so that the unmanned aerial vehicle can fly more safely, efficiently and energy-effectively. The research of path planning can help to develop a more intelligent unmanned aerial vehicle system, so that the operation efficiency of the unmanned aerial vehicle is improved, and the requirements of different application scenes are met. The research of path planning not only can help to improve the operation efficiency of the unmanned aerial vehicle, but also can provide a reliable guarantee for the unmanned aerial vehicle system, and ensure the safety of the unmanned aerial vehicle in the flight process. In addition, path planning studies can also help develop unmanned aerial vehicle systems that can cope with complex environments, enabling them to fly safely in complex environments. Therefore, the unmanned aerial vehicle path planning research has important significance, and lays a solid foundation for the development and application of unmanned aerial vehicle systems. Path planning in a complex environment is one of the key technologies of unmanned aerial vehicles. In recent years, intelligent optimization algorithms are widely applied to path planning of unmanned aerial vehicles in various environments. For example, particle swarm optimization, ant swarm optimization, bat algorithm are widely applied in the unmanned plane path planning field and have good results. And novel evolutionary algorithms such as the wolf algorithm and the whale algorithm are also optimized in a targeted manner aiming at the respective direction of emphasis.
The algorithm can solve the problem of path planning of the unmanned aerial vehicle. How to effectively plan the optimal path under specific environments is a problem that we need to consider. Inspired by the special predation mode of the ray, a new meta-heuristic optimization algorithm, the Hepialus ray foraging optimization algorithm (MRFO), was originally proposed by Zhao Wengang in 2020. It has significant advantages in terms of global convergence and is therefore applied to many optimization problems. The original foraging optimization algorithm of the ray of the bats has the advantages of few parameters, fast convergence, strong robustness and the like, but the method is easy to sink into the defects of local optimum, early convergence, low calculation precision and the like. Therefore, the invention mainly aims at the unmanned aerial vehicle static global path planning of MRFO, and the problems of low precision and easy sinking into local optimum exist in the prior art planning method.
Disclosure of Invention
Aiming at the problems that the existing batray foraging optimization algorithm is poor in population diversity and prone to being in local optimum, the invention provides an unmanned plane path planning method capable of effectively jumping out of local optimum and balancing global exploration capacity and local exploration capacity.
The invention adopts the technical scheme that the unmanned aerial vehicle path planning method based on the enhanced type ray of the Hepialus insect foraging optimization algorithm comprises the following steps:
step 1: establishing a three-dimensional map containing barriers, setting the number n of the ray individuals contained in the ray population, and setting the maximum iteration number T; a bate ray population corresponds to a pair of starting points and end points, and the bate ray individuals in the bate ray population are different unmanned aerial vehicle paths under the same starting points and end points; an unmanned plane path between a starting point and a finishing point corresponding to a bate ray population, wherein a bate ray individual in the bate ray population is a position point in the unmanned plane path; randomly generating unmanned plane paths avoiding obstacles, and taking the paths as alternative bata ray populations;
step 2: generating an initial ray population for iteration by adopting a Tent chaotic map based on the alternative ray population;
step 3: calculating the fitness function value of each individual of the initial bated ray in the initial bated ray population according to the fitness function;
step 4: iteratively updating the positions of the individual bats, specifically:
firstly, calculating a control parameter conf according to the current iteration times t, generating a random value rand with a value range of (0, 1), and setting a preset threshold value with the value range of (0, 1);e is a natural constant; and then adopting three steps of updating iteration:
the first step: different foraging strategies are adopted according to the size relation of rand, conf and a preset threshold value to obtain updated t+1st iteration of the individual positions of the bats: when the rand is greater than or equal to a preset threshold, adopting a chained foraging strategy; when the rand is smaller than a preset threshold value and the conf is larger than or equal to the rand, adopting a spiral foraging strategy based on the optimal position as a reference position; when the rand is smaller than a preset threshold value and the conf is smaller than the rand, adopting a spiral foraging strategy based on a new random position as a reference position;
and a second step of: adopting a flip bucket foraging strategy to update the positions of the individual units of the ray of the bats obtained in the first step, wherein the iteration is t+1st;
and a third step of: updating the updated result of the t+1st iteration of the individual positions of the ray obtained in the second step by adopting the Levy flight strategy to obtain the final t+1st iteration of the individual positions of the ray obtained in the step 4;
step 5: calculating corresponding path curve length f based on the individual positions of the batray of the t+1st iteration output in the step 4 L Cost of radar threat f R Obstacle collision cost f C Cost of height change f H Setting a punishment factor p according to whether the current ray individual collides with the obstacle or not;
step 6: f determined by step 5 L 、f R 、f C 、f H Calculating the fitness function value of the current individual ray; updating t=t+1, reserving the minimum value of the fitness function value in the whole iteration process completed by the t-th iteration as a current global optimal solution, taking the position of a point corresponding to the current global optimal solution as the position of an optimal individual, taking a path curve generated according to the position of the optimal individual as a global optimal curve, judging whether the condition of iteration ending is reached or not, if not, returning to repeat the step 4-6 until the iteration is completed, and if so, entering the step 7;
step 7: and (3) taking the output global optimal curve as the current unmanned aerial vehicle path planning output, updating i=i+1, returning to the step (1) until i=n, and taking the output global optimal curve as the unmanned aerial vehicle path planning result.
In order to make the bated ray foraging optimization algorithm better applied to unmanned aerial vehicle path planning, the following improvements are carried out on the bated ray foraging optimization algorithm:
(1) The Tent chaotic mapping mechanism is introduced, the chaotic motion has the characteristics of randomness, regularity and ergodic property, and the characteristics can enable an algorithm to easily escape from a local optimal solution when solving a function optimization problem, so that the diversity of a population can be maintained, and the global searching capability is improved.
(2) The control parameter conf adjustment strategy is improved, and the global development capability and the local development capability are balanced.
(3) By adding the Levy flight strategy, for the path planning problem, the jump-out of the local optimal solution is the key of the intelligent optimization algorithm of the group, and the Lewk flight strategy in the cuckoo algorithm is characterized in that the Levy flight strategy randomly flies in a far-near alternative way, so that the capability of the algorithm for jumping out of the local optimal solution can be enhanced, and the calculation precision of the algorithm is improved.
The invention has the beneficial effects that by introducing a Tent chaotic map, controlling a parameter adjustment strategy and adding a levy flight strategy on the basis, the three improved introduction are integrated into a ray foraging optimization algorithm to obtain a final enhanced ray foraging optimization algorithm, and according to simulation results, the enhanced ray foraging optimization algorithm has better global property compared with the original ray foraging optimization algorithm; the method improves the precision of the flight path planning of the unmanned aerial vehicle, ensures smoother paths, saves iteration time and resources required by calculation, and completes the unmanned aerial vehicle flight ground task in a complex environment more efficiently.
Drawings
FIG. 1 is a flow chart of an unmanned aerial vehicle path planning algorithm based on an enhanced bata foraging optimization algorithm;
FIG. 2 is a three-dimensional map of an embodiment;
FIG. 3 is a graph comparing fitness function values of various algorithms;
FIG. 4 is a front view of a three-dimensional path plan;
FIG. 5 is a top view of a three-dimensional path plan;
Detailed Description
The following describes the embodiments of the present invention in further detail with reference to the drawings.
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in figure 1 of the drawings,
step 1: establishing a three-dimensional map with barriers; in particular, the obstacles include mountain obstacles and radar obstacles; setting the number of individuals contained in the ray population, and the maximum iteration number T;
an unmanned plane path between a starting point and a finishing point corresponding to a bate ray population, wherein a bate ray individual in the bate ray population is a position point in the unmanned plane path; randomly generating unmanned plane paths avoiding obstacles, and taking the paths as alternative bata ray populations; an individual ray is represented by xyz three-dimensional coordinates. The position coordinates of the ith ray of the ray are (x) i ,y i ,z i )。
After the map is generated, the horizontal and vertical xy axes of the map are divided into 100 x 100 matrices, the value on each matrix is the Z-axis coordinate value, and when the point (x p ,y p ,z p ) With mountain obstacle points (x) m ,y m ,z m ) In comparison, in the case of the same xy coordinates, z p Greater than z m In the process, the unmanned aerial vehicle is described as being above the obstacle, and no collision occurs, but the collision occurs.
When determining the position of each point between the starting point and the end point, a path is generated, and the process of determining a position coordinate of the individual bats ray by the enhanced bats ray foraging optimization algorithm of the present invention will be described in detail below.
To simplify the description, the following steps describe only the processing in the x-dimension, and the processing in the y-and z-dimensions is the same as the x-dimension.
Step 2: generating an initial ray population for iteration by adopting a Tent chaotic map based on the alternative ray population;
the adjustment value expression of the initial population generated by the Tent chaotic mapping on the x dimension is as follows:
wherein x is i (0) Is the initial position, x of the iteration of the ith ray individual i (t) is the position of the ith individual in the t-th iteration. u is a preset mapping parameter, and when u=0.5, the Tent mapping has the most typical form, and the obtained sequence has uniform distribution and approximately uniform distribution density for different parameters, so u=0.5 is preferable.
And (3) path adjustment: for each ray, the initial position is adjusted using the generated random number sequence. Generating three random number sequences (adjustment values) using three independent Tent maps to update (x i ,y i ,z i ) Obtain the adjusted position (x i (0),y i (0),z i (0))：
x i (0)＝x i +(r_x-0.5)*range_x
y i (0)＝y i +(r_y-0.5)*range_y
z i (0)＝z i +(r_z-0.5)*range_z
Where range_x, range_y, and range_z are parameters of the adjustment range, which are adjusted according to the specific problem and the size of the search space, here we set them to 0.5.
Step 3: calculating the fitness function value of each individual of the initial bated ray in the initial bated ray population according to the fitness function;
specifically, the calculation mode is as follows:
J＝w 1 ×f L +w 2 ×f R +w 3 ×f C +w 4 ×f H +p
wherein J is the individual of each ray, and the smaller the value is, the better the path is; w (w) 1 ，w 2 ，w 3 ，w 4 The sub-table represents the occupied weight of the corresponding parameter; wherein f L Represents the path curve length, f R Representing radar threat costs, f C Representing the cost of obstacle collision, f H Representing the cost of the high variation, p representing the penalty factor, the example takes a value of 10000, is used for when the route is passing through the obstacle or enters the radar range, will add the punishment value that the numerical value is positive to this route;
specifically, path curve length f L Determined by the following formula:
where n is the total number of points on the path, 1 point is not long enough, so the length is calculated from 2 points; x is x i Is the x-dimensional coordinates, y, of the i-th node on the path i ，z i And the same is true.
Cost of obstacle collision f C Determined by the following formula:
wherein x is obs Is the x-dimensional coordinates, y of the obstacle obs Is the y-dimensional coordinate, z, of the obstacle obs Is the z-dimensional coordinate of the obstruction.
Radar threat cost f R Determined by the following formula:
wherein, (x) r ,y r ,z r ) Is the xyz coordinate of the radar area.
Cost of altitude change f H Determined by the following formula:
wherein,is the z-dimensional coordinate average of n nodes.
Step 4: iteratively updating the positions of the individual bats, and punishing the collision points with the obstacles;
the chained foraging strategy, the spiral foraging strategy and the turnover foraging strategy used in the updating mode of the individual positions of the ray are all common techniques of the existing ray algorithm. In a specific selection of which strategy it is necessary to use a random value rand and a control parameter conf, the random value rand randomly generating values between 0,1 at the beginning of each iteration. The control parameter conf is updated with the number of iterations t. The control parameter conf plays an important role in balancing the global development capability and the local development capability of the algorithm, and the value is also between [0,1 ]. When conf < rand, all individuals search with random locations as reference locations, so the new individual is far from the best, at which point the global search capability of the algorithm is emphasized. When conf > rand, all individuals search with the best position as the reference position, focusing on the local development ability of the algorithm. The previous control parameter conf is set to conf=t/T, where T is the current number of iterations and T is the maximum number of iterations.
The applicant aims at the problem of low calculation precision of the Hepialus ray foraging optimization algorithm, and increases the local development capability of the algorithm by properly increasing the conf value in the iterative process, but cannot make the later stage unable to perform global exploration. The innovative way of setting the value of conf is adopted:e is a natural constant.
Describing the next generation position of each ray of the individual in detail of the x-dimensional iteration update, firstly generating a random value rand between [0,1], calculating a control parameter conf according to the current iteration times t, and then carrying out three steps of update iteration:
the first step: generate [0,1]]Random number r between them, and according to the size relation of rand, conf and preset threshold value, adopting different foraging strategies to obtain updated t+1st iteration of individual position x of the ray i ' (t+1): the embodiment sets the preset threshold to 0.5;
(1) When the rand is more than or equal to 0.5, the method is obtained by adopting a chained foraging strategy:
wherein x is i (t) is the position of the ith individual in the t-th iteration, r is a random number, x best (t) represents the position of the optimal individual in the whole iteration completed by the t-th iteration, and for the case where the first iteration starts t=0, the initial position x is used i (0) As the location of the optimal individual; alpha is a weight coefficient;
(2) When rand <0.5 and conf is equal to or greater than rand, adopting a spiral foraging strategy based on the optimal position as a reference position:
wherein β is a weight coefficient;
(3) When rand<0.5 and conf<In rand, a new random position x is adopted ramd Spiral foraging strategy as reference position:
x ramd ＝Lb+r·(Ub-Lb)
x ramd represents the randomly generated position in the search space in the t-th iteration, and Ub, lb are the upper and lower limits of the current position change, respectively.
And a second step of: after any one of the three modes is evolved, adopting a flip bucket foraging strategy to feed the x i ' update (t+1) to get x i ″(t+1)：
x i ″(t+1)＝x i ′(t+1)+S·(r 2 ·x best (t)-r 3 ·x i ′(t+1))i＝1,...,n；
S is a flip bucket foraging strategy parameter, and the embodiment sets s=2; r is (r) 2 ，r 3 Is [0,1]]Random numbers in between.
And a third step of: for the path planning problem, the jump-out of the local optimal solution is the key of a group intelligent optimization algorithm, and the Levy flight strategy in the cuckoo algorithm is characterized in that the Levy flight strategy is characterized in that the search range alternately flies far and near, the capacity of the jump-out of the local optimal solution can be enhanced, and the calculation precision of the algorithm is improved, so that the Levy flight strategy is adopted for x i Update (t+1) to get x i (t+1)，x i (t+1) is the x-dimensional position of the ray individual at the t+1st iteration:
x i (t+1)＝λL V (x besti (t)-x i ″(t+1))+x i ″(t+1)
wherein L is V Is a weight coefficient, the coefficient lambda is a proportional coefficient intermediate value u, v meets normal distribution, u-N (0, sigma) u 2 ),v～N(0,σ v 2 )。σ u 2 And sigma (sigma) v 2 Variance of normal distribution, sigma u ，σ v The definition is as follows:
σ v ＝1
wherein ρ is a coefficient having a value between [0,2], the example value is 1.5, Γ represents a factorization.
The position (x) of the ith ray individual of the (t+1) th iteration is obtained in the same manner i (t+1),y i (t+1),z i (t+1))。
Step 5: update the current ray individual (x) i (t+1),y i (t+1),z i (t+1)) as (x) i ,y i ,z i ) To calculate the corresponding path curve length f L Cost of radar threat f R Obstacle collision cost f C Cost of height change f H Setting a punishment factor p according to whether the current ray individual collides with the obstacle or not;
step 6: calculating the corresponding path curve length f using the determination of step 5 L Cost of radar threat f R Obstacle collision cost f C Cost of height change f H Setting punishment factor p according to whether the current individual is collided with obstacle, and calculating out current individual (x i (t+1),y i (t+1),z i (t+1)) fitness function value; the penalty factor p may be set to a sufficiently large value, such as 10000; in the event of a collision, p is assigned to f C The method comprises the steps of carrying out a first treatment on the surface of the F if no collision occurs C Is 0. Then updating t=t+1, reserving the minimum value of the fitness function value in the whole iteration process completed by the t-th iteration as a current global optimal solution, taking the position of a point corresponding to the current global optimal solution as the position of an optimal individual, judging whether a path curve generated according to the position of the optimal individual is a global optimal curve, if not, returning to repeat the step 4-6 until the iteration is completed, and if so, entering the step 7;
step 7: and (3) taking the output global optimal curve as an x-dimensional position, a y-dimensional position and a z-dimensional position of the current unmanned aerial vehicle path planning output in the same way, updating i=i+1, and returning to the step (1) until i=n, wherein the output global optimal curve is taken as a result of unmanned aerial vehicle path planning.
Examples
A map was created, as shown in fig. 2, with a starting point (5,5,1) and an ending point (90,90,5), having 3 simulated radar areas, 2 mountain obstacles, placed in a three-dimensional map, and 3 radar areas each having coordinates (40.5,57.5,2), (80,85,2), (38,30,2) being semi-circular spheres with radii of 7,8,9, respectively. The threat of 2 mountain barriers is (55,65,8) and (70,70,8) respectively, and the radii are 2. After the map is generated, the shortest path from the starting point to the end point is found by using the enhanced ray foraging algorithm.
Setting basic parameters, wherein the basic parameters comprise maximum iteration times T, population numbers, initial global optimal path values and path points. In this embodiment, the basic parameters are set to a maximum iteration number of 200, a population number of 50, an initial global optimum path value of infinity, a number of path points of 30, and then an empty structure is constructed, including the position information of the ray, the fitness function value information of the ray, target solution information of the individual bats, current optimal position information of the bats, the information of the current optimal fitness function value of the ray and the current optimal solution information of the ray. The related information of each individual of each iteration of the subsequent ray of the Hepialus-ray foraging algorithm updating iteration is stored
Among this structure.
The initialization parameters are that each individual ray represents a feasible path, which is a discrete path consisting of 30 path points. Starting from a first individual, generating the positions of the ray individuals by utilizing a Tent chaotic map, wherein the positions comprise x coordinate, y coordinate and z coordinate information in 30 path points in the ray individuals, generating the position information of 50 ray individuals by using a circulation sentence, and finally storing the position information into a ray structure. In the first iteration, namely initialization, initial current optimal solution information can be obtained, the fitness function value information exists in a global optimal structure body generated in advance, the position information exists in a front optimal structure body of a ray structure body generated in advance, and in the later iteration, the current optimal value obtained in the initial iteration is used for updating the position information of the ray individual.
In the subsequent updating iteration, the algorithm starts to approach gradually towards the direction of the optimal fitness function value, the algorithm is specifically updated in each iteration to obtain the position information of the batray, wherein the core part is the foraging updating mechanism part of the batray algorithm, and the position information in the code of the original batray algorithm is one-dimensional, and the position information and the model information in the path planning method are three-dimensional, so that the one-dimensional method in the updating mechanism of the original batray algorithm is required to be changed into three-dimensional.
The position updating mechanism decides the selection through the generated random number and conf, and adopts a chained foraging strategy when the rand is more than 0.5; when rand is less than 0.5 and conf is greater than or equal to rand, adopting a spiral foraging strategy based on the optimal position as a reference position; when rand <0.5 and conf is less than rand, a spiral foraging strategy based on a new random position as a reference position is employed. After any one of the three modes is evolved, the position is updated by adopting a flip bucket foraging strategy, and then the Lewy flight updated position is introduced.
The fitness is a detection mode for evaluating whether the position of each ray collides with an obstacle or not, and is also used for evaluating whether the length of a generated curve can be small enough or not, if the generated curve is smaller than a current global optimal solution, the generated curve information is replaced by the newly generated curve information, and if the generated curve information is larger than the current global optimal solution, the current global optimal solution is discarded.
Collision detection: after the map is generated, the X, Y coordinate axes of the map are divided into 100X 100 matrices, the value on each matrix is the Z-axis coordinate value, and when the point (X p ,y p ,z p ) And a point (x) m ,y m ,z m ) In comparison, x is the same abscissa p Greater than x m In the process, the unmanned aerial vehicle is described as being above the obstacle, and no collision occurs, but the collision occurs.
And adding the distances between all the discrete points in the graph to obtain curve lengths, wherein each iteration line curve is different, comparing the curve length of each iteration with the global optimum in an algorithm, if the curve length of each iteration is smaller than the current global optimum, replacing the curve length of the global optimum solution with the curve length of each iteration, if the curve length of each iteration is larger than the current global optimum, ignoring the curve length, retaining the current global optimum, and adopting different intelligent calculation methods for comparison, wherein the enhanced MRFO effect is optimal as shown in the graph of FIG. 3.
Finally, after 200 iterations, the algorithm finally finds an optimal path, and as shown in fig. 4 and 5, the optimal path is a front view and a top view of the generated path respectively, so that the length of the enhanced MRFO path is shorter and smoother.
Claims (4)
1. An unmanned aerial vehicle path planning method based on an enhanced ray foraging optimization algorithm is characterized by comprising the following steps:
step 1: establishing a three-dimensional map containing barriers, setting the number n of the ray individuals contained in the ray population, and setting the maximum iteration number T; a bate ray population corresponds to a pair of starting points and end points, and the bate ray individuals in the bate ray population are different unmanned aerial vehicle paths under the same starting points and end points; an unmanned plane path between a starting point and a finishing point corresponding to a bate ray population, wherein a bate ray individual in the bate ray population is a position point in the unmanned plane path; randomly generating unmanned plane paths avoiding obstacles, and taking the paths as alternative bata ray populations;
step 2: generating an initial ray population for iteration by adopting a Tent chaotic map based on the alternative ray population;
step 3: calculating the fitness function value of each individual of the initial bated ray in the initial bated ray population according to the fitness function;
step 4: iteratively updating the positions of the individual bats, specifically:
firstly, calculating a control parameter conf according to the current iteration times t, generating a random value rand with a value range of (0, 1), and setting a preset threshold value with the value range of (0, 1);e is a natural constant; and then adopting three steps of updating iteration:
the first step: different foraging strategies are adopted according to the size relation of rand, conf and a preset threshold value to obtain updated t+1st iteration of the individual positions of the bats: when the rand is greater than or equal to a preset threshold, adopting a chained foraging strategy; when the rand is smaller than a preset threshold value and the conf is larger than or equal to the rand, adopting a spiral foraging strategy based on the optimal position as a reference position; when the rand is smaller than a preset threshold value and the conf is smaller than the rand, adopting a spiral foraging strategy based on a new random position as a reference position;
and a second step of: adopting a flip bucket foraging strategy to update the positions of the individual units of the ray of the bats obtained in the first step, wherein the iteration is t+1st;
and a third step of: updating the updated result of the t+1st iteration of the individual positions of the ray obtained in the second step by adopting the Levy flight strategy to obtain the final t+1st iteration of the individual positions of the ray obtained in the step 4;
step 5: calculating corresponding path curve length f based on the individual positions of the batray of the t+1st iteration output in the step 4 L Cost of radar threat f R Obstacle collision cost f C Cost of height change f H Setting a punishment factor p according to whether the current ray individual collides with the obstacle or not;
step 6: f determined by step 5 L 、f R 、f C 、f H Calculating the fitness function value of the current individual ray; updating t=t+1, reserving the minimum value of the fitness function value in the whole iteration process completed by the t-th iteration as a current global optimal solution, taking the position of a point corresponding to the current global optimal solution as the position of an optimal individual, taking a path curve generated according to the position of the optimal individual as a global optimal curve, judging whether the condition of iteration ending is reached or not, if not, returning to repeat the step 4-6 until the iteration is completed, and if so, entering the step 7;
step 7: and (3) taking the output global optimal curve as the current unmanned aerial vehicle path planning output, updating i=i+1, returning to the step (1) until i=n, and taking the output global optimal curve as the unmanned aerial vehicle path planning result.
2. The method of claim 1, wherein the obstacle comprises a mountain obstacle and a radar obstacle.
3. The method according to claim 1, wherein step 2 is specifically:
2-1) first, according to the position coordinates of the ith individual (x) i ,y i ,z i ) Generating an adjustment value of the initial population by using the Tent chaotic map;
the adjusting value expression of the initial population generated by the Tent chaotic mapping on the x dimension is as follows:
wherein x is i (0) Is the x-dimensional initial position of the ith individual iteration of the ray, X is x i (t) is the x-dimensional position of the ith individual in the t-th iteration; u is a preset mapping parameter; the adjustment values r_y, r_z in the y-dimension and the z-dimension are obtained in the same way;
2-1) path adjustment: for each individual ray, three adjustment values r_x, r_y, r_z are generated using three independent Tent maps to calculate the initial individual ray position (x i (0),y i (0),z i (0))：
x i (0)＝x i +(r_x-0.5)*range_x
y i (0)＝y i +(r_y-0.5)*range_y
z i (0)＝z i +(r_z-0.5)*range_z
Where range_x, range_y, and range_z are parameters of the adjustment range.
4. The method of claim 1, wherein the fitness function value for each individual ray of the ray is calculated by:
J＝w 1 ×f L +w 2 ×f R +w 3 ×f C +w 4 ×f H +p
wherein J is the individual of each ray, and the smaller the value is, the better the path is; w (w) 1 ，w 2 ，w 3 ，w 4 The sub-table represents the occupied weight of the corresponding parameter; wherein f L Represents the path curve length, f R Representing radar threat costs, f C Representing the cost of obstacle collision, f H Representation ofThe altitude change cost, p, represents a penalty factor for adding a penalty value of positive value to the path when the path is in the range of passing through the obstacle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310792476.2A CN117308942A (en) | 2023-06-30 | 2023-06-30 | Unmanned aerial vehicle path planning method based on enhanced type bata foraging optimization algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310792476.2A CN117308942A (en) | 2023-06-30 | 2023-06-30 | Unmanned aerial vehicle path planning method based on enhanced type bata foraging optimization algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117308942A true CN117308942A (en) | 2023-12-29 |
Family
ID=89272550
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310792476.2A Pending CN117308942A (en) | 2023-06-30 | 2023-06-30 | Unmanned aerial vehicle path planning method based on enhanced type bata foraging optimization algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117308942A (en) |
-
2023
- 2023-06-30 CN CN202310792476.2A patent/CN117308942A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Mobile robot path planning using ant colony algorithm and improved potential field method | |
| Liu et al. | Multi-UAV path planning based on fusion of sparrow search algorithm and improved bioinspired neural network | |
| Li et al. | Trajectory planning for UAV based on improved ACO algorithm | |
| CN108388250B (en) | Water surface unmanned ship path planning method based on self-adaptive cuckoo search algorithm | |
| CN102013037A (en) | Method and device for searching path based on particle swarm optimization (PSO) | |
| CN108919818B (en) | Spacecraft attitude orbit collaborative planning method based on chaotic population variation PIO | |
| CN111664852A (en) | Unmanned aerial vehicle path planning method and device | |
| CN113848919A (en) | Ant colony algorithm-based indoor AGV path planning method | |
| CN116225066A (en) | Unmanned aerial vehicle path optimization method based on chaotic mapping pely optimization algorithm | |
| CN112269382B (en) | Robot multi-target path planning method | |
| CN110530373B (en) | Robot path planning method, controller and system | |
| CN113836803A (en) | Improved wolf colony algorithm-based unmanned aerial vehicle cluster resource scheduling method | |
| CN113391633A (en) | Urban environment-oriented mobile robot fusion path planning method | |
| Wang et al. | Research on dynamic path planning of wheeled robot based on deep reinforcement learning on the slope ground | |
| Bai et al. | Design and Simulation of a Collision-free Path Planning Algorithm for Mobile Robots Based on Improved Ant Colony Optimization. | |
| Song et al. | UAV Path Planning Based on an Improved Ant Colony Algorithm | |
| CN112486185A (en) | Path planning method based on ant colony and VO algorithm in unknown environment | |
| Cui et al. | Multi-strategy adaptable ant colony optimization algorithm and its application in robot path planning | |
| CN117308942A (en) | Unmanned aerial vehicle path planning method based on enhanced type bata foraging optimization algorithm | |
| CN116382299A (en) | Path planning method, path planning device, electronic equipment and storage medium | |
| Ma et al. | Robot path planning using fusion algorithm of ant colony optimization and genetic algorithm | |
| CN108921354A (en) | A method of the ant colony algorithm for solving TSP problems based on particle group optimizing | |
| Zhang et al. | Target Tracking and Path Planning of Mobile Sensor Based on Deep Reinforcement Learning | |
| CN114727251B (en) | Data transmission optimization method and system | |
| CN113780787B (en) | Collaborative task allocation method for multi-mobile-platform system under complex water environment |
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 |