CN112880688B - Unmanned aerial vehicle three-dimensional track planning method based on chaotic self-adaptive sparrow search algorithm - Google Patents
Unmanned aerial vehicle three-dimensional track planning method based on chaotic self-adaptive sparrow search algorithm Download PDFInfo
- Publication number
- CN112880688B CN112880688B CN202110110630.4A CN202110110630A CN112880688B CN 112880688 B CN112880688 B CN 112880688B CN 202110110630 A CN202110110630 A CN 202110110630A CN 112880688 B CN112880688 B CN 112880688B
- Authority
- CN
- China
- Prior art keywords
- sparrow
- algorithm
- track
- adaptive
- aerial vehicle
- 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.)
- Active
Links
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
-
- 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)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an unmanned aerial vehicle three-dimensional track planning method based on a chaotic self-adaptive sparrow search algorithm, which comprises the following steps of: building a flight environment model according to the flight environment; establishing an unmanned aerial vehicle flight cost function, and evaluating the performance of the unmanned aerial vehicle flight path; adopting a chaos initialization population strategy, a self-adaptive weight strategy and a Cauchy-Gaussian mixed variation strategy to improve a sparrow search algorithm, and providing a chaos self-adaptive sparrow search algorithm; planning the unmanned aerial vehicle track in the three-dimensional environment by adopting a chaotic self-adaptive sparrow searching algorithm to obtain an optimal solution of unmanned aerial vehicle track planning, and obtaining a planning result; the improved sparrow algorithm has obvious advantages in solving quality, the chaotic strategy and the self-adaptive strategy enable the algorithm to have high convergence speed and excellent convergence precision, and the variation strategy enables the algorithm to have strong capability of jumping out of local optimum, so that an excellent unmanned plane flight path can be obtained rapidly.
Description
Technical Field
The invention relates to the research field of unmanned aerial vehicle track optimization, in particular to an unmanned aerial vehicle three-dimensional track planning method based on a chaotic self-adaptive sparrow search algorithm.
Background
Unmanned aerial vehicle track planning is well known to be one of the important things defining unmanned aerial vehicle tasks. The three-dimensional path planning required for unmanned aerial vehicle flight tasks can be defined as a non-deterministic polynomial (NP) problem, the main purpose of which is to optimize the path from the departure point to the target point. In this process, a plurality of constraints need to be handled, such as performance constraints of the drone itself, threat constraints, environmental constraints, and so on. In order for the planned track to meet the actual flyable requirements, the track must also be smoothed. In summary, the unmanned three-dimensional track normalization problem can be considered as a multi-constraint optimization problem.
With the increasing complexity of planning problems, the difficulty and the calculated amount of corresponding solution also rapidly increase. According to the no free lunch theorem (NFL), an optimization algorithm may perform well in one set of questions and poorly in another set of questions. Therefore, an unmanned aerial vehicle track planning method which can effectively cope with all complex environments is difficult to find in the existing algorithm.
The sparrow search algorithm (Sparrow Search Algorithm, SSA) is a novel group intelligent optimization algorithm. The algorithm is developed through the elicitation of the foraging and anti-predation actions of sparrows. The standard SSA algorithm has the advantages of few adjustment parameters, high convergence speed, simple calculation and the like. However, in the aspect of defects, when solving the complex engineering optimization problem, the SSA algorithm starts to generate the phenomenon of 'early ripening', so that the convergence accuracy is not high, and the local optimization is easy to fall into, so that the flying property of the obtained track is not high when the track planning problem is directly solved by the standard SSA algorithm.
Disclosure of Invention
The invention mainly aims to overcome the defects and shortcomings of the prior art and provides an unmanned aerial vehicle three-dimensional track planning method based on a chaotic self-adaptive sparrow search algorithm.
The aim of the invention is achieved by the following technical scheme:
the unmanned aerial vehicle three-dimensional track planning method based on the chaotic self-adaptive sparrow searching algorithm is characterized by comprising the following steps of:
building a flight environment model according to the flight environment;
establishing an unmanned aerial vehicle flight cost function, and evaluating the performance of the unmanned aerial vehicle flight path;
adopting a chaos initialization population strategy, a self-adaptive weight strategy and a Cauchy-Gaussian mixed variation strategy to improve a sparrow search algorithm, and providing a chaos self-adaptive sparrow search algorithm;
and planning the unmanned aerial vehicle track in the three-dimensional environment by adopting a chaotic self-adaptive sparrow search algorithm to obtain an optimal solution of unmanned aerial vehicle track planning, and obtaining a planning result.
Further, the building of the flight environment model according to the flight environment is specifically as follows: and acquiring a digital elevation model of the target flight area, and processing by MATLAB to obtain a three-dimensional map model.
Further, the three-dimensional map model includes a threat region, and a flight start point and a target coordinate point and threat distribution coordinates are set in the three-dimensional map model.
Further, the three-dimensional flight path planning model is built, namely an unmanned aerial vehicle flight cost function is built, and the unmanned aerial vehicle flight path performance is evaluated, specifically:
setting performance indexes of three-dimensional flight path planning of the unmanned aerial vehicle: track length, flying height, maximum rotation angle;
acquiring the track length through a track length cost function; acquiring the flying height through a flying height model; obtaining a maximum corner through a corner cost model;
obtaining a track cost function through the track length cost function, the flying height model and the corner cost model:
J cost ＝w 1 L path +w 2 H height +w 3 J turn ，
wherein J is turn Is the total track cost function, L path Is a trackLength cost function, h height As a standard deviation cost function of height, J turn Is the corner cost function, parameter w i I=1, 2,3 represents the weight of each cost function, and the following condition is satisfied:
and solving the cost function to obtain a track composed of line segments, calling a B spline curve function by using an interpolation mode, and smoothing the obtained track to finally obtain the track which can be flown by the unmanned aerial vehicle.
Further, the track length is obtained through the track length cost function, as follows: setting the complete track to have n nodes, and the distance between the ith track point and the (i+1) th track point as l i The coordinates of the two track points are denoted as g (i) = (x) i ,y i ,z i ),g(i+1)＝(x i+1 ,y i+1 ,z i+1 ) The track needs to meet the following conditions:
wherein L is path As a track length cost function, say
The flying height is obtained through the flying height model, and the flying height is obtained as follows: the fly height model is:
wherein h is height For the standard deviation cost function of altitude, n is the number of track nodes,
as the height average value, z i The altitude of the ith track point;
the maximum rotation angle is obtained through the rotation angle cost model, and the maximum rotation angle is as follows: the corner cost model is as follows:
wherein J is turn Is a corner cost function, phi is the maximum corner, theta is the current corner, a i Is the ith flight path vector, |a i The i indicates the length of vector a.
Further, the improved chaotic self-adaptive sparrow searching algorithm is provided, a chaotic initialization population strategy is adopted in an algorithm initialization stage to enhance algorithm stability, a self-adaptive weight factor is introduced in a finder position updating stage, and a Cauchy-Gaussian mixed variation strategy is adopted for elite individuals; the following is shown:
adopting a standard SSA algorithm to simulate sparrow groups into a finder-jointer model, and superposing a reconnaissance early warning mechanism; the discoverer is an individual which is easy to find food, other individuals are joiners, meanwhile, the population selects a certain proportion of individuals as early warning persons, and forages at the position are abandoned if threat is detected; based on a standard SSA algorithm, an improved chaotic self-adaptive sparrow search algorithm is provided, a chaotic initialization population strategy is adopted in an algorithm initialization stage to enhance algorithm stability, a self-adaptive weight factor is introduced in a finder position updating stage, and a Cauchy-Gaussian mixed variation strategy is adopted for elite individuals;
further, the standard SSA algorithm comprises the following procedures:
initializing: setting the sparrow population scale N, the number of discoverers Pd, the number of early warning persons Sd, the dimension D of an objective function, the upper bound ub, the lower bound lb and the maximum iteration number T of initial values max ；
In the D-dimension search space, N sparrows exist, and the position of the ith sparrow in the D-dimension space is as follows:
X i ＝[x 1 ,…x D ],
where i=1, 2,..,
the fitness value of the ith sparrow can be expressed as:
wherein f represents a fitness value;
the discoverer with good adaptability can obtain food preferentially in the foraging process and provide foraging directions for all the participants, so that the discoverer has a larger search range than the participants; the location update formula is as follows:
wherein X is i The position of the ith sparrow in the D-dimensional space is represented, and t represents the current iteration times of the algorithm; alpha epsilon (0, 1)]Representing a random number; r is R 2 ∈(0,1]Representing early warning values, ST epsilon [0.5, 1) representing security values; q represents a random number subject to normal distribution; l represents a matrix of 1 row and 1 column with all elements 1; when R is 2 When ST is less than that of the search, the seeker can perform a wide range of search operations, if R 2 If not less than ST, indicating that part of sparrows find predators and send out alarm signals, and at the moment, all the sparrows need to be transferred to a safe position;
the rest sparrows of the population are all the participants, and the position update formula of the participants is as follows:
wherein X is i Representing the position of the ith sparrow in the D-dimensional space, T represents the current iteration frequency of the algorithm, and T max Represents the maximum iteration number of the algorithm, X best The method is characterized in that the method is the optimal position occupied by the current population, namely the individual position of elite sparrow, xworth is the worst position, Q represents random numbers obeying normal distribution, A is a d x d matrix, and each element of the matrix is randomly assigned with 1 or-1; l represents a matrix of 1 row and 1 column with all elements 1, when
Then forge near the optimal position, +.>
When the ith adding person does not acquire food, the ith adding person needs to fly to the place to find food; />
All sparrows in the population have a reconnaissance and early warning mechanism, and generally, the detected dangerous sparrows account for 10% -20% of the population, and the reconnaissance and early warning sparrows have a position updating formula as follows:
wherein X is i Representing the position of the ith sparrow in the D-dimensional space, t represents the current iteration frequency of the algorithm and X best Is the best position occupied by the current population, beta is a step size parameter, is a random number with mean value=0, variance=1 and obeys normal distribution; k epsilon [ -1,1]Is a random number, f i Is the adaptation degree of the ith sparrow, f b Is the current best fitness value, f w Is the current worst fitness value; epsilon is a constant and is between (1.00E-10,1.00E-9), so that the equation son can avoid the situation that the denominator is equal to zero.
Further, the improved chaotic self-adaptive sparrow searching algorithm specifically comprises the following steps:
adopting a cubic mapping chaotic operator to carry out population initialization on a sparrow algorithm:
p i+1 ＝4p i 3 -3p i
-1＜p i ＜1,p i ≠0,i＝0,1,...,N
X i ＝X lb +(X lb -X ub )×(p i +1)×0.5
wherein, p represents a cubic mapping chaotic operator, which is a D-dimensional vector with (-1, 1) value of each dimension, wherein X is expressed in the formula i Is the individual variable value of sparrow, X lb ，X ub The upper and lower boundaries of the sparrow individuals in each dimension;
using cubesMapping chaos operator to initialize sparrow population with population size N: randomly generating a d-dimensional vector, wherein each dimension takes (-1, 1) as a first operator, performing iterative operation on each dimension of the first operator to obtain the rest (N-1) operators, and finally mapping the operator values generated by cube mapping onto sparrow individuals by adopting (10), wherein X is the formula i Is the individual variable value of sparrow, X lb ，X ub The upper and lower boundaries of the sparrow individuals in each dimension;
introducing an adaptive weight factor strategy:
introducing a nonlinear time-varying self-adaptive weight factor w into a position updating formula of a finder, and leading a small fitness value to have a large optimizing range of the algorithm at the initial stage of iteration by introducing the self-adaptive weight factor, wherein the large fitness value is beneficial to improving the convergence accuracy of the algorithm at the later stage; alpha in the standard SSA finder position updating formula is a random number, and a dynamically nonlinear variable weight factor is introduced to control the value range of alpha, and the value range is defined as follows:
f in i Is the fitness value of the current sparrow individual, f g Is a global optimal fitness value, t is the current iteration number;
introducing a cauchy-Gaussian mixture variation strategy:
in the later stage of the solution of the sparrow algorithm, the sparrow population gradually gathers towards the optimal individual, which can lead to insufficient population diversity and cause the algorithm to fall into stagnation. In order to solve the problem, the invention introduces a cauchy-Gaussian mixture mutation strategy, carries out mutation operation on the individual with the best current fitness, selects the optimal individual from the individuals before and after mutation to enter the next iteration, and is defined as follows:
in the method, in the process of the invention,
is the current elite sparrow individual position with the best population adaptability, and is->
Is the position after the elite individual mutation, cauchy (0, 1) is the random variable satisfying the cauchy distribution, gauss (0, 1) is the random variable satisfying the gaussian distribution, and>
is a dynamic parameter adaptively adjusted with the iteration number.
Compared with the prior art, the invention has the following advantages and beneficial effects:
the improved sparrow algorithm has obvious advantages in solving quality, the chaotic strategy and the self-adaptive strategy of the improved sparrow algorithm enable the algorithm to have rapid convergence speed and excellent convergence precision, and the variation strategy enables the algorithm to have strong capability of jumping out of local optimum, so that an excellent unmanned aerial vehicle flight path can be obtained rapidly.
Drawings
FIG. 1 is a flow chart of a three-dimensional flight path planning method of an unmanned aerial vehicle based on a chaotic self-adaptive sparrow search algorithm;
FIG. 2 is a schematic representation of a three-dimensional map model in accordance with an embodiment of the present invention;
FIG. 3 is a schematic diagram of a threat distribution model in accordance with an embodiment of the invention;
FIG. 4 is a flowchart of a chaotic adaptive sparrow search algorithm in accordance with the exemplary embodiment of the present invention;
FIG. 5 is a simulation diagram of three-dimensional flight path planning of an unmanned aerial vehicle based on CASSA algorithm in the embodiment of the invention;
FIG. 6 is a simulation of two-dimensional trajectory planning in accordance with the embodiments of the present invention;
fig. 7 is a graph showing the convergence of the CASSA algorithm in the embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to examples and drawings, but embodiments of the present invention are not limited thereto.
Examples:
the unmanned aerial vehicle three-dimensional track planning method based on the chaotic self-adaptive sparrow searching algorithm is shown in fig. 1, and comprises the following steps:
building a flight environment model according to the flight environment;
establishing a three-dimensional flight path planning model, namely establishing an unmanned aerial vehicle flight cost function, and evaluating the performance of the unmanned aerial vehicle flight path;
the improved chaotic self-adaptive sparrow searching algorithm is provided, and concretely comprises the following steps: in the algorithm initialization stage, a chaos initialization population strategy is adopted to enhance algorithm stability, an adaptive weight factor is introduced in the finder position updating stage, and a Cauchy-Gaussian mixed variation strategy is adopted for elite sparrow individuals;
and applying the chaotic self-adaptive sparrow search algorithm to a flight path planning model to obtain an optimal solution, namely a planning result, of unmanned aerial vehicle flight path planning.
The method comprises the following steps:
the first step: building a flight environment model: firstly, a Digital Elevation Model (DEM) of a target flight area is acquired, and a three-dimensional map model is obtained through MATLAB processing, as shown in fig. 2. In addition, unmanned aerial vehicles often encounter areas of threat to flight safety, known as threat areas, when performing flight tasks, which may be enemy radar or missile systems, etc., where the unmanned aerial vehicle is likely to crash once entering the threat areas. To simplify the model, the present invention uses a cylindrical region with radius r to represent the threat region. The unmanned aerial vehicle flight start point (10, 90) and target point coordinates (140, 10), and threat distribution coordinates (10, 60), (30, 40), (60, 20), (70, 60), (120, 70), (110, 30) are set, and the threat distribution model is shown in fig. 3.
And a second step of: and establishing a three-dimensional flight path planning model, establishing a reasonable unmanned aerial vehicle flight cost function, and evaluating the unmanned aerial vehicle flight path performance. The performance indexes of the unmanned aerial vehicle three-dimensional track planning mainly comprise track length, flight height and maximum rotation angle, and the performance indexes are as follows: .
The track length is very important to the planning task, a shorter track can save more fuel and more time, and the probability of encountering other unknown threats is lower. The flight path is defined as the value of the distance the drone has traveled from the start point to the end point.
A complete track has n nodes, wherein the distance between the ith track point and the (i+1) th track point is l i The coordinates of the two track points are denoted as g (i) = (x) i ,y i ,z i ),g(i+1)＝(x i+1 ,y i+1 ,z i+1 ) The track needs to meet the following conditions:
wherein L is path As a path length cost function, if the unmanned aerial vehicle falls into a dangerous area or collides with an obstacle to face the risk of crashing, the unmanned aerial vehicle is marked as L path And E, carrying out punishment processing in the simulation.
The flying height needs enough stability, and too high a height is unfavorable for avoiding unknown threats, and too low a height can increase the collision probability of the unmanned aerial vehicle with mountain obstacle. The present invention uses the following flying height model:
wherein h is height For the standard deviation cost function of altitude, n is the number of track nodes,
is the average value of the height, z i Is the height of the ith track point.
The corner cost function affects the operability and flight stability of the unmanned aerial vehicle, and the corner of the flight path should not be larger than a preset maximum corner in the course of planning the flight path. The invention uses the following corner cost model:
wherein J is turn Is a corner cost function, phi is the maximum corner, theta is the current corner, a i Is the ith flight path vector, |a i The i indicates the length of vector a.
By establishing a cost function for the track length, the flight height and the maximum rotation angle, the obtained track cost function is as follows:
J cost ＝w 1 L path +w 2 H height +w 3 J turn (4)
wherein J is turn Is the total track cost function, parameter w i I=1, 2,3 represents the weight of each cost function, and the following condition is satisfied:
and solving the cost function to obtain a track consisting of line segments, calling a B spline curve function in an interpolation mode, and smoothing the acquired track to finally obtain the track which can be flown by the unmanned aerial vehicle.
And a third step of: track planning based on chaotic self-adaptive sparrow search algorithm: the chaotic self-adaptive sparrow searching algorithm is provided, a chaotic initialization population strategy is adopted in an algorithm initialization stage to enhance algorithm stability, a self-adaptive weight factor is introduced in a finder position updating stage, and the Cauchy-Gaussian mixed variation strategy is adopted for elite individuals to promote the algorithm to jump out of local optimal capacity.
The standard SSA algorithm is to find a solution to the optimization problem by simulating the feeding process of sparrows. The algorithm principle is as follows: simulating sparrow groups as a finder-joiner model, and superposing a reconnaissance early warning mechanism. The discoverer is an individual which can easily find food, other individuals are joiners, meanwhile, the population selects a certain proportion of individuals as early warning persons, and forages at the position are abandoned if threat is detected.
step1: initializing: setting the sparrow population scale N, the number of discoverers Pd, the number of early warning persons Sd, the dimension D of an objective function, the upper bound ub, the lower bound lb and the maximum iteration number T of initial values max 。
step2: in the D-dimension search space, N sparrows exist, and the position of the ith sparrow in the D-dimension space is X i ＝[x 1 ,...x D ]Where i=1, 2,.. the fitness value of the ith sparrow can be expressed as:
where f represents the fitness value.
step3: discoverers with better fitness will take food preferentially during the foraging process and provide foraging directions to all the participants, so that discoverers have a greater search range than the participants. The location update formula is as follows:
where t represents the number of current iterations of the algorithm. Alpha epsilon (0, 1)]Representing a random number. R is R 2 ∈(0,1]Representing the early warning value, ST e [0.5, 1) representing the security value. Q represents a random number subject to normal distribution. L represents a matrix of 1 row and 1 column with all elements 1. When R is 2 When ST is less than that of the search, the seeker can perform a wide range of search operations, if R 2 And (5) ST, indicating that part of sparrows find predators and give out alarm signals, and all sparrows need to be transferred to a safe position.
step4: the rest sparrows of the population are all the participants, and the position update formula of the participants is as follows:
wherein X is best Is the best position occupied by the current population, namely the individual position of elite sparrow, xworth is the worst position, and a is a d×d matrix, and each element of the matrix is randomly assigned 1 or-1. When (when)
Then food is sought around the optimal location,
when the ith participant does not acquire food, the ith participant needs to fly to the place to find food.
Step5: all sparrows in the population have a reconnaissance and early warning mechanism, and generally, the detected dangerous sparrows account for 10% -20% of the population, and the reconnaissance and early warning sparrows have a position updating formula as follows:
where β is a step parameter, which is a random number with mean=0, variance=1, and obeying normal distribution. K epsilon [ -1,1]Is a random number, f i Is the adaptation degree of the ith sparrow, f b Is the current best fitness value, f w Is the current worst fitness value. Epsilon is a constant and is between (1.00E-10,1.00E-9), so that the equation can avoid the situation that the denominator is equal to zero.
Fourth step: the specific improvement and application of the chaotic self-adaptive sparrow search algorithm are as follows:
the flow chart of the chaotic self-adaptive sparrow search algorithm is shown in fig. 4:
introducing a chaos initialization population strategy:
when solving the complex optimization problem, the sparrow algorithm has the defect of reduced population diversity in the later iteration population, is easy to converge in premature and falls into local optimum. Therefore, the invention adopts the cubic mapping chaotic operator to carry out population initialization on the sparrow algorithm, and can improve the population diversity of the algorithm according to the randomness and regularity advantages of the chaotic operator.
X i ＝X lb +(X lb -X ub )×(p i +1)×0.5 (10)
Initializing sparrow populations with the population size of N by adopting a cubic mapping chaotic operator: randomly generating a d-dimensional vector, wherein each dimension takes (-1, 1) as a first operator, performing iterative operation on each dimension of the first operator by adopting a formula (9) to obtain the rest (N-1) operators, and finally mapping operator values generated by cube mapping onto sparrow individuals by adopting a formula (10), wherein X is the formula i Is the individual variable value of sparrow, X lb ，X ub Is the upper and lower boundaries of sparrow individuals in each dimension.
Introducing an adaptive weight factor strategy:
the nonlinear time-varying self-adaptive weight factor w is introduced into the position updating formula of the step3 finder, and the algorithm has a larger optimizing range due to a smaller fitness value at the initial stage of iteration by introducing the self-adaptive weight factor, and the convergence accuracy of the algorithm is improved due to the larger fitness value at the later stage. The alpha in the standard SSA finder position updating formula is a random number, and the invention introduces a dynamic nonlinear variation weight factor to control the value range of the alpha, and the definition is as follows:
f in i Is the fitness value of the current sparrow individual, f g Is the global best fitness value, t is the current iteration number.
Introducing a cauchy-Gaussian mixture variation strategy:
in the later stage of the solution of the sparrow algorithm, the sparrow population gradually gathers towards the optimal individual, which can lead to insufficient population diversity and cause the algorithm to fall into stagnation. In order to solve the problem, the invention introduces a cauchy-Gaussian mixture mutation strategy, carries out mutation operation on the individual with the best current fitness, selects the optimal individual from the individuals before and after mutation to enter the next iteration, and is defined as follows:
in the method, in the process of the invention,
is the current elite sparrow individual position with the best population adaptability, and is->
Is the position after the elite individual mutation, cauchy (0, 1) is the random variable satisfying the cauchy distribution, gauss (0, 1) is the random variable satisfying the gaussian distribution, and>
is a dynamic parameter adaptively adjusted with the iteration number.
Simulation verification:
and the CASSA algorithm is used for solving the three-dimensional track planning problem of the unmanned aerial vehicle, and the CASSA is used for optimizing and solving the objective function. In the algorithm, each sparrow represents a track, the dimension of each sparrow represents the number of track points, the value of each dimension of each sparrow represents the coordinate value of the track point, and the fitness of each sparrow is the objective function value of the unmanned aerial vehicle track, and is lower and better. The finch population discoverer is an individual with a better current objective function value, the follower is a worse individual, the optimal position of the finch population is obtained by updating the positions of the discoverer and the follower, and the optimal solution returned after the algorithm reaches the maximum iteration number is the optimal track found. The three-dimensional flight path planning simulation diagram of the unmanned aerial vehicle based on the CASSA algorithm is shown in fig. 5, and fig. 6 is a two-dimensional flight path planning simulation diagram; fig. 7 is a graph of the CASSA algorithm convergence.
The specific implementation flow is as follows:
the first step: and initializing parameters, namely initializing each parameter of the CASSA algorithm, such as the maximum iteration times, the population scale, the number of discoverers and early warning persons, and the like, and setting the weights of three cost functions of unmanned aerial vehicle track planning.
And a second step of: setting a flight starting point coordinate and a flight ending point coordinate of the unmanned aerial vehicle, and setting a coordinate of a threat area and a threat range.
And a third step of: and carrying out optimization solution on the unmanned aerial vehicle track evaluation function by using a CASSA algorithm, and continuously updating and storing the acquired optimal track.
Fourth step: judging whether the algorithm reaches the maximum iteration times, if not, continuing to execute the loop, and if so, ending the algorithm, and outputting the acquired optimal track.
The above examples are preferred embodiments of the present invention, but the embodiments of the present invention are not limited to the above examples, and any other changes, modifications, substitutions, combinations, and simplifications that do not depart from the spirit and principle of the present invention should be made in the equivalent manner, and the embodiments are included in the protection scope of the present invention.
Claims (5)
1. The unmanned aerial vehicle three-dimensional track planning method based on the chaotic self-adaptive sparrow searching algorithm is characterized by comprising the following steps of:
building a flight environment model according to the flight environment;
establishing an unmanned aerial vehicle flight cost function, and evaluating the performance of the unmanned aerial vehicle flight path;
adopting a chaos initialization population strategy, a self-adaptive weight strategy and a Cauchy-Gaussian mixed variation strategy to improve a sparrow search algorithm, and providing a chaos self-adaptive sparrow search algorithm;
planning the unmanned aerial vehicle track in the three-dimensional environment by adopting a chaotic self-adaptive sparrow searching algorithm to obtain an optimal solution of unmanned aerial vehicle track planning, and obtaining a planning result;
the chaotic initialization population strategy, the adaptive weight strategy and the Cauchy-Gaussian mixture variation strategy are adopted to improve the sparrow search algorithm, and the chaotic adaptive sparrow search algorithm is provided as follows:
adopting a standard SSA algorithm to simulate sparrow groups into a finder-jointer model, and superposing a reconnaissance early warning mechanism; the discoverer is an individual which is easy to find food, other individuals are joiners, meanwhile, the population selects a certain proportion of individuals as early warning persons, and forages at the position are abandoned if threat is detected; based on a standard SSA algorithm, an improved chaotic self-adaptive sparrow search algorithm is provided, a chaotic initialization population strategy is adopted in an algorithm initialization stage to enhance algorithm stability, a self-adaptive weight factor is introduced in a finder position updating stage, and a Cauchy-Gaussian mixed variation strategy is adopted for elite individuals;
the standard SSA algorithm comprises the following steps:
initializing: setting a sparrow population scale N, the number Pd of discoverers, the number Sd of early warning persons, the dimension D of an objective function, the upper bound ub, the lower bound lb of an initial value and the maximum iteration number ss;
in the D-dimension search space, N sparrows exist, and the position of the ith sparrow in the D-dimension space is as follows:
X i ＝[x 1 ,...x D ],
where i=1, 2,..,
the fitness value of the ith sparrow can be expressed as:
wherein f represents a fitness value;
the discoverer with good adaptability can obtain food preferentially in the foraging process and provide foraging directions for all the participants, so that the discoverer has a larger search range than the participants; the location update formula is as follows:
wherein X is i The position of the ith sparrow in the D-dimensional space is represented, and t represents the current iteration times of the algorithm; alpha epsilon (0, 1)]Representing a random number; r is R 2 ∈(0,1]Representing early warning values, ST epsilon [0.5, 1) representing security values; q represents a random number subject to normal distribution; l represents a matrix of 1 row and 1 column with all elements 1; when R is 2 When ST is less than that of the search, the seeker can perform a wide range of search operations, if R 2 If not less than ST, indicating that part of sparrows find predators and send out alarm signals, and at the moment, all the sparrows need to be transferred to a safe position;
the rest sparrows of the population are all the participants, and the position update formula of the participants is as follows:
wherein X is i Representing the position of the ith sparrow in the D-dimensional space, T represents the current iteration frequency of the algorithm, and T max Represents the maximum iteration number of the algorithm, X best Is the best position occupied by the current population, namely the individual position of elite sparrow, X worst Is the worst position, Q represents a random number subject to normal distribution, A is a d x d matrix, and each element of the matrix is randomly assigned 1 or-1; l represents a matrix of 1 row and 1 column with all elements 1, when
Then forge near the optimal position, +.>
When the ith adding person does not acquire food, the ith adding person needs to fly to the place to find food;
all sparrows in the population have a reconnaissance and early warning mechanism, and generally, the detected dangerous sparrows account for 10% -20% of the population, and the reconnaissance and early warning sparrows have a position updating formula as follows:
wherein X is i Representing the position of the ith sparrow in the D-dimensional space, t represents the current iteration frequency of the algorithm and X best Is the best position occupied by the current population, beta is a step size parameter, is a random number with mean value=0, variance=1 and obeys normal distribution; k epsilon [ -1,1]Is a random number, f i Is the adaptation degree of the ith sparrow, f b Is the current best fitness value, f w Is the current worst fitness value; epsilon is a constant and the value is between 1.00E and 10,1.00E and 9, so that the formula avoids the situation that the denominator is equal to zero;
the improved chaotic self-adaptive sparrow searching algorithm specifically comprises the following steps:
adopting a cubic mapping chaotic operator to carry out population initialization on a sparrow algorithm:
p i+1 ＝4p i 3 -3p i
-1＜p i ＜1,p i ≠0,i＝0,1,K,N
X i ＝X lb +(X lb -X ub )×(p i +1)×0.5
wherein, p represents a cubic mapping chaotic operator, which is a D-dimensional vector with (-1, 1) value of each dimension, wherein X is expressed in the formula i Is the individual variable value of sparrow, X lb ，X ub The upper and lower boundaries of the sparrow individuals in each dimension;
initializing sparrow populations with the population size of N by adopting a cubic mapping chaotic operator: randomly generating a d-dimensional vector, wherein each dimension takes (-1, 1) as a first operator, performing iterative operation on each dimension of the first operator to obtain the rest (N-1) operators, and finally mapping the operator values generated by cube mapping onto sparrow units, wherein X is the formula i Is the individual variable value of sparrow, X lb ，X ub The upper and lower boundaries of the sparrow individuals in each dimension;
introducing an adaptive weight factor strategy:
introducing a nonlinear time-varying self-adaptive weight factor w into a position updating formula of a finder, and leading a small fitness value to have a large optimizing range of the algorithm at the initial stage of iteration by introducing the self-adaptive weight factor, wherein the large fitness value is beneficial to improving the convergence accuracy of the algorithm at the later stage; alpha in the standard SSA finder position updating formula is a random number, and a dynamically nonlinear variable weight factor is introduced to control the value range of alpha, and the value range is defined as follows:
f in i Is the fitness value of the current sparrow individual, f g Is a global optimal fitness value, t is the current iteration number;
introducing a cauchy-Gaussian mixture variation strategy:
in the later solving stage of the sparrow algorithm, the sparrow population gradually gathers towards the optimal individual, which can lead to insufficient population diversity and cause the algorithm to fall into stagnation; in order to solve the problem, a cauchy-Gaussian mixture mutation strategy is introduced, mutation operation is carried out on an individual with the best current fitness, and the optimal individual is selected from individuals before and after mutation to enter the next iteration, wherein the method is defined as follows:
in the method, in the process of the invention,
is the current elite sparrow individual position with the best population adaptability, and is->
Is the position after the individual elite is mutatedCauchy (0, 1) is a random variable satisfying the cauchy distribution, gauss (0, 1) is a random variable satisfying the gaussian distribution,
is a dynamic parameter adaptively adjusted with the iteration number.
2. The unmanned aerial vehicle three-dimensional track planning method based on the chaotic self-adaptive sparrow search algorithm according to claim 1, wherein the method is characterized in that a flight environment model is built according to a flight environment, and specifically comprises the following steps: and acquiring a digital elevation model of the target flight area, and processing by MATLAB to obtain a three-dimensional map model.
3. The unmanned aerial vehicle three-dimensional track planning method based on the chaotic self-adaptive sparrow search algorithm according to claim 2, wherein the three-dimensional map model comprises a threat area, and a flight starting point, a target coordinate point and threat distribution coordinates are set in the three-dimensional map model.
4. The unmanned aerial vehicle three-dimensional track planning method based on the chaotic self-adaptive sparrow search algorithm according to claim 1, wherein the unmanned aerial vehicle flight cost function is established to evaluate unmanned aerial vehicle track performance, specifically:
setting performance indexes of three-dimensional flight path planning of the unmanned aerial vehicle: track length, flying height, maximum rotation angle;
acquiring the track length through a track length cost function; acquiring the flying height through a flying height model; obtaining a maximum corner through a corner cost model;
obtaining a track cost function through the track length cost function, the flying height model and the corner cost model:
J cost ＝w 1 L path +w 2 H height +w 3 J turn ，
wherein J is cost Is the total track cost function, L path For track length cost function, H height As a standard deviation cost function of height, J turn Is the corner cost function, parameter w i I=1, 2,3 represents the weight of each cost function, and the following condition is satisfied:
and solving the cost function to obtain a track composed of line segments, calling a B spline curve function by using an interpolation mode, and smoothing the obtained track to finally obtain the track which can be flown by the unmanned aerial vehicle.
5. The three-dimensional track planning method of the unmanned aerial vehicle based on the chaotic self-adaptive sparrow search algorithm according to claim 4, wherein the track length is obtained through a track length cost function as follows: setting the complete track to have n nodes, and the distance between the ith track point and the (i+1) th track point as l i The coordinates of the two track points are denoted as g (i) = (x) i ,y i ,z i ),g(i+1)＝(x i+1 ,y i+1 ,z i+1 ) The track needs to meet the following conditions:
wherein L is path As a function of the track length cost,
the flying height is obtained through the flying height model, and the flying height is obtained as follows: the fly height model is:
wherein H is height For the standard deviation cost function of altitude, n is the number of track nodes,
as the height average value, z i The altitude of the ith track point;
the maximum rotation angle is obtained through the rotation angle cost model, and the maximum rotation angle is as follows: the corner cost model is as follows:
wherein J is turn Is a corner cost function, phi is the maximum corner, theta is the current corner, a i Is the ith flight path vector, |a i The i represents vector a i Is a length of (c).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110110630.4A CN112880688B (en) | 2021-01-27 | 2021-01-27 | Unmanned aerial vehicle three-dimensional track planning method based on chaotic self-adaptive sparrow search algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110110630.4A CN112880688B (en) | 2021-01-27 | 2021-01-27 | Unmanned aerial vehicle three-dimensional track planning method based on chaotic self-adaptive sparrow search algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112880688A CN112880688A (en) | 2021-06-01 |
| CN112880688B true CN112880688B (en) | 2023-05-23 |
Family
ID=76053375
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110110630.4A Active CN112880688B (en) | 2021-01-27 | 2021-01-27 | Unmanned aerial vehicle three-dimensional track planning method based on chaotic self-adaptive sparrow search algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112880688B (en) |
Families Citing this family (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113344828B (en) * | 2021-06-30 | 2023-05-30 | 太原理工大学 | Coal-rock demarcation image enhancement method based on chaotic sparrow search algorithm |
| CN113759313B (en) * | 2021-07-23 | 2023-09-29 | 哈尔滨工程大学 | Time difference/frequency difference positioning method based on chaotic sparrow algorithm |
| CN113762603B (en) * | 2021-08-13 | 2023-08-22 | 广西大学 | Photovoltaic base station short-term photovoltaic power prediction method based on improved sparrow algorithm optimization |
| CN113805568B (en) * | 2021-08-17 | 2024-04-09 | 北京理工大学 | Man-machine collaborative perception method based on multi-agent space-time modeling and decision |
| CN113947009B (en) * | 2021-08-31 | 2024-03-08 | 西北大学 | Sparse LSTM landslide dynamic prediction method based on Cauchy disturbance sparrow optimization |
| CN114115329B (en) * | 2021-10-28 | 2023-06-16 | 中国人民解放军陆军工程大学 | Relay collaborative unmanned aerial vehicle task planning method and device |
| CN114020031B (en) * | 2021-11-16 | 2023-09-22 | 南京航空航天大学 | Unmanned aerial vehicle cluster collaborative dynamic target searching method based on improved pigeon colony optimization |
| CN114237282B (en) * | 2021-11-29 | 2023-10-27 | 南京邮电大学 | Unmanned aerial vehicle flight path intelligent planning method for intelligent industrial park monitoring |
| CN113867369B (en) * | 2021-12-03 | 2022-03-22 | 中国人民解放军陆军装甲兵学院 | Robot path planning method based on alternating current learning seagull algorithm |
| CN114485665A (en) * | 2021-12-31 | 2022-05-13 | 东华大学 | Unmanned aerial vehicle flight path planning method based on sparrow search algorithm |
| CN114417712B (en) * | 2022-01-01 | 2023-07-04 | 西北工业大学 | Airship propeller reliability estimation method based on chaos initialization SSA-BP neural network |
| CN114460941B (en) * | 2022-02-09 | 2023-10-24 | 云南大学 | Robot path planning method and system based on improved sparrow search algorithm |
| CN114440893A (en) * | 2022-02-16 | 2022-05-06 | 北京邮电大学 | Cooperative positioning method, system and storage medium for resolving TDOA (time difference of arrival) signals |
| CN115018149B (en) * | 2022-06-01 | 2023-04-28 | 南京林业大学 | Method for planning take-off and landing points of helicopter aviation pesticide application aircraft |
| CN114995149B (en) * | 2022-06-13 | 2023-06-13 | 南通大学 | Hydraulic position servo system improved chaos variable weight sparrow search parameter identification method |
| CN115277770B (en) * | 2022-07-20 | 2023-04-25 | 华北电力大学（保定） | Unmanned aerial vehicle information collection method based on joint optimization of node access and flight strategy |
| CN115542944A (en) * | 2022-10-24 | 2022-12-30 | 广东电网有限责任公司云浮供电局 | Multi-unmanned aerial vehicle path planning method based on power distribution network environment and related device |
| CN115542936B (en) * | 2022-10-28 | 2024-04-16 | 中国地质大学（武汉） | Intelligent optimization method and device for steering engine layout of aeromagnetic unmanned aerial vehicle and electronic equipment |
| CN115657693B (en) | 2022-12-28 | 2023-03-17 | 安徽省交通航务工程有限公司 | Ship path optimization method, electronic device and storage medium |
| CN116562331B (en) * | 2023-05-19 | 2023-11-21 | 石家庄铁道大学 | Method for optimizing SVM by improving reptile search algorithm and application thereof |
| CN117056847B (en) * | 2023-10-10 | 2024-01-30 | 中南大学 | Method, system, equipment and storage medium for detecting abnormality of stream data |
| CN117170413B (en) * | 2023-11-03 | 2024-01-30 | 北京卓翼智能科技有限公司 | Unmanned aerial vehicle path planning method and device based on modified sine and cosine algorithm |
| CN117807356B (en) * | 2024-02-29 | 2024-05-10 | 齐鲁工业大学(山东省科学院) | Double-vector hydrophone positioning method based on improved sparrow algorithm optimized particle filtering |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1835370A2 (en) * | 2006-03-17 | 2007-09-19 | Thales | Automatic trajectory planner |
| CN108413959A (en) * | 2017-12-13 | 2018-08-17 | 南京航空航天大学 | Based on the Path Planning for UAV for improving Chaos Ant Colony Optimization |
| US10140875B1 (en) * | 2017-05-27 | 2018-11-27 | Hefei University Of Technology | Method and apparatus for joint optimization of multi-UAV task assignment and path planning |
| CN109144102A (en) * | 2018-09-19 | 2019-01-04 | 沈阳航空航天大学 | A kind of Path Planning for UAV based on improvement bat algorithm |
| CN109631900A (en) * | 2018-12-24 | 2019-04-16 | 中国矿业大学 | A kind of no-manned plane three-dimensional track multi-objective particle swarm Global Planning |
| CN110608743A (en) * | 2019-10-18 | 2019-12-24 | 南京航空航天大学 | Multi-unmanned aerial vehicle collaborative route planning method based on multi-population chaotic grayling algorithm |
| JP2020019336A (en) * | 2018-07-31 | 2020-02-06 | 旻新科技股▲分▼有限公司 | Planning method for flight path of unmanned aerial vehicle using flight route of bird |
| CN111815055A (en) * | 2020-07-11 | 2020-10-23 | 哈尔滨理工大学 | Unmanned aerial vehicle flight path planning method based on improved Levy flight ant lion optimization algorithm |
| CN112033416A (en) * | 2020-09-18 | 2020-12-04 | 中原工学院 | Static track planning method and device for unmanned aerial vehicle |
| CN112130581A (en) * | 2020-08-19 | 2020-12-25 | 昆明理工大学 | Unmanned aerial vehicle cluster cooperative task planning method for aerial maneuver battle |
| CN112230678A (en) * | 2020-10-29 | 2021-01-15 | 皖江工学院 | Three-dimensional unmanned aerial vehicle path planning method and planning system based on particle swarm optimization |
-
2021
- 2021-01-27 CN CN202110110630.4A patent/CN112880688B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1835370A2 (en) * | 2006-03-17 | 2007-09-19 | Thales | Automatic trajectory planner |
| US10140875B1 (en) * | 2017-05-27 | 2018-11-27 | Hefei University Of Technology | Method and apparatus for joint optimization of multi-UAV task assignment and path planning |
| CN108413959A (en) * | 2017-12-13 | 2018-08-17 | 南京航空航天大学 | Based on the Path Planning for UAV for improving Chaos Ant Colony Optimization |
| JP2020019336A (en) * | 2018-07-31 | 2020-02-06 | 旻新科技股▲分▼有限公司 | Planning method for flight path of unmanned aerial vehicle using flight route of bird |
| CN109144102A (en) * | 2018-09-19 | 2019-01-04 | 沈阳航空航天大学 | A kind of Path Planning for UAV based on improvement bat algorithm |
| CN109631900A (en) * | 2018-12-24 | 2019-04-16 | 中国矿业大学 | A kind of no-manned plane three-dimensional track multi-objective particle swarm Global Planning |
| CN110608743A (en) * | 2019-10-18 | 2019-12-24 | 南京航空航天大学 | Multi-unmanned aerial vehicle collaborative route planning method based on multi-population chaotic grayling algorithm |
| CN111815055A (en) * | 2020-07-11 | 2020-10-23 | 哈尔滨理工大学 | Unmanned aerial vehicle flight path planning method based on improved Levy flight ant lion optimization algorithm |
| CN112130581A (en) * | 2020-08-19 | 2020-12-25 | 昆明理工大学 | Unmanned aerial vehicle cluster cooperative task planning method for aerial maneuver battle |
| CN112033416A (en) * | 2020-09-18 | 2020-12-04 | 中原工学院 | Static track planning method and device for unmanned aerial vehicle |
| CN112230678A (en) * | 2020-10-29 | 2021-01-15 | 皖江工学院 | Three-dimensional unmanned aerial vehicle path planning method and planning system based on particle swarm optimization |
Non-Patent Citations (5)
| Title |
|---|
| A novel swarm intelligence optimization approach：sparrow search algorithm;XUE J等;《Systems Science and Control Engineering》;第8卷(第1期);第22-34页 * |
| Obstacle Avoidance of UAV Based on Neural Networks and Interfered Fluid Dynamical System;Wang Y等;《2020 3rd International Conference on Unmanned Systems》;第1066-1071页 * |
| 一种新型的群智能优化技术的研究与应用 ——麻雀搜索算法;薛建凯;《中国优秀硕士学位论文全文数据库信息科技辑(月刊)》(第1期);第I140-134页 * |
| 基于动态路径规划的车载自组织网络贪婪路由协议;赵普凡等;《国外电子测量技术》;第39卷(第11期);第46-51页 * |
| 基于混沌麻雀搜索算法的无人机航迹规划方法;汤安迪等;《计算机应用》;第41卷(第7期);第1-11页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112880688A (en) | 2021-06-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112880688B (en) | Unmanned aerial vehicle three-dimensional track planning method based on chaotic self-adaptive sparrow search algorithm | |
| CN110608743B (en) | Multi-unmanned aerial vehicle collaborative route planning method based on multi-population chaotic grayling algorithm | |
| CN113791634B (en) | Multi-agent reinforcement learning-based multi-machine air combat decision method | |
| CN108153328B (en) | Multi-missile collaborative track planning method based on segmented Bezier curve | |
| Yang et al. | UAV air combat autonomous maneuver decision based on DDPG algorithm | |
| CN110456823B (en) | Double-layer path planning method aiming at unmanned aerial vehicle calculation and storage capacity limitation | |
| CN111240353B (en) | Unmanned aerial vehicle collaborative air combat decision method based on genetic fuzzy tree | |
| CN110928329B (en) | Multi-aircraft track planning method based on deep Q learning algorithm | |
| CN110412874B (en) | Multi-missile cooperative guidance law design method for maneuvering target and time delay communication | |
| CN111859541B (en) | PMADDPG multi-unmanned aerial vehicle task decision method based on transfer learning improvement | |
| CN114330115B (en) | Neural network air combat maneuver decision-making method based on particle swarm search | |
| CN110986958B (en) | Multi-unmanned aerial vehicle collaborative path planning method based on multi-population collaborative drosophila optimization | |
| CN114063644B (en) | Unmanned fighter plane air combat autonomous decision-making method based on pigeon flock reverse countermeasure learning | |
| CN112666981B (en) | Unmanned aerial vehicle cluster dynamic route planning method based on dynamic group learning of original pigeon group | |
| CN108983800B (en) | Airplane attitude control method based on deep learning | |
| CN114485665A (en) | Unmanned aerial vehicle flight path planning method based on sparrow search algorithm | |
| CN113159266A (en) | Air combat maneuver decision method based on sparrow search neural network | |
| CN113139331A (en) | Air-to-air missile situation perception and decision method based on Bayesian network | |
| CN113625569A (en) | Small unmanned aerial vehicle prevention and control hybrid decision method and system based on deep reinforcement learning and rule driving | |
| CN113741186B (en) | Double-aircraft air combat decision-making method based on near-end strategy optimization | |
| CN116661496B (en) | Multi-patrol-missile collaborative track planning method based on intelligent algorithm | |
| Kaneshige et al. | Artificial immune system approach for air combat maneuvering | |
| CN110986948B (en) | Multi-unmanned aerial vehicle grouping collaborative judgment method based on reward function optimization | |
| CN115422776A (en) | Multi-base heterogeneous unmanned cluster multi-wave-time unified cooperative task allocation method and system | |
| CN114819055A (en) | Missile interception point prediction method based on LSTM network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |