CN109144102A - A kind of Path Planning for UAV based on improvement bat algorithm - Google Patents
A kind of Path Planning for UAV based on improvement bat algorithm Download PDFInfo
- Publication number
- CN109144102A CN109144102A CN201811091770.6A CN201811091770A CN109144102A CN 109144102 A CN109144102 A CN 109144102A CN 201811091770 A CN201811091770 A CN 201811091770A CN 109144102 A CN109144102 A CN 109144102A
- Authority
- CN
- China
- Prior art keywords
- bat
- aerial vehicle
- unmanned aerial
- algorithm
- threat
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 claims abstract description 68
- 230000000694 effects Effects 0.000 claims abstract description 17
- 238000009826 distribution Methods 0.000 claims abstract description 10
- 230000008859 change Effects 0.000 claims abstract description 6
- 230000004888 barrier function Effects 0.000 claims abstract 2
- 230000008569 process Effects 0.000 claims description 27
- 238000005457 optimization Methods 0.000 claims description 13
- 239000000446 fuel Substances 0.000 claims description 10
- 238000009499 grossing Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 9
- 230000007246 mechanism Effects 0.000 claims description 7
- 241000288673 Chiroptera Species 0.000 claims description 6
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 230000008901 benefit Effects 0.000 claims description 5
- 230000000739 chaotic effect Effects 0.000 claims description 5
- 230000009194 climbing Effects 0.000 claims description 4
- 230000003068 static effect Effects 0.000 claims description 4
- 230000001133 acceleration Effects 0.000 claims description 3
- 230000014509 gene expression Effects 0.000 claims description 3
- 230000005686 electrostatic field Effects 0.000 claims description 2
- 238000011478 gradient descent method Methods 0.000 claims description 2
- 230000010354 integration Effects 0.000 claims description 2
- 230000005012 migration Effects 0.000 claims description 2
- 238000013508 migration Methods 0.000 claims description 2
- 238000005295 random walk Methods 0.000 claims description 2
- 230000007704 transition Effects 0.000 claims description 2
- 238000009827 uniform distribution Methods 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 claims 1
- 230000008713 feedback mechanism Effects 0.000 claims 1
- FTOAOBMCPZCFFF-UHFFFAOYSA-N 5,5-diethylbarbituric acid Chemical compound CCC1(CC)C(=O)NC(=O)NC1=O FTOAOBMCPZCFFF-UHFFFAOYSA-N 0.000 description 27
- 238000004088 simulation Methods 0.000 description 15
- 238000010586 diagram Methods 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 6
- 238000002474 experimental method Methods 0.000 description 6
- 230000007547 defect Effects 0.000 description 4
- 230000009189 diving Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000013211 curve analysis Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A kind of Path Planning for UAV based on improvement bat algorithm, this method is based on traditional bat algorithm, optimizing success rate is introduced to change bat individual speed update mode, distribution using chaos method initialization bat individual in search space simultaneously, and utilize the repulsion field of the gravitational field of the conceptual modeling terminal of Artificial Potential Field and starting point and barrier, the speed for accelerating bat individual to move to optimal solution, finally proposes the improvement bat algorithm based on chaos Artificial Potential Field.In Path Planning for Unmanned Aircraft Vehicle task, this method compares traditional bat algorithm, and track length is short by 36.56%, and planning time is short by 56.05%, avoidance effect fitness value low 49.53%；Compared to differential evolution bat algorithm, track length is short by 27.16%, and planning time is short by 27.30%, avoidance effect fitness value low 42.46%.It is a kind of Route Planning Algorithm for having and having significant practical applications.
Description
Technical Field
The invention belongs to the technical field of intelligent control, and relates to an unmanned aerial vehicle route planning method, in particular to an unmanned aerial vehicle route planning method based on an improved bat algorithm.
Background
The unmanned aerial vehicle route planning generally refers to a process of finding a flyable route which is from a starting point to a target point and meets the performance index of the unmanned aerial vehicle under a specific constraint condition. The algorithm adopted for the unmanned aerial vehicle route planning problem directly influences the success rate and efficiency of route planning. The swarm intelligence algorithm generally has the advantages of high convergence speed, strong robustness, potential parallelism and the like, and is widely applied to unmanned aerial vehicle route planning. However, when the group intelligent algorithms are used for solving the route planning problem, the defects that the solving precision is not high enough, the planned track is not smooth and the local optimization is easy to happen generally exist. Therefore, an intelligent algorithm with excellent optimization performance is selected and pertinently improved, so that the unmanned aerial vehicle routing problem is better.
The swarm intelligence algorithm is widely applied to solving the problem of unmanned aerial vehicle route planning by researchers at home and abroad, and a typical algorithm is selected and introduced as follows. Shibo Li and the like firstly use a particle swarm algorithm and combine fuzzy logic to solve the problem of two-dimensional unmanned aerial vehicle route planning, and carry out comparative analysis on different planning effects after parameter change in the particle swarm algorithm, but the defect that the two-dimensional experimental environment is too simple to set exists, and meanwhile, a three-dimensional simulation experiment does not exist; hao Meng and the like use a genetic algorithm to combine a digital elevation map and an RBF neural network to solve three-dimensional unmanned aerial vehicle route planning, provide a strict mathematical demonstration process, and obtain an intuitive three-dimensional route planning effect, but the method is limited by the genetic algorithm, and the convergence rate of the three-dimensional route planning and the route planning effect have a great space; the differential evolution algorithm is applied to the problem of multi-unmanned aerial vehicle collaborative route planning by Ioannis K.Nikolos and the like, a better solution is provided for the unmanned aerial vehicle formation to jointly complete tasks, but experimental results show that the route which is only planned by the differential evolution algorithm has the characteristic of Levy flight trajectory and cannot be directly used as the unmanned aerial vehicle flight route, in addition, the solving speed of the algorithm is not fast enough, and the execution stability of the algorithm is not high enough; GaigeWang et al apply bat algorithm to optimize flight cost function optimization in the unmanned aerial vehicle air route planning problem, carry on the contrastive analysis with other optimization effects of traditional group intelligence algorithm, prove that bat algorithm have solving fast, convergence precision high, algorithm stability advantage such as being good in optimizing the flight cost function, but lack the simulation experiment of the intuitive two-dimentional and three-dimensional air route planning effect; in subsequent researches, Gai-Ge Wang applies a bat algorithm based on a differential evolution algorithm to unmanned aerial vehicle route planning and provides two-dimensional and three-dimensional simulation experiment results, and compared and demonstrated the route planning effect of the bat algorithm combined with the differential evolution algorithm and the route planning effect of only using the bat algorithm, the superiority of the proposed algorithm is verified, but the experimental environment setting has the defect of over simplicity, which is not beneficial to the real optimizing and obstacle avoiding performance of the detection algorithm, and in addition, the planned route also has the characteristic of a Levy flight track, and route smoothing processing is not carried out.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides an unmanned aerial vehicle route planning method based on an improved bat algorithm, and the flow chart of the algorithm is shown in figure 1. The execution process of the route planning method comprises five main steps of improving a bat algorithm to carry out route planning, accelerating an iteration process by an artificial potential field method, homogenizing population distribution of a Logistic function of a chaotic strategy, establishing a route planning constraint condition and an objective function, and smoothing a route track. As will be explained in detail below.
Firstly, improving bat algorithm
The bat algorithm is a new meta-heuristic intelligent algorithm published by Yang.X.S in 2010, and the inspiration source of the bat algorithm is the behavior of bat in nature for capturing prey and avoiding obstacles and natural enemies through echo positioning; the bat algorithm follows the following three rules:
1. each bat individual in the search space is positioned only by relying on ultrasonic echo without involving other sensory factors such as vision and the like; in addition, the bat can judge the difference between food, game and obstacles according to the echo difference.
2. Flight optimization parameter setting of the bat individuals: the bat i flies at a speed vi, the real-time position is represented by xi, and the initial sound frequency isfmin. The bat can dynamically adjust the frequency f and the volume A of the ultrasonic wave emitted by the bat according to the degree of approaching a target in the searching process0。
3. Ideal restriction is made on the sound volume of bat sound production, namely the sound volume of bat sound production is assumed to be from a great positive number A0To the minimum value Amin without going out of bounds.
For the virtual bat in a d-dimensional search space, the bat sound production frequency f at the time tiVelocity viAnd position xiThe update formula of (2) is:
fi＝fmin+(fmax-fmin)×β (1)
xi t＝xi t-1+vi t(3)
for the update of the voicing frequency of equation (1), β is a random variable subject to uniform distribution and satisfies β E [0, 1]]；fmaxAnd fminThe maximum value and the minimum value of the initial set sounding frequency range. X in formula (2)*Is the position of the current global optimal solution, and the value is the optimal value obtained by comparing fitness values of all the individuals in the bat population. The bat individual is positioned according to the position of the bat individual at the last momentAnd global optimal solution x*Measure the acceleration of its movement to the optimal solution (urgency); the moving speed at the next moment also takes the inertia of the bat body into consideration, namely the moving speed at the next moment, besides the acceleration generated by referring to the near-global optimal solutionAnd is also subjected toVelocity at a momentThe influence of (c). Formula (3) describes the process that the bat body is located and continuously shifts along with the movement.
The above is an iterative mechanism followed by the bat population when global search is performed in a solution space, and bats near the global optimal solution generate a local new solution by adopting a random walk rule:
xnew＝xold+εAt(4)
in the formula (4), ε ∈ [ -1,1]Is a random number;is the average volume of all bats at time t.
The update formula of the sound emission frequency and loudness at this time is described as follows:
α and gamma in equations (5) and (6) are constants, usually α -gamma-0.9, it can be analyzed from the expression that as bats approach the optimal solution indefinitely, their loudness of sound decreases and halts sound when the optimal solution is reached, while the frequency of sound is approaching the initial pulse rate over time
Similar to exploration operation and mining operation in heuristic search algorithm, the swarm intelligence algorithm has global search and local search processes in the optimizing process. Global search is carried out to determine the approximate range of the optimal solution; while local searches are refined within these ranges.
The trade-off between global search and local search directly affects the search efficiency and the optimization accuracy. In order to better control the speed of global search of bat individuals, one of the innovation points of the invention is to introduce an adaptive inertia weight w to rewrite a bat speed updating formula (2), as shown in a formula (7):
and the concept of the optimizing success rate is introduced, so that the inertia weight is adaptively adjusted along with the optimizing success rate of the bat group. The adaptive inertial weight based on the optimizing success rate is defined as follows:
wherein,the success rate of the bat group optimization is achieved; n represents the bat population number;shows the optimizing result of the bat individual i in the process of the t-th iteration,the adaptive value of t generation is superior to t-1 generation, and a better solution is searched, if not, the optimal solution is obtained
Second, artificial potential field method
The artificial potential field method is originally published by Khatib in 1994, is applied to obstacle avoidance motion planning of a robot operating arm, and is then largely applied to path planning of a mobile robot; at present, no precedent exists that an artificial potential field method and an improved bat algorithm are fused and applied to the unmanned aerial vehicle route planning problem. The inspiration of the artificial potential field method is derived from the principle that electrostatic field heterogeneous charges generate attraction and homogeneous charges generate repulsion, and the acting force between an obstacle and an aircraft in a search space is defined as repulsion and the acting force between a target point and the aircraft. The stress diagram of the aircraft in the artificial potential field is shown in FIG. 3:
in the context of figure 3, it is shown,which is indicative of the repulsive force,which is indicative of the force of attraction,representing the resultant force to which the aircraft is subjected, directly affecting the motion of the aircraft. According to the gradient descent method of the artificial potential field, the repulsive force and the attractive force can be expressed as formula (9) and formula (10):
let n be any point in the search space that is subject to an attractive force Fa(x) And repulsive force Fr(x) Can be expressed as:
Fa(x)＝-grad(Ua(x))＝kρG(q) (11)
third, chaos strategy and Logistic mapping
The basis of the chaotic algorithm is a logistic mapping:
xn+1＝μxn(1-xn-1)n＝1,2,..... (13)
when μ is 4, the mapping is a perfect mapping over the interval [0, 1], the iteratively generated value is in a pseudo-randomly distributed state, and when other values are taken, the generated value converges to a specific value after a certain number of iterations. The bat populations are randomly distributed in the normalized search space, so that the overall search efficiency of the populations is greatly improved; meanwhile, the bat individuals are extremely difficult to have position transition in a large range in the respective local search process, and the uniform and random distribution of the initial population effectively solves the problem that the bat population is easy to fall into a local optimal solution in the later period of search.
Therefore, when an artificial potential field is combined, the method provides a second innovation point, namely, Logistic mapping based on a chaos strategy is adopted to initialize distribution of the bat populations in a solution space, so that the overall convergence speed of the algorithm is accelerated, and the possibility of falling into a local optimal solution is greatly reduced.
Constraint condition and objective function of route planning task
The definition of unmanned aerial vehicle route planning is a process of finding a route which has the minimum cost from a flight starting point to an end point and meets the performance index of the unmanned aerial vehicle under certain specific constraint conditions. The essence of the method is that under the condition of multiple constraints, the extremum is solved by a multi-objective function. The following analysis was made for each of the routings problems.
The cost function in the flight process of the unmanned aerial vehicle can be divided into three parts, namely, the route length cost, the threat cost and the fuel consumption cost. The total cost function is denoted by J, and the minimization problem with J is defined as follows:
min J＝k1JL+k2JT+(1-k1-k2)JF(14)
wherein, JLIs the cost of the length of the flight path, JTIs the cost of the threat, JFRefers to the fuel consumption penalty incurred in flight. k is a radical of1,k2Are all normal numbers and satisfy k being more than or equal to 01≤1,0≤k2≤1。
For the length of flight path cost JLThe definition is as follows:
wherein L is the length of the total flight path, LijThe length of the track segment is used for calculating the length of the air route which cannot be calculated by integration before the air route is smoothly carried out.
Cost J for threatTThe definition is as follows:
wherein, tkThe threat factor is a measure of the threat degree of the threat source to the unmanned aerial vehicle; n is a radical oftRepresenting the total number of threat sources; the current coordinate of the unmanned aerial vehicle is (x, y); the center coordinate of the threat source is (x)k,yk)。
For fuel consumption cost JFThe definition is as follows:
wherein,k in (1) represents the fuel cost consumed by the unmanned aerial vehicle for driving a path with a unit length;in H is the height of the unmanned aerial vehicle flight safety circle, the flight height of the unmanned aerial vehicle should not exceed the value, w0The fuel cost that the unmanned aerial vehicle needs to consume when maintaining the height H is shown, and H shows the current height of the unmanned aerial vehicle.
The unmanned aerial vehicle needs to accord with the dynamic characteristics of the unmanned aerial vehicle in the flying process, so that the preplanned air route needs to meet the limits of some constraint conditions. In order to more intuitively illustrate the constraints, a part of the waypoints in the flight path is selected as a model for illustration. Let A (x)i-1,yi-1,zi-1) As the last waypoint, B (x)i,yi,zi) As the current waypoint, C (x)i+1,yi+1,zi+1) For the next waypoint and recordsAnd (4) a track point migration vector.
When the unmanned aerial vehicle wants to change the self height in the flying process, climbing or diving operation is needed, the invention assumes that the maximum climbing and diving angle is theta, and then the constraint on the climbing/diving angle of the unmanned aerial vehicle is as follows:
when the unmanned aerial vehicle avoids the obstacle, the situation that the turning radius corresponding to the planned track inscribed circle is too small may occur, and the flight characteristics of the unmanned aerial vehicle are violated. Therefore, a limit is made on the minimum turning radius of the unmanned aerial vehicle in flight, and the turning radius limit is schematically shown in fig. 4:
route angleThe minimum turning angle may be determined by:
wherein r isminIs the minimum turning radius.
The fly height limit depends on the specific characteristics of the mission being performed by the drone; in order to reduce consumption and ensure that the air route is hidden as much as possible, the absolute height H of the ground is limited to be the maximum value H which is not more than H, wherein H is the height of the plane where the flight safety circle is located; and in order to react to terrain changes in time, the relative height h of the unmanned aerial vehicle from the terrain surface is requiredi≥hmin。
The unmanned aerial vehicle detects static obstacles and dynamic obstacles by utilizing a sensor of the unmanned aerial vehicle, and an avoidance mechanism of the obstacles after the obstacles are identified is a key factor influencing the route planning effect. As shown in fig. 5:
in order to meet the characteristics of the flight motion direction and the yaw angle of the unmanned aerial vehicle, the avoidance mechanism of the unmanned aerial vehicle on the obstacle is explained by using the motion trail under the polar coordinate system. In the figure, O is the track start point and G is the track end point, L1To LkThe track segment between every two adjacent segments is generated after equal segmentation based on the polar axis, and the starting point of each segmented track segment is identified by a square. The mechanism for measuring and avoiding threats between every two track points is visually shown in figure 6:
segmenting the sub-track section again according to the number of the threat sources to calculate the threat costIn general, this threat cost may be expressed as:
wherein N isTRepresenting the number of threat sources, tjThreat factor representing a source of threat, dk(i, j) represents the starting point of the k-th sub track segment i and jThe linear distance therebetween.
The obstacle avoidance process is the process of minimizing the threat cost under the condition of meeting the constraint condition, the advantage of the optimization problem is solved by using an intelligent algorithm, and the pre-planned optimal route can effectively avoid the static obstacle threat in the space. For avoiding the dynamic obstacle, the unmanned aerial vehicle is required to return to the pre-planned optimal route again after recognizing the dynamic obstacle and emergently avoiding the dynamic obstacle, and the process is also called route following.
And (4) carrying out route flyability detection on a result of the pre-planned route, namely checking whether the planned route meets the flight constraint condition of the unmanned aerial vehicle. The planned route meeting the constraint conditions meets the Levy flight trajectory, but the phenomenon of unsmooth route may exist, so an effective route smoothing method is needed.
Fifth, route smoothing method
This patent adopts two points cubic Hermite interpolation method to realize the route smoothing, assumes that the curve to be smoothed is a broken line segment from A to B to C under the rectangular coordinate system, as shown in FIG. 7:
known interpolation node x0,x1The function value and the derivative value are respectively as follows:
yi＝f(xi),mi＝f′(xi),(i＝0,1) (21)
a polynomial H with a degree not exceeding 3 is required3(x) So as to satisfy the following conditions:
H3(xi)＝yi,H3′(xi)＝mi,(i＝0,1) (22)
introduction of interpolation basis function α0(x),α1(x),β0(x),β1(x) To obtain H3(x) In that respect Can be expressed as:
H3(x)＝y0α0(x)+y1α1(x)+m0β0(x)+m1β1(x) (23)
to satisfy the interpolation condition, the difference basis function has the following limitations:
and solving the expressions of the interpolation basis functions by using an undetermined coefficient method:
to-be-planned route broken line segmentAfter two-point three times Hermite interpolation, the arc segment is usedThe method replaces the prior broken line flight path, and realizes the pre-planning route smoothing problem.
Has the advantages that: in previous research work, an artificial potential field method and a chaos strategy are applied to the unmanned aerial vehicle route planning problem, but a heuristic A-star algorithm is adopted as a main method for searching and expanding the route, and compared with a swarm intelligence algorithm, the method is easy to fall into local optimization, and has the problems of low convergence speed and low convergence precision. Therefore, on the basis of the previous research, the method introduces an optimization success rate to the traditional bat algorithm to change the speed updating mode of the bat individuals, simultaneously adopts a chaos method to initialize the distribution of the bat individuals in a search space, utilizes the concept of an artificial potential field to simulate a gravitational field of a terminal point, a starting point and a repulsive field of an obstacle, accelerates the bat individuals to move to an optimal solution speed, and finally provides the improved bat algorithm based on the chaos artificial potential field to solve the problem of unmanned aerial vehicle route planning under the constraint condition.
In the proposed improved algorithm, the introduction of the self-adaptive inertia weight balances the global search and the local search, and avoids the algorithm from falling into the local optimal solution; the chaos strategy is combined to randomize and homogenize the initial distribution of the bat population, so that the solution space is searched and traversed more comprehensively; the artificial potential field is introduced by referring to the characteristics of the unmanned aerial vehicle route planning problem, the information of the terrain, the starting point and the ending point is utilized to a greater extent, and the algorithm execution efficiency is improved.
Drawings
FIG. 1 is a flow chart of a route planning task using the improved algorithm set forth in this patent;
FIG. 2 is a pseudo-code diagram of an improved bat algorithm based on an artificial potential field and a chaos strategy;
FIG. 3 is a diagram of an aircraft in an artificial potential field;
FIG. 4 is a schematic view of a turn radius limitation;
fig. 5 is a schematic diagram of an unmanned aerial vehicle avoiding an obstacle;
FIG. 6 is a schematic diagram of threat cost measurement between split track points;
FIG. 7 is a schematic diagram of Hermite interpolation for implementing airway smoothing;
FIG. 8 shows comparison of the routing effects of BA, DEBA and CPFIBA in a two-dimensional terrain environment;
FIG. 9 is a comparison of convergence curves of the BA, DEBA, CPFIBA route cost functions in the two-dimensional terrain environment;
FIG. 10 illustrates a perspective view and a side view of a three-dimensional terrain environment;
FIG. 11 is a comparison of the effects of the BA, DEBA, CPFIBA route planning in the three-dimensional terrain environment;
FIG. 12 is a comparison of the convergence curves of the fitness function of the BA, DEBA and CPFIBA route planning cost functions in the three-dimensional terrain environment.
Detailed Description
Implementation hardware conditions:
the implementation environment is a PC with 64-bit windows 7 operating system, performance parameters Intel (R) core (TM) i5-3470 CPU 3.20GHz, and ROM size 8 GB. The simulation experiments under the two-dimensional terrain and the three-dimensional terrain are realized by programming under MatlabR2016a software.
Setting related algorithm parameters:
representing an original bat algorithm by BA; DEBA stands for an improved bat algorithm based on a differential evolution algorithm; CPFIBA represents the improved bat algorithm based on the chaos strategy and artificial potential field proposed by this patent.
Basic bat algorithm iterative formula parameter setting:the population size N is 90; the iteration number NC under the two-dimensional environment is 30; the iteration number NC in the three-dimensional environment is 30.
The differential evolution algorithm used for comparison iterates formula parameter settings: NP is 30, a is 0.95, Q is r is F is 0.5; the population size N is 90; the iteration number NC under the two-dimensional environment is 30; the iteration number NC in the three-dimensional environment is 30.
Parameter setting in the improved bat algorithm based on artificial potential field and chaos strategy is mu-4, k-1, m-1, rho00.5, 90 for population size N; the iteration number NC under the two-dimensional environment is 30; the iteration number NC in the three-dimensional environment is 30.
Example 1:
in the two-dimensional environment simulation experiment, the two-dimensional terrain environment overall appearance can be reflected from the air route planning effect diagram, and the terrain diagram is not presented independently. The two-dimensional rectangular coordinates of the starting point in the two-dimensional terrain environment are (0, 0), the coordinates of the target point are (110, 100), and the respective obstacle settings are shown in table 1:
TABLE 1 two-dimensional environmental simulation experiment threat source settings
The optimal airway length, the airway cost fitness function value and the algorithm execution time comparison (30 times of single experiment iteration, and ten times of independent experiment average) of BA, DEBA and CPFIBA in the two-dimensional environment are shown in table 2:
TABLE 2 comparison of Performance indicators of improved Algorithm in two-dimensional Environment
The three algorithms of BA, DEBA and CPFIBA are applied to the unmanned aerial vehicle route planning problem under the two-dimensional complex environment, the two-dimensional route planning simulation effect is obtained and is shown in figure 8, and the route cost fitness function convergence curve is shown in figure 9.
The following analysis can be made for experimental data, simulation result graphs and convergence curve analysis in a two-dimensional environment: under the same terrain condition, the length of the air route planned by CPFIBA is 197.35km, which is shortened by 7.30% compared with 212.89km of the air route planned by DEBA and 25.73% compared with 265.73km of the air route planned by BA, namely the air route planned by CPFIBA is shorter; under the same constraint condition, the flight cost function under the same iteration number is converged. The fitness function for the route cost of CPFIBA is 273.83, 9.26% lower than the fitness value 301.76 of DEBA and 17.06% lower than the fitness value 330.14 of BA. The final fitness convergence value reflects the optimizing precision of each algorithm, and the optimizing precision of CPFIBA obtained from the airway cost fitness function value is higher than that of DEBA and BA. The slope of the curve during initial iteration can be used for obtaining that CPFIBA has higher stability compared with DEBA and BA; from the algorithm execution time perspective analysis, the CPFIBA execution time of 423.83ms saves 13.35% of the execution time compared to the DEBA execution time of 543.92ms, and 59.84% of the execution time compared to the BA execution time of 617.62 ms. From the iteration times when the objective function tends to be stable, the CPFIBA convergence rate is faster than that of DEBA and BA; the comparison of the convergence of the cost function to the final value can result in that CPFIBA is more excellent in the optimizing accuracy. In conclusion, the performance of the CPFIBA in the problem of the two-dimensional air route planning of the unmanned aerial vehicle is better than that of the DEBA and the BA, and the CPFIBA has better applicability.
Example 2:
in the three-dimensional environment simulation experiment, the starting point coordinates are (0, 0, 100), and the target point coordinates are (100, 100, 100). The concept of a safety circle of flight is introduced, i.e. the flying height of the drone cannot be higher than the level of the safety circle of flight, where the safety circle is set parallel to the plane and z is 600 m. The panoramic view and the side view of the three-dimensional unmanned aerial vehicle flight simulation environment terrain model set by using the digital elevation map are shown in fig. 10.
The parameter settings for BA, DEBA and CPFIBA were consistent with the two-dimensional experiments. The three algorithms are respectively utilized to carry out the route planning in the three-dimensional terrain space, the obtained route planning simulation result is shown in fig. 11, and the route cost fitness function convergence curve is shown in fig. 12.
Optimal path lengths, airway cost fitness function values and algorithm execution time comparison of the BA, the DEBA and the CPFIBA in the three-dimensional environment (30 times of single experiment iteration, and ten times of independent experiment average values) are shown in Table 3:
TABLE 3 comparison of Performance indicators of improved Algorithm in three-dimensional Environment
The three-dimensional simulation experiment result also comprises experiment data, a simulation effect graph and a flight cost convergence curve. Under the same three-dimensional terrain setting, the length of the air route planned by CPFIBA is 567.37km, which is 27.16% shorter than the length 778.91km of the air route planned by DEBA, and is 36.56% shorter than the length 894.38km planned by BA, and the simulation result shows that the length of the air route planned by CPFIBA is shorter than that of DEBA and BA; from the analysis of the angle of the airway cost adaptability value, the airway cost adaptability function value of the CPFIBA is 110.35, is 42.46 percent less than the DEBA adaptability value 153.47 and 49.53 percent less than the BA adaptability value 218.64, and the final convergence value of the CPFIBA is lower than that of the DEBA and the BA, namely the convergence precision of the CPFIBA is higher than that of the DEBA and the BA; from the analysis of algorithm implementation time, the CPFIBA execution time is 521.34ms, which saves 27.3% than the DEBA execution time 639.05ms, and 56.05% than the BA execution time 813.54ms, and the convergence time of the CPFIBA is shorter than that of the DEBA and the BA, namely the convergence speed is faster than that of the DEBA and the BA. As can be seen from the effect of route planning, the CPFIBA can avoid falling into local optimum, and meanwhile, the convergence precision is greatly superior to DEBA and BA; the convergence curve of the airway cost fitness function verifies the superiority of the convergence precision, the convergence speed and the convergence stability of the CPFIBA relative to the DEBA and the BA. Simulation experiment results show that the CPFIBA algorithm has better applicability than DEBA and BA in three-dimensional environment unmanned aerial vehicle air route planning, and is an air route planning algorithm with practical application significance.
Claims (4)
1. An unmanned aerial vehicle route planning method based on an improved bat algorithm, the improved bat algorithm: firstly, based on the traditional bat algorithm, the optimization success rate is introduced to change the speed updating mode of the bat; secondly, a chaos method is adopted to initialize the distribution of the bat individuals in a search space, so that the search efficiency is improved; thirdly, simulating a gravitational field at a terminal point, a repulsive force field at a starting point and an obstacle by utilizing the concept of an artificial potential field, and accelerating the speed of the bat individual moving to an optimal solution; an improved bat algorithm based on the chaotic artificial potential field is provided by combining the three points; the method is characterized in that:
the method is applied to unmanned aerial vehicle route planning, and specifically comprises the following steps:
step 1: setting necessary parameters in the execution process of the bat algorithm, wherein the necessary parameters comprise iteration times, initial speed, initial position, initial sounding frequency and initial loudness; setting chaotic strategy parameters, and uniformly distributing; setting an artificial potential field, and defining a function of attractive force and repulsive force of a starting point, a target point and an obstacle;
step 2: establishing an unmanned aerial vehicle flight model according to the unmanned aerial vehicle flight cost function and the constraint condition, and determining a performance evaluation mechanism of an unmanned aerial vehicle route planning task;
and step 3: and optimizing the unmanned aerial vehicle route planning cost function by using an improved bat algorithm based on an artificial potential field and a chaos strategy to finally obtain a flyable track of the unmanned aerial vehicle route planning.
2. The unmanned aerial vehicle route planning method based on the improved bat algorithm as claimed in claim 1, wherein the specific steps of the step 1 are as follows:
step 1.1, under d-dimensional search space, the bat sound frequency f at the time tiVelocity viAnd position xiThe update formula of (2) is:
fi＝fmin+(fmax-fmin)×β
xi t＝xi t-1+vi t
for the update of the sounding frequency, β is a random variable subject to uniform distribution and satisfies β E [0, 1]]；fmaxAnd fminThe maximum value and the minimum value of the initial set sounding frequency range; x in the formula*The position of the current global optimal solution is the optimal value obtained by comparing fitness values of all individuals in the bat population; the bat individual is located according to the last moment of the bat individualPosition ofAnd global optimal solution x*Measure the acceleration of its movement to the optimal solution; speed of movement at the next momentAnd also receives the speed of the last momentThe influence of (a);
the above is an iterative mechanism followed by the bat population when global search is performed in a solution space, and bats near the global optimal solution generate a local new solution by adopting a random walk rule:
xnew＝xold+εAt
in the formula, epsilon [ -1,1 ∈ [ ]]Is a random number;is the average loudness of all bats at time t;is the average sound frequency of all bats at the time t;
the updated formula of the bat individual sound frequency and loudness at the time t is described as follows:
α and γ are constants, and α ═ γ ═ 0.9 is usually adopted.
Step 1.2: the inspiration of the artificial potential field method is derived from the principle that electrostatic field heterogeneous charges generate attraction and homogeneous charges generate repulsion, the acting force between an obstacle and an aircraft in a search space is defined as repulsion, and the acting force between a target point and the aircraft is defined as attraction; applying an artificial potential field method to the problem of route planning, setting barriers and threat sources as repulsive fields, and setting target points as gravitational fields, so that the convergence speed of the whole route planning algorithm is accelerated by the strategy;
which is indicative of the repulsive force,which is indicative of the force of attraction,representing the resultant force to which the aircraft is subjected, directly affecting the motion of the aircraft; according to the gradient descent method of the artificial potential field, the repulsive force and the attractive force can be expressed as:
let n be any point in the search space that is subject to an attractive force Fa(x) And repulsive force Fr(x) Can be expressed as:
Fa(x)＝-grad(Ua(x))＝kρG(q)
step 1.3: the basis of the chaotic algorithm is a logistic mapping:
xn+1＝μxn(1-xn-1)n＝1,2,.....
when mu is 4, the mapping is a full mapping on the [0, 1] interval, the iteratively generated value is in a pseudo-random distribution state, and when other values are taken, after a certain number of iterations, the generated value converges to a specific value, the bat populations are randomly distributed in the normalized search space, and the global search efficiency of the populations is greatly improved; meanwhile, the bat individuals are extremely difficult to have position transition in a large range in the respective local search process, and the uniform and random distribution of the initial population effectively solves the problem that the bat population is easy to fall into a local optimal solution in the later period of search;
therefore, when the artificial potential field is combined, the Logistic mapping based on the chaos strategy is adopted to initialize the distribution of the bat population in the solution space, so that the overall convergence speed of the algorithm is accelerated, and the possibility of falling into the local optimal solution is greatly reduced.
3. The unmanned aerial vehicle route planning method based on the improved bat algorithm as claimed in claim 1, wherein the specific steps of the step 2 are as follows:
step 2.1: the group intelligent algorithm has the processes of global search and local search in the optimizing process, and the global search is used for determining the approximate range of the optimal solution; and the local search is carried out to precisely optimize in the ranges;
the balance between the global search and the local search directly influences the search efficiency and the optimization precision, and the bat speed updating formula is rewritten by using the adaptive inertia weight w as follows:
vi t＝wvi t-1+(xi t-1-x*)×f
and introducing the concept of the optimizing success rate, so that the inertia weight is adaptively adjusted along with the optimizing success rate of the bat group, and the adaptive inertia weight based on the optimizing success rate is defined as follows:
wherein,is the optimizing success rate of bat group(ii) a N represents the bat population number;shows the optimizing result of the bat individual i in the process of the t-th iteration,the adaptive value of t generation is superior to t-1 generation, and a better solution is searched, if not, the optimal solution is obtained
The self-adaptive inertia weight of the optimizing success rate is introduced, and the method is different from the traditional linear inertia weight, and better balances the proportion of global search and local search. The introduction of the optimizing success rate is a parameter adjusting method with a feedback mechanism, and the optimizing result of the global search influences the value of the self-adaptive inertia weight, so that the speed of the bat individual and the time for the bat individual to enter the local search are changed.
Step 2.2: the cost function of the unmanned aerial vehicle in the flying process can be divided into three parts, namely, the route length cost, the threat cost and the fuel consumption cost; the total cost function is denoted by J, and the minimization problem with respect to the total cost function J is defined as follows:
min J＝k1JL+k2JT+(1-k1-k2)JF
wherein, JLIs the cost of the length of the flight path, JTIs the cost of the threat, JFRefers to the fuel consumption penalty incurred in flight; k is a radical of1,k2Are all normal numbers and satisfy k being more than or equal to 01≤1,0≤k2≤1；
For the length of flight path cost JLThe definition is as follows:
wherein L refers to the length of the total flight path, LijIs track segmentationLength, which is used for calculating the length of the air route which can not be calculated by integration before the air route is smoothly carried out;
cost J for threatTThe definition is as follows:
wherein, tkThe threat factor is a measure of the threat degree of the threat source to the unmanned aerial vehicle; nt represents the total number of threat sources; the current coordinate of the unmanned aerial vehicle is (x, y); the center coordinate of the threat source is (x)k,yk)；
For fuel consumption cost JFThe definition is as follows:
wherein,k in (1) represents the fuel cost consumed by the unmanned aerial vehicle for driving a path with a unit length;
in H is the height of the unmanned aerial vehicle flight safety circle, the flight height of the unmanned aerial vehicle does not exceed the value, w0The fuel cost that the unmanned aerial vehicle needs to consume when maintaining the height H is shown, and H shows the current height of the unmanned aerial vehicle.
4. The unmanned aerial vehicle route planning method based on the improved bat algorithm as claimed in claim 1, wherein the specific steps of the step 3 are as follows:
step 3.1: the unmanned aerial vehicle needs to accord with the self dynamic characteristics in the flying process, a part of route points in the flight path are selected as a model for explanation, and A (x) is seti-1,yi-1,zi-1) As the last waypoint, B (x)i,yi,zi) For the current voyageWaypoints, C (x)i+1,yi+1,zi+1) For the next waypoint and recordsA track point migration vector is obtained;
when wanting to change self height among the unmanned aerial vehicle flight process, need do and climb or dive operation, assume that the biggest climbing is theta with dive angle, then to unmanned aerial vehicle climb/dive angle's restraint do:
when the unmanned aerial vehicle avoids the obstacle, the situation that the turning radius corresponding to the planned track inscribed circle is too small may occur, and the flight characteristics of the unmanned aerial vehicle are violated; therefore, the minimum turning radius of the unmanned aerial vehicle in flight is limited, and the included angle of the air routeThe minimum turning angle may be determined by:
wherein r isminIs the minimum turning radius;
the absolute height H of the ground has the maximum value that H is limited to be less than or equal to H, wherein H is the height of the plane where the flight safety circle is located; and in order to react to terrain changes in time, the relative height h of the unmanned aerial vehicle from the terrain surface is requiredi≥hmin；
Step 3.2: the unmanned aerial vehicle detects static obstacles and dynamic obstacles by utilizing a sensor thereof, and an avoidance mechanism of the obstacles after the obstacles are identified is a key factor influencing the route planning effect;
segmenting the sub-track section again according to the number of the threat sources to calculate the threat costIn general, this threat cost may be expressed as:
wherein N isTRepresenting the number of threat sources, tjThreat factor representing a source of threat, dk(i, j) represents a straight-line distance between the starting points i and j of the kth branch track segment; liRepresenting the number of track segments;
the obstacle avoidance process is the process of minimizing the threat cost under the condition of meeting the constraint condition, the advantage of the optimization problem is solved by using an intelligent algorithm, and the pre-planned optimal route can effectively avoid the static obstacle threat in the space; for avoiding the dynamic obstacle, the unmanned aerial vehicle is required to return to the preplanned optimal route again after recognizing the dynamic obstacle and emergently avoiding the dynamic obstacle, and the process is also called route following;
step 3.3: a two-point three-time Hermite interpolation method is adopted to realize airway smoothing;
known interpolation node x0,x1The function value and the derivative value are respectively as follows:
yi＝f(xi),mi＝f′(xi),(i＝0,1)
a polynomial H with a degree not exceeding 3 is required3(x) So as to satisfy the following conditions:
H3(xi)＝yi,H′3(xi)＝mi,(i＝0,1)
introduction of interpolation basis function α0(x),α1(x),β0(x),β1(x) To obtain H3(x) (ii) a Can be expressed as:
H3(x)＝y0α0(x)+y1α1(x)+m0β0(x)+m1β1(x)
to satisfy the interpolation condition, the difference basis function has the following limitations:
βi(xj)＝0,βi′(xj)＝δij,(i,j＝0,1)
and solving the expressions of the interpolation basis functions by using an undetermined coefficient method:
to-be-planned route broken line segmentAfter two-point three times Hermite interpolation, the arc segment is usedThe method replaces the prior broken line flight path, and realizes the pre-planning route smoothing problem.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811091770.6A CN109144102B (en) | 2018-09-19 | 2018-09-19 | Unmanned aerial vehicle route planning method based on improved bat algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811091770.6A CN109144102B (en) | 2018-09-19 | 2018-09-19 | Unmanned aerial vehicle route planning method based on improved bat algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109144102A true CN109144102A (en) | 2019-01-04 |
| CN109144102B CN109144102B (en) | 2021-08-20 |
Family
ID=64814948
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811091770.6A Active CN109144102B (en) | 2018-09-19 | 2018-09-19 | Unmanned aerial vehicle route planning method based on improved bat algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109144102B (en) |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109870906A (en) * | 2019-02-25 | 2019-06-11 | 北京航空航天大学 | A kind of high-speed rotor aircraft paths planning method based on BBO optimization Artificial Potential Field |
| CN110162077A (en) * | 2019-06-18 | 2019-08-23 | 哈尔滨工程大学 | A kind of unmanned aerial vehicle flight path planing method based on flying fish algorithm |
| CN110274608A (en) * | 2019-05-21 | 2019-09-24 | 深圳壹账通智能科技有限公司 | Intelligent paths planning method, device and computer readable storage medium |
| CN110274607A (en) * | 2019-05-21 | 2019-09-24 | 深圳壹账通智能科技有限公司 | Intelligent paths planning method, device and computer readable storage medium |
| CN110427046A (en) * | 2019-07-26 | 2019-11-08 | 沈阳航空航天大学 | A kind of three-dimensional smooth random walk unmanned aerial vehicle group mobility model |
| CN110632922A (en) * | 2019-09-10 | 2019-12-31 | 青岛理工大学 | Path planning method based on bat algorithm and reinforcement learning |
| CN110967016A (en) * | 2019-11-22 | 2020-04-07 | 中国人民解放军63629部队 | Off-line planning method and device for aircraft route and computer equipment |
| CN110989656A (en) * | 2019-11-13 | 2020-04-10 | 中国电子科技集团公司第二十研究所 | Conflict resolution method based on improved artificial potential field method |
| CN111123976A (en) * | 2019-12-24 | 2020-05-08 | 一飞智控(天津)科技有限公司 | Unmanned aerial vehicle cluster path planning processing method based on artificial potential field and unmanned aerial vehicle |
| CN111189455A (en) * | 2020-01-14 | 2020-05-22 | 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) | Unmanned aerial vehicle route planning method and system based on combination of improved biophysical algorithm and Bessel function and storage medium |
| CN111813144A (en) * | 2020-06-11 | 2020-10-23 | 南京航空航天大学 | Multi-unmanned aerial vehicle collaborative route planning method based on improved flocks of sheep algorithm |
| CN111832725A (en) * | 2019-04-15 | 2020-10-27 | 电子科技大学 | Multi-robot multi-task allocation method and device based on improved genetic algorithm |
| CN111880561A (en) * | 2020-07-16 | 2020-11-03 | 河南大学 | Unmanned aerial vehicle three-dimensional path planning method based on improved whale algorithm in urban environment |
| CN111930121A (en) * | 2020-08-10 | 2020-11-13 | 哈尔滨工程大学 | Mixed path planning method for indoor mobile robot |
| CN111969488A (en) * | 2020-08-21 | 2020-11-20 | 福州大学 | Coordinate transformation-based unmanned aerial vehicle inspection obstacle avoidance method for high-voltage line overhead area |
| CN112444248A (en) * | 2019-08-27 | 2021-03-05 | 广州极飞科技有限公司 | Route generation method, device, equipment and storage medium |
| CN112462803A (en) * | 2020-11-27 | 2021-03-09 | 北京工商大学 | Unmanned aerial vehicle path planning method based on improved NSGA-II |
| CN112880688A (en) * | 2021-01-27 | 2021-06-01 | 广州大学 | Unmanned aerial vehicle three-dimensional flight path planning method based on chaotic self-adaptive sparrow search algorithm |
| CN113190037A (en) * | 2021-04-08 | 2021-07-30 | 上海吞山智能科技有限公司 | Unmanned aerial vehicle optimal path searching method based on improved fluid disturbance and sparrow algorithm |
| CN113359773A (en) * | 2021-07-07 | 2021-09-07 | 大连海事大学 | Unmanned ship navigation path decision method and system |
| CN113759958A (en) * | 2021-07-07 | 2021-12-07 | 哈尔滨工程大学 | Unmanned aerial vehicle formation flight path planning method based on positioning precision |
| CN114527746A (en) * | 2022-01-12 | 2022-05-24 | 燕山大学 | Intelligent automobile path planning and obstacle avoidance tracking method |
| CN114779821A (en) * | 2022-05-25 | 2022-07-22 | 四川大学 | Unmanned aerial vehicle self-adaptive repulsion coefficient path planning method based on deep learning |
| CN114895707A (en) * | 2022-05-13 | 2022-08-12 | 华南农业大学 | Agricultural unmanned aerial vehicle path planning method and system based on variable-frequency bat algorithm |
| CN116400737A (en) * | 2023-06-02 | 2023-07-07 | 中国传媒大学 | Safety path planning system based on ant colony algorithm |
| CN117556979A (en) * | 2024-01-11 | 2024-02-13 | 中国科学院工程热物理研究所 | Unmanned plane platform and load integrated design method based on group intelligent search |
| CN117647997A (en) * | 2024-01-29 | 2024-03-05 | 中国人民解放军战略支援部队航天工程大学 | Knowledge bidirectional migration unmanned aerial vehicle collaborative track local re-planning method and system |
| CN117913962A (en) * | 2024-03-19 | 2024-04-19 | 哈尔滨工业大学 | MPPT power supply control method for satellite based on improved BA-P & O hybrid algorithm |
| CN118113068A (en) * | 2024-03-01 | 2024-05-31 | 中国人民解放军海军工程大学 | Unmanned cluster route planning method and system based on improved particle swarm algorithm |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104406593A (en) * | 2014-12-03 | 2015-03-11 | 广西民族大学 | Method for determining optimal route of airway of unmanned aerial vehicle |
| CN105427348A (en) * | 2015-12-03 | 2016-03-23 | 山东理工大学 | Video object tracking method based on bat algorithm |
| CN107103397A (en) * | 2017-06-26 | 2017-08-29 | 广东工业大学 | A kind of traffic flow forecasting method based on bat algorithm, apparatus and system |
| CN107253194A (en) * | 2017-07-31 | 2017-10-17 | 中南大学 | A kind of carrying machine human arm manipulation multiple spot mapping intelligent control method and system |
| CN107272705A (en) * | 2017-07-31 | 2017-10-20 | 中南大学 | A kind of multiple neural network controlling planning method of robot path under intelligent environment |
| CN107392317A (en) * | 2017-07-28 | 2017-11-24 | 中南大学 | A kind of neutral net colony mixing computational methods of intelligent environment carrying robot identification floor |
-
2018
- 2018-09-19 CN CN201811091770.6A patent/CN109144102B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104406593A (en) * | 2014-12-03 | 2015-03-11 | 广西民族大学 | Method for determining optimal route of airway of unmanned aerial vehicle |
| CN105427348A (en) * | 2015-12-03 | 2016-03-23 | 山东理工大学 | Video object tracking method based on bat algorithm |
| CN107103397A (en) * | 2017-06-26 | 2017-08-29 | 广东工业大学 | A kind of traffic flow forecasting method based on bat algorithm, apparatus and system |
| CN107392317A (en) * | 2017-07-28 | 2017-11-24 | 中南大学 | A kind of neutral net colony mixing computational methods of intelligent environment carrying robot identification floor |
| CN107253194A (en) * | 2017-07-31 | 2017-10-17 | 中南大学 | A kind of carrying machine human arm manipulation multiple spot mapping intelligent control method and system |
| CN107272705A (en) * | 2017-07-31 | 2017-10-20 | 中南大学 | A kind of multiple neural network controlling planning method of robot path under intelligent environment |
Cited By (42)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109870906A (en) * | 2019-02-25 | 2019-06-11 | 北京航空航天大学 | A kind of high-speed rotor aircraft paths planning method based on BBO optimization Artificial Potential Field |
| CN111832725B (en) * | 2019-04-15 | 2023-05-26 | 电子科技大学 | Multi-robot multi-task allocation method and device based on improved genetic algorithm |
| CN111832725A (en) * | 2019-04-15 | 2020-10-27 | 电子科技大学 | Multi-robot multi-task allocation method and device based on improved genetic algorithm |
| CN110274608A (en) * | 2019-05-21 | 2019-09-24 | 深圳壹账通智能科技有限公司 | Intelligent paths planning method, device and computer readable storage medium |
| CN110274607A (en) * | 2019-05-21 | 2019-09-24 | 深圳壹账通智能科技有限公司 | Intelligent paths planning method, device and computer readable storage medium |
| CN110162077B (en) * | 2019-06-18 | 2022-04-05 | 哈尔滨工程大学 | Unmanned aerial vehicle flight path planning method based on flying fish algorithm |
| CN110162077A (en) * | 2019-06-18 | 2019-08-23 | 哈尔滨工程大学 | A kind of unmanned aerial vehicle flight path planing method based on flying fish algorithm |
| CN110427046B (en) * | 2019-07-26 | 2022-09-30 | 沈阳航空航天大学 | Three-dimensional smooth random-walking unmanned aerial vehicle cluster moving model |
| CN110427046A (en) * | 2019-07-26 | 2019-11-08 | 沈阳航空航天大学 | A kind of three-dimensional smooth random walk unmanned aerial vehicle group mobility model |
| CN112444248A (en) * | 2019-08-27 | 2021-03-05 | 广州极飞科技有限公司 | Route generation method, device, equipment and storage medium |
| CN110632922B (en) * | 2019-09-10 | 2022-06-17 | 青岛理工大学 | Path planning method based on bat algorithm and reinforcement learning |
| CN110632922A (en) * | 2019-09-10 | 2019-12-31 | 青岛理工大学 | Path planning method based on bat algorithm and reinforcement learning |
| CN110989656A (en) * | 2019-11-13 | 2020-04-10 | 中国电子科技集团公司第二十研究所 | Conflict resolution method based on improved artificial potential field method |
| CN110967016A (en) * | 2019-11-22 | 2020-04-07 | 中国人民解放军63629部队 | Off-line planning method and device for aircraft route and computer equipment |
| CN111123976A (en) * | 2019-12-24 | 2020-05-08 | 一飞智控(天津)科技有限公司 | Unmanned aerial vehicle cluster path planning processing method based on artificial potential field and unmanned aerial vehicle |
| CN111189455A (en) * | 2020-01-14 | 2020-05-22 | 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) | Unmanned aerial vehicle route planning method and system based on combination of improved biophysical algorithm and Bessel function and storage medium |
| CN111189455B (en) * | 2020-01-14 | 2022-02-01 | 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) | Unmanned aerial vehicle route planning method, system and storage medium |
| CN111813144A (en) * | 2020-06-11 | 2020-10-23 | 南京航空航天大学 | Multi-unmanned aerial vehicle collaborative route planning method based on improved flocks of sheep algorithm |
| CN111813144B (en) * | 2020-06-11 | 2022-02-18 | 南京航空航天大学 | Multi-unmanned aerial vehicle collaborative route planning method based on improved flocks of sheep algorithm |
| CN111880561A (en) * | 2020-07-16 | 2020-11-03 | 河南大学 | Unmanned aerial vehicle three-dimensional path planning method based on improved whale algorithm in urban environment |
| CN111930121A (en) * | 2020-08-10 | 2020-11-13 | 哈尔滨工程大学 | Mixed path planning method for indoor mobile robot |
| CN111969488A (en) * | 2020-08-21 | 2020-11-20 | 福州大学 | Coordinate transformation-based unmanned aerial vehicle inspection obstacle avoidance method for high-voltage line overhead area |
| CN112462803A (en) * | 2020-11-27 | 2021-03-09 | 北京工商大学 | Unmanned aerial vehicle path planning method based on improved NSGA-II |
| CN112462803B (en) * | 2020-11-27 | 2022-06-17 | 北京工商大学 | Unmanned aerial vehicle path planning method based on improved NSGA-II |
| CN112880688B (en) * | 2021-01-27 | 2023-05-23 | 广州大学 | Unmanned aerial vehicle three-dimensional track planning method based on chaotic self-adaptive sparrow search algorithm |
| CN112880688A (en) * | 2021-01-27 | 2021-06-01 | 广州大学 | Unmanned aerial vehicle three-dimensional flight path planning method based on chaotic self-adaptive sparrow search algorithm |
| CN113190037A (en) * | 2021-04-08 | 2021-07-30 | 上海吞山智能科技有限公司 | Unmanned aerial vehicle optimal path searching method based on improved fluid disturbance and sparrow algorithm |
| CN113759958B (en) * | 2021-07-07 | 2023-08-01 | 哈尔滨工程大学 | Unmanned aerial vehicle formation track planning method based on positioning precision |
| CN113359773A (en) * | 2021-07-07 | 2021-09-07 | 大连海事大学 | Unmanned ship navigation path decision method and system |
| CN113759958A (en) * | 2021-07-07 | 2021-12-07 | 哈尔滨工程大学 | Unmanned aerial vehicle formation flight path planning method based on positioning precision |
| CN114527746A (en) * | 2022-01-12 | 2022-05-24 | 燕山大学 | Intelligent automobile path planning and obstacle avoidance tracking method |
| CN114895707A (en) * | 2022-05-13 | 2022-08-12 | 华南农业大学 | Agricultural unmanned aerial vehicle path planning method and system based on variable-frequency bat algorithm |
| CN114779821A (en) * | 2022-05-25 | 2022-07-22 | 四川大学 | Unmanned aerial vehicle self-adaptive repulsion coefficient path planning method based on deep learning |
| CN116400737B (en) * | 2023-06-02 | 2023-08-25 | 中国传媒大学 | Safety path planning system based on ant colony algorithm |
| CN116400737A (en) * | 2023-06-02 | 2023-07-07 | 中国传媒大学 | Safety path planning system based on ant colony algorithm |
| CN117556979A (en) * | 2024-01-11 | 2024-02-13 | 中国科学院工程热物理研究所 | Unmanned plane platform and load integrated design method based on group intelligent search |
| CN117556979B (en) * | 2024-01-11 | 2024-03-08 | 中国科学院工程热物理研究所 | Unmanned plane platform and load integrated design method based on group intelligent search |
| CN117647997A (en) * | 2024-01-29 | 2024-03-05 | 中国人民解放军战略支援部队航天工程大学 | Knowledge bidirectional migration unmanned aerial vehicle collaborative track local re-planning method and system |
| CN117647997B (en) * | 2024-01-29 | 2024-04-16 | 中国人民解放军战略支援部队航天工程大学 | Knowledge bidirectional migration unmanned aerial vehicle collaborative track local re-planning method and system |
| CN118113068A (en) * | 2024-03-01 | 2024-05-31 | 中国人民解放军海军工程大学 | Unmanned cluster route planning method and system based on improved particle swarm algorithm |
| CN117913962A (en) * | 2024-03-19 | 2024-04-19 | 哈尔滨工业大学 | MPPT power supply control method for satellite based on improved BA-P & O hybrid algorithm |
| CN117913962B (en) * | 2024-03-19 | 2024-05-14 | 哈尔滨工业大学 | MPPT power supply control method for satellite based on improved BA-P & O hybrid algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109144102B (en) | 2021-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109144102B (en) | Unmanned aerial vehicle route planning method based on improved bat algorithm | |
| US11727812B2 (en) | Airplane flight path planning method and device based on the pigeon-inspired optimization | |
| CN109655066B (en) | Unmanned aerial vehicle path planning method based on Q (lambda) algorithm | |
| Lin et al. | A Novel Improved Bat Algorithm in UAV Path Planning. | |
| Wen et al. | UAV online path planning algorithm in a low altitude dangerous environment | |
| CN110134140B (en) | Unmanned aerial vehicle path planning method based on potential function reward DQN under continuous state of unknown environmental information | |
| CN111381600B (en) | UUV path planning method based on particle swarm optimization | |
| CN109871031B (en) | Trajectory planning method for fixed-wing unmanned aerial vehicle | |
| CN111930121B (en) | Mixed path planning method for indoor mobile robot | |
| CN109597425A (en) | Navigation of Pilotless Aircraft and barrier-avoiding method based on intensified learning | |
| CN108919818B (en) | Spacecraft attitude orbit collaborative planning method based on chaotic population variation PIO | |
| CN110926477A (en) | Unmanned aerial vehicle route planning and obstacle avoidance method | |
| CN113268074B (en) | Unmanned aerial vehicle flight path planning method based on joint optimization | |
| CN114397896A (en) | Dynamic path planning method for improving particle swarm optimization | |
| CN114518770B (en) | Unmanned aerial vehicle path planning method integrating potential field and deep reinforcement learning | |
| Li et al. | A behavior-based mobile robot navigation method with deep reinforcement learning | |
| CN113391633A (en) | Urban environment-oriented mobile robot fusion path planning method | |
| Sarabakha et al. | Y6 tricopter autonomous evacuation in an indoor environment using Q-learning algorithm | |
| CN115903888A (en) | Rotor unmanned aerial vehicle autonomous path planning method based on longicorn swarm algorithm | |
| Wang et al. | Obstacle avoidance of UAV based on neural networks and interfered fluid dynamical system | |
| Cui et al. | UAV path planning method for data collection of fixed-point equipment in complex forest environment | |
| Hasanzade et al. | A dynamically feasible fast replanning strategy with deep reinforcement learning | |
| Wang et al. | An improved particle swarm optimization algorithm for unmanned aerial vehicle route planning | |
| Chronis et al. | Dynamic navigation in unconstrained environments using reinforcement learning algorithms | |
| CN116698037B (en) | Unmanned aerial vehicle track planning method |
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 |