CN111026126A - Unmanned ship global path multi-target planning method based on improved ant colony algorithm - Google Patents
Unmanned ship global path multi-target planning method based on improved ant colony algorithm Download PDFInfo
- Publication number
- CN111026126A CN111026126A CN201911372167.XA CN201911372167A CN111026126A CN 111026126 A CN111026126 A CN 111026126A CN 201911372167 A CN201911372167 A CN 201911372167A CN 111026126 A CN111026126 A CN 111026126A
- Authority
- CN
- China
- Prior art keywords
- path
- pheromone
- global
- global path
- ant colony
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 91
- 238000000034 method Methods 0.000 title claims abstract description 45
- 239000003016 pheromone Substances 0.000 claims abstract description 139
- 238000005457 optimization Methods 0.000 claims abstract description 24
- 238000009499 grossing Methods 0.000 claims abstract description 23
- 238000011156 evaluation Methods 0.000 claims abstract description 15
- 230000003044 adaptive effect Effects 0.000 claims abstract description 14
- 230000007704 transition Effects 0.000 claims abstract description 13
- 241000257303 Hymenoptera Species 0.000 claims description 17
- 230000000694 effects Effects 0.000 claims description 11
- 230000001419 dependent effect Effects 0.000 claims description 4
- 238000013461 design Methods 0.000 description 19
- 238000005516 engineering process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000003068 static effect Effects 0.000 description 5
- 238000009825 accumulation Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 230000002028 premature Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000414 obstructive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
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
- G05D1/02—Control of position or course in two dimensions
- G05D1/0206—Control of position or course in two dimensions specially adapted to water vehicles
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)
- Feedback Control In General (AREA)
Abstract
The invention belongs to the field of unmanned ship global path planning, and particularly relates to an unmanned ship global path multi-target planning method based on an improved ant colony algorithm, which comprises the following steps: establishing a marine environment map model by using a Maklink graph theory; improving a path heuristic information strategy to obtain a path average value; designing an ant pheromone volatilization adaptive adjustment strategy; designing a local pheromone updating and global pheromone updating combination strategy; improving the ant colony search next node state transition probability through the heading angle deviation factor of the unmanned ship; and (3) designing an evaluation function by integrating the requirements of shortest overall path length, minimum optimization iteration times of the improved ant colony algorithm, minimum path smoothing coefficient and the like. The invention comprehensively considers the global path distance of the unmanned ship in the sea navigation, improves the ant colony algorithm to optimize the iteration times of the global path, the smooth coefficient of the planned global path and other multiple targets, and finally plans the optimal global path of the unmanned ship in the sea navigation, and has higher safety.
Description
Technical Field
The invention belongs to the field of unmanned ship global path planning, and particularly relates to an unmanned ship global path multi-target planning method based on an improved ant colony algorithm.
Background
With the development of modern society, technical means such as sensor miniaturization and high precision, intelligent control theory, equipment system engineering unmanned and the like are continuously brought forward, and along with the continuous update of the technologies and the wide application of unmanned equipment systems in armies, patrols, exploration and the like, the unmanned system becomes a leading-edge top technology which is strived for by the strong world science and technology. The Unmanned Surface Vehicle (USV) is a representative of an unmanned system in the ocean, can perform marine scientific research and engineering tasks for a long time at low cost and in a large range, and has a very common potential use space in the military field and the civil field, such as anti-submarine operations, anti-special operations, search and mine-discharge, submarine surveying and mapping, ocean resource exploration and development, ocean environment monitoring and other multiple uses. One of important technical means for supporting the rapid development of the unmanned surface vessel is an autonomous navigation technology of the unmanned surface vessel, and the global path planning of the unmanned surface vessel is the basis and the premise of the autonomous navigation technology.
Disclosure of Invention
The invention aims to provide a global path multi-target planning scheme of an unmanned ship based on an improved ant colony algorithm, which aims to solve the problems that the basic ant colony algorithm is low in convergence speed, easy to fall into a local extreme value, high in global path smoothing coefficient and the like.
An unmanned ship global path multi-target planning method based on an improved ant colony algorithm comprises the following steps:
(1) establishing a marine environment map model by using a Maklink graph theory;
(2) improving a path heuristic information strategy to obtain a path average value;
(3) designing an ant pheromone volatilization adaptive adjustment strategy;
(4) designing a local pheromone updating and global pheromone updating combination strategy;
(5) improving the state transition probability of the ant colony search next node through the heading angle deviation factor of the unmanned ship;
(6) and (3) designing an evaluation function by integrating the requirements of shortest overall path length, minimum optimization iteration times of the improved ant colony algorithm, minimum path smoothing coefficient and the like.
The establishing of the marine environment map model by using the Maklink graph theory comprises the following steps:
the Maklink graph theory is that a feasible space is planned in a two-dimensional path of an environment map by utilizing a large number of generated Maklink line segments; the Maklink line segment comprises a vertical line from a vertex of the convex polygon of the obstacle to the boundary and a connecting line between the vertices;
(1.1) making respective perpendicular lines from the vertexes to the boundaries of the convex polygons forming the obstacles and storing the perpendicular lines in a set according to a certain sequence number; connecting the vertexes of the convex polygon forming the obstacle and storing the connecting lines in the set;
(1.2) selecting a first line segment in the set, judging whether the line segment is intersected with the convex polygon boundary, if so, deleting the line segment from the set, and if not, checking the next line segment in the set;
(1.3) looking at the line segment and the vertex of the convex polygon, wherein two external angles can be generated between the line segment and the vertex of the convex polygon, and if the two external angles are both smaller than 180 degrees, the line segment is the optimal route;
(1.4) examining whether an external angle in the alternative line segments is larger than 180 degrees, if so, selecting the next line segment in the set, and returning to the step (1.2);
(1.5) deleting redundant connecting line segments;
(1.6) circulating the step (1.1) -the step (1.5) for multiple times until all the vertexes are traversed;
and (1.7) connecting the midpoints on the adjacent Maklin line segments, wherein the Maklin line segments, the vertexes and the midpoints form an environment map model of the unmanned surface vessel when the unmanned surface vessel sails at sea.
The improving the path heuristic information strategy to obtain a path average value comprises:
path average value:
in the formula (d)ijIs the distance between node i and node j.
The design of the ant pheromone volatilization adaptive adjustment strategy comprises the following steps:
designing a Logistic growth function to simulate the influence of a complex marine geographic environment on the volatilization coefficient of the ants pheromone, carrying out self-adaptive adjustment on the volatilization of the pheromone, wherein the Logistic function is an S-shaped function, and selecting an outer layer loop strategy iteration number NCAs an independent variable of the growth function, the pheromone volatilization coefficient rho is a dependent variable; in the early stage of algorithm convergence, the pheromone volatilization coefficient obtained by the growth function is small, and the guidance effect of an ant colony on each ant is weak, so that the global solution space of algorithm search is enlarged, and the search precision is improved; in the later stage of convergence of the algorithm, the pheromone volatilization coefficient obtained by the growth function is increased, the guidance effect of the ant colony on each ant is enhanced, and the convergence speed of the ant colony for searching the optimal global path is obviously accelerated; by initializing the values of Theta1, Theta2, Theta3, Theta4, the maximum, minimum and growth rates of the pheromone volatilization coefficients can be determined, and the resulting pheromone volatilization adaptive adjustment strategy is given by:
wherein Theta1 and Theta2 are the upper and lower limits of the growth function respectively, Theta3 is the value x of the center point of the growth function, and Theta4 is the growth speed of the growth function.
The method for designing the local pheromone updating and global pheromone updating combination strategy comprises the following steps:
pheromone local ij path segment update regulation rule
The kth ant walks a path, resulting in the pheromone update of this path:
τij k(t+1)＝ρ·τ0+(1-ρ)τk ij(t)
in the formula tau0Is the initial value of pheromone concentration, with tau on the left and right sidesij(t) the pheromone flow rates of the paths before and after the ants walk respectively, and the significance of local pheromone updating and adjusting is to reduce the pheromone flow rate of the path segment which is walked currently and increase the probability of the path segment which is not walked to be selected;
pheromone global update adjustment rules
After all ants finish respective food searching paths, finding the optimal global path by comparison, and finishing global pheromone updating and adjusting on the optimal global path:
wherein, tau (k) on the left and right sides is the pheromone flow before and after the ant updates on the optimal global path, lbestIndicating that the best global path is obtained in each outer loop, Q is the pheromone initialization strength, LkThe sum of the lengths of the paths traveled by the most ants;
pheromone threshold setting
By using a maximum and minimum ant system for reference, the maximum and minimum values of the pheromone on each section of the global path are constrained, and the specific formula is as follows:
wherein, tauij(t) represents the pheromone flow on the front and back paths of the ant, tauminIs the minimum value of the flow of the pheromone, taumaxIs the maximum value of the pheromone flow.
The method for improving the state transition probability of the ant colony search next node through the heading angle deviation factor of the unmanned ship comprises the following steps:
deviation F of the heading angle of the unmanned shipa＝|ψr-ψtConsidering the state transition probability of the ant colony to select the next node to improve the smoothness of the global path;
probability of ant colony from node i to node j:
wherein χ is a heading angle deviation heuristic factor and represents the importance degree of the global path smoothing coefficient to the global path planning, α is a pheromone heuristic factor, β is a path information heuristic factor, η is a path information heuristic factorijIs heuristic information of the path from node i to node j, tauijIs the amount of pheromone on the segment of path (i, j).
The method for designing the evaluation function by integrating the requirements of shortest overall path length, minimum optimization iteration times of the improved ant colony algorithm, minimum path smoothing coefficient and the like comprises the following steps of:
the evaluation function is formulated as:
f＝n1Lk+n2Nk+n3Sk
where f is the specific value of the evaluation function, LkIs the length of the optimal global path, N, obtained by the optimal ant kkIs the number of iterations, SkIs a path smoothness factor, n1,n2,n3Respectively are the weight proportions of the three components;
optimal global path length objective
The path length reflects the requirement of the unmanned ship on the shortest distance when navigating at sea, and the length of the optimal global path is expressed as:
wherein p isN kIs the sum of the number of path nodes that the optimal ant k has traveled in the Nth iteration, d (g)i,gi+1) Is the distance between node i and the next node traveled, given by:
wherein (x)i,yi) Is the abscissa and ordinate of node i, (x)i,yi) Is the abscissa and ordinate of the node i + 1;
minimum target of path smoothing coefficient
The optimal global path smoothness reflects the minimum requirement on the accumulated deflection angle of the heading angle when the unmanned ship sails at sea, and the global path tracking control safety coefficient of the unmanned ship can be improved, and the specific formula is as follows:
wherein psiiRepresenting an included angle between the i-1 th section and the i-th section which project the optimal global path section on the horizontal plane;
objective of minimum number of iterations
The algorithm optimizes iteration times reflecting the computer time consumed by the intelligent algorithm in optimizing the optimal solution of the search object, and the iteration times N need to be ensured in the ant colony algorithm optimization processkA minimum value is reached.
The invention has the beneficial effects that:
1. according to the invention, the optimal unmanned ship marine navigation optimal global path is finally planned by comprehensively considering the global path distance of the unmanned ship marine navigation and improving multiple targets such as the ant colony algorithm to optimize the iteration times of the global path and the smooth coefficient of the planned global path, and the safety is higher;
2. the invention provides an improved heuristic information strategy for changing the average path length, an pheromone volatilization adaptive adjustment strategy, a local pheromone updating and global pheromone updating combination strategy and a global path smoothness enhancement strategy from the viewpoint of overcoming the defects that the ant colony algorithm is low in convergence speed and easy to fall into a local extreme value and the like, and also provides the global path smoothness enhancement strategy from the viewpoint of the navigation safety of the unmanned ship, so that the efficiency and the intelligent level of the global path of the unmanned ship are improved by the ant colony algorithm, and the security is higher.
Drawings
FIG. 1 is a schematic diagram of the unmanned surface vehicle global path planning of the present invention;
FIG. 2 is a Maklink graph theory-based map model of an unmanned surface vessel environment;
FIG. 3 is a schematic view of the deviation of the heading angle of the unmanned surface vehicle of the present invention;
FIG. 4 is a design diagram of Logistic growth function of the present invention;
FIG. 5 is a flow chart of an improved ant colony algorithm design of the present invention;
FIG. 6 is a graph of the calculation of the path smoothing coefficients according to the present invention;
FIG. 7 is a diagram of the global path planning result of the first embodiment
FIG. 8 is a graph of total path length versus iteration number for the first embodiment;
FIG. 9 is a diagram of the global path planning result of the second embodiment
FIG. 10 is a graph of the total path length and the number of iterations for the second embodiment.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
The invention relates to an unmanned ship global path multi-target planning method based on an improved ant colony algorithm, which comprises the following steps:
1. and generating an environment map model for marine navigation for the unmanned surface vessel by using the Maklink graph theory technology.
2. Aiming at the problem that the ant colony algorithm is easy to fall into a local extreme value, an improved heuristic information strategy for changing the average path length is designed.
3. Aiming at the problem of low convergence speed of the ant colony algorithm, an pheromone volatilization self-adaptive adjustment strategy and a local pheromone updating and global pheromone updating combination strategy are designed.
4. Aiming at the problem of high global path smoothing coefficient of the unmanned ship, a state transition probability strategy is designed and improved based on the deviation factor of the heading angle of the unmanned ship.
5. The multiple targets of shortest overall path length, minimum algorithm optimization iteration times, minimum path smoothing coefficient and the like are considered, simulation analysis and example test are carried out on the improved ant colony algorithm, and the optimal overall path from the starting point to the ending point of the unmanned ship sailing at sea is obtained.
An unmanned ship global path multi-target planning method based on an improved ant colony algorithm is realized by the following steps:
firstly, establishing a marine environment map model for the unmanned ship by using a Maklink graph theory, then providing an improved heuristic information strategy for changing the average path length, an pheromone volatilization adaptive adjustment strategy and a local pheromone updating and global pheromone updating combination strategy aiming at the problems that the ant colony algorithm is low in convergence speed and easy to fall into a local extreme value and the like, and finally designing an improved state transition probability strategy based on a heading angle deviation factor of the unmanned ship in order to ensure the safety of the unmanned ship in marine navigation, and obtaining an improved ant colony algorithm planning unmanned ship global path scheme under multiple targets of shortest path length, minimum optimization iteration times, minimum path smoothing coefficient and the like.
1) Constructing an environment map model based on a Maklink graph theory:
the method to be protected is characterized in that the method of Maklink graph theory is adopted to model the environment map;
the Maklink graph theory is that a large number of generated Maklink points and Maklink line segments are utilized to realize the establishment of an environment model of the unmanned ship for marine navigation;
a connecting line between vertexes and a midpoint of a central line of the convex polygon forming the static obstacle and a parallel connecting line between the vertexes and a boundary are called as a Maklink line segment, and the midpoint on the free link line is obtained according to a generation method of the Maklink free link line;
constructing a non-directional network line, a Maklink line segment, a top point of an obstacle and a middle point through the middle point on the Maklink line to form an environment map model of the unmanned surface vessel sailing at sea;
2) the improved ant colony algorithm design for improving the ant state transition probability by using the unmanned ship heading angle deviation factor is as follows:
the protection method is characterized in that the state transition probability of the next node of the ant colony search is improved through the heading angle deviation factor of the unmanned ship, and the lowest global path smoothing coefficient is used as one of the planning targets of the global path of the unmanned ship;
2.1) deviation of the heading angle F of the unmanned shipa＝|ψr-ψtConsidering the state transition probability of the ant colony to select the next node to improve the smoothness of the global path;
2.2) calculating the probability of the ant colony from the node i to the node j:
wherein χ is a heading angle deviation heuristic factor, which represents the importance of the global path smoothing coefficient to the global path planning, α is a pheromone heuristic factor, β is a path information heuristic factor, ηijIs heuristic information of the path from node i to node j, tauijIs the amount of pheromone on the path (i, j) segment;
3) considering the global path planning design of the unmanned ship under multiple targets of shortest global path length, minimum optimization iteration times of the improved ant colony algorithm, minimum path smoothing coefficient and the like, a specific evaluation function formula is given as follows:
f＝n1Lk+n2Nk+n3Sk
wherein f is a specific value of the evaluation function, LkIs the length of the optimal global path, N, obtained by the optimal ant kkIs the number of iterations, SkIs a path smoothness factor, n1,n2,n3The weight ratios of the three are respectively.
The scheme for planning the global path of the unmanned ship by the improved ant colony algorithm is characterized by integrating the scheme for planning the global path of the unmanned ship by the improved ant colony algorithm under multiple targets of shortest global path length, minimum optimized iteration times of the improved ant colony algorithm, minimum path smoothing coefficient and the like:
3.1) Global Path Length shortest target
The path length reflects the requirement of the unmanned ship on the shortest distance when the unmanned ship sails on the sea, is one of the targets of algorithm optimization, and is designed as follows:
in the formula, pN kIs the sum of the number of path nodes that the optimal ant k has traveled in the Nth iteration, d (g)i,gi+1) Is the distance between node i and the next node traveled, given by:
in the formula (x)i,yi) Is the abscissa and ordinate of node i, (x)i,yi) Is the abscissa and ordinate of the node i + 1.
3.2) path smoothing coefficient minimum target
The optimal global path smoothness reflects the requirement of minimum accumulated deflection angle of the heading angle when the unmanned ship sails at sea, can improve the global path tracking control safety coefficient of the unmanned ship, and is one of the targets of algorithm optimization. The specific formula is designed as follows:
in the formula, #iRepresenting the angle between the i-1 th segment and the i-th segment projected onto the horizontal plane of the optimal global path segment.
3.3) objective of minimum number of iterations
The algorithm optimizes iteration times reflecting the computer time consumed by the intelligent algorithm in optimizing the optimal solution of the search object, and the iteration times N need to be ensured in the ant colony algorithm optimization processkA minimum value is reached.
The unmanned ship global path multi-target planning is embodied in the design of an evaluation function, the evaluation performance function reflects the quality of the optimal global path planned by a basic ant colony algorithm and an improved ant colony algorithm, and the optimization of the algorithm can be guided to develop towards the direction close to indexes such as safety, high efficiency and the like of the unmanned ship marine navigation. The evaluation function performance index requires consideration of the integration of multiple targets, such as shortest path, minimum convergence iteration times of the algorithm, good global path smoothness and the like, and the specific formula is as follows:
f＝n1Lk+n2Nk+n3Sk
wherein f is a specific value of the evaluation function, LkIs the length of the optimal global path, N, obtained by the optimal ant kkIs the number of iterations, SkIs a path smoothness factor, n1,n2,n3The weight ratios of the three are respectively.
Optimal global path length objective
The path length reflects the requirement of the unmanned ship on the shortest distance when the unmanned ship sails at sea, and is one of the targets of algorithm optimization. The design is as follows:
in the formula pN kIs the sum of the number of path nodes that the optimal ant k has traveled in the Nth iteration, d (g)i,gi+1) Is the distance between node i and the next node traveled, given by:
in the formula (x)i,yi) Is the abscissa and ordinate of node i, (x)i,yi) Is the abscissa and ordinate of node i +1
Optimal global path smoothness target
The optimal global path smoothness reflects the requirement of minimum accumulated deflection angle of the heading angle when the unmanned ship sails at sea, can improve the global path tracking control safety coefficient of the unmanned ship, and is one of the targets of algorithm optimization. When the USV controls the change of the heading, an additional heading angle is needed to assist the propeller to work, but the auxiliary heading angle propeller consumes larger energy to work, and meanwhile, the larger heading angle change possibly exceeds the maximum limit of the USV propeller, so that the turning operation cannot be finished. The design is as follows:
in the formula psiiThe included angle between the i-1 th section and the i-th section projected by the optimal global path section on the horizontal plane is shown, and the change of the heading angle of a certain node can be calculated according to the previous path planning point and the subsequent passing planning point, as shown in fig. 5.
Objective of minimum number of iterations
The algorithm optimizes iteration times reflecting the computer time consumed by the intelligent algorithm in optimizing the optimal solution of the search object, and the iteration times N need to be ensured in the ant colony algorithm optimization processkA minimum value is reached.
The purpose of the invention can be realized by the following technical scheme:
1) establishment of environment map model based on Maklink graph theory
The method adopts a Maklik graph theory method to model the environment map. Referring to the attached figure 2, a sea map model is established for the unmanned ship in a space of 200km x 200km, the initial position is S (20.02km,179.58km), the final position is T (161.47km,82.55km), the initial heading angle is 90 degrees, black polygons represent sea static obstacles, and the modeling is carried out by using a Maklink diagram theory, and the whole process and method steps are as follows:
1.1) Maklink's theory is to utilize the large number of Maklink's line segments generated to plan feasible space, such as midline and undirected free-connecting line, in the two-dimensional path of the environment map.
1.2) a connecting line between the vertex of the convex polygon forming the obstacle and the midpoint of the central line and a parallel connecting line between the vertex and the boundary are called Maklik line segments, and the point on the free link line is obtained as the midpoint according to the generation method of the Maklik free link line.
1.3) the following algorithm flow generates a undirected network graph.
1. The elements in the set belong to the vertexes of the convex polygon of the obstacle, and the points in the set to the boundary are respectively made into vertical lines and stored in another set according to a certain sequence number.
2. The first line segment in the set is selected.
3. And judging whether the line segment intersects with the convex polygon boundary. If the segments are intersected, the segment is abandoned and cannot be made into a Maklink segment, next, the next segment in the set is checked, and if the segments are not intersected, the step 4 is carried out.
4. Looking at the vertices of the Maklink line segment and the convex polygon, two outer angles will be created between them. When both external angles are less than 180 deg., then the link is the optimal route.
5. Examine if there is an external angle in the alternative connection lines that is greater than 180. If so, selecting the next line segment in the set, and returning to the step 3; if not, go to step 6.
6. And deleting redundant connecting line segments except the Maklink line segment.
7. And (5) repeating the steps 1-6 for multiple times, and traversing to all the vertexes.
And then, constructing an undirected network map by using midpoints on the Maklin lines, and finally forming an environment map model of the unmanned surface vessel when the unmanned surface vessel sails at sea by using the Maklin line segments, the vertexes and the midpoints.
Improved path heuristic information strategy design
The path heuristic information plays a very important role in expanding the global solution space and the stability of the ant colony algorithm. In the basic ant colony algorithm, path heuristic information generally selects the reciprocal of the length of the path, but the path heuristic only finds the optimal path from the single aspect of shortest distance, and in complex geographic environment and multi-task comprehensive path optimization, the method is not feasible any longer, and the shortest distance causes excessive accumulation of the pheromone quantity of ants on the path, so that the algorithm optimizes the local optimal solution too fast, and is easy to fall into the local extremum solution, thereby causing the stability deviation of the algorithm. For the situation, a path average value concept is designed, and a specific formula is given as follows:
in the formula (d)ijIs the distance between node i and node j.
Pheromone volatilization adaptive adjustment strategy design
In the ant colony algorithm, the pheromone volatilization coefficient represents the volatilization speed of pheromone concentration on a path segment, is a constant and does not change. The pheromone volatilization speed under the actual condition can be gradually changed along with the time lapse or the change of other conditions (such as temperature, humidity and the like), especially, the volatilization speed of the pheromone concentration can be different due to the influence of the complex environment of storm flow of the local sea area on the unmanned boat when the unmanned boat sails on the sea, and the method is one of important conditions that an ant colony can find an optimal path in the natural world in a good intelligent manner. Therefore, an ant pheromone volatilization self-adaptive adjustment strategy is designed, the guiding effect of the ant pheromone is increased, the convergence speed of the algorithm is increased, and the unmanned ship global path can be planned better and more accurately.
The following Logistic growth function is designed to simulate the influence of a marine complex geographic environment on the volatilization coefficient of the ant pheromone, and the pheromone volatilization self-adaptive adjustment is carried out. The Logistic function is a common S-shaped function, as shown in figure 4, and the iteration number N of the outer loop strategy is selectedCThe pheromone volatility coefficient ρ is the dependent variable as the independent variable of the growth function. In the early stage of algorithm convergence, the pheromone volatilization coefficient obtained by the growth function is small, and the guidance effect of the ant colony on each ant is weak, so that the global solution space of algorithm search is enlarged, and the search precision is improved. Signal obtained by increasing function in later convergence stage of algorithmThe pheromone volatilization coefficient is increased, the guidance effect of the ant colony on each ant is enhanced, and the convergence speed of the ant colony for searching the optimal global path is obviously accelerated. By initializing the values of Theta1, Theta2, Theta3, Theta4, the maximum, minimum and growth rates of the pheromone volatilization coefficients can be determined, and the resulting pheromone volatilization adaptive adjustment strategy is given by:
local pheromone updating and global pheromone updating combined strategy design
In order to increase the rate of ant searching for the optimal global path, the section improves the strategy of ant colony pheromone updating adjustment. Different from a basic ant colony algorithm strategy that pheromone concentration is updated and adjusted after each ant searches a section of path, the method provides a more purposeful and more efficient pheromone updating strategy, and the pheromone concentration updating of each section of the optimal global path searched by the optimal ant is combined with the pheromone updating of each section of the local path after each external circulation, so that the iteration frequency of optimizing of an external circulation path is reduced, the convergence speed of the algorithm is improved, and meanwhile, pheromone threshold limit is introduced to avoid large accumulated difference of the pheromone concentration of each path section.
Pheromone local ij path segment update regulation rule
The kth ant walks a path, resulting in the pheromone update of this path:
τij k(t+1)＝ρ·τ0+(1-ρ)τk ij(t)
in the formula tau0Is the initial value of pheromone concentration, with tau on the left and right sidesijAnd (t) respectively represents the pheromone flow on the paths before and after the ants walk, and the significance of local pheromone updating and adjusting is to reduce the pheromone flow of the path segment which is walked at present and increase the probability of the path segment which is not walked to be selected.
Pheromone global update adjustment rules
After all ants finish respective food searching paths, finding the optimal global path by comparison, and finishing global pheromone updating and adjusting on the optimal global path:
the left and right edges τ (k) of the formula are the pheromone flow before and after the best ant updates on the optimal global path, lbestIndicating that the best global path is obtained in each outer loop, Q is the pheromone initialization strength, LkIs the sum of the lengths of the paths taken by the most ants.
Pheromone threshold setting
In order to avoid that the pheromone quantity accumulation difference of each section of the global path is huge in the process of searching the global path by the ant colony algorithm, so that the optimization process is stagnated or premature, the Maximum and Minimum Ant System (MMAS) is used for reference, the maximum and minimum pheromone values on each section of the global path are restrained, and a specific formula is given as follows:
5) global path smoothness enhancement policy design
In FIG. 3, point S is the starting point of the global path plan, point T is the ending point of the global path plan, Pi-1As the point at which the current ant colony is located, PiThe next search point for the ant colony, ψtFor ant colony, angle of direction of connecting line of current nodes, psirDirection angle, F, of line connecting start and end points of the ant colonya＝|ψr-ψtI is the deviation of the heading angle of the unmanned boat; the state transition probability of the ant searching the next node is as follows:
and χ is a heading angle deviation heuristic factor and represents the importance degree of the global path smoothing coefficient to the global path planning.
FIG. 1 is a flow chart of the method, and particularly describes the working process and the function of the method in the unmanned surface vessel global path multi-objective planning.
Example 1 was carried out as follows:
for a certain unmanned surface vessel, the initialization of the improved ant colony algorithm is as follows:
the probability of the next node for ant colony tracking is modified as follows:
the next node for ant tracing:
j is the adjusted heading angle when the USV shipborne laser radar scans and detects the obstructive object within the safe distance
The next node to arrive.
Pheromone selection threshold: pheThres ═ 0.8,
pheromone calculation parameters: pheCacuPara 2,
pheromone update parameters: pheUpPara ═ 0.1,0.0003,
heuristic information parameters: qfzPara1 ═ ons (10,1) × 0.5, qfzPara2 ═ 1.1
The number of ants: m is equal to 10, and m is equal to 10,
iterative algebra: the NC is 500, and the NC is 500,
link line point ratio parameter: hi is pathk (l +1, k)/10,
USV real-time azimuth angle: ψ t ═ acos (angle-angle),
desired direction angle of USV: and calculating according to the coordinates of S and T.
α＝2,β＝5,χ＝4,C＝0.003,Q＝1,ρ＝0.1,n1＝0.3,n2＝0.2,n3＝0.5
Theta1＝1,Theta2＝0.003,Theta3＝200,Theta4＝0.1
Step 1: in the attached figure 2, a sea map model is established for the unmanned ship in a space of 200km x 200km, the initial position is S (20.02km,179.58km), the end position is T (161.47km,82.55km), the initial heading angle is 90 degrees, a black polygon represents a sea static obstacle, and modeling is carried out by using a MAKLINK graph theory method.
Step 2: dijkstra algorithm design
The basic idea of Dijkstra algorithm is to calculate the distance between points, calculate the shortest distance set from the source point to each point, and then form the corresponding weight value table. The method comprises the following specific steps:
initializing a set V and a set S, wherein the set V is a node of which the shortest path is not determined, and the set S is determined. In the weighted graph there is an adjacency matrix arcs, which is used to initialize the shortest path length D, i.e. the length from the source to the other nodes.
The minimum value D [ i ] in the set D is optimized, namely D [ i ] is the shortest path length from the source point to the point i, and the next step is to take out the point i in the set V and put the point i in the set S.
And modifying the path length value corresponding to the node k by comparing with the node i.
And (3) multiple times of steps 2 and 3, and stopping the algorithm when the shortest paths from the source point to all the nodes are found.
And 3, step 3: improved heuristic information policy design
The concept of path average value is designed, and the obtained path heuristic information is shown in the following formula:
through the design of the path mean value, the difference of the accumulated ant pheromone quantity on the optimal global path segment and the worst global path segment is greatly reduced, and meanwhile, under the condition of not reducing the convergence speed of the ant colony algorithm, the path segment is poorer or the candidate optimal global path segment is possibly selected by ants, the global solution space searched by the algorithm is expanded, and the situation that the ant pheromone quantity falls into a local extreme value is avoided.
And 4, step 4: pheromone volatilization adaptive adjustment strategy design
The following Logistic growth function is designed to simulate the influence of a marine complex geographic environment on the volatilization coefficient of the ant pheromone, and the pheromone volatilization self-adaptive adjustment is carried out. The specific formula is given by the following formula:
in the formula, Theta3 is an x value of a central point of an increasing function, Theta4 represents the increasing speed of the increasing function and is a design part of pheromone volatilization adaptive adjustment, and Theta1 and Theta2 are upper and lower limits of the increasing function respectively. Selecting outer loop strategy iteration number NCThe pheromone volatility coefficient ρ is the dependent variable as the independent variable of the growth function. In the early stage of algorithm convergence, the pheromone volatilization coefficient obtained by the growth function is small, and the guidance effect of the ant colony on each ant is weak, so that the global solution space of algorithm search is enlarged, and the search precision is improved. In the later stage of convergence of the algorithm, the pheromone volatilization coefficient obtained by the growth function is increased, the guidance effect of the ant colony on each ant is enhanced, and the convergence speed of the ant colony for searching the optimal global path is obviously accelerated. By initializing the values of Theta1, Theta2, Theta3 and Theta4, the maximum value, the minimum value and the growth rate of the pheromone volatilization coefficient can be determined, and the obtained pheromone volatilization adaptive adjustment strategy is shown as the following formula:
and 5, step 5: global pheromone and local pheromone updating combined strategy design
Pheromone local ij path segment update regulation rule
The kth ant walks a path, resulting in the pheromone update of this path:
τij k(t+1)＝ρ·τ0+(1-ρ)τk ij(t)
in the formula tau0Is the initial value of pheromone concentration, with tau on the left and right sidesijAnd (t) respectively represents the pheromone flow on the paths before and after the ants walk, and the significance of local pheromone updating and adjusting is to reduce the pheromone flow of the path segment which is walked at present and increase the probability of the path segment which is not walked to be selected.
Pheromone global update adjustment rules
After all ants finish respective food searching paths, finding the optimal global path by comparison, and finishing global pheromone updating and adjusting on the optimal global path:
the left and right edges τ (k) of the formula are the pheromone flow before and after the best ant updates on the optimal global path, lbestIndicating that the best global path is obtained in each outer loop, Q is the pheromone initialization strength, LkIs the sum of the lengths of the paths taken by the most ants.
Pheromone threshold setting
In order to avoid that the pheromone quantity accumulation difference of each section of the global path is huge in the process of searching the global path by the ant colony algorithm, so that the optimization process is stagnated or premature, the Maximum and Minimum Ant System (MMAS) is used for reference, and the maximum and minimum pheromone values on each section of the global path are constrained, the specific formula is as follows:
and 6, step 6: and according to the established environment map model and the designed improved ant colony algorithm, carrying out simulation experiment of unmanned ship global path planning by considering the multi-objective task with shortest global path and shortest algorithm optimization iteration times.
The final planning result of the embodiment is shown in the attached figures 7 and 8, the invention effect of the invention is realized, and the unmanned surface vessel can safely and automatically avoid collision when encountering a static state in the process of sailing to the preset target point by considering the multi-target task with the shortest global path and the shortest algorithm optimization iteration times.
Example 2 was carried out as follows:
this example is substantially the same as example 1, and is characterized in that:
in the step 6, a simulation experiment of the unmanned ship global path planning is carried out by considering multi-target tasks such as the shortest global path, the shortest algorithm optimization iteration times, the lowest path smoothing coefficient and the like. The global path smoothing coefficient of the unmanned ship is designed as follows:
the optimal global path smoothness reflects the requirement of minimum accumulated deflection angle of the heading angle when the unmanned ship sails at sea, can improve the global path tracking control safety coefficient of the unmanned ship, and is one of the targets of algorithm optimization. When the USV controls the heading to change, an additional heading angle auxiliary propeller is needed to work, but the auxiliary heading angle propeller consumes larger energy to work, and meanwhile, the larger heading angle change possibly exceeds the maximum limit of the USV propeller, so that the turning operation cannot be finished, and the design is as follows:
in the formula psiiIndicating projection of the optimal global path segment onto the horizontal planeThe included angle between the i-1 section and the i-th section, and the change of the heading angle of a certain node can be obtained by calculation according to the previous path planning point and the next passing planning point.
The final planning result of the embodiment is shown in the attached drawings 9 and 10, and the invention effect of the invention is realized, and in the process that the unmanned surface vessel sails towards the target point, the multi-target tasks such as the shortest global path, the shortest algorithm optimization iteration times, the lowest path smoothing coefficient and the like are considered, so that the unmanned surface vessel can safely and automatically avoid collision in a static state during sailing and can smoothly reach the preset target point.
The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
Claims (7)
1. An unmanned ship global path multi-target planning method based on an improved ant colony algorithm is characterized by comprising the following steps:
(1) establishing a marine environment map model by using a Maklink graph theory;
(2) improving a path heuristic information strategy to obtain a path average value;
(3) designing an ant pheromone volatilization adaptive adjustment strategy;
(4) designing a local pheromone updating and global pheromone updating combination strategy;
(5) improving the state transition probability of the ant colony search next node through the heading angle deviation factor of the unmanned ship;
(6) and (3) designing an evaluation function by integrating the requirements of shortest overall path length, minimum optimization iteration times of the improved ant colony algorithm, minimum path smoothing coefficient and the like.
2. The unmanned ship global path multi-objective planning method based on the improved ant colony algorithm as claimed in claim 1, wherein the establishing of the marine environment map model by using the Maklink graph theory comprises:
the Maklink graph theory is that a feasible space is planned in a two-dimensional path of an environment map by utilizing a large number of generated Maklink line segments; the Maklink line segment comprises a vertical line from a vertex of the convex polygon of the obstacle to the boundary and a connecting line between the vertices;
(1.1) making respective perpendicular lines from the vertexes to the boundaries of the convex polygons forming the obstacles and storing the perpendicular lines in a set according to a certain sequence number; connecting the vertexes of the convex polygon forming the obstacle and storing the connecting lines in the set;
(1.2) selecting a first line segment in the set, judging whether the line segment is intersected with the convex polygon boundary, if so, deleting the line segment from the set, and if not, checking the next line segment in the set;
(1.3) looking at the line segment and the vertex of the convex polygon, wherein two external angles can be generated between the line segment and the vertex of the convex polygon, and if the two external angles are both smaller than 180 degrees, the line segment is the optimal route;
(1.4) examining whether an external angle in the alternative line segments is larger than 180 degrees, if so, selecting the next line segment in the set, and returning to the step (1.2);
(1.5) deleting redundant connecting line segments;
(1.6) circulating the step (1.1) -the step (1.5) for multiple times until all the vertexes are traversed;
and (1.7) connecting the midpoints on the adjacent Maklin line segments, wherein the Maklin line segments, the vertexes and the midpoints form an environment map model of the unmanned surface vessel when the unmanned surface vessel sails at sea.
3. The unmanned ship global path multi-objective planning method based on the improved ant colony algorithm as claimed in claim 1, wherein the improving the path heuristic information strategy to obtain a path average value comprises:
path average value:
in the formula (d)ijIs between node i and node jThe distance of (c).
4. The unmanned ship global path multi-objective planning method based on the improved ant colony algorithm as claimed in claim 1, wherein the designing of the ant pheromone volatilization adaptive adjustment strategy comprises:
designing a Logistic growth function to simulate the influence of a complex marine geographic environment on the volatilization coefficient of the ants pheromone, carrying out self-adaptive adjustment on the volatilization of the pheromone, wherein the Logistic function is an S-shaped function, and selecting an outer layer loop strategy iteration number NCAs an independent variable of the growth function, the pheromone volatilization coefficient rho is a dependent variable; in the early stage of algorithm convergence, the pheromone volatilization coefficient obtained by the growth function is small, and the guidance effect of an ant colony on each ant is weak, so that the global solution space of algorithm search is enlarged, and the search precision is improved; in the later stage of convergence of the algorithm, the pheromone volatilization coefficient obtained by the growth function is increased, the guidance effect of the ant colony on each ant is enhanced, and the convergence speed of the ant colony for searching the optimal global path is obviously accelerated; by initializing the values of Theta1, Theta2, Theta3, Theta4, the maximum, minimum and growth rates of the pheromone volatilization coefficients can be determined, and the resulting pheromone volatilization adaptive adjustment strategy is given by:
wherein Theta1 and Theta2 are the upper and lower limits of the growth function respectively, Theta3 is the value x of the center point of the growth function, and Theta4 is the growth speed of the growth function.
5. The unmanned ship global path multi-objective planning method based on the improved ant colony algorithm as claimed in claim 1, wherein the designing of the local pheromone updating and global pheromone updating combination strategy comprises:
pheromone local ij path segment update regulation rule
The kth ant walks a path, resulting in the pheromone update of this path:
τij k(t+1)＝ρ·τ0+(1-ρ)τk ij(t)
in the formula tau0Is the initial value of pheromone concentration, with tau on the left and right sidesij(t) the pheromone flow rates of the paths before and after the ants walk respectively, and the significance of local pheromone updating and adjusting is to reduce the pheromone flow rate of the path segment which is walked currently and increase the probability of the path segment which is not walked to be selected;
pheromone global update adjustment rules
After all ants finish respective food searching paths, finding the optimal global path by comparison, and finishing global pheromone updating and adjusting on the optimal global path:
wherein, tau (k) on the left and right sides is the pheromone flow before and after the ant updates on the optimal global path, lbestIndicating that the best global path is obtained in each outer loop, Q is the pheromone initialization strength, LkThe sum of the lengths of the paths traveled by the most ants;
pheromone threshold setting
By using a maximum and minimum ant system for reference, the maximum and minimum values of the pheromone on each section of the global path are constrained, and the specific formula is as follows:
wherein, tauij(t) represents the pheromone flow on the front and back paths of the ant, tauminAs informationMinimum of prime flow, τmaxIs the maximum value of the pheromone flow.
6. The unmanned ship global path multi-objective planning method based on the improved ant colony algorithm as claimed in claim 1, wherein the improving the state transition probability of the ant colony search for the next node by the heading angle deviation factor of the unmanned ship comprises:
deviation F of the heading angle of the unmanned shipa＝|ψr-ψtConsidering the state transition probability of the ant colony to select the next node to improve the smoothness of the global path;
probability of ant colony from node i to node j:
wherein χ is a heading angle deviation heuristic factor and represents the importance degree of the global path smoothing coefficient to the global path planning, α is a pheromone heuristic factor, β is a path information heuristic factor, η is a path information heuristic factorijIs heuristic information of the path from node i to node j, tauijIs the amount of pheromone on the segment of path (i, j).
7. The unmanned ship global path multi-objective planning method based on the improved ant colony algorithm as claimed in claim 1, wherein the evaluation function is designed based on the requirements of shortest overall path length, minimum number of optimized iterations of the improved ant colony algorithm, minimum path smoothing coefficient and the like, and comprises:
the evaluation function is formulated as:
f＝n1Lk+n2Nk+n3Sk
where f is the specific value of the evaluation function, LkIs the length of the optimal global path, N, obtained by the optimal ant kkIs the number of iterations, SkIs a path smoothness factor, n1,n2,n3Respectively are the weight proportions of the three components;
optimal global path length objective
The path length reflects the requirement of the unmanned ship on the shortest distance when navigating at sea, and the length of the optimal global path is expressed as:
wherein p isN kIs the sum of the number of path nodes that the optimal ant k has traveled in the Nth iteration, d (g)i,gi+1) Is the distance between node i and the next node traveled, given by:
wherein (x)i,yi) Is the abscissa and ordinate of node i, (x)i,yi) Is the abscissa and ordinate of the node i + 1;
minimum target of path smoothing coefficient
The optimal global path smoothness reflects the minimum requirement on the accumulated deflection angle of the heading angle when the unmanned ship sails at sea, and the global path tracking control safety coefficient of the unmanned ship can be improved, and the specific formula is as follows:
wherein psiiRepresenting an included angle between the i-1 th section and the i-th section which project the optimal global path section on the horizontal plane;
objective of minimum number of iterations
The algorithm optimizes iteration times reflecting the computer time consumed by the intelligent algorithm in optimizing the optimal solution of the search object, and the iteration times N need to be ensured in the ant colony algorithm optimization processkA minimum value is reached.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911372167.XA CN111026126A (en) | 2019-12-27 | 2019-12-27 | Unmanned ship global path multi-target planning method based on improved ant colony algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911372167.XA CN111026126A (en) | 2019-12-27 | 2019-12-27 | Unmanned ship global path multi-target planning method based on improved ant colony algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111026126A true CN111026126A (en) | 2020-04-17 |
Family
ID=70214973
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911372167.XA Pending CN111026126A (en) | 2019-12-27 | 2019-12-27 | Unmanned ship global path multi-target planning method based on improved ant colony algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111026126A (en) |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111641930A (en) * | 2020-06-01 | 2020-09-08 | 秦川 | Layered data acquisition system and method applied to ocean information network |
| CN111639811A (en) * | 2020-06-01 | 2020-09-08 | 中国农业大学 | Multi-agricultural-machine cooperative work remote management scheduling method based on improved ant colony algorithm |
| CN111880542A (en) * | 2020-08-04 | 2020-11-03 | 昆山九毫米电子科技有限公司 | Multiple unmanned target vehicle path planning method based on improved ant colony algorithm |
| CN112036537A (en) * | 2020-08-04 | 2020-12-04 | 中国农业大学 | Three-dimensional path planning method and system for land scraper navigation |
| CN112113569A (en) * | 2020-09-03 | 2020-12-22 | 中国联合网络通信集团有限公司 | Inspection path optimization method and device |
| CN112148030A (en) * | 2020-09-23 | 2020-12-29 | 天津大学 | Underwater glider path planning method based on heuristic algorithm |
| CN112161627A (en) * | 2020-09-23 | 2021-01-01 | 同济大学 | Intelligent path planning method for fire-fighting robot |
| CN112306097A (en) * | 2020-10-29 | 2021-02-02 | 杭州电子科技大学 | Novel unmanned aerial vehicle path planning method |
| CN112819211A (en) * | 2021-01-21 | 2021-05-18 | 安徽农业大学 | Multi-region scheduling route planning method based on ant colony iterative algorithm |
| CN112866902A (en) * | 2021-01-12 | 2021-05-28 | 武汉理工大学 | Dynamic dangerous shipborne environment self-adaptive emergency navigation method |
| CN113190017A (en) * | 2021-05-24 | 2021-07-30 | 东南大学 | Harvesting robot operation path planning method based on improved ant colony algorithm |
| CN113204348A (en) * | 2021-04-30 | 2021-08-03 | 北京连山科技股份有限公司 | Domestic road network data compiling method based on linkage hierarchy |
| CN113326979A (en) * | 2021-05-25 | 2021-08-31 | 汕头大学 | Regional scenery spot two-way route multi-target planning method based on improved ant colony algorithm |
| CN113325856A (en) * | 2021-05-31 | 2021-08-31 | 中国船舶工业集团公司第七0八研究所 | UUV optimal operation path planning method based on countercurrent approximation strategy |
| CN113341998A (en) * | 2021-06-29 | 2021-09-03 | 厦门大学 | Three-dimensional underwater under-actuated AUV path planning method for improving ant colony algorithm |
| CN113607172A (en) * | 2021-08-09 | 2021-11-05 | 北京中安智能信息科技有限公司 | Underwater route planning method and device for underwater vehicle under multi-constraint condition |
| CN113655785A (en) * | 2021-06-29 | 2021-11-16 | 航天科工深圳（集团）有限公司 | Unmanned ship group control method based on hybrid algorithm |
| CN113917929A (en) * | 2021-11-11 | 2022-01-11 | 中国船舶重工集团公司第七一九研究所 | Unmanned ship path optimization method and system based on hybrid particle swarm algorithm |
| CN113919771A (en) * | 2021-09-24 | 2022-01-11 | 成都信息工程大学 | Unmanned aerial vehicle multi-target intelligent distribution method |
| CN114089754A (en) * | 2021-11-11 | 2022-02-25 | 中国船舶重工集团公司第七一九研究所 | Autonomous path planning method and system based on artificial intelligence |
| CN114111824A (en) * | 2021-11-11 | 2022-03-01 | 中国船舶重工集团公司第七一九研究所 | Unmanned ship path optimization method and system based on multi-objective optimization |
| CN114115237A (en) * | 2021-11-03 | 2022-03-01 | 中国人民解放军陆军防化学院 | Multi-target radiation reconnaissance method based on path optimization |
| CN114527746A (en) * | 2022-01-12 | 2022-05-24 | 燕山大学 | Intelligent automobile path planning and obstacle avoidance tracking method |
| CN114844824A (en) * | 2022-04-11 | 2022-08-02 | 广州杰赛科技股份有限公司 | Method and device for planning network information transmission path and terminal equipment |
| CN114879669A (en) * | 2022-04-28 | 2022-08-09 | 贵州民族大学 | Robot control method based on multi-target path planning and intelligent picking |
| CN115134288A (en) * | 2021-03-10 | 2022-09-30 | 中国移动通信集团广东有限公司 | Communication network routing scheduling method and system |
| CN115137351A (en) * | 2022-07-22 | 2022-10-04 | 安徽大学 | Electromyographic signal-based upper limb elbow joint angle estimation method and system |
| CN115202365A (en) * | 2022-08-10 | 2022-10-18 | 广东工业大学 | Robot welding obstacle avoidance and optimization path planning method based on three-dimensional discrete point construction |
| CN115695290A (en) * | 2022-09-27 | 2023-02-03 | 重庆品胜科技有限公司 | Method for acquiring optimal path of optical resource based on improved ant colony algorithm |
| CN115796813A (en) * | 2023-02-03 | 2023-03-14 | 中铁城际规划建设有限公司 | Digital acquisition, management and comprehensive application method and system for engineering investigation information |
| CN116518982A (en) * | 2023-07-03 | 2023-08-01 | 江西啄木蜂科技有限公司 | Low-altitude forestry monitoring remote sensing unmanned aerial vehicle path multi-target planning method |
| CN116518979A (en) * | 2023-06-26 | 2023-08-01 | 深圳市森歌数据技术有限公司 | Unmanned plane path planning method, unmanned plane path planning system, electronic equipment and medium |
| CN116645383A (en) * | 2023-07-27 | 2023-08-25 | 天津恒宇医疗科技有限公司 | Method and system for optimizing path of interested blood vessel segment based on deflection angle |
| CN116880531A (en) * | 2023-08-08 | 2023-10-13 | 深圳市华赛睿飞智能科技有限公司 | Indoor unmanned aerial vehicle path planning method and path planning system |
| CN117555341A (en) * | 2024-01-12 | 2024-02-13 | 中国石油大学(华东) | Deep sea mining vehicle path planning method and system based on improved ant colony algorithm |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104992242A (en) * | 2015-07-01 | 2015-10-21 | 广东工业大学 | Method for solving logistic transport vehicle routing problem with soft time windows |
| CN107037809A (en) * | 2016-11-02 | 2017-08-11 | 哈尔滨工程大学 | A kind of unmanned boat collision prevention method based on improvement ant group algorithm |
| CN108416152A (en) * | 2018-03-18 | 2018-08-17 | 哈尔滨工程大学 | The optimal global path planning method of unmanned boat ant colony energy consumption based on electronic chart |
| CN109840625A (en) * | 2019-01-10 | 2019-06-04 | 华南理工大学 | A kind of method of courier's group path navigation |
| CN110196061A (en) * | 2019-05-29 | 2019-09-03 | 华北理工大学 | Based on the mobile robot global path planning method for improving ant group algorithm |
| CN110320907A (en) * | 2019-06-03 | 2019-10-11 | 哈尔滨工程大学 | A kind of unmanned water surface ship bilayer collision prevention method based on improvement ant group algorithm and oval collision cone deduction model |
-
2019
- 2019-12-27 CN CN201911372167.XA patent/CN111026126A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104992242A (en) * | 2015-07-01 | 2015-10-21 | 广东工业大学 | Method for solving logistic transport vehicle routing problem with soft time windows |
| CN107037809A (en) * | 2016-11-02 | 2017-08-11 | 哈尔滨工程大学 | A kind of unmanned boat collision prevention method based on improvement ant group algorithm |
| CN108416152A (en) * | 2018-03-18 | 2018-08-17 | 哈尔滨工程大学 | The optimal global path planning method of unmanned boat ant colony energy consumption based on electronic chart |
| CN109840625A (en) * | 2019-01-10 | 2019-06-04 | 华南理工大学 | A kind of method of courier's group path navigation |
| CN110196061A (en) * | 2019-05-29 | 2019-09-03 | 华北理工大学 | Based on the mobile robot global path planning method for improving ant group algorithm |
| CN110320907A (en) * | 2019-06-03 | 2019-10-11 | 哈尔滨工程大学 | A kind of unmanned water surface ship bilayer collision prevention method based on improvement ant group algorithm and oval collision cone deduction model |
Non-Patent Citations (5)
| Title |
|---|
| WENTING WEI等: "Energy Efficient Virtual Machine Placement With an Improved Ant Colony Optimization Over Data Center Networks", 《IEEE ACCESS》 * |
| 张勇: "基于改进蚁群算法物流配送路径优化的研究", 《控制工程》 * |
| 张楠楠，等: "改进蚁群算法在AUV三维路径规划中的研究", 《计算机工程与应用》 * |
| 王捷晨等: "基于改进蚁群算法的PCB孔加工路径优化", 《化工自动化及仪表》 * |
| 王辉等: "基于改进蚁群算法的泊车系统路径规划", 《控制工程》 * |
Cited By (54)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11305848B2 (en) | 2020-06-01 | 2022-04-19 | Chuan Qin | Layered data acquisition system applied to marine information network and method thereof |
| CN111641930B (en) * | 2020-06-01 | 2021-04-13 | 秦川 | Layered data acquisition system and method applied to ocean information network |
| CN111641930A (en) * | 2020-06-01 | 2020-09-08 | 秦川 | Layered data acquisition system and method applied to ocean information network |
| CN111639811A (en) * | 2020-06-01 | 2020-09-08 | 中国农业大学 | Multi-agricultural-machine cooperative work remote management scheduling method based on improved ant colony algorithm |
| CN111639811B (en) * | 2020-06-01 | 2023-10-31 | 中国农业大学 | Multi-agricultural-machine collaborative operation remote management scheduling method based on improved ant colony algorithm |
| CN112036537A (en) * | 2020-08-04 | 2020-12-04 | 中国农业大学 | Three-dimensional path planning method and system for land scraper navigation |
| CN112036537B (en) * | 2020-08-04 | 2023-12-26 | 中国农业大学 | Three-dimensional path planning method and system for land leveler navigation |
| CN111880542B (en) * | 2020-08-04 | 2022-12-27 | 昆山九毫米电子科技有限公司 | Route planning method for multiple unmanned target vehicles based on improved ant colony algorithm |
| CN111880542A (en) * | 2020-08-04 | 2020-11-03 | 昆山九毫米电子科技有限公司 | Multiple unmanned target vehicle path planning method based on improved ant colony algorithm |
| CN112113569A (en) * | 2020-09-03 | 2020-12-22 | 中国联合网络通信集团有限公司 | Inspection path optimization method and device |
| CN112148030A (en) * | 2020-09-23 | 2020-12-29 | 天津大学 | Underwater glider path planning method based on heuristic algorithm |
| CN112161627A (en) * | 2020-09-23 | 2021-01-01 | 同济大学 | Intelligent path planning method for fire-fighting robot |
| CN112148030B (en) * | 2020-09-23 | 2023-11-24 | 天津大学 | Underwater glider path planning method based on heuristic algorithm |
| CN112306097A (en) * | 2020-10-29 | 2021-02-02 | 杭州电子科技大学 | Novel unmanned aerial vehicle path planning method |
| CN112866902A (en) * | 2021-01-12 | 2021-05-28 | 武汉理工大学 | Dynamic dangerous shipborne environment self-adaptive emergency navigation method |
| CN112819211A (en) * | 2021-01-21 | 2021-05-18 | 安徽农业大学 | Multi-region scheduling route planning method based on ant colony iterative algorithm |
| CN115134288A (en) * | 2021-03-10 | 2022-09-30 | 中国移动通信集团广东有限公司 | Communication network routing scheduling method and system |
| CN115134288B (en) * | 2021-03-10 | 2023-08-15 | 中国移动通信集团广东有限公司 | Communication network route scheduling method and system |
| CN113204348A (en) * | 2021-04-30 | 2021-08-03 | 北京连山科技股份有限公司 | Domestic road network data compiling method based on linkage hierarchy |
| CN113190017A (en) * | 2021-05-24 | 2021-07-30 | 东南大学 | Harvesting robot operation path planning method based on improved ant colony algorithm |
| CN113190017B (en) * | 2021-05-24 | 2022-02-15 | 东南大学 | Harvesting robot operation path planning method based on improved ant colony algorithm |
| CN113326979A (en) * | 2021-05-25 | 2021-08-31 | 汕头大学 | Regional scenery spot two-way route multi-target planning method based on improved ant colony algorithm |
| CN113325856A (en) * | 2021-05-31 | 2021-08-31 | 中国船舶工业集团公司第七0八研究所 | UUV optimal operation path planning method based on countercurrent approximation strategy |
| CN113325856B (en) * | 2021-05-31 | 2022-07-08 | 中国船舶工业集团公司第七0八研究所 | UUV optimal operation path planning method based on countercurrent approximation strategy |
| CN113655785B (en) * | 2021-06-29 | 2024-06-28 | 航天科工深圳（集团）有限公司 | Unmanned ship group control method based on hybrid algorithm |
| CN113341998A (en) * | 2021-06-29 | 2021-09-03 | 厦门大学 | Three-dimensional underwater under-actuated AUV path planning method for improving ant colony algorithm |
| CN113655785A (en) * | 2021-06-29 | 2021-11-16 | 航天科工深圳（集团）有限公司 | Unmanned ship group control method based on hybrid algorithm |
| CN113607172B (en) * | 2021-08-09 | 2024-04-30 | 北京中安智能信息科技有限公司 | Underwater vehicle underwater route planning method and device under multiple constraint conditions |
| CN113607172A (en) * | 2021-08-09 | 2021-11-05 | 北京中安智能信息科技有限公司 | Underwater route planning method and device for underwater vehicle under multi-constraint condition |
| CN113919771A (en) * | 2021-09-24 | 2022-01-11 | 成都信息工程大学 | Unmanned aerial vehicle multi-target intelligent distribution method |
| CN113919771B (en) * | 2021-09-24 | 2023-09-01 | 成都信息工程大学 | Multi-target intelligent distribution method for unmanned aerial vehicle |
| CN114115237A (en) * | 2021-11-03 | 2022-03-01 | 中国人民解放军陆军防化学院 | Multi-target radiation reconnaissance method based on path optimization |
| CN114111824A (en) * | 2021-11-11 | 2022-03-01 | 中国船舶重工集团公司第七一九研究所 | Unmanned ship path optimization method and system based on multi-objective optimization |
| CN114089754A (en) * | 2021-11-11 | 2022-02-25 | 中国船舶重工集团公司第七一九研究所 | Autonomous path planning method and system based on artificial intelligence |
| CN113917929A (en) * | 2021-11-11 | 2022-01-11 | 中国船舶重工集团公司第七一九研究所 | Unmanned ship path optimization method and system based on hybrid particle swarm algorithm |
| CN114527746A (en) * | 2022-01-12 | 2022-05-24 | 燕山大学 | Intelligent automobile path planning and obstacle avoidance tracking method |
| CN114844824A (en) * | 2022-04-11 | 2022-08-02 | 广州杰赛科技股份有限公司 | Method and device for planning network information transmission path and terminal equipment |
| CN114844824B (en) * | 2022-04-11 | 2023-06-23 | 广州杰赛科技股份有限公司 | Planning method and device for network information transmission path and terminal equipment |
| CN114879669B (en) * | 2022-04-28 | 2024-05-28 | 贵州民族大学 | Robot control method based on multi-target path planning and intelligent pickup |
| CN114879669A (en) * | 2022-04-28 | 2022-08-09 | 贵州民族大学 | Robot control method based on multi-target path planning and intelligent picking |
| CN115137351A (en) * | 2022-07-22 | 2022-10-04 | 安徽大学 | Electromyographic signal-based upper limb elbow joint angle estimation method and system |
| CN115137351B (en) * | 2022-07-22 | 2023-07-14 | 安徽大学 | Method and system for estimating angle of elbow joint of upper limb based on electromyographic signals |
| CN115202365A (en) * | 2022-08-10 | 2022-10-18 | 广东工业大学 | Robot welding obstacle avoidance and optimization path planning method based on three-dimensional discrete point construction |
| CN115695290A (en) * | 2022-09-27 | 2023-02-03 | 重庆品胜科技有限公司 | Method for acquiring optimal path of optical resource based on improved ant colony algorithm |
| CN115796813A (en) * | 2023-02-03 | 2023-03-14 | 中铁城际规划建设有限公司 | Digital acquisition, management and comprehensive application method and system for engineering investigation information |
| CN116518979B (en) * | 2023-06-26 | 2023-08-29 | 深圳市森歌数据技术有限公司 | Unmanned plane path planning method, unmanned plane path planning system, electronic equipment and medium |
| CN116518979A (en) * | 2023-06-26 | 2023-08-01 | 深圳市森歌数据技术有限公司 | Unmanned plane path planning method, unmanned plane path planning system, electronic equipment and medium |
| CN116518982B (en) * | 2023-07-03 | 2023-09-19 | 江西啄木蜂科技有限公司 | Low-altitude forestry monitoring remote sensing unmanned aerial vehicle path multi-target planning method |
| CN116518982A (en) * | 2023-07-03 | 2023-08-01 | 江西啄木蜂科技有限公司 | Low-altitude forestry monitoring remote sensing unmanned aerial vehicle path multi-target planning method |
| CN116645383A (en) * | 2023-07-27 | 2023-08-25 | 天津恒宇医疗科技有限公司 | Method and system for optimizing path of interested blood vessel segment based on deflection angle |
| CN116645383B (en) * | 2023-07-27 | 2023-11-03 | 天津恒宇医疗科技有限公司 | Method and system for optimizing path of interested blood vessel segment based on deflection angle |
| CN116880531A (en) * | 2023-08-08 | 2023-10-13 | 深圳市华赛睿飞智能科技有限公司 | Indoor unmanned aerial vehicle path planning method and path planning system |
| CN117555341A (en) * | 2024-01-12 | 2024-02-13 | 中国石油大学(华东) | Deep sea mining vehicle path planning method and system based on improved ant colony algorithm |
| CN117555341B (en) * | 2024-01-12 | 2024-05-24 | 中国石油大学(华东) | Deep sea mining vehicle path planning method and system based on improved ant colony algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111026126A (en) | Unmanned ship global path multi-target planning method based on improved ant colony algorithm | |
| CN110609552B (en) | Method for planning formation plane flight path of underwater unmanned aircraft | |
| CN111880561B (en) | Unmanned aerial vehicle three-dimensional path planning method based on improved whale algorithm in urban environment | |
| CN113985922B (en) | Unmanned aerial vehicle hierarchical path planning method under multi-target constraint | |
| CN109931943B (en) | Unmanned ship global path planning method and electronic equipment | |
| CN114625150B (en) | Rapid ant colony unmanned ship dynamic obstacle avoidance method based on danger coefficient and distance function | |
| CN106774425A (en) | A kind of method and system of unmanned plane during flying navigation | |
| CN114879666A (en) | RRT algorithm-based water surface unmanned ship path planning method and device | |
| CN109916419A (en) | A kind of hybrid genetic algorithm unmanned boat real-time route planing method of object-oriented | |
| CN115167398A (en) | Unmanned ship path planning method based on improved A star algorithm | |
| CN115357031A (en) | Ship path planning method and system based on improved ant colony algorithm | |
| CN111176281A (en) | Multi-surface unmanned ship coverage type collaborative search method and system based on quadrant method | |
| CN114610023A (en) | Unmanned ship path tracking control method | |
| CN113325867A (en) | Path planning method and device for searching of unmanned aircraft and unmanned aircraft | |
| CN110320907B (en) | Double-layer collision avoidance method for unmanned surface vessel based on improved ant colony algorithm and elliptic collision cone deduction model | |
| CN116430856A (en) | Ship track control method based on variable forward looking distance LOS algorithm | |
| CN115951682A (en) | Constraint four-target AUV global path planning method under condition of considering ocean current existence | |
| Li et al. | Research on AUV path planning based on improved ant colony algorithm | |
| Guo et al. | Global Dynamic Path Planning Algorithm for USV Based on Improved Bidirectional RRT | |
| CN114839966A (en) | Unmanned ship optimal path planning method based on reachable set | |
| Tanil | Cooperative path planning for multiple missiles-an evolutionary speciation approach | |
| Yang et al. | UAV Route Planning Based on Fuzzy PID Control Ant Colony Algorithm | |
| Chen et al. | Real time path planning for UAV based on focused D | |
| CN118113068A (en) | Unmanned cluster route planning method and system based on improved particle swarm algorithm | |
| CN117035263B (en) | Task allocation method, computer and storage medium for multiple AUV nodes in underwater large-scale environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200417 |