CN108664022B - Robot path planning method and system based on topological map - Google Patents

Robot path planning method and system based on topological map Download PDF

Info

Publication number
CN108664022B
CN108664022B CN201810393365.3A CN201810393365A CN108664022B CN 108664022 B CN108664022 B CN 108664022B CN 201810393365 A CN201810393365 A CN 201810393365A CN 108664022 B CN108664022 B CN 108664022B
Authority
CN
China
Prior art keywords
path
objective function
function value
optimal solution
judgment result
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201810393365.3A
Other languages
Chinese (zh)
Other versions
CN108664022A (en
Inventor
邹娟
高宏志
刘尧
肖思慧
王求真
郑金华
杨圣祥
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xiangtan University
Original Assignee
Xiangtan University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xiangtan University filed Critical Xiangtan University
Priority to CN201810393365.3A priority Critical patent/CN108664022B/en
Publication of CN108664022A publication Critical patent/CN108664022A/en
Application granted granted Critical
Publication of CN108664022B publication Critical patent/CN108664022B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle

Abstract

The invention discloses a robot path planning method and system based on a topological map. The method comprises the following steps: acquiring a scatter diagram, and setting an initial movement point and a target point of a robot in the scatter diagram, wherein the scatter diagram is formed by abstracting an actual environment containing barrier nodes; constructing a Veno diagram corresponding to the scatter diagram according to the scatter diagram; calculating the driving cost of each side in the Veno graph; adopting an improved Di-Jie-Tesla algorithm according to the driving cost to obtain a plurality of paths; the shortest path is determined from a plurality of said paths according to a particle swarm algorithm. The method or the system can avoid the defects that the weight assignment of the objective function depends on experience and the search space is incomplete.

Description

Robot path planning method and system based on topological map
Technical Field
The invention relates to the field of robot path planning, in particular to a robot path planning method and system based on a topological map.
Background
The path planning technology is one of the core contents of robot research, and the robot positioning and environment map construction serve the path planning. The robot path planning technology is that the robot automatically plans a safe operation route according to the perception of the sensor to the environment, and simultaneously completes the operation task with high efficiency. Generally, mobile robot path planning needs to solve three problems: enabling the robot to move from an initial position to a target position; the obstacle can be bypassed by a certain algorithm; on the premise of completing the tasks, the running track of the robot is optimized as much as possible. The invention patent number CN107368077A discloses a robot path planning method based on a genetic-ant colony algorithm, which adopts a grid method to model the environment, converts a global space into a large number of small grids and adopts an evolutionary algorithm to optimize a path. When the global environment is smaller, the method has higher accuracy and practicability, but has the defect of excessive occupation of storage resources in a large environment. The invention patent with the patent number of CN107065876A is based on an improved particle swarm optimization mobile robot path planning method, and adopts a method of converting multi-target weighted summation into a single-target problem, compared with a multi-target particle swarm algorithm, the method has the advantages that the search space is limited, the weight is updated continuously, and the algorithm complexity is increased.
Disclosure of Invention
The invention aims to provide a robot path planning method and system based on a topological map, which avoid the defects that the weight assignment of an objective function is dependent on experience and the search space is incomplete.
In order to achieve the above object, the present invention provides the following solutions:
a robot path planning method based on a topological map, the method comprising:
acquiring a scatter diagram, and setting an initial movement point and a target point of a robot in the scatter diagram, wherein the scatter diagram is formed by abstracting an actual environment containing barrier nodes;
constructing a Veno diagram corresponding to the scatter diagram according to the scatter diagram;
calculating the driving cost of each side in the Veno graph;
adopting an improved Di-Jie-Tesla algorithm according to the driving cost to obtain a plurality of paths;
the shortest path is determined from a plurality of said paths according to a particle swarm algorithm.
Optionally, the constructing a voronoi diagram corresponding to the scatter diagram according to the scatter diagram specifically includes:
sequentially connecting three barrier nodes closest to each other in the scatter diagram to obtain a plurality of triangles, wherein the circumscribed circles of the triangles do not contain other barrier nodes, and each triangle forms a triangle net;
and making a perpendicular bisector on each side of the triangular net to obtain a grid diagram formed by intersecting the perpendicular bisectors, wherein the grid diagram is a Veno diagram.
Optionally, the driving cost includes a path length and a risk degree.
Optionally, the calculating the driving cost of each side in the voronoi diagram specifically includes:
according toCalculating a path length d;
where d is the path length between two different points, (x) 1 ,y 1 ) Is the coordinates of the edge endpoint 1, (x 2 ,y 2 ) Coordinates of the side end point 2;
according toCalculating the risk degree w;
where w is the sum of threat values across all obstacle nodes, (x) 1 ,y 1 ) Is the coordinates of the edge endpoint 1, (x 2 ,y 2 ) Is the coordinates of the edge end point 2, (x) i ,y i ) For the coordinates of the obstacle node, d1 represents the length of the first path from the obstacle node to the side end point 1, and d2 represents the length of the second path from the obstacle node to the side end point 2.
Optionally, the determining the shortest path according to the particle swarm algorithm specifically includes:
constructing a particle swarm, and initializing a point optimal solution of the particle swarm, wherein the point optimal solution in the particle swarm corresponds to paths in the voronoi diagram, and each path comprises a first objective function value and a second objective function value;
judging whether the first objective function value of the first path is smaller than the first objective function value of the second path or not, and obtaining a first judgment result;
if the first judging result indicates that the first objective function value of the first path is smaller than the first objective function value of the second path, judging whether the second objective function value of the first path is smaller than the second objective function value of the second path, and obtaining a second judging result;
if the second judgment result shows that the second objective function value of the first path is smaller than the second objective function value of the second path, selecting the first path as a point optimal solution;
if the second judgment result indicates that the second objective function value of the first path is larger than or equal to the second objective function value of the second path, randomly selecting the first path or the second path as a point optimal solution;
if the first judging result indicates that the first objective function value of the first path is greater than or equal to the first objective function value of the second path, judging whether the second objective function value of the first path is greater than the second objective function value of the second path or not, and obtaining a third judging result;
if the third judging result shows that the second objective function value of the first path is larger than the second objective function value of the second path, selecting the second path as a point optimal solution;
if the third judgment result shows that the second objective function value of the first path is smaller than or equal to the second objective function value of the second path, randomly selecting the first path or the second path as a point optimal solution;
updating the speed and the position of the particle swarm according to the third judging result;
judging whether the iteration times are smaller than an iteration threshold value or not, and obtaining a fourth judgment result;
if the fourth judgment result indicates that the iteration times are smaller than an iteration threshold, judging whether the first objective function value of the first path is smaller than the first objective function value of the second path again, and obtaining a first judgment result;
and if the fourth judgment result indicates that the iteration times are greater than or equal to an iteration threshold, determining the shortest path according to the optimal solution of the current point.
In order to achieve the above object, the present invention provides the following solutions:
a topological map-based robotic path planning system, the system comprising:
the system comprises a scatter diagram acquisition module, a control module and a control module, wherein the scatter diagram acquisition module is used for acquiring a scatter diagram, setting initial movement points and target points of a robot in the scatter diagram, and the scatter diagram is formed by abstracting an actual environment containing barrier nodes;
the Winogram acquisition module is used for constructing a Winogram corresponding to the scatter diagram according to the scatter diagram;
the driving cost acquisition module is used for calculating the driving cost of each side in the voronoi diagram;
the path acquisition module is used for acquiring a plurality of paths by adopting an improved Di-Jie-Tesla algorithm according to the driving cost;
and the shortest path determining module is used for determining the shortest path from a plurality of paths according to a particle swarm algorithm.
Optionally, the voronoi diagram obtaining module specifically includes:
the triangular network unit is used for sequentially connecting three barrier nodes closest to each other in the scatter diagram to obtain a plurality of triangles, the circumscribed circles of the triangles do not contain other barrier nodes, and the triangles form a triangular network;
and the grid diagram unit is used for making a perpendicular bisector on each side of the triangular net to obtain a grid diagram formed by intersecting the perpendicular bisectors, wherein the grid diagram is a Veno diagram.
Optionally, the driving cost includes a path length and a risk degree.
Optionally, the driving cost obtaining module specifically includes:
a path length determining unit for determining the path length according toCalculating a path length d;
where d is the path length between two different points, (x) 1 ,y 1 ) Is the coordinates of the edge endpoint 1, (x 2 ,y 2 ) Coordinates of the side end point 2;
a risk level determining unit for determining according toCalculating the risk degree w;
where w is the sum of threat values across all obstacle nodes, (x) 1 ,y 1 ) Is the coordinates of the edge endpoint 1, (x 2 ,y 2 ) Is the coordinates of the edge end point 2, (x) i ,y i ) For the coordinates of the obstacle node, d1 represents a first path length from the obstacle node to the side end point 1, and d2 represents a second path length from the obstacle node to the side end point 2.
Optionally, the shortest path determining module specifically includes:
the particle swarm construction unit is used for constructing a particle swarm, initializing a point optimal solution of the particle swarm, wherein the point optimal solution in the particle swarm corresponds to paths in the voronoi diagram, and each path comprises a first objective function value and a second objective function value;
a first judgment result obtaining unit, configured to judge whether a first objective function value of the first path is smaller than a first objective function value of the second path, to obtain a first judgment result;
a second judgment result obtaining unit, configured to determine whether a second objective function value of the first path is smaller than a second objective function value of the second path if the first judgment result indicates that the first objective function value of the first path is smaller than the first objective function value of the second path, and obtain a second judgment result;
a first optimal solution unit, configured to select the first path as a point optimal solution if the second judgment result indicates that the second objective function value of the first path is smaller than the second objective function value of the second path;
a second optimal solution unit, configured to randomly select the first path or the second path as a point optimal solution if the second judgment result indicates that the second objective function value of the first path is greater than or equal to the second objective function value of the second path;
a third judgment result obtaining unit, configured to determine whether a second objective function value of the first path is greater than a second objective function value of the second path if the first judgment result indicates that the first objective function value of the first path is greater than or equal to the first objective function value of the second path, and obtain a third judgment result;
a third optimal solution unit, configured to randomly select the second path as a point optimal solution if the third determination result indicates that the second objective function value of the first path is greater than the second objective function value of the second path;
a fourth optimal solution unit, configured to randomly select the first path or the second path as a point optimal solution if the third determination result indicates that the second objective function value of the first path is less than or equal to the second objective function value of the second path;
an updating unit, configured to update the speed and the position of the particle swarm according to the third determination result;
a fourth judgment result obtaining unit, configured to judge whether the iteration number is smaller than the iteration threshold, and obtain a fourth judgment result;
the re-judging unit is used for re-judging whether the first objective function value of the first path is smaller than the first objective function value of the second path or not if the fourth judging result indicates that the iteration times are smaller than an iteration threshold value, and obtaining a first judging result;
and the shortest path determining unit is used for determining the shortest path according to the optimal solution of the current point if the fourth judging result indicates that the iteration times are greater than or equal to an iteration threshold.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention provides a robot path planning method and a robot path planning system based on a topological map, which avoid the defect of excessively high complexity of time and space represented by a grid method in a large environment by modeling the environment of a robot through using a Veno diagram. The feasible solution space is obtained through an improved Di Jie St-Law algorithm, and then the scheme of evolutionary algorithm optimization is adopted, so that the problem that a feasible solution is difficult to find in the scheme from the conventional non-feasible solution optimization to the feasible solution is solved. The multi-target particle swarm algorithm is adopted to carry out robot path planning, so that the defect that the searching space is incomplete due to the fact that the weight assignment of the target function in the single-target particle swarm algorithm is based on experience is avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a robot path planning method based on a topological map in an embodiment of the invention;
FIG. 2 is a diagram of a robot path planning system based on a topological map in accordance with an embodiment of the present invention;
FIGS. 3-5 are schematic diagrams of the construction of a Veno diagram according to embodiments of the present invention;
FIG. 6 is a schematic diagram of threat level calculation for a certain point to a certain edge according to an embodiment of the invention;
fig. 7 is a final planned route map according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention aims to provide a robot path planning method and system based on a topological map, which avoid the defects that the weight assignment of an objective function is dependent on experience and the search space is incomplete.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
Specific example 1:
fig. 1 is a flow chart of a robot path planning method based on a topological map according to an embodiment of the invention. As shown in fig. 1, a robot path planning method based on a topological map, the method comprises:
step 101: acquiring a scatter diagram, and setting an initial movement point and a target point of a robot in the scatter diagram, wherein the scatter diagram is formed by abstracting an actual environment containing barrier nodes;
step 102: constructing a Veno diagram corresponding to the scatter diagram according to the scatter diagram;
the method specifically comprises the steps of sequentially connecting three barrier nodes closest to each other in the scatter diagram to obtain a plurality of triangles, wherein the circumscribed circles of the triangles do not contain other barrier nodes, and each triangle forms a triangle net;
and making a perpendicular bisector on each side of the triangular net to obtain a grid diagram formed by intersecting the perpendicular bisectors, wherein the grid diagram is a Veno diagram.
Step 103: calculating the running cost of each side in the voronoi diagram, wherein the running cost comprises path length and danger degree, and specifically comprises the following steps:
according toCalculating a path length d;
where d is the path length between two different points, (x) 1 ,y 1 ) Is the coordinates of the edge endpoint 1, (x 2 ,y 2 ) Coordinates of the side end point 2;
according toCalculating the risk degree w;
where w is the sum of threat values across all obstacle nodes, (x) 1 ,y 1 ) Is the coordinates of the edge endpoint 1, (x 2 ,y 2 ) Is the coordinates of the edge end point 2, (x) i ,y i ) For the coordinates of the obstacle node, d1 represents the length of the first path from the obstacle node to the edge end point 1,d2 denotes the length of the second path from the obstacle node to the edge end point 2.
Step 104: adopting an improved Di-Jie-Tesla algorithm according to the driving cost to obtain a plurality of paths;
step 105: determining a shortest path from a plurality of paths according to a particle swarm algorithm;
the method specifically comprises the following steps: constructing a particle swarm, and initializing a point optimal solution of the particle swarm, wherein the point optimal solution in the particle swarm corresponds to paths in the voronoi diagram, and each path comprises a first objective function value and a second objective function value;
judging whether the first objective function value of the first path is smaller than the first objective function value of the second path or not, and obtaining a first judgment result;
if the first judging result indicates that the first objective function value of the first path is smaller than the first objective function value of the second path, judging whether the second objective function value of the first path is smaller than the second objective function value of the second path, and obtaining a second judging result;
if the second judgment result shows that the second objective function value of the first path is smaller than the second objective function value of the second path, selecting the first path as a point optimal solution;
if the second judgment result indicates that the second objective function value of the first path is larger than or equal to the second objective function value of the second path, randomly selecting the first path or the second path as a point optimal solution;
if the first judging result indicates that the first objective function value of the first path is greater than or equal to the first objective function value of the second path, judging whether the second objective function value of the first path is greater than the second objective function value of the second path or not, and obtaining a third judging result;
if the third judging result shows that the second objective function value of the first path is larger than the second objective function value of the second path, selecting the second path as a point optimal solution;
if the third judgment result shows that the second objective function value of the first path is smaller than or equal to the second objective function value of the second path, randomly selecting the first path or the second path as a point optimal solution;
updating the speed and the position of the particle swarm according to the third judging result;
judging whether the iteration times are smaller than an iteration threshold value or not, and obtaining a fourth judgment result;
if the fourth judgment result indicates that the iteration times are smaller than an iteration threshold, judging whether the first objective function value of the first path is smaller than the first objective function value of the second path again, and obtaining a first judgment result;
and if the fourth judgment result indicates that the iteration times are greater than or equal to an iteration threshold, determining the shortest path according to the optimal solution of the current point.
According to the robot path planning method based on the topological map, the environment of the robot is modeled by using the Veno diagram, so that the defect of excessively high time and space complexity of grid representation in a large environment is avoided. The feasible solution space is obtained through an improved Di Jie St-Law algorithm, and then the scheme of evolutionary algorithm optimization is adopted, so that the problem that a feasible solution is difficult to find in the scheme from the conventional non-feasible solution optimization to the feasible solution is solved. The method is a typical and universal robot path planning method, is used for solving the problems of dangerous goods transportation, unmanned aerial vehicle obstacle avoidance flight, communication routing, power communication routing planning and the like, and has wide application prospect. The robot with path planning can select a route which meets the requirement of a user as far as possible to move towards a target point, can perform tasks more reliably, improves the system efficiency and can reduce the system consumption.
Fig. 2 is a diagram of a robot path planning system based on a topological map according to an embodiment of the present invention. As shown in fig. 2, a robot path planning system based on a topological map, the system comprising:
a scatter diagram acquisition module 201, configured to acquire a scatter diagram, and set an initial movement point and a target point of a robot in the scatter diagram, where the scatter diagram is abstracted from an actual environment including an obstacle node;
a voronoi diagram obtaining module 202, configured to construct a voronoi diagram corresponding to the scatter diagram according to the scatter diagram;
the running cost obtaining module 203 is configured to calculate a running cost of each side in the voronoi diagram, where the running cost includes a path length and a risk degree;
a path acquisition module 204, configured to obtain a plurality of paths by adopting an improved dijkstra algorithm according to the driving cost;
the shortest path determining module 205 is configured to determine a shortest path from a plurality of paths according to a particle swarm algorithm.
The voronoi diagram obtaining module 202 specifically includes:
the triangular network unit is used for sequentially connecting three barrier nodes closest to each other in the scatter diagram to obtain a plurality of triangles, the circumscribed circles of the triangles do not contain other barrier nodes, and the triangles form a triangular network;
and the grid diagram unit is used for making a perpendicular bisector on each side of the triangular net to obtain a grid diagram formed by intersecting the perpendicular bisectors, wherein the grid diagram is a Veno diagram.
The driving cost obtaining module 203 specifically includes:
a path length determining unit for determining the path length according toCalculating a path length d;
where d is the path length between two different points, (x) 1 ,y 1 ) Is the coordinates of the edge endpoint 1, (x 2 ,y 2 ) Coordinates of the side end point 2;
a risk level determining unit for determining according toCalculating the risk degree w;
where w is the sum of threat values across all obstacle nodes, (x) 1 ,y 1 ) Is the coordinates of the edge endpoint 1, (x 2 ,y 2 ) Is the coordinates of the edge end point 2, (x) i ,y i ) For the coordinates of the obstacle node, d1 represents a first path length from the obstacle node to the side end point 1, and d2 represents a second path length from the obstacle node to the side end point 2.
The shortest path determining module 205 specifically includes:
the particle swarm construction unit is used for constructing a particle swarm, initializing a point optimal solution of the particle swarm, wherein the point optimal solution in the particle swarm corresponds to paths in the voronoi diagram, and each path comprises a first objective function value and a second objective function value;
a first judgment result obtaining unit, configured to judge whether a first objective function value of the first path is smaller than a first objective function value of the second path, to obtain a first judgment result;
a second judgment result obtaining unit, configured to determine whether a second objective function value of the first path is smaller than a second objective function value of the second path if the first judgment result indicates that the first objective function value of the first path is smaller than the first objective function value of the second path, and obtain a second judgment result;
a first optimal solution unit, configured to select the first path as a point optimal solution if the second judgment result indicates that the second objective function value of the first path is smaller than the second objective function value of the second path;
a second optimal solution unit, configured to randomly select the first path or the second path as a point optimal solution if the second judgment result indicates that the second objective function value of the first path is greater than or equal to the second objective function value of the second path;
a third judgment result obtaining unit, configured to determine whether a second objective function value of the first path is greater than a second objective function value of the second path if the first judgment result indicates that the first objective function value of the first path is greater than or equal to the first objective function value of the second path, and obtain a third judgment result;
a third optimal solution unit, configured to randomly select the second path as a point optimal solution if the third determination result indicates that the second objective function value of the first path is greater than the second objective function value of the second path;
a fourth optimal solution unit, configured to randomly select the first path or the second path as a point optimal solution if the third determination result indicates that the second objective function value of the first path is less than or equal to the second objective function value of the second path;
an updating unit, configured to update the speed and the position of the particle swarm according to the third determination result;
a fourth judgment result obtaining unit, configured to judge whether the iteration number is smaller than the iteration threshold, and obtain a fourth judgment result;
the re-judging unit is used for re-judging whether the first objective function value of the first path is smaller than the first objective function value of the second path or not if the fourth judging result indicates that the iteration times are smaller than an iteration threshold value, and obtaining a first judging result;
and the shortest path determining unit is used for determining the shortest path according to the optimal solution of the current point if the fourth judging result indicates that the iteration times are greater than or equal to an iteration threshold.
Specific example 2:
step 1: and initializing a system. The actual environment including the obstacle is abstracted into a scatter diagram, and the generated scatter diagram is shown in fig. 3. Wherein, the obstacle point is respectively numbered 1, 2, 3, 11, 12, the robot starting point is numbered S, and the robot end point is numbered E.
Step 2: constructing a voronoi diagram corresponding to the scatter diagram in fig. 3 specifically includes:
(1) three obstacle points closest to each other in the scatter diagram of fig. 3 are sequentially connected, and each obtained triangle is required, and the circumscribed circle of the triangle does not contain other obstacle points, so that a Delaunay triangle network is obtained, and the Delaunay triangle network is shown as a black line in fig. 4.
(2) And (3) making a perpendicular line on each side in the constructed Delaunay triangle network, wherein a grid formed by intersecting all perpendicular lines is a Veno diagram, and the grid is shown as a dotted line in fig. 4. The final produced voronoi diagram is shown in fig. 5, with the voronoi diagram vertices labeled (1), (2) in sequence.
Since the path planning is performed on the edges of the voronoi diagram, the voronoi diagram vertex closest to the start point euclidean distance is selected as the start point of the path planning, and the voronoi diagram vertex closest to the end point euclidean distance is selected as the end point of the path planning. In this example, the voronoi diagram vertex (1) shown in fig. 5 is used as the starting point of path planning, and the voronoi diagram vertex shown in fig. 5As an end point for path planning.
Step 3: and calculating the driving cost of each side in the Veno diagram, wherein the driving cost is used as the scale of the robot driving on the path, and the smaller the total cost of the path is, the larger the probability that the robot selects the path to drive is. There are two evaluation points for the cost: path length and degree of risk.
The path length is the Euclidean distance between two points, if the point (x 1 ，y 1 ) And point (x) 2 ，y 2 ) The path length d between them is calculated using the following formula:
the risk level is the sum of the threat values of all obstacle nodes to the edge. FIG. 6 is a schematic diagram of the threat level calculation of a certain point to a certain edge according to an embodiment of the invention. If edge end point 1 (x 1 ,y 1 ) And side end point 2 (x 2 ,y 2 ) The degree of risk of the path between them, using (x i ′,y i ') represents the coordinates of obstacle point i, then all n obstacle nodes threaten the edge as:
where d1 represents the euclidean distance from the obstacle node i to the side end point 1, d2 represents the euclidean distance from the obstacle node i to the side end point 2, and the root number is the distance from the obstacle node i to the side midpoint.
Step 4: the feasible solution set is found using the modified Dijkstra algorithm. The multiple evaluation values of the edge are weighted and converted into a single evaluation value, and the edge only has the single evaluation value, and a feasible solution, namely a shortest path corresponding to the current weighting method can be obtained by using Dijkstra algorithm. And continuously modifying the weights used for weighting the plurality of evaluation values to obtain a plurality of feasible solutions, namely a feasible solution set.
Step 5: the particle swarm algorithm is initialized. Considering the discreteness of the solutions in the feasible solution sets, the feasible solution set obtained in the step 4 is directly used as the feasible solution space of the particle swarm algorithm, and the speed of the particle swarm algorithm is difficult to effectively define, so that the feasible solutions in the feasible solution sets are subjected to conflict-free binary coding, the feasible solution sets are mapped to a binary coding set, and the feasible solution sets are used as the feasible solution space of the particle swarm algorithm. The feasible solution sets may be numbered 1, 2, 3 … and then the numbers may be changed to binary.
The solution of the algorithm is a binary sequence whose values are binary codes corresponding to the locations of the solution in the solution set. Each particle in the population is initialized to a random solution, namely a random 0/1 sequence, and the sequence length n= [ log ] 2 Size of solution space]。
The particle velocity is a plurality of exchange pairs, the exchange pairs are composed of subscript pairs, and refer to digital exchanges of any two subscript positions in a de-sequence. If the data at index i and index j in the de-sequence is exchanged, then it is denoted as (i, j) and the speed is a random number of such exchange pairs.
The set of point optimal solutions is initialized to the optimal solution that appears in the current population. The optimal solution set size is selected according to the specific problem, and in the example, the optimal solution set size is equal to the population scale.
Step 6: calculating a point optimal solution pBest and global according to target updateAnd (5) an optimal solution gBest. The objective function is defined as the sum of the costs of all adjacent vertex corresponding edges in the shortest path, and since the cost has two evaluation points, the cost of the solution corresponds to two objective functions, and the point sequence of the solution is assumed to be p 1 p 2 …p n Then the objective function:
to represent the sum of the path lengths of all sides through which the path passes.
To represent the sum of the risk levels of all sides through which the path passes.
Comparison of merits for two solutions:
since the solutions correspond to two objective function values, there may be cases where the objective function values of the solutions are larger and smaller, the comparison is performed uniformly as follows. Two different solutions are respectively set as a solution 1 and a solution 2, and compared, if the objective function value 1 and the objective function value 2 of the solution 1 are both better than the solution 2, the solution 1 is better than the solution 2; if the objective function value 1 and the objective function value 2 of the solution 1 are both inferior to the solution 2, the solution 1 is inferior to the solution 2; otherwise, solution 1 or solution 2 is randomly selected as the preferred solution.
And updating the point optimal solution according to the objective function, if the point current solution is better than the point historical optimal solution, updating the point optimal solution, otherwise, not updating.
Updating for non-dominant solution sets. And selecting an optimal solution in the optimal solution set of the step points, and replacing a solution inferior to the solution in the non-dominant solution set res by the solution.
And selecting an optimal solution in the non-dominant solution set to update the global optimal solution.
An adaptive mesh of non-dominant solution sets is constructed. A two-dimensional coordinate system is established for the adaptive mesh, the abscissa is the objective function f1, and the ordinate is the objective function f2. The objective function value for each solution in the non-dominant set of solutions is first calculated and the points represented by the solution are represented in the coordinate system. And selecting x (a value is determined according to actual conditions), 1 in the example, dividing the grids by y (a value is determined according to actual conditions), assigning a value to each grid, and determining the corresponding point number in the grid.
Definition x i The reciprocal of the number of points in grid i, for all m grids with points other than 0,
grid i corresponds to probabilityI.e. the more points in the grid, the lower the corresponding probability. And selecting the least crowded grid from the m grids according to a roulette algorithm, and randomly selecting a solution from the selected grids as a current global optimal solution gBest. In this example, x=1 and y=1 are taken when dividing the grid.
Step 7: update speed and particle position.
v[i]＝w*v[i]+c1*rand()*(pbest[i]-present[i])+c2*rand()*(gbest-present[i])
present[i]＝present[i]+v[i]
Where v [ i ] represents the speed of the ith particle. w represents an inertial weight, and has a value of 0-1, in this example 0.5. c1 and c2 represent learning parameters, typically take the value c1=c2=2, in this example take the value c1=c2=2, rand () represents a random number between 0-1, pbest [ i ] represents the point optimal solution for the ith particle, gbest global optimal solution, and present [ i ] represents the current solution for the ith particle. Wherein the difference between the present and the pbest or the gbest is the exchange pair from the present to the pbest or the gbest.
Step 8: a mutation operation is added to the current particle position. The variation probability is set to be 0.1 in the example, after the particle position is updated, a random number between 0 and 1 is generated, if the value is smaller than 0.1, then a random number a and b between two 1 and n are generated, wherein n is assigned to the length of the binary sequence in the step 5(1), so that the values of a and b are smaller than or equal to the length, and an exchange pair (a and b) is formed, so that the position is adjusted, and the specific adjustment method is that the number of a subscript positions and the number of b subscript positions in the binary sequence are exchanged; if the value is not less than 0.1, go directly to step 8.
Step 9: judging to beIf the maximum iteration times are not met, returning to the step 6 for execution; if yes, the algorithm is ended, and the current global optimal solution is the algorithm solution. Since the feasible solution set of the original problem has been mapped to the binary sequence space in step 5, the algorithm is also finally converted into a feasible solution form of the original problem, i.e. a shortest path. The shortest path finally obtained is (1) (3) (7)Plus the robot start and end points, the final planned path is shown in fig. 7.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.

Claims (4)

1. A robot path planning method based on a topological map, the method comprising:
acquiring a scatter diagram, and setting an initial movement point and a target point of a robot in the scatter diagram, wherein the scatter diagram is formed by abstracting an actual environment containing barrier nodes;
constructing a Veno diagram corresponding to the scatter diagram according to the scatter diagram;
calculating the driving cost of each side in the Veno graph; the driving cost comprises a path length and a dangerous degree; the calculating the driving cost of each side in the voronoi diagram specifically comprises the following steps:
according toCalculating a path length d;
where d is the path length between two different points, (x) 1 ,y 1 ) Is the coordinates of the edge endpoint 1, (x 2 ,y 2 ) Coordinates of the side end point 2;
according toCalculating the risk degree w;
where w is the sum of threat values across all obstacle nodes, (x) 1 ,y 1 ) Is the coordinates of the edge endpoint 1, (x 2 ,y 2 ) Is the coordinates of the edge end point 2, (x) i ,y i ) For the coordinates of the obstacle node, d1 represents the length of the first path from the obstacle node to the side end point 1, and d2 represents the length of the second path from the obstacle node to the side end point 2;
adopting an improved Di-Jie-Tesla algorithm according to the driving cost to obtain a plurality of paths;
determining a shortest path from a plurality of paths according to a particle swarm algorithm, wherein the method specifically comprises the following steps:
constructing a particle swarm, and initializing a point optimal solution of the particle swarm, wherein the point optimal solution in the particle swarm corresponds to paths in the voronoi diagram, and each path comprises a first objective function value and a second objective function value; the first objective function value of a path represents the sum of path lengths of all sides through which the path passes; the second objective function value of the path represents the sum of the risk levels of all sides traversed by the path;
judging whether the first objective function value of the first path is smaller than the first objective function value of the second path or not, and obtaining a first judgment result;
if the first judging result indicates that the first objective function value of the first path is smaller than the first objective function value of the second path, judging whether the second objective function value of the first path is smaller than the second objective function value of the second path, and obtaining a second judging result;
if the second judgment result shows that the second objective function value of the first path is smaller than the second objective function value of the second path, selecting the first path as a point optimal solution;
if the second judgment result indicates that the second objective function value of the first path is larger than or equal to the second objective function value of the second path, randomly selecting the first path or the second path as a point optimal solution;
if the first judging result indicates that the first objective function value of the first path is greater than or equal to the first objective function value of the second path, judging whether the second objective function value of the first path is greater than the second objective function value of the second path or not, and obtaining a third judging result;
if the third judging result shows that the second objective function value of the first path is larger than the second objective function value of the second path, selecting the second path as a point optimal solution;
if the third judgment result shows that the second objective function value of the first path is smaller than or equal to the second objective function value of the second path, randomly selecting the first path or the second path as a point optimal solution;
updating the speed and the position of the particle swarm according to the third judging result;
judging whether the iteration times are smaller than an iteration threshold value or not, and obtaining a fourth judgment result;
if the fourth judgment result indicates that the iteration times are smaller than an iteration threshold, judging whether the first objective function value of the first path is smaller than the first objective function value of the second path again, and obtaining a first judgment result;
and if the fourth judgment result indicates that the iteration times are greater than or equal to an iteration threshold, determining the shortest path according to the optimal solution of the current point.
2. The robot path planning method based on the topological map according to claim 1, wherein the constructing the voronoi diagram corresponding to the scatter diagram according to the scatter diagram specifically comprises:
sequentially connecting three barrier nodes closest to each other in the scatter diagram to obtain a plurality of triangles, wherein the circumscribed circles of the triangles do not contain other barrier nodes, and the triangles form a triangular network;
and making a perpendicular bisector on each side of the triangular net to obtain a grid diagram formed by intersecting the perpendicular bisectors, wherein the grid diagram is a Veno diagram.
3. A topological map-based robotic path planning system, the system comprising:
the system comprises a scatter diagram acquisition module, a control module and a control module, wherein the scatter diagram acquisition module is used for acquiring a scatter diagram, setting initial movement points and target points of a robot in the scatter diagram, and the scatter diagram is formed by abstracting an actual environment containing barrier nodes;
the Winogram acquisition module is used for constructing a Winogram corresponding to the scatter diagram according to the scatter diagram;
the driving cost acquisition module is used for calculating the driving cost of each side in the voronoi diagram; the driving cost comprises a path length and a dangerous degree; the driving cost acquisition module specifically comprises:
a path length determining unit for determining the path length according toCalculating a path length d;
where d is the path length between two different points, (x) 1 ,y 1 ) Is the coordinates of the edge endpoint 1, (x 2 ,y 2 ) Coordinates of the side end point 2;
a risk level determining unit for determining according toCalculating the risk degree w;
where w is the sum of threat values across all obstacle nodes，(x 1 ,y 1 ) Is the coordinates of the edge endpoint 1, (x 2 ,y 2 ) Is the coordinates of the edge end point 2, (x) i ,y i ) For coordinates of the obstacle node, d1 represents a first path length from the obstacle node to the side end point 1, and d2 represents a second path length from the obstacle node to the side end point 2;
the path acquisition module is used for acquiring a plurality of paths by adopting an improved Di-Jie-Tesla algorithm according to the driving cost;
the shortest path determining module is used for determining the shortest path from a plurality of paths according to a particle swarm algorithm;
the shortest path determining module specifically includes:
the particle swarm construction unit is used for constructing a particle swarm, initializing a point optimal solution of the particle swarm, wherein the point optimal solution in the particle swarm corresponds to paths in the voronoi diagram, and each path comprises a first objective function value and a second objective function value; the first objective function value of a path represents the sum of path lengths of all sides through which the path passes; the second objective function value of the path represents the sum of the risk levels of all sides traversed by the path;
a first judgment result obtaining unit, configured to judge whether a first objective function value of the first path is smaller than a first objective function value of the second path, to obtain a first judgment result;
a second judgment result obtaining unit, configured to determine whether a second objective function value of the first path is smaller than a second objective function value of the second path if the first judgment result indicates that the first objective function value of the first path is smaller than the first objective function value of the second path, and obtain a second judgment result;
a first optimal solution unit, configured to select the first path as a point optimal solution if the second judgment result indicates that the second objective function value of the first path is smaller than the second objective function value of the second path;
a second optimal solution unit, configured to randomly select the first path or the second path as a point optimal solution if the second judgment result indicates that the second objective function value of the first path is greater than or equal to the second objective function value of the second path;
a third judgment result obtaining unit, configured to determine whether a second objective function value of the first path is greater than a second objective function value of the second path if the first judgment result indicates that the first objective function value of the first path is greater than or equal to the first objective function value of the second path, and obtain a third judgment result;
a third optimal solution unit, configured to select the second path as a point optimal solution if the third determination result indicates that the second objective function value of the first path is greater than the second objective function value of the second path;
a fourth optimal solution unit, configured to randomly select the first path or the second path as a point optimal solution if the third determination result indicates that the second objective function value of the first path is less than or equal to the second objective function value of the second path;
an updating unit, configured to update the speed and the position of the particle swarm according to the third determination result;
a fourth judgment result obtaining unit, configured to judge whether the iteration number is smaller than the iteration threshold, and obtain a fourth judgment result;
the re-judging unit is used for re-judging whether the first objective function value of the first path is smaller than the first objective function value of the second path or not if the fourth judging result indicates that the iteration times are smaller than an iteration threshold value, and obtaining a first judging result;
and the shortest path determining unit is used for determining the shortest path according to the optimal solution of the current point if the fourth judging result indicates that the iteration times are greater than or equal to an iteration threshold.
4. A robot path planning system based on a topological map according to claim 3, characterized in that said voronoi diagram acquisition module comprises in particular:
the triangular network unit is used for sequentially connecting three barrier nodes closest to each other in the scatter diagram to obtain a plurality of triangles, the circumscribed circles of the triangles do not contain other barrier nodes, and the triangles form a triangular network;
and the grid diagram unit is used for making a perpendicular bisector on each side of the triangular net to obtain a grid diagram formed by intersecting the perpendicular bisectors, wherein the grid diagram is a Veno diagram.
CN201810393365.3A 2018-04-27 2018-04-27 Robot path planning method and system based on topological map Active CN108664022B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810393365.3A CN108664022B (en) 2018-04-27 2018-04-27 Robot path planning method and system based on topological map

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810393365.3A CN108664022B (en) 2018-04-27 2018-04-27 Robot path planning method and system based on topological map

Publications (2)

Publication Number Publication Date
CN108664022A CN108664022A (en) 2018-10-16
CN108664022B true CN108664022B (en) 2023-09-05

Family

ID=63781322

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810393365.3A Active CN108664022B (en) 2018-04-27 2018-04-27 Robot path planning method and system based on topological map

Country Status (1)

Country Link
CN (1) CN108664022B (en)

Families Citing this family (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109668572B (en) * 2018-12-28 2022-05-17 芜湖哈特机器人产业技术研究院有限公司 Laser forklift path searching method based on floyd algorithm
CN109947129A (en) * 2019-03-29 2019-06-28 华南理工大学 Rotor wing unmanned aerial vehicle paths planning method based on Dijkstra and improvement particle swarm algorithm
CN110057361B (en) * 2019-04-23 2020-10-09 河南宙合网络科技有限公司 Shortest path planning method based on GPS
CN110427032B (en) * 2019-08-12 2022-07-22 湘潭大学 Agricultural data acquisition method and system based on flow type data acquisition points
CN111209626B (en) * 2020-01-09 2023-04-21 北京林业大学 Method and system for determining sand barrier paving path
CN111752302B (en) * 2020-02-26 2021-09-10 广州极飞科技股份有限公司 Path planning method and device, electronic equipment and computer readable storage medium
CN111447005B (en) * 2020-03-26 2022-03-04 北京卫星信息工程研究所 Link planning method and device for software defined satellite network
CN111860880A (en) * 2020-06-01 2020-10-30 北京骑胜科技有限公司 Path determining method and device, electronic equipment and storage medium
CN111620023B (en) * 2020-06-04 2021-08-10 南京音飞峰云科技有限公司 Method for realizing dense library equipment path planning based on dynamic edge weight topological graph
CN112070165A (en) * 2020-09-09 2020-12-11 深圳市城市规划设计研究院有限公司 Hamiltonian path fast solving method based on triangular expansion
CN112344941B (en) * 2020-11-06 2022-04-26 杭州国辰机器人科技有限公司 Path planning method, system, robot and storage medium
CN112783169B (en) * 2020-12-31 2022-11-01 科大讯飞(苏州)科技有限公司 Path planning method, path planning equipment and computer readable storage medium
CN112911535A (en) * 2021-02-01 2021-06-04 合肥工业大学 Underwater AUV path forming method based on Dirichlet vertex
CN114255241B (en) * 2021-11-16 2023-10-20 鹏城实验室 Region segmentation method, device, equipment and storage medium for path planning
CN114065520B (en) * 2021-11-17 2022-07-05 西安理工大学 Fish migration channel determination method and system
CN114115286B (en) * 2021-12-06 2024-03-19 国网山东省电力公司汶上县供电公司 Substation robot inspection system and method
CN115265577B (en) * 2022-09-30 2023-02-10 北京智行者科技股份有限公司 Topological relation construction method, system and moving tool based on Voronoi diagram
CN115930969B (en) * 2023-01-09 2023-06-02 季华实验室 Path planning method and device for mobile robot, electronic equipment and storage medium

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005032196A (en) * 2003-07-11 2005-02-03 Japan Science & Technology Agency System for planning path for moving robot
CN101122974A (en) * 2007-09-13 2008-02-13 北京航空航天大学 Un-manned plane fairway layout method based on Voronoi graph and ant colony optimization algorithm
CN101387888A (en) * 2008-09-27 2009-03-18 江南大学 Mobile robot path planning method based on binary quanta particle swarm optimization
KR20100137091A (en) * 2009-06-22 2010-12-30 재단법인대구경북과학기술원 Method and apparatus for storing map data for robot
CN102129249A (en) * 2011-01-10 2011-07-20 中国矿业大学 Method for planning global path of robot under risk source environment
CN102880186A (en) * 2012-08-03 2013-01-16 北京理工大学 Flight path planning method based on sparse A* algorithm and genetic algorithm
US8793200B1 (en) * 2009-09-22 2014-07-29 Hrl Laboratories, Llc Method for particle swarm optimization with random walk
CN106444835A (en) * 2016-10-11 2017-02-22 哈尔滨工程大学 Underwater vehicle three-dimensional path planning method based on Lazy Theta satellite and particle swarm hybrid algorithm
CN106650298A (en) * 2017-01-11 2017-05-10 湘潭大学 Flexible needle route planning method based on environmental characteristics and stochastic method
CN106705970A (en) * 2016-11-21 2017-05-24 中国航空无线电电子研究所 Multi-UAV(Unmanned Aerial Vehicle) cooperation path planning method based on ant colony algorithm
CN107065876A (en) * 2017-04-28 2017-08-18 西北工业大学 Method for planning path for mobile robot based on Modified particle swarm optimization

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005032196A (en) * 2003-07-11 2005-02-03 Japan Science & Technology Agency System for planning path for moving robot
CN101122974A (en) * 2007-09-13 2008-02-13 北京航空航天大学 Un-manned plane fairway layout method based on Voronoi graph and ant colony optimization algorithm
CN101387888A (en) * 2008-09-27 2009-03-18 江南大学 Mobile robot path planning method based on binary quanta particle swarm optimization
KR20100137091A (en) * 2009-06-22 2010-12-30 재단법인대구경북과학기술원 Method and apparatus for storing map data for robot
US8793200B1 (en) * 2009-09-22 2014-07-29 Hrl Laboratories, Llc Method for particle swarm optimization with random walk
CN102129249A (en) * 2011-01-10 2011-07-20 中国矿业大学 Method for planning global path of robot under risk source environment
CN102880186A (en) * 2012-08-03 2013-01-16 北京理工大学 Flight path planning method based on sparse A* algorithm and genetic algorithm
CN106444835A (en) * 2016-10-11 2017-02-22 哈尔滨工程大学 Underwater vehicle three-dimensional path planning method based on Lazy Theta satellite and particle swarm hybrid algorithm
CN106705970A (en) * 2016-11-21 2017-05-24 中国航空无线电电子研究所 Multi-UAV(Unmanned Aerial Vehicle) cooperation path planning method based on ant colony algorithm
CN106650298A (en) * 2017-01-11 2017-05-10 湘潭大学 Flexible needle route planning method based on environmental characteristics and stochastic method
CN107065876A (en) * 2017-04-28 2017-08-18 西北工业大学 Method for planning path for mobile robot based on Modified particle swarm optimization

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
郭国强.基于空间约束的路径规划与视景仿真研究.中国优秀硕士学位论文全文数据库工程科技Ⅱ辑.2012,(第3期),C034-4. *

Also Published As

Publication number Publication date
CN108664022A (en) 2018-10-16

Similar Documents

Publication Publication Date Title
CN108664022B (en) Robot path planning method and system based on topological map
Hu et al. Voronoi-based multi-robot autonomous exploration in unknown environments via deep reinforcement learning
CN111240319B (en) Outdoor multi-robot cooperative operation system and method thereof
Renzaglia et al. Multi-robot three-dimensional coverage of unknown areas
CN110147101B (en) End-to-end distributed multi-robot formation navigation method based on deep reinforcement learning
Wang et al. Autonomous robotic exploration by incremental road map construction
Jun et al. Multi-objective mobile robot path planning based on improved genetic algorithm
Wang et al. Efficient autonomous robotic exploration with semantic road map in indoor environments
CN112462803B (en) Unmanned aerial vehicle path planning method based on improved NSGA-II
CN110544296A (en) intelligent planning method for three-dimensional global flight path of unmanned aerial vehicle in environment with uncertain enemy threat
Kim et al. PLGRIM: Hierarchical value learning for large-scale exploration in unknown environments
CN112947591A (en) Path planning method, device, medium and unmanned aerial vehicle based on improved ant colony algorithm
CN111880561A (en) Unmanned aerial vehicle three-dimensional path planning method based on improved whale algorithm in urban environment
Sahoo et al. Navigational path planning of multi-robot using honey bee mating optimization algorithm (HBMO)
CN116954233A (en) Automatic matching method for inspection task and route
CN112415997A (en) Path planning method and system for multi-robot cooperation
CN114815801A (en) Adaptive environment path planning method based on strategy-value network and MCTS
Tusi et al. Using ABC and RRT algorithms to improve mobile robot path planning with danger degree
CN108227718B (en) Self-adaptive switching automatic carrying trolley path planning method
CN112484732B (en) IB-ABC algorithm-based unmanned aerial vehicle flight path planning method
CN115576333B (en) Optimal obstacle avoidance strategy
Li et al. Path planning of mobile robot based on improved td3 algorithm
CN115826586A (en) Path planning method and system fusing global algorithm and local algorithm
CN115454062A (en) Robot dynamic path planning method and system based on Betz curve
Renzaglia et al. Adaptive-based, scalable design for autonomous multi-robot surveillance

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