CN112486185B - Path planning method based on ant colony and VO algorithm in unknown environment - Google Patents
Path planning method based on ant colony and VO algorithm in unknown environment Download PDFInfo
- Publication number
- CN112486185B CN112486185B CN202011452945.9A CN202011452945A CN112486185B CN 112486185 B CN112486185 B CN 112486185B CN 202011452945 A CN202011452945 A CN 202011452945A CN 112486185 B CN112486185 B CN 112486185B
- Authority
- CN
- China
- Prior art keywords
- path
- map
- algorithm
- speed
- pheromone
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 68
- 238000000034 method Methods 0.000 title claims abstract description 25
- 239000011159 matrix material Substances 0.000 claims abstract description 39
- 230000003068 static effect Effects 0.000 claims abstract description 30
- 230000008569 process Effects 0.000 claims abstract description 8
- 239000003016 pheromone Substances 0.000 claims description 60
- 239000003795 chemical substances by application Substances 0.000 claims description 39
- 241000257303 Hymenoptera Species 0.000 claims description 29
- 230000007704 transition Effects 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 7
- 238000013461 design Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 2
- 230000004888 barrier function Effects 0.000 abstract description 7
- 230000000694 effects Effects 0.000 abstract description 4
- 230000002431 foraging effect Effects 0.000 description 5
- 238000005457 optimization Methods 0.000 description 5
- 238000004088 simulation Methods 0.000 description 5
- 230000006399 behavior Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 230000019637 foraging behavior Effects 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012795 verification 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
- G05D1/021—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, 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
- G05D1/021—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, 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
- G05D1/021—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, 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
- G05D1/021—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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a path planning method based on ant colony and VO algorithm in an unknown environment, so as to realize the avoidance of an intelligent agent on dynamic obstacles and static obstacles in the unknown environment. Firstly, an initial map matrix is built through rasterization of map known information, a global path under a known environment is built through an ant colony algorithm, and a path planning strategy is specifically divided into two parts aiming at the problem that the map environment is unknown and other static barriers and dynamic barriers possibly exist. For unknown static obstacles, when an intelligent agent detects static obstacle information in the motion process, updating a global map matrix, and reconstructing a global path through an ant colony algorithm. For the dynamic obstacle, a corresponding punishment function formula is designed by combining a VO algorithm, and the optimal speed is selected from the speed candidate set, so that the effects of avoiding the dynamic obstacle and tracking a path are achieved. Experimental results show that the path planning method provided by the invention can effectively avoid dynamic obstacles and static obstacles in an unknown environment.
Description
Technical field:
the invention relates to a path planning method based on ant colony and VO algorithm in an unknown environment, which can realize real-time path planning under the condition that unknown static barriers exist in the environment and dynamic barriers exist, and belongs to the technical field of intelligent optimization algorithm.
The background technology is as follows:
the ant colony algorithm is a heuristic search algorithm, which was first proposed by Dorigo in 1991. The algorithm simulates the foraging behavior of ants in nature. Ants in the ant colony can leave pheromone on the self advancing path, follow-up ants can select advancing directions according to the concentration of the pheromone on the path, and the ant colony can finally find a foraging path through accumulation of the pheromone on the path.
Social animal clustering activities tend to produce striking self-organizing behaviors, such as individual behaviors that appear simple, and blind ants make up the ant colony, and the shortest path from the ant nest to the food source can be found later. Biologists have carefully studied ants to find the shortest path through indirect communication and cooperation of a substance called "pheromone". Inspired by this phenomenon, italian scholars M.Dorigo, V.Maniezzo and a.colorni proposed a population-based simulated evolutionary algorithm, the ant colony algorithm, by simulating ant colony foraging behavior. The algorithm is greatly focused by students, and in the past twenty years, the ant colony algorithm has been widely applied in the fields of combination optimization, function optimization, system identification, network routing, robot path planning, data mining, comprehensive wiring design of a large-scale integrated circuit and the like, and has better effects.
Great research work is carried out on the defects of ant colony algorithms such as MarcoDorigo and ThomasStutzle, and various improved strategies [1] such as elite ant colony optimization algorithm, maximum and minimum ant system and the like are provided for solving the optimization problem of different characteristics in different fields more effectively (see ManiezzoV, gambardellaLM, luigiFD.Antcolonyoptimization.NewOptimizationTechniquesinEngineering [ M ]. Springer Berlin Heidelberg,2004: 422-423.); the modified ant colony Algorithm (ACS) is an ant colony algorithm adopting a local pheromone updating strategy, and can improve the probability of selecting an unaccessed path and strengthen the global searching capability of the algorithm; applying a spatial global pheromone update strategy to strengthen the concentration of pheromones on the obtained local optimal path so as to enhance the positive feedback effect of the algorithm and accelerate the convergence speed [2] of the algorithm (see Dorigo M, gambardella L.Ant color system: A cooperative learningap proach to the traveling salesman problem [ J ]. IEEE Transon Evolutionary Computation,1997,1 (1): 53-56.); aiming at the problem of continuous domains, in order to improve the capability of searching global optimal solutions and convergence speed and balance the convergence speed and the convergence speed, an improved ant colony algorithm [3] for adaptively adjusting a solution updating mode of the volatilization of pheromones and an information sharing mechanism is provided (see, in all directions, ge Hongwei and Su Shuzhi; computer engineering and application based on an adaptive continuous domain mixed ant colony algorithm [ J ] of the pheromones, 2017,53 (6): 156-161.); zhang Chun et al propose an improved algorithm that exploits the strong global search capability of genetic algorithms and the feedback mechanism of the combined ant colony algorithm. The ability of crossing and mutation can be carried out by applying a genetic algorithm, and the ant population is subjected to crossing mutation operation under certain conditions to obtain a new population, wherein the new population is used as an initial population of the ant colony algorithm to carry out fine estimation on the power distribution network state, and can more accurately reflect the power distribution network state [4] (see Zhang Chun, wang Li. Power distribution network state estimation [ J ] of the genetic-ant colony algorithm, modern electronic technology, 2016,39 (19): 165-168); the reasonable improvement of the selection strategy of the path of the ant colony algorithm in the optimizing process is beneficial to reducing the possibility that the ant colony algorithm is easy to fall into local optimum and improving the performance of the algorithm.
The invention comprises the following steps:
in order to ensure the safety and reliability of the movement of an agent on a planned path in an unknown environment, the invention provides a path planning design method based on an ant colony algorithm and a VO algorithm, so that the real-time path planning is safely and reliably performed under the condition that an unknown dynamic and static obstacle exists in the environment. The invention utilizes the ant colony foraging simulating strategy, finds out a reliable path by leaving pheromones in the map environment, and performs a new path planning round when a new static obstacle is found in the detection radius by maintaining a global known map matrix, thereby reducing the operation cost. Meanwhile, by combining with the VO obstacle avoidance strategy, dynamic obstacles are effectively avoided while path planning is completed, and by designing the path tracking strategy, the moving route of the intelligent agent is optimized, so that the moving route is smoother, and meanwhile, the problem of a detour route possibly existing in an ant colony algorithm is solved.
In order to achieve the above object, the technical scheme of the present invention is as follows: the path planning method based on ant colony and VO algorithm in unknown environment includes the following steps:
step 1, constructing an initialization matrix Map according to known Map information; wherein, the value of the area where the static obstacle exists is 1, and the value of other areas is 0;
step 2, calculating a global path PathList by using an ant colony algorithm;
step 3, after the global path is obtained, the intelligent agent performs path tracking according to a tracking strategy; setting a serial number for each path point, and recording the path point on the currently tracked global path through the trackId;
step 4, finding out the movement speed of the intelligent body at the next moment according to the VO algorithm;
step 6, if no new static obstacle appears in the detection radius, turning to step 3; if a new static obstacle appears, updating Map, turning to step 2, and planning a new path;
further, the specific construction method of the global path from the starting point to the end point in the step 2 is as follows:
step 2-1, setting iteration times G of an ant colony algorithm, the number n of ants and the parameter information of a pheromone volatilization coefficient rho;
step 2-2, constructing a pheromone concentration matrix pheomone Map with the same size according to the size of the matrix Map, setting the initial value of the pheromone concentration matrix pheomone Map as 1, constructing a temporary pheromone storage matrix tempPheomone Map with the same size, and setting the initial value of the temporary pheromone storage matrix tempPheomone Map as 0;
step 2-3, placing ants with the number of n at the starting point, sequentially searching paths of the ants with the serial numbers of 0 to n-1, and recording paths selected by each ant;
step 2-4, constructing a tabu table recordMap with the same size according to the size of the matrix Map, and recording the positions where ants have passed;
step 2-5, calculating an optional direction set availabledirect according to Map and recordMap information; selecting an optimal direction from the availableDirection set according to a state transition probability formula, and taking the optimal direction as a moving direction; if the availableDirection set is empty, i.e. no walkable direction exists, turning to the step 2-3, and starting the path planning process of the next ant;
wherein ,
is the probability that the kth ant transitions from node i to node j; τ ij (t) represents the pheromone concentration on the path from node i to node j; η (eta) i Is a heuristic function, ++>
d i Representing the distance of node i to the target point; alpha and beta respectively represent the concentration of pheromones and the relative importance degree of heuristic information;allowed k is the set of nodes that ants can select in the next step;
meanwhile, in order to accelerate the algorithm convergence speed, a state transition mode is adopted, wherein q represents a random number between 1 and 100, and q 1 Is a constant with a value between 1 and 100, m represents selecting the next node by adopting a roulette mode;
step 2-6, if the current position and the final position of the ants are the same, calculating a pheromone value according to a pheromone calculation formula according to a recording path, and storing corresponding pheromones in a temporary pheromone storage matrix, wherein the temporary pheromone storage matrix storage value is the sum of the pheromones left by all ants on the path in one iteration; otherwise, executing the step 2-5;
step 2-7, when n ants have completed the route searching process, updating the pheromone concentration matrix according to the temporary pheromone storage matrix; if the iteration times are reached, executing the step 3; otherwise, executing the step 2-3;
τ ij (t+Δt)＝(1-ρ)τ ij (t)+Δτ ij (t)
step 2-8, placing a path-finding ant at a starting point, enabling the path-finding ant to select a moving direction according to the concentration of pheromones, and recording a moving route of the path-finding ant, wherein the route is a global path list;
further, the specific design of the step 3 agent for path tracking according to the tracking strategy is as follows:
step 3-1, if the trackId is equal to the maximum sequence number on the path, the task is completed;
step 3-2, if the distance between the intelligent body and the path point is smaller than dmin, increasing the trackId; if the distance between the intelligent agent and the path point is greater than dmax, resetting the path point closest to the intelligent agent as a tracking path point;
step 3-3, setting an agent tracking path point target according to the trackId;
further, in step 4, the step of moving the speed of the agent at the next moment is specifically:
step 4-1, randomly initializing a candidate speed set and setting safety factor parameters;
step 4-2, selecting candidate speed from the set, calculating collision time of the intelligent body and all dynamic obstacles and static obstacles according to the speed, and recording the minimum collision time t; if the intelligent body has no collision with all the obstacles, the collision time t is infinity; calculating a punishment value according to the punishment function;
wherein μ is a safety factor, V pre For ideal speed, tar is the tracking path point position, position is the agent position, ||V max The I is the maximum speed of the intelligent agent;
step 4-3, if the speed candidate set is traversed, selecting a speed candidate with the minimum punishment value as the speed of the intelligent agent at the next moment; if the speed candidate set is not traversed, turning to step 4;
compared with the prior art, the invention has the following advantages: the invention discloses a path planning design method based on an ant colony algorithm and a VO algorithm, which realizes real-time path planning safely and reliably under the condition that unknown dynamic and static obstacles exist in the environment. The invention utilizes the ant colony foraging simulating strategy, finds out a reliable path by leaving pheromones in the map environment, and performs a new path planning round when a new static obstacle is found in the detection radius by maintaining a global known map matrix, thereby reducing the operation cost. Meanwhile, by combining with the VO obstacle avoidance strategy, dynamic obstacles are effectively avoided while path planning is completed, and by designing the path tracking strategy, the moving route of the intelligent agent is optimized, so that the moving route is smoother, and meanwhile, the problem of a detour route possibly existing in an ant colony algorithm is solved.
Drawings
Fig. 1 is a schematic flow chart of a path planning method based on ant colony and VO algorithm in an unknown environment according to the present invention;
FIG. 2 is a schematic diagram of a known environment route for an agent using QT simulation in accordance with the present invention, with unknown static and dynamic obstructions present in the environment;
FIG. 3 (a) is a map of the known environmental route of an agent constructed by matlab of the present invention, and FIG. 3 (b) is a map of the environment where unknown obstacles are actually present;
FIG. 4 (a) is a diagram of an agent quadratic programming path simulated by QT simulation according to the present invention, and FIG. 4 (b) is a partial enlarged view of the agent quadratic programming path;
FIG. 5 is a comparison of the path of an agent quadratic programming constructed using matlab according to the present invention;
FIG. 6 (a) is a schematic diagram of the motion behavior of an agent simulated by QT simulation in the present invention when it is predicted that a collision will occur when it encounters an unknown dynamic obstacle, and FIG. 6 (b) is a schematic diagram of the motion behavior of an agent when it is predicted that it can pass when it encounters an unknown dynamic obstacle;
Detailed Description
Example 1: the objects, technical schemes and advantages of the present invention will be further described in detail with reference to the accompanying drawings.
At present, the application of the intelligent agent is wider and wider, and the requirements on the safety and reliability of the intelligent agent path planning are higher and higher. In conventional classical path planning algorithms, it is often necessary to obtain all information about the environment. However, in an actual operating environment, there are often unknown static and dynamic obstacles, which place higher demands on the path planning of the agent. Therefore, the research is reliable and safe, and the problem that unknown barriers appear in the running environment must be overcome by an efficient path planning algorithm.
Based on the above consideration, the invention firstly utilizes the ant colony foraging simulating strategy, finds out the reliable path by leaving the pheromone in the map environment, and performs a new path planning round when a new static obstacle is found in the detection radius by maintaining the global known map matrix, thereby reducing the operation cost. Meanwhile, by combining with the VO obstacle avoidance strategy, dynamic obstacles are effectively avoided while path planning is completed, and by designing the path tracking strategy, the moving route of the intelligent agent is optimized, so that the moving route is smoother, and meanwhile, the problem of a detour route possibly existing in an ant colony algorithm is solved.
Fig. 1 shows a path planning method based on ant colony and VO algorithm in an unknown environment, which is specifically implemented as follows:
step 1, constructing an initialization matrix Map according to known Map information, wherein the value of a region where a static obstacle exists is 1, and the value of other regions is 0;
step 2, calculating a global path PathList by using an ant colony algorithm;
the step 2 comprises the following steps:
step 2-1, setting iteration times G of an ant colony algorithm, the number n of ants and the parameter information of a pheromone volatilization coefficient rho;
step 2-2, constructing a pheromone concentration matrix pheomone Map with the same size according to the size of the matrix Map, and setting the initial value of the matrix Map as 1; constructing a temporary pheromone storage matrix tempPheromonenMap with the same size, and setting the initial value of the temporary pheromone storage matrix tempPheromonenMap to be 0;
step 2-3, placing ants with the number of n at the starting point, sequentially searching paths of the ants with the serial numbers of 0 to n-1, and recording paths selected by each ant;
step 2-4, constructing a tabu table recordMap with the same size according to the size of the matrix Map, and recording the positions where ants have passed;
step 2-5, calculating an optional direction set availabledirect according to Map and recordMap information; selecting an optimal direction from the availableDirection set according to a state transition probability formula, and taking the optimal direction as a moving direction; if the availableDirection set is empty, i.e. no walkable direction exists, turning to the step 2-3, and starting the path planning process of the next ant;
wherein ,
is the probability that the kth ant transitions from node i to node j; τ ij (t) represents the pheromone concentration on the path from node i to node j; η (eta) i Is a heuristic function, ++>
d i Representing the distance of node i to the target point; alpha and beta respectively represent the concentration of pheromones and the relative importance degree of heuristic information; allowed k Is the set of nodes that ants can select in the next step;
meanwhile, in order to accelerate the algorithm convergence speed, a state transition mode is adopted, wherein q represents a random number between 1 and 100, and q 1 Is a constant with a value between 1 and 100, m represents selecting the next node by adopting a roulette mode;
step 2-6, if the current position and the final position of the ants are the same, calculating a pheromone value according to a pheromone calculation formula according to a recording path, and storing corresponding pheromones in a temporary pheromone storage matrix, wherein the temporary pheromone storage matrix storage value is the sum of the pheromones left by all ants on the path in one iteration; otherwise, executing the step 2-5;
step 2-7, when n ants have completed the route searching process, updating the pheromone concentration matrix according to the temporary pheromone storage matrix; if the iteration times are reached, executing the step 3; otherwise, executing the step 2-3;
τ ij (t+Δt)＝(1-ρ)τ ij (t)+Δτ ij (t)
step 2-8, placing a path-finding ant at a starting point, enabling the path-finding ant to select a moving direction according to the concentration of pheromones, and recording a moving route of the path-finding ant, wherein the route is a global path list;
step 3, after the global path is obtained, the intelligent agent performs path tracking according to a tracking strategy; setting a serial number for each path point, and recording the path point on the currently tracked global path through the trackId;
the step 3 comprises the following steps:
step 3-1, if the trackId is equal to the maximum sequence number on the path, the task is completed;
step 3-2, if the distance between the intelligent body and the path point is smaller than dmin, the trackId is increased progressively, so that some knotted paths can be avoided, and meanwhile, the movement route of the intelligent body can be smoother; if the distance between the intelligent body and the path point is greater than dmax, resetting the path point closest to the intelligent body as a tracking path point, so that the path point tracking can be carried out again after the dynamic obstacle is avoided from deviating from the tracking path point, and the original position is not required to be returned;
step 3-3, setting an agent tracking path point target according to the trackId;
step 4, finding out the movement speed of the intelligent body at the next moment according to the VO algorithm;
the step 4 comprises the following steps:
step 4-1, randomly initializing a candidate speed set and setting safety factor parameters;
step 4-2, selecting candidate speed from the set, calculating the collision time of the intelligent body and all dynamic obstacles and static obstacles according to the speed, and recording the minimum collision time t, wherein if the intelligent body and all the obstacles have no collision, the collision time t is infinite; calculating a punishment value according to the punishment function;
wherein μ is a safety factor, V pre For ideal speed, tar is the tracking path point position, position is the agent position, ||V max The I is the maximum speed of the intelligent agent;
step 4-3, if the speed candidate set is traversed, selecting a speed candidate with the minimum punishment value as the speed of the intelligent agent at the next moment; if the speed candidate set is not traversed, turning to step 4;
step 6, if no new static obstacle appears in the detection radius, turning to step 3; if a new static obstacle appears, updating Map, turning to step 2, and planning a new path;
the following is simulation verification of the path planning method based on ant colony and VO algorithm under unknown environment.
In order to prove the feasibility and effectiveness of the path planning method based on the ant colony and the VO algorithm in an unknown environment, the invention carries out an agent path planning simulation experiment through QT. By setting the map environment, the situation that unknown static barriers and dynamic barriers exist is simulated. The information of each parameter of the algorithm in the experiment is shown in table 1, and the experimental results are shown in fig. 2 to 6.
Table 1 parameter settings of the algorithm
As can be seen from fig. 2 to 6, in an environment where unknown static obstacles and dynamic obstacles exist, the path planning method based on the ant colony algorithm and the VO algorithm performs well, and real-time path planning can be performed quickly and efficiently, and the dynamic and static obstacles can be avoided safely and reliably.
The path planning method based on the ant colony algorithm and the VO algorithm designed by the invention can rapidly and efficiently carry out real-time path planning and safely and reliably avoid obstacles under the condition that unknown static obstacles and dynamic obstacles exist.
The invention provides a path planning method based on an ant colony algorithm and a VO algorithm, which is characterized in that after a map is rasterized, a reliable path is found by utilizing an ant colony foraging simulating strategy and leaving pheromones in a map environment, and a new path planning is performed when a new static obstacle is found in a detection radius by maintaining a global known map matrix, so that the operation cost is reduced. Meanwhile, by combining with the VO obstacle avoidance strategy, dynamic obstacles are effectively avoided while path planning is completed, and by designing the path tracking strategy, the moving route of the intelligent agent is optimized, so that the moving route is smoother, and meanwhile, the problem of a detour route possibly existing in an ant colony algorithm is solved.
It should be noted that, in the drawings or the text of the specification, implementations not shown or described are all forms known to those of ordinary skill in the art, and not described in detail. Furthermore, the above definitions of the elements and methods are not limited to the specific structures, shapes or modes mentioned in the embodiments, and may be simply modified or replaced by those of ordinary skill in the art.
The above embodiments are merely specific examples of the present invention, and it should be noted that the above embodiments do not limit the present invention, and various changes and modifications can be made by the related staff without departing from the scope of the technical idea of the present invention, which falls within the protection scope of the present invention.
Claims (1)
1. The path planning and designing method based on ant colony and VO algorithm in unknown environment is characterized by comprising the following steps:
step 1, constructing an initialization matrix Map according to known Map information; wherein, the value of the area where the static obstacle exists is 1, and the value of other areas is 0;
step 2, calculating a global path PathList by using an ant colony algorithm;
step 3, after the global path is obtained, the intelligent agent performs path tracking according to a tracking strategy; setting a serial number for each path point, and recording the path point on the currently tracked global path through the trackId;
step 4, finding out the movement speed of the intelligent body at the next moment according to the VO algorithm;
step 5, moving the intelligent body according to the calculated speed in the step 4;
step 6, if no new static obstacle appears in the detection radius, turning to step 3; if a new static obstacle appears, updating Map, turning to step 2, and planning a new path;
the specific construction method of the global path from the starting point to the end point in the step 2 comprises the following steps:
step 2-1, setting iteration times G of an ant colony algorithm, the number n of ants and the parameter information of a pheromone volatilization coefficient rho;
step 2-2, constructing a pheromone concentration matrix pheomone Map with the same size according to the size of the matrix Map, setting the initial value of the pheromone concentration matrix pheomone Map as 1, constructing a temporary pheromone storage matrix tempPheomone Map with the same size, and setting the initial value of the temporary pheromone storage matrix tempPheomone Map as 0;
step 2-3, placing ants with the number of n at the starting point, sequentially searching paths of the ants with the serial numbers of 0 to n-1, and recording paths selected by each ant;
step 2-4, constructing a tabu table recordMap with the same size according to the size of the matrix Map, and recording the positions where ants have passed;
step 2-5, calculating an optional direction set availabledirect according to Map and recordMap information; selecting an optimal direction from the availableDirection set according to a state transition probability formula, and taking the optimal direction as a moving direction; if the availableDirection set is empty, i.e. no walkable direction exists, turning to the step 2-3, and starting the path planning process of the next ant;
wherein ,
is the probability that the kth ant transitions from node i to node j; τ ij (t) represents the pheromone concentration on the path from node i to node j; η (eta) i Is a heuristic function, ++>
d i Representing the distance of node i to the target point; alpha and beta respectively represent the concentration of pheromones and the relative importance degree of heuristic information; allowed k Is the set of nodes that ants can select in the next step;
meanwhile, in order to accelerate the algorithm convergence speed, a state transition mode is adopted, wherein q represents a random number between 1 and 100, and q 1 Is a constant with a value between 1 and 100, m represents selecting the next node by adopting a roulette mode;
step 2-6, if the current position and the final position of the ants are the same, calculating a pheromone value according to a pheromone calculation formula according to a recording path, and storing corresponding pheromones in a temporary pheromone storage matrix, wherein the temporary pheromone storage matrix storage value is the sum of the pheromones left by all ants on the path in one iteration; otherwise, executing the step 2-5;
step 2-7, when n ants have completed the route searching process, updating the pheromone concentration matrix according to the temporary pheromone storage matrix; if the iteration times are reached, executing the step 3; otherwise, executing the step 2-3;
τ ij (t+Δt)＝(1-ρ)τ ij (t)+Δτ ij (t)
step 2-8, placing a path-finding ant at a starting point, enabling the path-finding ant to select a moving direction according to the concentration of pheromones, and recording a moving route of the path-finding ant, wherein the route is a global path list;
step 3, the specific design of the intelligent agent for path tracking according to the tracking strategy is as follows:
step 3-1, if the trackId is equal to the maximum sequence number on the path, the task is completed;
step 3-2, if the distance between the intelligent body and the path point is smaller than dmin, increasing the trackId; if the distance between the intelligent agent and the path point is greater than dmax, resetting the path point closest to the intelligent agent as a tracking path point;
step 3-3, setting an agent tracking path point target according to the trackId;
in step 4, the step of the movement speed of the intelligent agent at the next moment is specifically as follows:
step 4-1, randomly initializing a candidate speed set and setting safety factor parameters;
step 4-2, selecting candidate speed from the set, calculating collision time of the intelligent body and all dynamic obstacles and static obstacles according to the speed, and recording the minimum collision time t; if the intelligent body has no collision with all the obstacles, the collision time t is infinity; calculating a punishment value according to the punishment function;
wherein μ is a safety factor, V pre For ideal speed, tar is the tracking path point position, position is the agent position, ||V max The I is the maximum speed of the intelligent agent;
step 4-3, if the speed candidate set is traversed, selecting a speed candidate with the minimum punishment value as the speed of the intelligent agent at the next moment; if the speed candidate set has not been traversed, go to step 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011452945.9A CN112486185B (en) | 2020-12-11 | 2020-12-11 | Path planning method based on ant colony and VO algorithm in unknown environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011452945.9A CN112486185B (en) | 2020-12-11 | 2020-12-11 | Path planning method based on ant colony and VO algorithm in unknown environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112486185A CN112486185A (en) | 2021-03-12 |
| CN112486185B true CN112486185B (en) | 2023-05-09 |
Family
ID=74916715
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011452945.9A Active CN112486185B (en) | 2020-12-11 | 2020-12-11 | Path planning method based on ant colony and VO algorithm in unknown environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112486185B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114281087B (en) * | 2021-12-31 | 2023-11-03 | 东南大学 | Path planning method based on life planning A and speed obstacle method |
| CN114578827B (en) * | 2022-03-22 | 2023-03-24 | 北京理工大学 | Distributed multi-agent cooperative full-coverage path planning method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108036790B (en) * | 2017-12-03 | 2020-06-02 | 景德镇陶瓷大学 | Robot path planning method and system based on ant-bee algorithm in obstacle environment |
| CN108241375B (en) * | 2018-02-05 | 2020-10-30 | 景德镇陶瓷大学 | Application method of self-adaptive ant colony algorithm in mobile robot path planning |
| CN108776483B (en) * | 2018-08-16 | 2021-06-29 | 圆通速递有限公司 | AGV path planning method and system based on ant colony algorithm and multi-agent Q learning |
| CN111694364A (en) * | 2020-06-30 | 2020-09-22 | 山东交通学院 | Hybrid algorithm based on improved ant colony algorithm and dynamic window method and applied to intelligent vehicle path planning |
-
2020
- 2020-12-11 CN CN202011452945.9A patent/CN112486185B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112486185A (en) | 2021-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111780777B (en) | Unmanned vehicle route planning method based on improved A-star algorithm and deep reinforcement learning | |
| CN110083165B (en) | Path planning method of robot in complex narrow environment | |
| Liu et al. | An autonomous path planning method for unmanned aerial vehicle based on a tangent intersection and target guidance strategy | |
| CN113093724A (en) | AGV path planning method based on improved ant colony algorithm | |
| CN112486185B (en) | Path planning method based on ant colony and VO algorithm in unknown environment | |
| Tang et al. | A novel hierarchical soft actor-critic algorithm for multi-logistics robots task allocation | |
| Liu et al. | Deep structured reactive planning | |
| Alpkiray et al. | Probabilistic roadmap and artificial bee colony algorithm cooperation for path planning | |
| Yang et al. | Mobile robot path planning based on enhanced dynamic window approach and improved A∗ algorithm | |
| Chen et al. | Path planning of mobile robot based on an improved genetic algorithm | |
| Huang et al. | Robot path planning using improved ant colony algorithm in the environment of internet of things | |
| CN113848911A (en) | Mobile robot global path planning method based on Q-learning and RRT | |
| Wu et al. | An adaptive conversion speed Q-learning algorithm for search and rescue UAV path planning in unknown environments | |
| CN117522078A (en) | Method and system for planning transferable tasks under unmanned system cluster environment coupling | |
| Wu et al. | Multi-agent collaborative learning with relational graph reasoning in adversarial environments | |
| Ma et al. | Robot path planning using fusion algorithm of ant colony optimization and genetic algorithm | |
| CN116523158A (en) | Multi-unmanned aerial vehicle track planning method, device, equipment and storage medium | |
| Jamal et al. | Adaptive maneuver planning for autonomous vehicles using behavior tree on apollo platform | |
| Cai | Decision-making of transportation vehicle routing based on particle swarm optimization algorithm in logistics distribution management | |
| Ma et al. | Adaptive deployment of UAV-aided networks based on hybrid deep reinforcement learning | |
| CN115202357A (en) | Autonomous mapping method based on impulse neural network | |
| CN116225046A (en) | Unmanned aerial vehicle autonomous path planning method based on deep reinforcement learning under unknown environment | |
| Tang et al. | A novel path planning approach based on appart and particle swarm optimization | |
| Tang et al. | Reinforcement learning for robots path planning with rule-based shallow-trial | |
| Tan et al. | Expected-mean gamma-incremental reinforcement learning algorithm for robot path planning |
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 |