CN112183710A - Method and device for determining path - Google Patents
Method and device for determining path Download PDFInfo
- Publication number
- CN112183710A CN112183710A CN202011141236.9A CN202011141236A CN112183710A CN 112183710 A CN112183710 A CN 112183710A CN 202011141236 A CN202011141236 A CN 202011141236A CN 112183710 A CN112183710 A CN 112183710A
- Authority
- CN
- China
- Prior art keywords
- path
- pheromone
- ant
- determining
- updating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 67
- 239000003016 pheromone Substances 0.000 claims abstract description 162
- 238000007689 inspection Methods 0.000 claims abstract description 49
- 241000257303 Hymenoptera Species 0.000 claims description 69
- 230000006870 function Effects 0.000 claims description 23
- 230000015654 memory Effects 0.000 claims description 19
- 238000004891 communication Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 8
- 230000004888 barrier function Effects 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 5
- 238000012546 transfer Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims 4
- 238000005457 optimization Methods 0.000 abstract description 6
- 230000008569 process Effects 0.000 description 15
- 238000010586 diagram Methods 0.000 description 10
- 230000000694 effects Effects 0.000 description 5
- 230000006399 behavior Effects 0.000 description 4
- 230000002457 bidirectional effect Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 125000004122 cyclic group Chemical group 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Manipulator (AREA)
Abstract
The application provides a method and a device for determining a path, relates to the field of robot path planning, and can accelerate the convergence speed of an ant colony algorithm and prevent the algorithm from falling into local optimization, so that the speed and the efficiency of routing inspection robot path optimization are improved. The method comprises the following steps: determining at least m paths between the starting position and the end position by an ant colony algorithm; updating pheromones on the effective path according to a first pheromone updating strategy; comparing the existing global optimal path with the local optimal path to determine the current global optimal path; updating pheromones on the current global optimal path according to a second pheromone updating strategy; adding one to the cycle number c, and if the cycle number c does not reach n times, repeating all the steps; and if the cycle number c reaches n times, determining the current global optimal path as a target path of the inspection robot, wherein the target path is used for indicating the inspection robot to reach the end point position from the starting position along the target path.
Description
Technical Field
The present application relates to the field of artificial intelligence, and in particular, to a method, an apparatus, and a system for determining a path.
Background
With the development of the fifth generation communication technology, the 5G communication is more and more widely applied in the industry. 5G accurate positioning, compared with traditional 4G positioning, the precision is higher. The inspection robot with the 5G ultrahigh network speed can quickly and accurately realize functions of early warning, meter reading, fault removal and the like, saves manpower and improves the working efficiency and accuracy. With the application of 5G inspection robots in more scenes, the complexity of the scenes is increased. To realize high-precision task execution, the 5G inspection robot must be capable of achieving accurate navigation. Considering the problems of power consumption, task execution time and the like of the robot, the 5G inspection robot needs to be capable of finding the shortest path from the departure place to the destination in the shortest time.
The ant colony algorithm is widely applied to the interior of the inspection robot and is used for the aspects of intelligent navigation, road block avoidance, optimal path search and the like of the robot. However, the traditional ant colony algorithm has the problems of low convergence speed, easy falling into local optimum and the like, and is easy to cause the conditions that the inspection robot has low efficiency, cannot respond in time and the like, so that the advantages of the 5G network cannot be fully exerted.
Disclosure of Invention
The application provides a method, a device and a system for determining a path, which are used for an inspection robot, can accelerate the convergence rate of path planning and prevent an algorithm from falling into local optimization.
In order to achieve the purpose, the technical scheme is as follows:
in a first aspect, the present application provides a method of determining a path, which may include: determining at least m paths between the starting position and the end position by an ant colony algorithm; the m is used for representing the total ant number of the ant colony algorithm, the value of the m is more than or equal to 1, the at least m paths comprise effective paths, and the effective paths comprise local optimal paths; updating pheromones on the effective path according to a first pheromone updating strategy; comparing the existing global optimal path with the local optimal path to determine the current global optimal path; updating pheromones on the current global optimal path according to a second pheromone updating strategy; adding one to the cycle number c, and if the cycle number c does not reach n times, repeating all the steps; wherein the initial value of c is 0, n is used for representing the total cycle number, and the value of n is more than 1; and if the cycle number c reaches n times, determining a current global optimal path as a target path of the inspection robot, wherein the target path is used for indicating the inspection robot to reach the end point position from the starting position along the target path.
In a second aspect, the present application provides an apparatus for determining a path, the apparatus comprising: the device comprises a cyclic search module, a first updating module, a first determining module, a second updating module, a first counting detection module and a second determining module. The loop search module is used for determining at least m paths between the starting position and the end position through an ant colony algorithm; the m is used for representing the total ant number of the ant colony algorithm, the value of the m is more than or equal to 1, the at least m paths comprise effective paths, and the effective paths comprise local optimal paths; the first updating module is used for updating the pheromone on the effective path according to a first pheromone updating strategy; the first determining module is used for comparing the existing global optimal path with the local optimal path and determining the current global optimal path; the second updating module is used for updating the pheromone on the current global optimal path according to a second pheromone updating strategy; the first counting detection module is used for adding one to the cycle number c and judging whether the cycle number c reaches n times; if the cycle number c does not reach n times, indicating all the modules to sequentially execute the corresponding steps again; wherein the initial value of c is 0, n is used for representing the total cycle number, and the value of n is more than 1; and the second determining module is used for determining the current global optimal path as a target path of the inspection robot if the cycle number c reaches n times, wherein the target path is used for indicating the inspection robot to reach the end position from the starting position along the target path.
In a third aspect, the present application provides an apparatus for determining a path, the apparatus comprising: a processor, a transceiver, and a memory. Wherein the memory is used to store one or more programs. The one or more programs include computer executable instructions which, when executed by the apparatus, cause the apparatus to perform the method of determining a path as described in any of the first aspect and its various alternative implementations.
In a fourth aspect, the present application provides a computer-readable storage medium having instructions stored therein, where the instructions, when executed by a computer, cause the computer to perform the method for determining a path according to any one of the first aspect and its various optional implementations.
In a fifth aspect, the present application provides a computer program product comprising a computer program which, when run on a computer, executes the method of determining a path of the first aspect and any of its various alternative implementations.
According to the method and the device for determining the path, the ant colony algorithm is used for carrying out c times of circular search between the initial position and the final position of the path to be determined by using m ants; searching in each cycle to obtain an effective path with the shortest length as a local optimal path, and updating pheromones on the effective path according to a first pheromone updating strategy; and after multiple cycles, searching to obtain a local optimal path with the shortest length as a global optimal path, and updating pheromones on the current global optimal path according to a second pheromone updating strategy. Compared with the prior art, all ants uniformly update pheromones after each cycle is finished. According to the method for determining the path, pheromone updating is carried out on the principle that the contribution of ants for finding the optimal path in each cycle is taken as the principle, namely, only pheromones on the effective path are increased, more pheromones are added on the local optimal path, and then the pheromones on the global optimal path are additionally increased, so that the convergence speed of the ant colony algorithm is increased, the algorithm can be prevented from falling into the local optimal path, and the speed and the accuracy for determining the path are improved.
Drawings
Fig. 1 is a schematic structural diagram of an inspection robot to which the method and the apparatus for determining a path according to the embodiment of the present application are applied;
fig. 2 is a schematic diagram of a method for determining a path according to an embodiment of the present disclosure;
fig. 3 is a schematic diagram of another method for determining a path according to an embodiment of the present application;
FIG. 4 is a schematic diagram of an environment model provided by an embodiment of the present application;
FIG. 5 is a first schematic structural diagram of an apparatus for determining a path according to an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram ii of an apparatus for determining a path according to an embodiment of the present application;
fig. 7 is a schematic structural diagram three of an apparatus for determining a path according to an embodiment of the present application;
fig. 8 is a fourth schematic structural diagram of the apparatus for determining a path according to the embodiment of the present application.
Detailed Description
First, terms related to embodiments of the present application will be described.
Ant colony algorithm: the ant colony algorithm (ant colony algorithm) is a population-based simulated evolution algorithm inspired by the research result of real ant colony behavior in nature, and belongs to a random search algorithm. The ant individuals carry out information transmission through pheromone, the ant can leave the pheromone on a path where the ant passes in the moving process, the ant can sense the existence and the strength of the pheromone in the moving process, and the ant tends to move towards a place with high pheromone concentration according to the moving direction of the ant. Therefore, the collective behavior of a colony of a large number of ants exhibits a positive feedback phenomenon of information: the more ants that travel on a path, the greater the probability that the next will select the path. The ant colony algorithm for finding the shortest path is derived from the collective behaviors of ants, the ant colony algorithm designs virtual ants to search different routes, and leaves virtual pheromones which gradually disappear along with time, and the optimal route can be found according to the principle that the route with thicker pheromones is closer.
Ants: the ant colony algorithm design simulates 'ants' simulating the ant behaviors in an ant colony, and each common ant has the following characteristics:
(1) the ants select the next nodes according to the probability function taking the pheromone and the heuristic information as variables.
(2) It is specified that unless the search is completed, ants cannot return to walk past nodes, controlled by the tabu table.
(3) After the search is completed, the ants leave the pheromone on the path they have traveled.
The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone.
The terms "first" and "second" and the like in the description and drawings of the present application are used for distinguishing different objects or for distinguishing different processes for the same object, and are not used for describing a specific order of the objects.
Furthermore, the terms "including" and "having," and any variations thereof, as referred to in the description of the present application, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements but may alternatively include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described herein as "exemplary" or "e.g.," is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present concepts related in a concrete fashion.
In the description of the present application, the meaning of "a plurality" means two or more unless otherwise specified.
The method, the apparatus and the system for determining a path provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the inspection robot provided in the embodiment of the present application is schematically shown in structure.
On the basis of the existing transformer substation inspection robot, the multifunctional inspection robot utilizes advanced communication, control and other technical means, enhances and expands the functions of the multifunctional inspection robot through 5G, and has the characteristics of being flexible, real-time, high-definition and panoramic and being 4. The inspection robot is used as an intelligent mobile platform, can quickly and intelligently position the fault point of the transformer substation, and can fully exert the advantage of large bandwidth of the 5G technology. The inspection robot can improve the efficiency of ordinary power inspection, can be generally applied to various scenes such as maintenance, rush repair and construction, improves field management and control and operation level, and improves operation efficiency and safety.
Wherein, 5G Customer Premises Equipment (CPE) is used to implement 5G communication; the laser navigation system adopts a laser radar to model an operation scene, so that a timed and fixed-point automatic cruise task is realized, and unmanned inspection is really realized; the VR panoramic camera adopts a virtual reality technology, and videos can be transmitted back to VR glasses of a monitoring center, so that the driving feeling of remote inspection personnel is improved, and the functions of remote manual sampling inspection and remote teaching are realized; the thermal infrared imager is used for measuring the temperature of the instrument; the high-definition camera is used for reading of a measuring instrument and meter, and high-precision and high-reliability operation scene environment and equipment image acquisition are achieved.
The embodiment of the application provides a method for determining a path, which is applied to an inspection robot shown in fig. 1, and as shown in fig. 2, the method may include steps S101 to S107:
and S101, determining at least m paths between the starting position and the end position through an ant colony algorithm.
Wherein m is used for representing the total ant number of the ant colony algorithm, and the value of m is more than or equal to 1. The m paths include a valid path and an invalid path.
According to an ant colony algorithm, m ants are searched between the initial position and the final position in one cycle, and if no ant is searched reversely, m ants can search to obtain m paths; if there are ants to choose to search backwards, then m ants will search for more than m paths. The path obtained by searching for the ant k may be an effective path or an ineffective path, the effective path is a path obtained by searching for ants and connecting the initial position and the end position, and the ineffective path is a path obtained by searching for ants which have not reached the end position or the initial position and have no next selectable position point. The effective path with the shortest path length is called a local optimal path.
And S102, updating the pheromone on the effective path according to the first pheromone updating strategy.
Specifically, the first pheromone updating strategy is to determine a path between adjacent position points i and j<i,j>Upper, t1Pheromone tau at time + deltatij(t1+ Δ t) and t1Time of day pheromone tauij(t1) Satisfies the following formula:
τij(t1+Δt)＝τij(t1)+Δ*τij(t1,t1+Δt)
wherein, tauij(t1) Indicating the path after the end of the cycle<i,j>The pheromone of (a); delta*τijRepresenting a path<i,j>Pheromone increment on; EP represents the active path; LB represents a locally optimal path; re represents the ratio of the total effective path length to the locally optimal path length.
And according to a first pheromone updating strategy, only performing pheromone increase on the effective path obtained by the circular search. Since the local optimal path is the effective path with the shortest length, the value of Re is always greater than or equal to 1, and compared with other effective paths, the pheromone on the local optimal path is greatly increased. Therefore, the first pheromone updating strategy has the effect that when ants select paths in the next cycle, effective paths can be selected with higher probability, so that the convergence speed of the ant colony algorithm is increased, and the efficiency of path searching is further improved.
S103, comparing the existing global optimal path with the local optimal path, and determining the current global optimal path.
Specifically, after the first cycle is finished, the local optimal path obtained by searching is an effective path with the shortest length of the current path, so that the local optimal path is determined as the current global optimal path; after more than two times of circulation, comparing the local optimal path generated by each circulation with the existing global optimal path, and determining the path with shorter length as the current global optimal path.
And S104, updating the pheromone on the current global optimal path according to a second pheromone updating strategy.
Specifically, the second pheromone updating strategy is to determine a path between adjacent position points i and j<i,j>Upper, t2Pheromone tau at time + deltatij(t2+ Δ t) and t2Time of day pheromone tauij(t2) Satisfies the following formula:
τij(t2+Δt)＝τij(t2)+Δ*τij(t2,t2+Δt)
wherein, tauij(t2) Indicating a post-pheromone path on the locally optimal path updated according to a first pheromone update policy<i,j>The pheromone of (a); l is*Representing a length of the global optimal path; GB denotes a global optimal path.
The second pheromone updating strategy has the effects that when ants select paths in the next cycle, the globally optimal paths can be selected with higher probability, the algorithm is prevented from falling into local optimization, and the accuracy of path searching is improved.
S105, adding one to the cycle number c.
And S106, judging whether the cycle number c reaches the total cycle number n.
Specifically, if the cycle count c does not reach the total cycle count n, repeating the steps S101 to S104; if yes, the process proceeds to step S107.
Optionally, if the cycle number c does not reach the total cycle number n, but it is detected that the current global optimal path is not changed within the preset time, the process proceeds to step S107. Wherein the preset time is 10 s.
And S107, determining the current global optimal path as a target path of the inspection robot.
Specifically, the target path is used for indicating the inspection robot to reach the end position from the starting position along the target path.
According to the method for determining the path, the ant colony algorithm is used for carrying out c times of circular search between the initial position and the final position of the path to be determined by using m ants; searching in each cycle to obtain an effective path with the shortest length as a local optimal path, and updating pheromones on the effective path according to a first pheromone updating strategy; and after multiple cycles, searching to obtain a local optimal path with the shortest length as a global optimal path, and updating pheromones on the current global optimal path according to a second pheromone updating strategy. Compared with the prior art, all ants uniformly update pheromones after each cycle is finished. According to the method for determining the path, pheromone updating is carried out on the principle that the contribution of ants for finding the optimal path in each cycle is taken as the principle, namely, only pheromones on the effective path are increased, more pheromones are added on the local optimal path, and then the pheromones on the global optimal path are additionally increased, so that the convergence speed of the ant colony algorithm is increased, the algorithm can be prevented from falling into the local optimal path, and the speed and the accuracy for determining the path are improved.
The traditional ant colony algorithm searches a target point from the starting point in a single direction, and finishes searching the target point, so that although an optimal path can be found, the convergence speed is slow, and the time spent is long. In addition, because the traditional ant colony algorithm has a tabu table, the ants are locked after entering the death cycle, and the ants are more blindness and easy to lock at the initial stage of the ant colony algorithm, so that the utilization rate of the ants is greatly reduced, and the efficiency of the ant colony algorithm is reduced.
In order to solve the above problem, an embodiment of the present application provides another method for determining a path, which is applied to an inspection robot shown in fig. 1, and as shown in fig. 3, the method may include S201-S215:
s201, the inspection robot establishes an environment model.
Specifically, the inspection robot establishes an environment model according to the environment information identified by the sensor of the inspection robot. Optionally, in order to facilitate the ant colony algorithm to search the optimal path, the inspection robot divides the environment by using a grid method, and two-dimensionalizes the working space of the inspection robot into a grid map. As shown in fig. 4, grid points in the grid map, that is, position points where ants move, include a start position and an end position of a path to be determined, and a limited number of obstacle position points.
S202, initializing initial parameters of the ant colony algorithm by the inspection robot.
The initial parameters include the initial position and the end position of the path to be determined, the total ant number m of the ant colony algorithm and the total cycle number n. Optionally, the initial parameter may also include other parameters, such as an information elicitation factor α, an expected elicitation factor β, a pheromone volatility factor ρ, an initial pheromone concentration, and the like, which are not limited in this application.
The initial parameters are used for determining a shortest path connecting the initial position and the end position and avoiding the obstacle position point by the inspection robot by adopting an ant colony algorithm.
S203, setting the search starting points of x ants in the m ants at the initial positions, and setting the search starting points of the other m-x ants at the final positions.
Specifically, the inspection robot randomly divides m ants into two groups, sets the search starting point of one group of x ants at the initial position to search a path to the end position, and sets the search starting point of the other group of m-x ants at the end position to search a path to the initial position, thereby realizing bidirectional search. The value of x can be adjusted according to the actual situation, that is, the number of the two sets of ants can be equal or unequal, and the application is not limited. Alternatively, the ants may be grouped according to the numbers of m ants, so that odd ants start searching from the initial position and even ants start searching from the final position.
On the basis of bidirectional search, reverse search and single ant pheromone updating are introduced, namely if the ant search obtains an effective path or no position point which can be selected next step exists, the pheromone updating is carried out, so that waiting during ant iteration is reduced, the repeated utilization rate of ants is increased, and the search efficiency is improved.
And S204, introducing a barrier avoidance function, and selecting the next position point of the ant k by using a roulette method.
Wherein the initial value of k is 1.
In one implementation, the obstacle avoidance function is:
wherein all iskAll position points which can be selected next by the ant k are shown, specifically, the ant k can reach adjacent position points on one position point along 8 directions of upper, right, lower, left, upper right, lower right, upper left and lower left, and the position points and barrier position points which are passed by the ant k are excluded, namely all position points which can be selected next by the ant k; dijRepresents the distance between location point i and location point j; sg jRepresents the shortest distance from the position point j to the end position g; and s represents the position point of the next step of the ant corresponding to the shortest distance.
After the obstacle avoidance function is introduced, the next position point is selected by a roulette method, namely, at the time t, ants k have the transition probability pk ij(t) from position point i to position point j. Wherein the transition probability pk ij(t) satisfies the following formula:
alpha is a nonzero constant, represents an information heuristic factor, represents the relative importance degree of pheromones in an ant colony algorithm, reflects the influence degree of the pheromone quantity on the ant selection path, and the larger the alpha value is, the stronger the collaboration among the ants is. Beta is a non-zero constant, representing an expected heuristic factor representing the relative importance of heuristic information in the ant colony algorithm.
The obstacle avoidance function has the effect that when the ant k selects the next position point, the position point closer to the end position can be selected with a higher probability.
And S205, judging whether the ant k searches for an effective path or does not have a next selectable position point.
Optionally, the path obtained by searching for the ant k may be an effective path or an ineffective path, the effective path is a path obtained by searching for the ant and connecting the initial position and the end position, and the ineffective path is a path obtained by searching for an ant that has not reached the end position or the initial position and does not have a next selectable position point.
If the ant k searches for an effective path or no next selectable position point exists, the step S206 is performed; if the ant k has not searched for a valid path and there are further selectable location points, the above step S204 is executed in a loop.
And S206, updating the pheromone of the single ant.
Specifically, the performing of the single ant pheromone updating is to perform a path between adjacent position points i and j<i,j>Pheromone tau at time t + DeltatijPheromone tau at (t + Deltat) and time tij(t) satisfies the following equation:
τij(t+Δt)＝(1-ρ)·τij(t)+Δτij k(t,t+Δt)
wherein, a constant rho epsilon (0,1) represents pheromone volatilization factor and represents the loss degree of the pheromone on the path, the magnitude of rho is related to the global search capability and convergence rate of the algorithm, and 1-rho represents the pheromoneA residual factor; tau isij(t) represents the path after searching the path<i,j>The pheromone of (a); delta tauij k(t) represents the ant k in the path after searching the path<i,j>Pheromone increment on; q is a constant representing the total pheromone amount released by the ant in one cycle; l iskRepresenting a path<i,j>Length of (d).
Specifically, after the ant k is judged to search for an effective path or no next selectable position point exists, that is, after the ant k completes the cycle, pheromones on all paths in the grid map are volatilized. The path traveled by ant k leaves pheromones released by ant k, and the shorter the path, the more pheromones remain.
And S207, if the ant k is searched to obtain the effective path, randomly selecting whether the ant k needs to be searched reversely.
Optionally, if the ant k first searches from the starting position to the ending position, it is randomly selected whether the ant k needs to use the ending position as a new search starting point, and a reverse search is performed towards the starting position. If the ant k reaches the initial position from the end position for the first time, whether the ant k needs to take the initial position as a new search starting point or not is randomly selected, and a reverse search is carried out towards the end position.
S208, judging whether the ant k needs to search reversely.
If the ant k is to search reversely, go to step S209(a), and repeat the above steps S204 to S207; if the ant k does not perform the reverse search, the process proceeds to step S209 (b).
S209(a), the current position point is set as a search start point.
Specifically, if the current position point is the starting position, the ant k takes the starting position as a new search starting point and carries out reverse search to the end position; and if the current position point is the end position, the ant k takes the end position as a new search starting point and carries out reverse search to the starting position.
S209(b), judging whether the ant number k reaches the total ant number m.
Specifically, the initial value of k is 1, which means that in the current cycle, k ants have completed the path search. If k does not reach m, which means that the present cycle has not ended, the process proceeds to step S210(a), and steps S204 to S208 are repeated; if k reaches m, which represents the end of the present cycle, the process proceeds to step S210 (b).
S210(a), adding one to the number k of ants.
And S210(b), updating pheromones on the effective path according to a first pheromone updating strategy.
Specifically, the first pheromone updating strategy is to determine a path between adjacent position points i and j<i,j>Upper, t1Pheromone tau at time + deltatij(t1+ Δ t) and t1Time of day pheromone tauij(t1) Satisfies the following formula:
τij(t1+Δt)＝τij(t1)+Δ*τij(t1,t1+Δt)
wherein, tauij(t1) Indicating the path after the end of the cycle<i,j>The pheromone of (a); delta*τijRepresenting a path<i,j>Pheromone increment on; EP represents the active path; LB represents a locally optimal path; re represents the ratio of the total effective path length to the locally optimal path length.
Specifically, after one cycle is finished, m ants search for at least m paths, including an effective path and an ineffective path, and the effective path with the shortest path length searched in the cycle is called a local optimal path LB.
And according to a first pheromone updating strategy, only performing pheromone increase on the effective path obtained by the cyclic search, wherein the local optimal path is the effective path with the shortest length, so that the value of Re is certainly more than or equal to 1, and compared with other effective paths, the pheromone on the local optimal path is greatly increased. Therefore, the first pheromone updating strategy has the effect that when ants select paths in the next cycle, effective paths can be selected with higher probability, so that the convergence speed of the ant colony algorithm is increased, and the efficiency of path searching is further improved.
And S211, comparing and determining the current global optimal path.
Specifically, after the first cycle is finished, the local optimal path obtained by searching is an effective path with the shortest length of the current path, so that the local optimal path is determined as the current global optimal path; after more than two times of circulation, comparing the local optimal path generated by each circulation with the existing global optimal path, and determining the path with shorter length as the current global optimal path.
And S212, updating the pheromone on the current global optimal path according to a second pheromone updating strategy.
Specifically, the second pheromone updating strategy is to determine a path between adjacent position points i and j<i,j>Upper, t2Pheromone tau at time + deltatij(t2+ Δ t) and t2Time of day pheromone tauij(t2) Satisfies the following formula:
τij(t2+Δt)＝τij(t2)+Δ*τij(t2,t2+Δt)
wherein, tauij(t2) Indicating a post-pheromone path on the locally optimal path updated according to a first pheromone update policy<i,j>The pheromone of (a); l is*Representing a length of the global optimal path; GB denotes a global optimal path.
The second pheromone updating strategy has the effects that when ants select paths in the next cycle, the globally optimal paths can be selected with higher probability, the algorithm is prevented from falling into local optimization, and the accuracy of path searching is improved.
S213, adding one to the cycle number c.
S214, judging whether the cycle number c reaches the total cycle number n.
Specifically, if the cycle count c does not reach the total cycle count n, the above steps S204 to S213 are repeated; if yes, the process proceeds to step S215.
Optionally, if the cycle number c does not reach the total cycle number n, but it is detected that the current global optimal path is not changed within the preset time, the process proceeds to step S215. Wherein the preset time is 10 s.
S215, determining the current global optimal path as a target path of the inspection robot.
Specifically, the target path is used for indicating the inspection robot to reach the end position from the starting position along the target path.
According to the method, the device and the system for determining the path, the ant colony algorithm is used for carrying out c times of circular search between the initial position and the final position of the path to be determined; setting the search starting points of x ants in the m ants at the initial positions, and setting the search starting points of the other m-x ants at the final positions; introducing a barrier avoidance function, and selecting the next position point of the ant k by using a roulette method; if the ant k searches for an effective path or no next selectable position point exists, updating the pheromone of a single ant; carrying out reverse search randomly; updating pheromones on the effective path according to a first pheromone updating strategy; and updating the pheromone on the current global optimal path according to a second pheromone updating strategy. Compared with the prior art, all ants uniformly update pheromones after each cycle is finished. According to the method for determining the path, pheromone updating is carried out on the principle that the contribution of ants for finding the optimal path in each cycle is large, namely, only pheromones on effective paths are increased, more pheromones are added on local optimal paths, and pheromones on global optimal paths are additionally added, so that the convergence speed of an ant colony algorithm is increased, the algorithm can be prevented from falling into local optimal paths, and the speed and accuracy for determining the paths are improved; on the basis of bidirectional search, reverse search and single ant pheromone updating are introduced, namely if an effective path is obtained by ant search or no position point which can be selected next step exists, pheromone updating is carried out, so that waiting during ant iteration is reduced, the repeated utilization rate of ants is increased, and the search efficiency is improved; and an obstacle avoidance function is introduced, so that the probability that ants select position points closer to the end point position is increased, the number of dead-locked ants is reduced, and the efficiency of searching global optimum by the ants in the whole algorithm is greatly improved.
In the embodiment of the present application, the device for determining a path may perform division of the functional modules or the functional units according to the above method example, for example, each functional module or functional unit may be divided corresponding to each function, or two or more functions may be integrated into one processing module. The integrated module may be implemented in a form of hardware, or may be implemented in a form of a software functional module or a functional unit. The division of the modules or units in the embodiment of the present application is schematic, and is only a logic function division, and there may be another division manner in actual implementation.
Fig. 5 shows a schematic diagram of a possible structure of the apparatus for determining a path according to the above embodiment. The apparatus includes a loop search module 204, a first update module 2051, a first determination module 2061, a second update module 2052, a first count detection module 207, and a second determination module 2062.
The loop search module 204 is configured to determine at least m paths between a start position and an end position through an ant colony algorithm; the m is used for representing the total ant number of the ant colony algorithm, the value of the m is greater than or equal to 1, the at least m paths comprise effective paths, and the effective paths comprise local optimal paths.
The first updating module 2051 is configured to update the pheromone on the effective path according to a first pheromone updating policy.
Wherein the first pheromone updating strategy is specifically a path between adjacent position points i and j<i,j>Upper, t1Pheromone tau at time + deltatij(t1+ Δ t) and t1Time of day pheromone tauij(t1) Satisfies the following formula:
τij(t1+Δt)＝τij(t1)+Δ*τij(t1,t1+Δt)
wherein, tauij(t1) Indicating the path after the end of the cycle<i,j>The pheromone of (a); delta*τijRepresenting a path<i,j>Pheromone increment on; EP represents the active path; LB represents a locally optimal path; re represents the ratio of the total effective path length to the locally optimal path length.
A first determining module 2061, configured to compare the existing global optimal path with the local optimal path, and determine a current global optimal path.
The second updating module 2052 is configured to update the pheromone on the current global optimal path according to a second pheromone updating policy.
Wherein the second pheromone updating strategy is specifically a path between adjacent position points i and j<i,j>Upper, t2Pheromone tau at time + deltatij(t2+ Δ t) and t2Time of day pheromone tauij(t2) Satisfies the following formula:
τij(t2+Δt)＝τij(t2)+Δ*τij(t2,t2+Δt)
wherein, tauij(t2) Indicating a post-pheromone path on the locally optimal path updated according to a first pheromone update policy<i,j>The pheromone of (a); q is a constant, representing pheromone concentration; l is*Representing a length of the global optimal path; GB denotes a global optimal path.
The first count detection module 2061 is configured to add one to the cycle number c, and determine whether the cycle number c reaches n times; if the cycle number c does not reach n times, indicating all the modules to sequentially execute the corresponding steps again; wherein the initial value of c is 0, n is used for representing the total cycle number, and the value of n is more than 1.
The second determining module 2062 is configured to determine, if the cycle number c reaches n times, a current global optimal path as a target path of the inspection robot, where the target path is used to indicate that the inspection robot reaches the end position from the start position along the target path.
Optionally, with reference to fig. 5 and as shown in fig. 6, the apparatus for determining a path provided in the embodiment of the present application may further include an environment modeling module 201, an algorithm initialization module 202, and an ant initialization module 203.
The environment modeling module 201 is configured to establish an environment model according to the environment information identified by the inspection robot sensor, where the environment model includes the start position and the end position.
The algorithm initialization module 202 is configured to initialize initial parameters of the ant colony algorithm, where the initial parameters include: the starting position of the path to be determined, the end position of the path to be determined, the total ant number m of the ant colony algorithm, and the total cycle number n.
The ant initialization module 203 is configured to set the search starting point of x ants in the m ants at the starting position, set the search starting points of the remaining m-x ants at the ending position, and set the value of x to be greater than 0 and smaller than m.
Optionally, with reference to fig. 5, as shown in fig. 7, in the apparatus for determining a path provided in the embodiment of the present application, the circular search module 204 includes a first selection unit 2041, a judgment unit 2042, a third update module 2043, a second selection unit 2044, a reverse search unit 2045, and a second count detection unit 2046.
The first selecting unit 2041 is configured to introduce an obstacle avoidance function, and select a next position point of the ant k by using a roulette method; the initial value of k is 1.
Wherein the obstacle avoidance function is:
wherein all iskAll the position points which can be selected by the ant k in the next step are shown; dijRepresents the distance between location point i and location point j; sg jRepresents the shortest distance from the position point j to the end position g; and s represents the position point of the next step of the ant corresponding to the shortest distance.
The first selecting unit 2041 is configured to, at time t, transfer an ant k from a location point i to a location point j according to a transfer probability pk ij(t) satisfies the following formula:
wherein alpha is a constant and represents an information heuristic factor; β is a constant, indicating a desired heuristic factor.
The determining unit 2042 is configured to determine whether the ant k searches for an effective path connecting the starting position and the ending position or does not have a next selectable position point, and if not, instruct the first selecting unit 2041 to perform a corresponding step.
The third updating unit 2043 is configured to perform single ant pheromone updating if the ant k searches for an effective path connecting the starting position and the ending position or there is no next selectable position point.
Wherein the single ant pheromone is updated specifically to be the path between the adjacent position points i and j<i,j>Pheromone tau at time t + DeltatijPheromone tau at (t + Deltat) and time tij(t) satisfies the following equation:
τij(t+Δt)＝(1-ρ)·τij(t)+Δτij k(t,t+Δt)
wherein the constant rho epsilon (0,1) represents a pheromone volatilization factor; tau isij(t) represents the path after searching the path<i,j>The pheromone of (a); delta tauij k(t) represents the ant k in the path after searching the path<i,j>Pheromone increment on; l iskRepresenting a path<i,j>Length of (d).
The second selecting unit 2044 is configured to randomly select whether the ant k needs to search in reverse direction if the ant k has searched for one of the effective paths.
The reverse search unit 2045 is configured to, if the ant k needs to perform reverse search, set the current location point as a search starting point, and instruct the first selection unit 2041, the determination unit 2042, the third update unit 2043, and the second selection unit 2044 to sequentially perform corresponding steps.
The second count detection unit 2046 is configured to determine whether k reaches m or not if the search is not performed in the reverse direction, and if k does not reach m, let k be k +1, and repeatedly execute the steps executed by all the modules.
According to the device for determining the path, provided by the embodiment of the application, the cyclic search is performed for c times by using m ants between the initial position and the final position of the path to be determined through an ant colony algorithm; setting the search starting points of x ants in the m ants at the initial positions, and setting the search starting points of the other m-x ants at the final positions; introducing a barrier avoidance function, and selecting the next position point of the ant k by using a roulette method; if the ant k searches for an effective path or no next selectable position point exists, updating the pheromone of a single ant; carrying out reverse search randomly; updating pheromones on the effective path according to a first pheromone updating strategy; and updating the pheromone on the current global optimal path according to a second pheromone updating strategy. According to the device for determining the path, pheromone updating is carried out on the principle that the contribution of ants for finding the optimal path in each cycle is large, namely, only pheromones on the effective path are increased, more pheromones are added on the local optimal path, and then pheromones on the global optimal path are additionally added, so that the convergence speed of an ant colony algorithm is increased, the algorithm can be prevented from falling into local optimization, and the speed and the accuracy for determining the path are improved; on the basis of bidirectional search, reverse search and single ant pheromone updating are introduced, namely if an effective path is obtained by ant search or no position point which can be selected next step exists, pheromone updating is carried out, so that waiting during ant iteration is reduced, the repeated utilization rate of ants is increased, and the search efficiency is improved; and an obstacle avoidance function is introduced, so that the probability that ants select position points closer to the end point position is increased, the number of dead-locked ants is reduced, and the efficiency of searching global optimum by the ants in the whole algorithm is greatly improved.
Fig. 8 shows a schematic diagram of another possible structure of the apparatus for determining a path according to the above embodiment. The device for determining the path comprises: a processor 301, the processor 301 configured to control and manage the actions of the apparatus, for example, perform the steps performed by the loop search module 204, the first update module 2051, the first determination module 2061, the second update module 2502, the first count detection module 207, the second determination module 2062, and/or other processes for performing the techniques described herein. The means for determining a path may further comprise a memory 302, a communication interface 303 and a bus 304, the communication interface 303 being adapted to support communication of the means for determining a path with other network entities, the memory 301 being adapted to store program codes and data of the means for determining a path.
The memory 301 may be a memory in a device for determining a path, etc., and the memory may include a volatile memory, such as a random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, a hard disk, or a solid state disk; the memory may also comprise a combination of memories of the kind described above.
The processor 302 may be implemented or performed with various illustrative logical blocks, modules, and circuits described in connection with the disclosure. The processor may be a central processing unit, general purpose processor, digital signal processor, application specific integrated circuit, field programmable gate array or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. The processor may also be a combination of computing functions, e.g., comprising one or more microprocessors, DSPs, and microprocessors, among others.
The bus 304 may be an Extended Industry Standard Architecture (EISA) bus or the like. The bus 304 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 8, but this is not intended to represent only one bus or type of bus.
Through the above description of the embodiments, it is clear to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional modules is merely used as an example, and in practical applications, the above function distribution may be completed by different functional modules according to needs, that is, the internal structure of the device may be divided into different functional modules to complete all or part of the above described functions. For the specific working processes of the system, the apparatus and the unit described above, reference may be made to the corresponding processes in the foregoing method embodiments, and details are not described here again.
The present application provides a computer program product containing instructions, which when run on a computer causes the computer to execute the method for determining a path according to the above method embodiments.
An embodiment of the present application further provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the network device executes the instructions, the network device executes each step executed by the apparatus for determining a path in the method flow shown in the foregoing method embodiment.
The computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM), a register, a hard disk, an optical fiber, a portable Compact Disc Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, any suitable combination of the above, or any other form of computer readable storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an Application Specific Integrated Circuit (ASIC). In embodiments of the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The above description is only an embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions within the technical scope of the present disclosure should be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A method of determining a path, for use with an inspection robot, the method comprising:
determining at least m paths between the starting position and the end position by an ant colony algorithm; the m is used for representing the total ant number of the ant colony algorithm, the value of the m is more than or equal to 1, the at least m paths comprise effective paths, and the effective paths comprise local optimal paths;
updating pheromones on the effective path according to a first pheromone updating strategy;
comparing the existing global optimal path with the local optimal path to determine the current global optimal path;
updating pheromones on the current global optimal path according to a second pheromone updating strategy;
adding one to the cycle number c, and if the cycle number c does not reach n times, repeating all the steps; wherein the initial value of c is 0, n is used for representing the total cycle number, and the value of n is more than 1;
and if the cycle number c reaches n times, determining a current global optimal path as a target path of the inspection robot, wherein the target path is used for indicating the inspection robot to reach the end point position from the starting position along the target path.
2. Method according to claim 1, characterized in that the first pheromone updating strategy is in particular a path between adjacent location points i and j<i,j>Upper, t1Pheromone tau at time + deltatij(t1+ Δ t) and t1Time of day pheromone tauij(t1) Satisfies the following formula:
τij(t1+Δt)＝τij(t1)+Δ*τij(t1,t1+Δt)
wherein the content of the first and second substances,
τij(t1) Indicating the path after the end of the cycle<i,j>The pheromone of (a); delta*τijRepresenting a path<i,j>Pheromone increment on; EP represents the active path; LB represents a locally optimal path; re represents the ratio of the total effective path length to the locally optimal path length.
3. The method of claim 1, wherein the first step is performedThe two-pheromone updating strategy is specifically that the path between the adjacent position points i and j<i,j>Upper, t2Pheromone tau at time + deltatij(t2+ Δ t) and t2Time of day pheromone tauij(t2) Satisfies the following formula:
τij(t2+Δt)＝τij(t2)+Δ*τij(t2,t2+Δt)
wherein the content of the first and second substances,
τij(t2) Indicating a post-pheromone path on the locally optimal path updated according to a first pheromone update policy<i,j>The pheromone of (a); q is a constant, representing pheromone concentration; l is*Representing a length of the global optimal path; GB denotes a global optimal path.
4. The method of any of claims 1-3, wherein prior to said determining at least m paths between the start and end positions by the ant colony algorithm, the method further comprises:
establishing an environment model according to the environment information identified by the inspection robot sensor, wherein the environment model comprises the starting position and the end position;
initializing initial parameters of the ant colony algorithm, the initial parameters comprising: the starting position of the path to be determined, the end position of the path to be determined, the total ant number m of the ant colony algorithm and the total cycle number n;
setting the search starting points of x ants in the m ants at the starting position, setting the search starting points of the other m-x ants at the end position, wherein the value of x is more than 0 and less than m.
5. The method according to any one of claims 1 to 3, wherein the determining at least m paths between the start position and the end position by the ant colony algorithm specifically comprises:
introducing a barrier avoidance function, and selecting the next position point of the ant k by using a roulette method; the initial value of k is 1;
judging whether the ant k searches for an effective path connecting the initial position and the end position or does not have a next selectable position point, if not, repeating the steps, and if so, updating the pheromone of a single ant;
if the ant k is searched to obtain the effective path, randomly selecting whether the ant k needs to be reversely searched;
if the ant k needs to search reversely, setting the current position point as a search starting point, repeating all the steps, and if the ant k does not search reversely, judging whether k reaches m;
and if k does not reach m, making k equal to k +1, and repeating all the steps.
6. The method of claim 5, wherein the obstacle avoidance function is:
wherein the content of the first and second substances,
allowkall the position points which can be selected by the ant k in the next step are shown; dijRepresents the distance between location point i and location point j; sg jRepresents the shortest distance from the position point j to the end position g; s represents the next position point of the ant corresponding to the shortest distance;
after the obstacle avoidance function is introduced, the next position point is selected by a roulette method, specifically, at the time t, an ant k is transferred from a position point i to a position point j according to a transfer probability pk ij(t) satisfies the following formula:
wherein the content of the first and second substances,
alpha is a constant and represents an information heuristic factor; β is a constant, indicating a desired heuristic factor.
7. A device for determining a path, applied to an inspection robot, comprising:
the loop search module is used for determining at least m paths between the starting position and the end position through an ant colony algorithm; the m is used for representing the total ant number of the ant colony algorithm, the value of the m is more than or equal to 1, the at least m paths comprise effective paths, and the effective paths comprise local optimal paths;
the first updating module is used for updating the pheromone on the effective path according to a first pheromone updating strategy;
the first determining module is used for comparing the existing global optimal path with the local optimal path and determining the current global optimal path;
the second updating module is used for updating the pheromone on the current global optimal path according to a second pheromone updating strategy;
the first counting detection module is used for adding one to the cycle number c and judging whether the cycle number c reaches n times; if the cycle number c does not reach n times, indicating all the modules to sequentially execute the corresponding steps again; wherein the initial value of c is 0, n is used for representing the total cycle number, and the value of n is more than 1;
and the second determining module is used for determining the current global optimal path as a target path of the inspection robot if the cycle number c reaches n times, wherein the target path is used for indicating the inspection robot to reach the end position from the starting position along the target path.
8. An apparatus for determining a path, the apparatus comprising: a processor, a transceiver, a communication interface, and a memory; wherein the memory is used to store one or more programs, the one or more programs including computer executable instructions, which when run by the apparatus, are executed by the processor to cause the apparatus to perform the method of determining a path of any one of claims 1 to 6.
9. A computer readable storage medium having stored therein instructions which, when executed by a computer, cause the computer to perform the method of determining a path of any of claims 1 to 6.
10. A computer program product, characterized in that it comprises a computer program which, when run on a computer, executes the method of determining a path according to any one of the preceding claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011141236.9A CN112183710B (en) | 2020-10-22 | 2020-10-22 | Method and device for determining path |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011141236.9A CN112183710B (en) | 2020-10-22 | 2020-10-22 | Method and device for determining path |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112183710A true CN112183710A (en) | 2021-01-05 |
| CN112183710B CN112183710B (en) | 2023-11-24 |
Family
ID=73923885
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011141236.9A Active CN112183710B (en) | 2020-10-22 | 2020-10-22 | Method and device for determining path |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112183710B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113050631A (en) * | 2021-03-11 | 2021-06-29 | 湖南大学 | Three-dimensional path planning method for electric automobile |
| CN113359761A (en) * | 2021-07-02 | 2021-09-07 | 广东电网有限责任公司 | Routing planning method and device for inspection path of robot for transformer substation and storage medium |
| CN113485360A (en) * | 2021-07-29 | 2021-10-08 | 福州大学 | AGV robot path planning method and system based on improved search algorithm |
| CN114995503A (en) * | 2022-06-16 | 2022-09-02 | 江西理工大学 | Unmanned aerial vehicle routing inspection path optimization method |
| CN115866071A (en) * | 2023-02-28 | 2023-03-28 | 中信云网有限公司 | Method and device for determining reporting path of initial equipment attribute information |
| CN116909320A (en) * | 2023-09-15 | 2023-10-20 | 众芯汉创(江苏)科技有限公司 | Electric power collaborative inspection strategy analysis method based on ant colony algorithm |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104199292A (en) * | 2014-08-11 | 2014-12-10 | 大连大学 | Method for planning space manipulator tail end effector avoidance path based on ant colony algorithm |
| CN106600049A (en) * | 2016-12-09 | 2017-04-26 | 国网北京市电力公司 | Path generation method and apparatus thereof |
| CN107272679A (en) * | 2017-06-15 | 2017-10-20 | 东南大学 | Paths planning method based on improved ant group algorithm |
| CN108413976A (en) * | 2018-01-23 | 2018-08-17 | 大连理工大学 | A kind of climbing robot intelligence paths planning method and system towards multi-state |
| WO2018156404A1 (en) * | 2017-02-23 | 2018-08-30 | Carrier Corporation | A control system and control method for building |
| CN108508745A (en) * | 2018-01-22 | 2018-09-07 | 中国铁道科学研究院通信信号研究所 | A kind of multiple target cycle tests collection optimization generation method |
| CN108563239A (en) * | 2018-06-29 | 2018-09-21 | 电子科技大学 | A kind of unmanned aerial vehicle flight path planing method based on potential field ant group algorithm |
| CN109164815A (en) * | 2018-09-06 | 2019-01-08 | 中国计量大学 | A kind of Autonomous Underwater Vehicle paths planning method based on improvement ant group algorithm |
| CN109214498A (en) * | 2018-07-10 | 2019-01-15 | 昆明理工大学 | Ant group algorithm optimization method based on search concentration degree and dynamic pheromone updating |
| CN109345008A (en) * | 2018-09-17 | 2019-02-15 | 摩佰尔（天津）大数据科技有限公司 | Automatic row's ship's method |
| CN111289007A (en) * | 2020-03-23 | 2020-06-16 | 南京理工大学 | Parking AGV path planning method based on improved ant colony algorithm |
| CN111382543A (en) * | 2020-03-13 | 2020-07-07 | 中国海洋石油集团有限公司 | Offshore cluster well drilling sequence optimization method based on improved ant colony algorithm |
| CN111539676A (en) * | 2020-05-12 | 2020-08-14 | 香港理工大学 | Network entity logistics system suitable for cross-border electronic commerce |
| 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 |
| CN111695668A (en) * | 2020-06-16 | 2020-09-22 | 江苏师范大学 | Ant colony algorithm optimization method based on reverse learning |
-
2020
- 2020-10-22 CN CN202011141236.9A patent/CN112183710B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104199292A (en) * | 2014-08-11 | 2014-12-10 | 大连大学 | Method for planning space manipulator tail end effector avoidance path based on ant colony algorithm |
| CN106600049A (en) * | 2016-12-09 | 2017-04-26 | 国网北京市电力公司 | Path generation method and apparatus thereof |
| WO2018156404A1 (en) * | 2017-02-23 | 2018-08-30 | Carrier Corporation | A control system and control method for building |
| CN107272679A (en) * | 2017-06-15 | 2017-10-20 | 东南大学 | Paths planning method based on improved ant group algorithm |
| CN108508745A (en) * | 2018-01-22 | 2018-09-07 | 中国铁道科学研究院通信信号研究所 | A kind of multiple target cycle tests collection optimization generation method |
| CN108413976A (en) * | 2018-01-23 | 2018-08-17 | 大连理工大学 | A kind of climbing robot intelligence paths planning method and system towards multi-state |
| CN108563239A (en) * | 2018-06-29 | 2018-09-21 | 电子科技大学 | A kind of unmanned aerial vehicle flight path planing method based on potential field ant group algorithm |
| CN109214498A (en) * | 2018-07-10 | 2019-01-15 | 昆明理工大学 | Ant group algorithm optimization method based on search concentration degree and dynamic pheromone updating |
| CN109164815A (en) * | 2018-09-06 | 2019-01-08 | 中国计量大学 | A kind of Autonomous Underwater Vehicle paths planning method based on improvement ant group algorithm |
| CN109345008A (en) * | 2018-09-17 | 2019-02-15 | 摩佰尔（天津）大数据科技有限公司 | Automatic row's ship's method |
| CN111382543A (en) * | 2020-03-13 | 2020-07-07 | 中国海洋石油集团有限公司 | Offshore cluster well drilling sequence optimization method based on improved ant colony algorithm |
| CN111289007A (en) * | 2020-03-23 | 2020-06-16 | 南京理工大学 | Parking AGV path planning method based on improved ant colony algorithm |
| CN111539676A (en) * | 2020-05-12 | 2020-08-14 | 香港理工大学 | Network entity logistics system suitable for cross-border electronic commerce |
| CN111695668A (en) * | 2020-06-16 | 2020-09-22 | 江苏师范大学 | Ant colony algorithm optimization method based on reverse 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 |
Non-Patent Citations (4)
| Title |
|---|
| JIANHUA LIU等: "An improved ant colony algorithm for robot path planning", 《SOFT COMPUTING》, vol. 21, pages 5829 - 5839, XP036327818, DOI: 10.1007/s00500-016-2161-7 * |
| 刘泽等: "基于改进蚁群算法的移动机器人二维路径规划", 《传感器与微系统》, vol. 39, no. 10, pages 149 - 152 * |
| 林玉龙: "复杂海洋环境中的无人船自主扫海路径规划研究", 《中国优秀硕士学位论文全文数据库_工程科技Ⅱ辑》, pages 036 - 300 * |
| 蒋华等: "基于蚁群的水下无线传感器网络能量路由协议", 《微电子学与计算机》, vol. 34, no. 08, pages 12 - 16 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113050631A (en) * | 2021-03-11 | 2021-06-29 | 湖南大学 | Three-dimensional path planning method for electric automobile |
| CN113359761A (en) * | 2021-07-02 | 2021-09-07 | 广东电网有限责任公司 | Routing planning method and device for inspection path of robot for transformer substation and storage medium |
| CN113359761B (en) * | 2021-07-02 | 2023-07-18 | 广东电网有限责任公司 | Method, device and storage medium for planning inspection path of robot for transformer substation |
| CN113485360A (en) * | 2021-07-29 | 2021-10-08 | 福州大学 | AGV robot path planning method and system based on improved search algorithm |
| CN114995503A (en) * | 2022-06-16 | 2022-09-02 | 江西理工大学 | Unmanned aerial vehicle routing inspection path optimization method |
| CN115866071A (en) * | 2023-02-28 | 2023-03-28 | 中信云网有限公司 | Method and device for determining reporting path of initial equipment attribute information |
| CN116909320A (en) * | 2023-09-15 | 2023-10-20 | 众芯汉创(江苏)科技有限公司 | Electric power collaborative inspection strategy analysis method based on ant colony algorithm |
| CN116909320B (en) * | 2023-09-15 | 2023-12-01 | 众芯汉创(江苏)科技有限公司 | Electric power collaborative inspection strategy analysis method based on ant colony algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112183710B (en) | 2023-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112183710A (en) | Method and device for determining path | |
| CN103994768B (en) | Method and system for seeking for overall situation time optimal path under dynamic time varying environment | |
| CN102176283B (en) | Traffic network simplifying model and navigating method based on same | |
| US20180089563A1 (en) | Decision making for autonomous vehicle motion control | |
| CN104050817B (en) | Speed limiting information base generation and speed limiting information detection method and system | |
| CN110570660A (en) | real-time online traffic simulation system and method | |
| CN104021674B (en) | A kind of quick and precisely prediction vehicle method by road trip time | |
| CN107367278A (en) | A kind of indoor navigation method and equipment | |
| CN113188562B (en) | Path planning method and device for travelable area, electronic equipment and storage medium | |
| CN111310992B (en) | Multi-unmanned aerial vehicle path optimization method for rapid evaluation after earthquake disaster | |
| CN112947591A (en) | Path planning method, device, medium and unmanned aerial vehicle based on improved ant colony algorithm | |
| JP2020042793A (en) | Obstacle distribution simulation method, device, and terminal based on probability plot | |
| CN109974729A (en) | Update method, the device and system of street view image | |
| CN113375689B (en) | Navigation method, navigation device, terminal and storage medium | |
| CN111737826B (en) | Rail transit automatic simulation modeling method and device based on reinforcement learning | |
| CN111161545B (en) | Intersection region traffic parameter statistical method based on video | |
| CN113899381B (en) | Method, apparatus, device, medium, and product for generating route information | |
| CN112764428B (en) | Spacecraft cluster reconstruction method and system | |
| CN114117752A (en) | Method and system for training reinforcement learning model of intelligent agent | |
| CN113895460A (en) | Pedestrian trajectory prediction method, device and storage medium | |
| CN110375735A (en) | Paths planning method and device | |
| CN115547050A (en) | Intelligent traffic signal control optimization method and software based on Markov decision process | |
| US20220300002A1 (en) | Methods and systems for path planning in a known environment | |
| CN114428889A (en) | Trajectory path binding method, model training method, device, equipment and storage medium | |
| KR20230024392A (en) | Driving decision making method and device and chip |
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 |