CN111426323B - Routing planning method and device for inspection robot - Google Patents
Routing planning method and device for inspection robot Download PDFInfo
- Publication number
- CN111426323B CN111426323B CN202010299152.1A CN202010299152A CN111426323B CN 111426323 B CN111426323 B CN 111426323B CN 202010299152 A CN202010299152 A CN 202010299152A CN 111426323 B CN111426323 B CN 111426323B
- Authority
- CN
- China
- Prior art keywords
- preset
- population
- routing inspection
- group
- filial generation
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
Abstract
The application discloses a routing planning method and a device for an inspection robot, wherein the method comprises the following steps: s1: calculating the fitness value of the individuals in the preset routing inspection line parent group through a preset fitness function; s2: performing cross operation of distant mating on a parent group of a preset routing inspection route, and selecting through a roulette algorithm to obtain a first offspring group; s3: performing mutation operation on the first filial generation population by adopting a preset self-adaptive probability to obtain a second filial generation population; s4: judging whether the second child population reaches a preset number, if so, executing S5, and if not, executing S2; s5: carrying out elimination operation and reverse mutation operation on the second filial generation population to obtain a third filial generation population; s6: and judging whether a better child individual does not appear after the iteration preset times, if so, calculating the fitness of the third generation child population to obtain an optimal routing inspection route, and if not, executing S1. The method and the device solve the technical problems that the convergence of the existing algorithm is poor and the existing algorithm is easy to fall into the local optimal solution.
Description
Technical Field
The application relates to the technical field of inspection robots, in particular to a routing planning method and device for an inspection robot.
Background
With the continuous development of economy, the electricity consumption of society rises rapidly, and the number of transformer substations also rises rapidly. The transformer substation is used as a node of a power grid and has a decisive significance for the safe operation of the power grid. The inspection work of the transformer substation site occupies an extremely important position in the aspect of ensuring the safe operation of the transformer substation site. However, the traditional inspection mode of the transformer substation is manual inspection, and the problems of low efficiency, non-uniform standard, high labor intensity of personnel, weather influence and the like exist. The operation automation of the power equipment shows the urgency, and various inspection robots are born by the way; how to improve the working efficiency of the inspection robot and how to complete the inspection task in the shortest time becomes an important research direction; how to find an optimal routing inspection route becomes a technical problem to be solved urgently.
The inspection robot in the transformer substation must move on a feasible path, the problem is different from the problem of classical path planning TSP, the conventional optimization algorithm is difficult to solve the problem, the genetic algorithm in the intelligent algorithm provided for path planning is one of the most extensive methods applied to the field of path planning, but the conventional genetic algorithm has the defects of poor convergence rate, easy falling into local optimal solution and the like.
Disclosure of Invention
The application provides a routing planning method and a routing planning device for an inspection robot, which are used for solving the technical problems that the convergence of the existing genetic algorithm for routing planning of the inspection robot is poor and the existing genetic algorithm is easy to fall into a local optimal solution.
In view of this, a first aspect of the present application provides a routing method for an inspection robot, including:
s1: calculating the fitness value of the individuals in the preset routing inspection line parent group through a preset fitness function;
s2: performing cross operation on the copied parent group of the preset routing inspection route in a distant mating mode, and performing group selection through a roulette algorithm to obtain a first child group;
s3: performing mutation operation on the first filial generation population by adopting a preset self-adaptive probability to obtain a second filial generation population;
s4: judging whether the second child population meets the requirement of a preset number, if so, executing step S5, otherwise, executing steps S2-S3 by taking the second child population as the parent population of the preset routing inspection route;
s5: carrying out elimination operation and reverse mutation operation on the copied second filial generation population to obtain a third filial generation population;
s6: and judging whether a better child individual does not appear after the iteration preset times, if so, calculating the fitness of the third generation child population to obtain an optimal routing inspection route corresponding to the maximum fitness value, and if not, executing the steps S1-S5.
Preferably, step S1 is preceded by:
s01: acquiring geometric features from an actual environment, and drawing a preset topological map, wherein the geometric features comprise line segments and angular points;
s02: fuzzifying an area which cannot be touched by the robot in the preset topological map to obtain an obstacle area;
s03: drawing an actual routing inspection route in a preset feasible area in the preset topological map, wherein the actual routing inspection route comprises a right-angle bend;
s04: and drawing the robot stop points in the preset topological map, wherein the number of the stop points is multiple.
Preferably, step S1 is preceded by:
numbering the stop points in the preset topological map without repeatability;
and generating the preset routing inspection route parent group according to the preset topological map and the stop points.
Preferably, step S2 includes:
copying the parent group of the preset routing inspection route according to a preset adaptive value;
performing cross operation on the copied preset routing inspection line parent population by adopting a preset distance probability to obtain a cross offspring population, wherein the preset distance probability is obtained by calculation according to the distance value between individuals in the preset routing inspection line parent population;
and carrying out selection operation on the crossed offspring population according to the roulette algorithm to obtain the first offspring population.
Preferably, step S3 is preceded by:
calculating according to a preset probability function to obtain the preset self-adaptive probability, wherein the preset probability function is as follows:
wherein, PmFor the preset adaptive probability, PmaxIs the maximum value of the variation probability, lambda is a preset fixed constant, U is a preset maximum iteration number, U is the current iteration number, and U belongs to [1, U]。
Preferably, step S5 includes:
deleting the copied bad individuals in the second filial generation population according to a preset elimination operator to obtain a third filial generation population;
and adding the updated population obtained after the reverse variation is carried out on all the bad individuals into the third generation sub-population.
The application second aspect provides a robot route planning device patrols and examines, includes:
the fitness calculation module is used for calculating the fitness value of the individuals in the preset routing inspection route parent group through a preset fitness function;
the cross selection module is used for carrying out cross operation on the copied parent group of the preset routing inspection route in a distant mating mode and carrying out group selection through a roulette algorithm to obtain a first child group;
the variation module is used for performing variation operation on the first filial generation group by adopting a preset self-adaptive probability to obtain a second filial generation group;
the first judgment module is used for judging whether the second filial generation group meets the requirement of the preset quantity, if so, the elimination reversing module is triggered, and if not, the second filial generation group is used as the preset routing inspection line parent generation group, and the cross selection module is triggered;
the elimination reversing module is used for carrying out elimination operation and reversing mutation operation on the copied second filial generation population to obtain a third filial generation population;
and the second judgment module is used for judging whether a better sub-population does not appear after the iteration preset times, if so, the fitness calculation is carried out on the third generation sub-population to obtain the optimal routing inspection route corresponding to the maximum fitness value, and if not, the fitness calculation module is triggered.
Preferably, the method further comprises the following steps:
the drawing module is used for acquiring geometric features from an actual environment and drawing a preset topological map, wherein the geometric features comprise line segments and angular points;
the fuzzy processing module is used for carrying out fuzzification processing on an area which cannot be touched by the robot in the preset topological map to obtain an obstacle area;
the route drawing module is used for drawing an actual routing inspection route in a preset feasible area in the preset topological map, and the actual routing inspection route comprises a right-angle bend;
the docking point drawing module is used for drawing the robot docking points in the preset topological map, and the number of the docking points is multiple;
the numbering module is used for numbering the stop points in the preset topological map in a non-repetitive manner;
and the generation module is used for generating the preset routing inspection route parent group according to the preset topological map and the stop points.
Preferably, the cross-selection module comprises:
the replication submodule is used for performing replication operation on the preset routing inspection line parent group according to a preset adaptation value;
the cross operation sub-module is used for carrying out cross operation on the copied preset routing inspection line parent population by adopting a preset distance probability to obtain a cross offspring population, and the preset distance probability is obtained by calculation according to the distance value between individuals in the preset routing inspection line parent population;
and the selection operation submodule is used for performing selection operation on the crossed offspring group according to the roulette algorithm to obtain the first offspring group.
Preferably, the reject reversal module comprises:
the eliminating submodule is used for deleting the copied bad individuals in the second filial generation population according to a preset eliminating operator to obtain a third filial generation population;
and the reversion submodule is used for adding an updated population obtained by performing reversion variation on all the bad individuals into the third generation subgroup.
According to the technical scheme, the embodiment of the application has the following advantages:
in the application, a routing planning method for an inspection robot is provided, which comprises the following steps: s1: calculating the fitness value of the individuals in the preset routing inspection line parent group through a preset fitness function; s2: performing cross operation on the copied preset routing inspection line parent group in a distant mating mode, and performing group selection through a roulette algorithm to obtain a first offspring group; s3: performing mutation operation on the first filial generation population by adopting a preset self-adaptive probability to obtain a second filial generation population; s4: judging whether the second child population meets the requirement of the preset number, if so, executing the step S5, otherwise, executing the steps S2-S3 by taking the second child population as a preset routing inspection route parent population; s5: carrying out elimination operation and reverse mutation operation on the copied second filial generation population to obtain a third filial generation population; s6: and judging whether a better child individual does not appear after the iteration preset times, if so, calculating the fitness of the third generation child population to obtain the optimal routing inspection route corresponding to the maximum fitness value, and if not, executing the steps S1-S5.
According to the routing planning method for the inspection robot, the inspection route of the robot is planned by adopting an improved genetic algorithm, the variation probability is higher when the evolution algebra is smaller, and the algorithm is required to be converged when the evolution enters the middle and later stages, so that the poor individuals are prevented from being introduced due to mutation, and therefore, the preset self-adaptive probability is adopted for carrying out variation operation, the variation probability is reduced in the middle and later stages, and the convergence speed of the algorithm is improved; poor population, namely individuals with poor fitness, can be removed by adopting elimination operation on the sub-generation population; in order to avoid routing inspection routes which do not meet the actual requirements, an inverse variation algorithm is adopted to process the filial generation group; the crossing operation by adopting the distant mating mode is to carry out crossing operation on individuals with larger differences, so that a new routing inspection route is obtained by each crossing operation, and the repeated condition cannot occur; the algorithm is optimized in a continuous planning space by means of elimination and reversion variation, and the algorithm is prevented from falling into a local optimal solution. Therefore, the method and the device can solve the technical problems that the existing genetic algorithm for routing inspection robot planning is poor in convergence and easy to fall into a local optimal solution.
Drawings
Fig. 1 is a schematic flow chart of a routing method for an inspection robot according to an embodiment of the present disclosure;
fig. 2 is another schematic flow chart of a routing method for an inspection robot according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a routing planning device of an inspection robot according to an embodiment of the present disclosure;
fig. 4 is a schematic diagram of a relationship between an inspection robot and an environment according to an embodiment of the present disclosure;
fig. 5 is a preset topological map after fuzzification processing provided in the embodiment of the present application;
fig. 6 is a distribution diagram of robot stop points in the preset topological map provided in the embodiment of the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
For easy understanding, referring to fig. 1, a first embodiment of a routing method for an inspection robot provided by the present application includes:
It should be noted that the preset fitness function is used for measuring the degree of each individual in the population approaching the optimal solution; regarding the robot as a particle, the optimal path should satisfy the shortest total length of the path, and thus a fitness function can be set; one individual in the preset routing inspection line parent group corresponds to one routing inspection line, and the fitness value of each routing inspection line needs to be obtained.
And 102, performing cross operation on the copied parent group of the preset routing inspection route in a distant mating mode, and performing group selection through a roulette algorithm to obtain a first child group.
The crossing operation method of distant mating means that a mutation probability required for crossing mutation is acquired according to the distance between individuals in a parent population, and then the crossing operation is performed, and the crossing operation of distant mating can avoid the occurrence of repeated individuals, that is, repeated routing inspection paths, in an obtained offspring population. The group selection of the roulette algorithm is to adapt to the genetic algorithm to carry out the operation of selecting the individuals from the group, the probability that the individual with a high fitness value is inherited to the next generation is higher, otherwise, the probability that the individual with a low fitness value is inherited to the next generation is lower, the roulette algorithm conforms to the rule, and the probability of the selected sequence is in direct proportion to the fitness value; the purpose of selection is to select a proper sequence from the parent generation group to be inherited to the next generation, and remove the improper sequence, so that the next generation group has better performance.
And 103, performing mutation operation on the first filial generation population by adopting a preset self-adaptive probability to obtain a second filial generation population.
It should be noted that the preset adaptive probability can be updated and changed according to actual requirements, and the mutation probability is relatively large when the iteration times of the genetic algorithm are relatively small; when the evolution iteration times are large, namely in the middle and later stages, the preset adaptive probability can reduce the variation probability, so that the convergence speed of the algorithm is improved; the specific process is that when the iteration times of the algorithm are small, in order to expand the search range of the optimal routing inspection route, the probability of variation can be improved by presetting the self-adaptive probability; but the mutation probability is gradually reduced along with the increase of the iteration number, thereby preventing the excellent individuals in the later period from introducing undesirable genes due to mutation.
And 104, judging whether the second filial generation group meets the preset quantity requirement, if so, executing step 105, and if not, executing step 102 and 103 by taking the second filial generation group as a preset routing inspection line parent group.
It should be noted that when the number of individuals in the obtained offspring population meets a certain requirement, the subsequent calculation can be continued, and the number is too small to meet the subsequent calculation requirement; the preset number can be set according to the actual condition, is not limited and is reasonable; the method is a method for expanding the search range of the optimal path, and obtains more offspring groups by mutation through the mutation probability, thereby meeting the requirement of the preset number.
And 105, carrying out elimination operation and reverse mutation operation on the copied second filial generation population to obtain a third filial generation population.
It should be noted that the elimination operation is mainly to delete some individuals with low fitness from the second generation sub-population, the specific deletion amount is determined according to the elimination rate, and the elimination rate is a parameter that can be set according to actual conditions and is not limited; and then, carrying out reverse mutation operation on the deleted individuals to obtain a new population, and adding the new population into a third filial generation population, so that not only can the diversity of the individuals be ensured, but also the bad individuals can be removed, and the convergence rate of the algorithm can be improved from the interior of the population.
And step 106, judging whether a better sub-population does not appear after the iteration preset times, if so, calculating the fitness of the third generation sub-population to obtain the optimal routing inspection route corresponding to the maximum fitness value, and if not, executing the step 101-105.
It should be noted that if the obtained individuals in the offspring population are not more excellent than the individuals obtained by the previous iteration, and such a situation reaches a certain number of times, namely a preset number of times, the iteration operation can be ended; the optimal routing inspection route is selected from the third generation of sub-population, and the selected index is the maximum fitness value; and calculating the fitness values of all individuals in the third generation sub-population, and obtaining the largest corresponding individual, namely the optimal individual, so as to obtain the optimal routing inspection route.
According to the routing planning method for the inspection robot, the inspection route of the robot is planned by adopting an improved genetic algorithm, the variation probability is higher when the evolution algebra is smaller, and the algorithm is required to be converged when the evolution enters the middle and later stages, so that the poor individuals are prevented from being introduced due to mutation, and therefore, the preset self-adaptive probability is adopted for carrying out variation operation, the variation probability is reduced in the middle and later stages, and the convergence speed of the algorithm is improved; poor population, namely individuals with poor fitness, can be removed by adopting elimination operation on the sub-generation population; in order to avoid routing inspection routes which do not meet the actual requirements, an inverse variation algorithm is adopted to process the filial generation group; the crossing operation by adopting the distant mating mode is to carry out crossing operation on individuals with larger differences, so that a new routing inspection route is obtained by each crossing operation, and the repeated condition cannot occur; the algorithm is optimized in a continuous planning space by means of elimination and reversion variation, and the algorithm is prevented from falling into a local optimal solution. Therefore, the method and the device can solve the technical problems that the existing genetic algorithm for routing inspection robot planning is poor in convergence and easy to fall into a local optimal solution.
For convenience of understanding, please refer to fig. 2, an embodiment two of a routing method for an inspection robot is provided in the embodiment of the present application, including:
Please refer to fig. 4, the interaction between the inspection robot and the environment mainly includes detection, navigation and actual environment; navigation is carried out according to a path planning scheme formulated by an actual environment, so that drawing of a preset topological map according to the environment is a very critical operation, and the obtained geometric features can be used for drawing the map and also can be used for target identification and autonomous positioning of the robot; the preset topological map reserves the connectivity and relative position relation of the line segment and the corner point.
It should be noted that, referring to fig. 5, an actual environment map of the substation is static and known, but a navigation process performed according to an actual situation is too complicated to perform fixed point identification and route planning, and therefore, a preset topology map needs to be fuzzified, a region that cannot be touched by the robot is fuzzified into an obstacle region, and then a preset feasible region, that is, a space where the inspection robot can move, is obtained according to the obstacle region, that is, a gap between the obstacle regions.
And 203, drawing an actual routing inspection route in a preset feasible area in the preset topological map, wherein the actual routing inspection route comprises a right-angle bend.
It should be noted that the correlation between the actual routing inspection route and the actual environment needs to be maintained, the routing inspection route is drawn at the middle position of the road in the preset feasible region, the same distance is kept between the routing inspection route and the obstacle regions on the two sides of the road, and the routing inspection robot can be prevented from being transversely dislocated.
And 204, drawing the robot stop points in a preset topological map, wherein the number of the stop points is multiple.
And step 205, carrying out non-repetitive numbering on the stop points in the preset topological map.
Please refer to fig. 6, which is only an example of the stop point labeling in the preset topological map of the present embodiment, and does not limit the unique stop point labeling manner in the present embodiment; the stop points associated with the actual environment are drawn on the preset topological map, and a non-repetitive serial number is added to each stop point, so that the subsequent route searching and planning are facilitated.
And step 206, generating a preset routing inspection route parent group according to the preset topological map and the stop points.
It should be noted that, the stop point No. 1 in fig. 6 is used as the initial stop point, the robot returns to the initial stop point after all the stop points are inspected from the initial stop point, and the sequence can be obtained according to the arrangement of the stop points on the inspection route of the inspection robot
Thereby generating a series of tour route sets,
representing the ith routing inspection route in the kth generation group, wherein k is 1 in the parent generation group, and the total length of each routing inspection route can be obtained according to the sequence set:
wherein the content of the first and second substances,
the total length of the ith routing inspection route in the kth generation group is B, and the length from the jth stop point to the j +1 th stop point in the kth generation group is B. The shortest routing inspection route in the kth generation group can be as follows:
and N is the total number of the routing inspection routes.
And step 207, calculating the fitness value of the individuals in the preset routing inspection route parent group through a preset fitness function.
It should be noted that the preset fitness function is used for measuring the degree of each individual in the population approaching the optimal solution; regarding the robot as a particle, the optimal path should satisfy the shortest total length of the path, and thus a fitness function can be set; one individual in the preset routing inspection line parent group corresponds to one routing inspection line, and the fitness value of each routing inspection line needs to be obtained. The fitness function in this embodiment is set according to the total length of the routing inspection route:
wherein, FiFor the fitness function, beta is a correlation coefficient, can be set according to actual conditions, and can find that the fitness value of each individual, namely the routing inspection route, is inversely proportional to the total length of the routing inspection route.
And 208, copying the preset routing inspection line parent group according to the preset adaptive value.
It should be noted that, in the process of the copying operation, the preset adaptive value of each sequence is calculated according to the total length of the routing inspection route corresponding to the sequence, and then the copying is performed according to the probability calculated by the preset adaptive value; if 2n copies are needed to perform the subsequent interleaving operation. Firstly, calculating a preset adaptive value, wherein the preset adaptive value of the ith routing inspection route in the kth generation group is as follows:
then, the probability that the ith routing inspection route in the kth generation group is selected is as follows:
and selecting the routing inspection route set according to the probability, and copying 2N routing inspection routes, wherein 2N is less than N.
And 209, performing cross operation on the copied preset routing inspection route parent population by adopting a preset distance probability to obtain a cross child population.
The preset distance probability is calculated according to the distance value between individuals in the preset routing inspection route parent group; the cross operation is a process of calculating the probability of the routing inspection routes obtained by copying in the cross area according to the distance between the routing inspection routes and then pairing the routing inspection routes according to the probability; suppose a routing inspection route
Calculating the distance between the routing inspection route and other routing inspection routes in the intersection area:
wherein x and y represent routing inspection routes respectively
The coordinates of (a). Then the probability that the ith routing inspection route in the low-k generation group crossing area is selected is as follows:
according to probability
Selecting a route to be inspected and a route to be inspected, i.e. a sequence
And matching to complete the cross recombination of one routing inspection route, wherein the number of the new routing inspection routes finally obtained by the cross recombination is 2 n.
And step 210, carrying out selection operation on the crossed offspring group according to a roulette algorithm to obtain a first offspring group.
It should be noted that the group selection of the roulette algorithm is an operation of adapting the genetic algorithm to make the individuals in the group win or lose, the probability that the individual with a large fitness value is inherited to the next generation is larger, otherwise, the probability that the individual with a small fitness value is inherited to the next generation is smaller, the roulette algorithm is in compliance with the rule, and the probability that the sequence is selected is in direct proportion to the fitness value; the purpose of selection is to select a proper sequence from the parent generation group to be inherited to the next generation, and remove the improper sequence, so that the next generation group has better performance. The probability that the patrol route is inherited to the next generation population in this embodiment can be expressed as:
and step 211, calculating according to a preset probability function to obtain a preset adaptive probability.
And 212, performing mutation operation on the first filial generation group by adopting a preset self-adaptive probability to obtain a second filial generation group.
It should be noted that the preset adaptive probability can be updated and changed according to actual requirements, and the mutation probability is relatively large when the iteration times of the genetic algorithm are relatively small; when the evolution iteration times are large, namely in the middle and later stages, the preset adaptive probability can reduce the variation probability, so that the convergence speed of the algorithm is improved; the specific process is that when the iteration times of the algorithm are small, in order to expand the search range of the optimal routing inspection route, the probability of variation can be improved by presetting the self-adaptive probability; but the mutation probability is gradually reduced along with the increase of the iteration number, thereby preventing the excellent individuals in the later period from introducing undesirable genes due to mutation. Because the single variable adopts the exponential function to fit the variation performance, which is more suitable for the evolution process of the population, the preset probability function in this embodiment is:
wherein, PmFor presetting the adaptive probability, PmaxIs the maximum value of the variation probability, lambda is a preset fixed constant, U is a preset maximum iteration number, U is the current iteration number, and U belongs to [1, U]。
It should be noted that, when the number of individuals in the obtained offspring population meets a certain requirement, subsequent calculation can be performed, and the number is too small to meet the subsequent calculation requirement; the preset number can be set according to the actual condition, is not limited and is reasonable; the method is a method for expanding the search range of the optimal path, and obtains more offspring groups by mutation through the mutation probability, thereby meeting the requirement of the preset number.
And 214, deleting the bad individuals in the copied second filial generation population according to a preset eliminating operator to obtain a third filial generation population.
It should be noted that, in order to improve the convergence rate, a culling operator is introduced, the iterated offspring can be calculated to obtain different fitness values, a specific culling rate is set, and individuals in the culling rate are deleted from the population, so that bad genes in the population can be removed, and the excellence degree of the individuals in the population is improved.
And step 215, adding an updated population obtained by carrying out reverse variation on all the bad individuals into the third generation sub-population.
It should be noted that the eliminated individuals are not directly discarded, in order to ensure the diversity of the individuals in the population and ensure the stability of the number of the individuals, the embodiment performs reverse mutation operation on the eliminated bad individuals to obtain an updated population, which is no longer within the range of elimination rate, and the updated population is added into the third filial generation population, so that the number of the individuals in the population is not changed, but the diversity of the individuals can be ensured, thereby improving the convergence rate of the algorithm.
And step 216, judging whether a better sub-population does not appear after the iteration preset times, if so, calculating the fitness of the third generation sub-population to obtain the optimal routing inspection route corresponding to the maximum fitness value, and if not, executing step 207-215.
It should be noted that if the obtained individuals in the offspring population are not more excellent than the individuals obtained by the previous iteration, and such a situation reaches a certain number of times, namely a preset number of times, the iteration operation can be ended; the optimal routing inspection route is selected from the third generation of sub-population, and the selected index is the maximum fitness value; and calculating the fitness values of all individuals in the third generation sub-population, and obtaining the largest corresponding individual, namely the optimal individual, so as to obtain the optimal routing inspection route. If the preset condition is not met, the iteration is required to be continued until the condition is met.
For easy understanding, please refer to fig. 3, an embodiment of the routing device for inspection robots is further provided in the present application, including:
the fitness calculation module 301 is used for calculating the fitness of individuals in a preset routing inspection route parent group through a preset fitness function;
the cross selection module 302 is used for performing cross operation on the copied parent group of the preset routing inspection route in a distant mating mode, and performing group selection through a roulette algorithm to obtain a first child group;
a mutation module 303, configured to perform mutation operation on the first progeny population by using a preset adaptive probability to obtain a second progeny population;
the first judgment module 304 is used for judging whether the second filial generation group meets the requirement of the preset quantity, if so, the elimination reversing module is triggered, and if not, the second filial generation group is used as a preset routing inspection route parent group, and the cross selection module is triggered;
a elimination reversal module 305, configured to perform elimination operation and reversal mutation operation on the copied second progeny population to obtain a third progeny population;
the second judging module 306 is configured to judge whether a better sub-population does not appear after the iteration for the preset number of times, if so, perform fitness calculation on the third-generation sub-population to obtain an optimal routing inspection route corresponding to the maximum fitness value, and if not, trigger the fitness calculating module.
Further, still include:
the drawing module 307 is configured to obtain geometric features from an actual environment, and draw a preset topological map, where the geometric features include line segments and corner points;
the fuzzy processing module 308 is configured to perform fuzzy processing on an area, which is not touched by the robot, in the preset topological map to obtain an obstacle area;
the route drawing module 309 is used for drawing an actual routing inspection route in a preset feasible region in a preset topological map, wherein the actual routing inspection route comprises a right-angle bend;
the docking point drawing module 310 is configured to draw a plurality of robot docking points in a preset topological map;
the numbering module 311 is configured to number the stop points in the preset topological map without repeatability;
the generating module 312 is configured to generate a preset routing inspection route parent group according to the preset topological map and the stop points.
Further, the cross-selection module 302 includes:
the replication sub-module 3021 is configured to perform replication operation on a preset routing inspection parent group according to a preset adaptation value;
the intersection operation sub-module 3022 is configured to perform intersection operation on the copied preset routing inspection parent population by using a preset distance probability to obtain an intersection child population, where the preset distance probability is calculated according to a distance value between individuals in the preset routing inspection parent population;
and the selection operation submodule 3023 is configured to perform selection operation on the crossed offspring population according to a roulette algorithm to obtain a first offspring population.
Further, the culling reversal module 305 includes:
the eliminating submodule 3051 is used for deleting the bad individuals in the copied second filial generation population according to a preset eliminating operator to obtain a third filial generation population;
and the reversion submodule 3052 is used for adding an updated population obtained by performing reversion variation on all the bad individuals into the third generation subgroup.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for executing all or part of the steps of the method described in the embodiments of the present application through a computer device (which may be a personal computer, a server, or a network device). And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (8)
1. A routing method for an inspection robot is characterized by comprising the following steps:
s1: calculating the fitness value of the individuals in the preset routing inspection line parent group through a preset fitness function;
s2: performing cross operation on the copied parent group of the preset routing inspection route in a distant mating mode, and performing group selection through a roulette algorithm to obtain a first child group;
s3: performing mutation operation on the first filial generation population by adopting a preset self-adaptive probability to obtain a second filial generation population;
s4: judging whether the second child population meets the requirement of a preset number, if so, executing step S5, otherwise, executing steps S2-S3 by taking the second child population as the parent population of the preset routing inspection route;
s5: deleting the copied bad individuals in the second filial generation population according to a preset eliminating operator to obtain a third filial generation population, and adding an updated population obtained by carrying out reverse variation on all the bad individuals into the third filial generation population;
s6: and judging whether a more optimal offspring individual does not appear after the iteration preset times, if so, calculating the fitness of the third offspring population to obtain an optimal routing inspection route corresponding to the maximum fitness value, and if not, executing the steps S1-S5.
2. The inspection robot path planning method according to claim 1, wherein the step S1 is preceded by:
s01: acquiring geometric features from an actual environment, and drawing a preset topological map, wherein the geometric features comprise line segments and angular points;
s02: fuzzifying an area which cannot be touched by the robot in the preset topological map to obtain an obstacle area;
s03: drawing an actual routing inspection route in a preset feasible area in the preset topological map, wherein the actual routing inspection route comprises a right-angle bend;
s04: and drawing the robot stop points in the preset topological map, wherein the number of the stop points is multiple.
3. The inspection robot path planning method according to claim 1, wherein the step S1 is preceded by:
carrying out non-repetitive numbering on stop points in a preset topological map;
and generating the preset routing inspection route parent group according to the preset topological map and the stop points.
4. The routing method for the inspection robots according to claim 1, wherein the step S2 includes:
copying the parent group of the preset routing inspection route according to a preset adaptive value;
performing cross operation on the copied preset routing inspection line parent population by adopting a preset distance probability to obtain a cross offspring population, wherein the preset distance probability is obtained by calculation according to the distance value between individuals in the preset routing inspection line parent population;
and carrying out selection operation on the crossed offspring population according to the roulette algorithm to obtain the first offspring population.
5. The inspection robot path planning method according to claim 1, wherein the step S3 is preceded by:
calculating according to a preset probability function to obtain the preset self-adaptive probability, wherein the preset probability function is as follows:
wherein, PmFor the preset adaptive probability, PmaxIs the maximum value of the variation probability, lambda is a preset fixed constant, U is a preset maximum iteration number, U is the current iteration number, and U belongs to [1, U]。
6. The utility model provides a patrol and examine robot route planning device which characterized in that includes:
the fitness calculation module is used for calculating the fitness value of the individuals in the preset routing inspection route parent group through a preset fitness function;
the cross selection module is used for carrying out cross operation on the copied parent group of the preset routing inspection route in a distant mating mode and carrying out group selection through a roulette algorithm to obtain a first child group;
the variation module is used for performing variation operation on the first filial generation group by adopting a preset self-adaptive probability to obtain a second filial generation group;
the first judgment module is used for judging whether the second filial generation group meets the requirement of the preset quantity, if so, the elimination reversing module is triggered, and if not, the second filial generation group is used as the preset routing inspection line parent generation group, and the cross selection module is triggered;
the elimination reversing module is used for deleting the copied bad individuals in the second filial generation population according to a preset elimination operator to obtain a third filial generation population, and adding an updated population obtained by reversing and mutating all the bad individuals into the third filial generation population;
and the second judgment module is used for judging whether a better filial generation individual does not appear after the iteration preset times, if so, the fitness calculation is carried out on the third filial generation group to obtain the optimal routing inspection route corresponding to the maximum fitness value, and if not, the fitness calculation module is triggered.
7. The inspection robot path planning apparatus according to claim 6, further comprising:
the drawing module is used for acquiring geometric features from an actual environment and drawing a preset topological map, wherein the geometric features comprise line segments and angular points;
the fuzzy processing module is used for carrying out fuzzification processing on an area which cannot be touched by the robot in the preset topological map to obtain an obstacle area;
the route drawing module is used for drawing an actual routing inspection route in a preset feasible area in the preset topological map, and the actual routing inspection route comprises a right-angle bend;
the docking point drawing module is used for drawing the robot docking points in the preset topological map, and the number of the docking points is multiple;
the numbering module is used for numbering the stop points in the preset topological map in a non-repetitive manner;
and the generation module is used for generating the preset routing inspection route parent group according to the preset topological map and the stop points.
8. The inspection robot path planning apparatus according to claim 6, wherein the cross-selection module includes:
the replication submodule is used for performing replication operation on the preset routing inspection line parent group according to a preset adaptation value;
the cross operation sub-module is used for carrying out cross operation on the copied preset routing inspection line parent population by adopting a preset distance probability to obtain a cross offspring population, and the preset distance probability is obtained by calculation according to the distance value between individuals in the preset routing inspection line parent population;
and the selection operation submodule is used for performing selection operation on the crossed offspring group according to the roulette algorithm to obtain the first offspring group.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010299152.1A CN111426323B (en) | 2020-04-16 | 2020-04-16 | Routing planning method and device for inspection robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010299152.1A CN111426323B (en) | 2020-04-16 | 2020-04-16 | Routing planning method and device for inspection robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111426323A CN111426323A (en) | 2020-07-17 |
| CN111426323B true CN111426323B (en) | 2022-04-12 |
Family
ID=71557933
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010299152.1A Active CN111426323B (en) | 2020-04-16 | 2020-04-16 | Routing planning method and device for inspection robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111426323B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111813124B (en) * | 2020-07-22 | 2022-08-19 | 浙江迈睿机器人有限公司 | Mobile robot hybrid scheduling method based on topological map |
| CN112381964B (en) * | 2020-11-12 | 2023-04-25 | 国网山东省电力公司泰安供电公司 | Power line inspection configuration method and system |
| CN115451974B (en) * | 2022-11-09 | 2023-04-07 | 广东电网有限责任公司湛江供电局 | Power equipment routing inspection path planning method, system, equipment and medium |
| CN115952942B (en) * | 2023-03-13 | 2023-06-02 | 季华实验室 | Multi-target inspection scheduling planning method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101699514A (en) * | 2009-10-30 | 2010-04-28 | 西安电子科技大学 | Immune clone quantum clustering-based SAR image segmenting method |
| CN108919641A (en) * | 2018-06-21 | 2018-11-30 | 山东科技大学 | A kind of unmanned aerial vehicle flight path planing method based on improvement cup ascidian algorithm |
| CN109192284A (en) * | 2018-07-13 | 2019-01-11 | 广东工业大学 | A method of service role is dispatched under the remote health monitoring line with weak rock mass |
| CN110347151A (en) * | 2019-05-31 | 2019-10-18 | 河南科技大学 | A kind of robot path planning method merging Bezier optimized Genetic Algorithm |
| CN110930182A (en) * | 2019-11-08 | 2020-03-27 | 中国农业大学 | Improved particle swarm optimization algorithm-based client classification method and device |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004104172A2 (en) * | 2003-05-15 | 2004-12-02 | Bioarray Solutions, Ltd. | Hybridization-mediated analysis of polymorphisms |
| CN108846472A (en) * | 2018-06-05 | 2018-11-20 | 北京航空航天大学 | A kind of optimization method of Adaptive Genetic Particle Swarm Mixed Algorithm |
| CN110243373B (en) * | 2019-06-25 | 2022-09-20 | 武汉工程大学 | Path planning method, device and system for dynamic storage automatic guided vehicle |
-
2020
- 2020-04-16 CN CN202010299152.1A patent/CN111426323B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101699514A (en) * | 2009-10-30 | 2010-04-28 | 西安电子科技大学 | Immune clone quantum clustering-based SAR image segmenting method |
| CN108919641A (en) * | 2018-06-21 | 2018-11-30 | 山东科技大学 | A kind of unmanned aerial vehicle flight path planing method based on improvement cup ascidian algorithm |
| CN109192284A (en) * | 2018-07-13 | 2019-01-11 | 广东工业大学 | A method of service role is dispatched under the remote health monitoring line with weak rock mass |
| CN110347151A (en) * | 2019-05-31 | 2019-10-18 | 河南科技大学 | A kind of robot path planning method merging Bezier optimized Genetic Algorithm |
| CN110930182A (en) * | 2019-11-08 | 2020-03-27 | 中国农业大学 | Improved particle swarm optimization algorithm-based client classification method and device |
Non-Patent Citations (2)
| Title |
|---|
| 基于改进遗传算法的矿山救援机器人路径规划;周栾 等;《煤炭技术》;20190630;第38卷(第06期);第139-142页 * |
| 基于改进遗传算法的移动机器人路径规划研究;田欣;《中国优秀硕士学位论文全文数据库 信息科技辑》;20170215;第I140-136页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111426323A (en) | 2020-07-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111426323B (en) | Routing planning method and device for inspection robot | |
| Ramirez-Rosado et al. | Genetic algorithms applied to the design of large power distribution systems | |
| Chen et al. | Patrol robot path planning in nuclear power plant using an interval multi-objective particle swarm optimization algorithm | |
| CN107133704A (en) | Follow the analogy method of the dynamic emergency evacuation of large-scale crowd of optimal-forgetting rules | |
| Li | Path planning of intelligent mobile robot based on Dijkstra algorithm | |
| Zhang et al. | Robot path planning based on genetic algorithm with hybrid initialization method | |
| Ewing et al. | Betweenness centrality in multi-agent path finding | |
| Liu et al. | Path planning of mobile robots based on improved Genetic algorithm | |
| CN114244774A (en) | LEO satellite network congestion avoidance multicast routing algorithm based on swarm intelligence | |
| Xia et al. | Robot path planning based on multi-objective optimization with local search | |
| Zhang et al. | Global path planning for mobile robot based on A∗ algorithm and genetic algorithm | |
| Zhang et al. | Optimal inspection path planning of substation robot in the complex substation environment | |
| Wang | Optimal scheduling of flow shop based on genetic algorithm | |
| CN116432077A (en) | Intelligent station secondary system fault positioning method based on optimized BP neural network | |
| CN116307325A (en) | Line planning method and device for power distribution network, electronic equipment and storage medium | |
| Zhan | Research on path planning method of humanoid robot based on improved genetic algorithm | |
| Zhao et al. | Path planning based on multi-objective topological map | |
| CN112288863B (en) | Map construction method in robot synchronous positioning and composition navigation | |
| CN110571791B (en) | Optimal configuration method for power transmission network planning under new energy access | |
| CN114779788A (en) | Path planning method for improving A-algorithm | |
| Fengchun et al. | Research on Power Grid Inspection Path Based on Edge Computing | |
| CN114465216A (en) | Active power distribution network fault recovery method based on MO-CGABC | |
| Boğar et al. | A hybrid genetic algorithm for mobile robot shortest path problem | |
| Lanfeng et al. | Lunar Rover Path Planning Based on Comprehensive Genetic Algorithm Based on Slip Prediction | |
| Zhang et al. | Multi-objective layout optimization of aircraft multi-branch cable harness based on MOPSO/D |
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 |