CN111401745B - 5G-based routing inspection robot cluster task allocation method and system - Google Patents
5G-based routing inspection robot cluster task allocation method and system Download PDFInfo
- Publication number
- CN111401745B CN111401745B CN202010185558.7A CN202010185558A CN111401745B CN 111401745 B CN111401745 B CN 111401745B CN 202010185558 A CN202010185558 A CN 202010185558A CN 111401745 B CN111401745 B CN 111401745B
- Authority
- CN
- China
- Prior art keywords
- inspection
- robot
- task
- tasks
- cost
- 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
- 238000007689 inspection Methods 0.000 title claims abstract description 132
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000004891 communication Methods 0.000 claims abstract description 6
- 230000035772 mutation Effects 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 6
- 108090000623 proteins and genes Proteins 0.000 claims description 6
- 239000012634 fragment Substances 0.000 claims description 5
- 230000002068 genetic effect Effects 0.000 abstract description 10
- 238000011156 evaluation Methods 0.000 description 2
- 238000010187 selection method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010353 genetic engineering Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000000178 monomer Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Manipulator (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Numerical Control (AREA)
Abstract
A5G-based routing inspection robot cluster task allocation method and system can solve the technical problems of unbalanced task allocation and low actual efficiency of the existing robot task allocation method. The invention is based on a robot cluster and a 5G base station, and comprises the following steps: carrying out inspection task planning on the robot cluster; calculating the cost of the inspection robot in the task execution process from three dimensions of time, distance and utility; distributing the inspection tasks; and sending a routing inspection instruction to the robot cluster through the 5G base station. The invention adopts 5G to solve the communication requirements of high speed, low delay and wide link when robot cluster tasks are distributed. By improving the genetic algorithm, the problems of slow convergence and closed competition in the task allocation process of the robot cluster are solved, and the task allocation efficiency is improved.
Description
Technical Field
The invention relates to the field of 5G robots, in particular to a 5G-based routing inspection robot cluster task allocation method and system.
Background
The inspection robot is guided by robot replacement under the background of 4.0 industry, and meets the unattended demands of various industries such as electric power, traffic, hospitals and the like. The inspection robot carries equipment such as an industrial camera, an infrared thermal imager, a temperature and humidity detector, a mechanical arm and the like and sensors through a moving platform which runs autonomously, and performs the monitoring of the equipment, the recording of data, the troubleshooting of faults and the like.
At present, the task scheduling of the inspection robot mostly takes a robot monomer as an object, and the existing network technology can only meet the current application requirements. In some large places, a plurality of robots, even a robot cluster, are needed to carry out inspection work, so that manual work is comprehensively replaced.
As inspection robots mature and become popular, the demand for robot cluster scheduling is also becoming stronger. The 5G high rate, low latency and wide link provide network support for scheduling of robot clusters. Robot cluster inspection often has a large number of inspection tasks and a certain number of inspection robots. The task allocation problem of the robot cluster is a key link of the robot cluster scheduling, and the allocation result directly influences the efficiency of robot inspection.
The task allocation of the inspection robot cluster is that a plurality of tasks are allocated to different robots in the system, so that the purposes of shortest total inspection time, lowest consumption, highest task completion degree and the like are achieved. The task allocation algorithm of the robot cluster at the present stage mostly aims at optimizing single indexes such as a total path or total time, so that the task allocation of each robot is unbalanced, and the actual efficiency is low.
Disclosure of Invention
The invention provides a 5G-based inspection robot cluster task allocation method and system, which can solve the technical problems of unbalanced task allocation and low actual efficiency of the existing robot task allocation method.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
A5G-based routing inspection robot cluster task allocation method is based on a robot cluster and a 5G base station and is characterized in that:
the method comprises the following steps:
s100, carrying out inspection task planning on a robot cluster;
s200, calculating the cost of the inspection robot in the task execution process from three dimensions of time, distance and utility;
s300, distributing the inspection tasks;
s400, sending a routing inspection instruction to the robot cluster through the 5G base station.
Wherein,
s100, carrying out inspection task planning on a robot cluster; the method comprises n inspection tasks to be executed: t= { T 1 ，t 2 ，…，t n One patrol point corresponding to each task: l= { L 1 ，l 2 ，…，l n }. The inspection robot cluster comprises m robot clusters capable of performing inspection tasks: r= { R 1 ，r 2 ，…，r m }。
Further, the inspection task cost in S200 is measured by three indexes, namely, a time cost, a path cost and a utility cost required for completing the inspection task. The following method is specifically adopted.
Inspection task t i And inspection task t j The distance cost between the two is c ij . Robot r i And inspection task t j Is the distance cost d ij . Robot executes inspection task t i The own journey cost is w i 。
The inspection tasks are divided into m groups: t= { T 1 ，T 2 ，…，T m }，T i Representation robot r i And distributing the obtained tasks. Robot r i There are k tasks: t (T) i1 ＝{t i1 ，t i2 ，...，t ik }。T i The sum of the journey costs of all the tasks in the network is W (r) i )＝w i1 +w i2 +...+w ik 。
The total path cost of a single robot is D { r } i ，T i }＝Dr i t i1 +∑k-1 j＝1ct ij t i(j+1) +W(r i ). Wherein Dr is i t i Representation robot r i From the initial position to the first inspection task t i1 Required path cost Σk-1 j =1ct ij t i(j+1) Representing the total path cost between the other k-1 tasks.
The time cost is: tt=max iD { r i ，T i }
The path cost is: dd= Σ m i =1d { r i ，T i }
The utility cost is: ee=min i D{r i ，T i }/max i D{r i ，T i }
Further, the routing inspection task allocation described in S300 is implemented by using an improved genetic algorithm. The following method is specifically adopted.
The robot clusters are first encoded. Dividing n tasks into m robots, adding m-1 virtual tasks, and dividing the whole tasks.
And secondly, designing a fitness function. The fitness function is related to time cost, journey cost and utility cost, definition A, B is two constants related to the number of inspection tasks, and the fitness function is F (x) =a/tt+b/dd+ee.
Then, the operations of selection, crossover and mutation are carried out. And selecting the individuals in the robot cluster according to the fitness value by the improved genetic algorithm, and selecting the individuals with higher fitness to enter the next step. Improved genetic algorithms produce new individuals by crossover. The first 10% of elite individuals are directly copied to the next generation without participating in crossover operations. The remaining individuals, by exchanging the two father-encoded fragments, produce two new offspring. The mutation operation generates new individuals by changing the gene value of a certain individual, adds new characteristics to the individuals and maintains the diversity of the population. The first 10% of elite individuals were directly copied to the next generation without participating in mutation operations. The remaining individuals randomly select to produce new offspring by exchanging the coding variations of the parent and offspring.
And finally judging whether the maximum iteration times are reached, and outputting an optimal result.
Finally, the inspection instruction issuing of S400 is realized through a robot terminal device (CPE) by adopting 5G communication.
On the other hand, the invention also discloses a task allocation system of the inspection robot cluster, which is used for allocating tasks to the robot cluster,
the method comprises the following modules:
the inspection task planning module is used for planning the inspection task of the robot cluster;
the task cost calculation module is used for calculating the cost of the inspection robot in the task execution process from three dimensions of time, distance and utility;
the inspection task distribution module is used for distributing inspection tasks;
and the inspection instruction issuing module is used for issuing an inspection instruction to the robot cluster through the 5G base station.
Compared with the prior art, the invention has the following technical effects:
1. adopting 5G to meet the communication requirements of high speed, low delay and wide link in the multi-task allocation of the robot cluster
2. The genetic algorithm is improved, the problem that task allocation is unbalanced due to single-dimension evaluation of the conventional robot cluster task allocation algorithm is solved, and efficient task allocation is achieved from three dimensions of time, distance and utility.
Drawings
FIG. 1 is a flow chart of task allocation of a 5G-based inspection robot cluster in accordance with the present invention;
FIG. 2 is a flow chart of an improved genetic algorithm implementation of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention.
The 5G-based inspection robot cluster task allocation method is based on a robot cluster and a 5G base station;
the method comprises the following steps:
s100, carrying out inspection task planning on a robot cluster;
s200, calculating the cost of the inspection robot in the task execution process from three dimensions of time, distance and utility;
s300, distributing the inspection tasks;
s400, sending a routing inspection instruction to the robot cluster through the 5G base station.
The following is described in detail with reference to fig. 1:
the inspection task described in S100 includes n inspection tasks to be executed: t= { T 1 ，t 2 ，…，t n One patrol point corresponding to each task: l= { L 1 ，l 2 ，…，l n }. The inspection robot cluster comprises m robot clusters capable of performing inspection tasks: r= { R 1 ，r 2 ，…，r m }。
The inspection task cost in S200 is measured by three indexes of time cost, path cost and utility cost required for finishing the inspection task. The following method is specifically adopted.
Inspection task t i And inspection task t j The distance cost between the two is c ij . Robot r i And inspection task t j Is the distance cost d ij . Robot executes inspection task t i The own journey cost is w i 。
The inspection tasks are divided into m groups: t= { T 1 ，T 2 ，…，T m }，T i Representation robot r i And distributing the obtained tasks. Robot r i There are k tasks: t (T) i1 ＝{t i1 ，t i2 ，...，t ik }。T i The sum of the journey costs of all the tasks in the network is W (r) i )＝w i1 +w i2 +...+w ik 。
The total path cost of a single robot is D { r } i ，T i }＝Dr i t i1 +∑k-1 j＝1ct ij t i(j+1) +W(r i ). Wherein Dr is i t i Representation robot r i From the initial position to the first inspection task t i1 Required path cost Σk-1 j =1ct ij t i(j+1) Representing the total path cost between the other k-1 tasks.
The time cost is: tt=max iD { r i ，T i }
The path cost is: dd= Σ m i =1d { r i ，T i }
The utility cost is: ee=min i D{r i ，T i }/max i D{r i ，T i }
And S300, the routing inspection task allocation is realized by adopting an improved genetic algorithm. The following method is specifically adopted.
The robot clusters are first encoded. Dividing n tasks into m robots, adding m-1 virtual tasks, and dividing the whole tasks. The m-1 virtual tasks are n+1, n+2, n+m-1, respectively.
For example. There are 8 inspection tasks, allocated to 3 inspection robots, and 2 virtual tasks 9, 10 are added as dividing points.
In the operation and calculation process of the robot cluster coding, the situation that the existing robots are not allocated to tasks is likely to occur, and unbalance among the robots is caused, so that the coding mode is eliminated.
And secondly, designing a fitness function. The fitness function is related to time cost, journey cost and utility cost, definition A, B is two constants related to the number of inspection tasks, and the fitness function is F (x) =a/tt+b/dd+ee.
Then, the operations of selection, crossover and mutation are carried out.
And selecting the individuals in the robot cluster according to the fitness value by the improved genetic algorithm, and selecting the individuals with higher fitness to enter the next step. Firstly, the elite selection method is adopted to copy and retain the elite individuals of the first 10 percent, so that the elite individuals in the current generation group directly enter the next generation group without crossing and mutation. The method ensures that the optimal individuals obtained during the genetic process are not lost. After the elite individuals are replicated, other individuals are selected using a proportional selection method. The higher the fitness value, the greater the probability of participating in a subsequent genetic manipulation.
After the selection is completed, new individuals are generated by crossover. The first 10% of elite individuals are directly copied to the next generation without participating in crossover operations. The remaining individuals, by exchanging the two father-encoded fragments, produce two new offspring. The specific process is as follows.
First, elite individuals not involved in crossover are removed, and the remaining individuals are paired pairwise in the order in which they are clustered. After pairing is completed, the location of the intersection in the two parents is determined, thereby determining a matching segment. Finally, two children are generated by copying the matching segment of one parent, preserving the relative positions of the genes of the other parent.
For example.
The intersection positions of two father individuals determine the matching segment:
(8 6 3|4 10 2 1|5 7 9) and (9 5 7|4 6 8 1|10 2 3)
Copy matching segments to children:
(4 10 2 1) and (4 6 8 1)
Copying codes that have not occurred in children from another parent in the original relative order, resulting in two new individuals:
(4 10 2 1 9 5 7 6 8 3) and (4 6 8 1 3 10 2 5 7 9)
Mutation operation generates new individuals by changing the gene value of an individual, and maintains population diversity. The first 10% of elite individuals were directly copied to the next generation without participating in mutation operations. The remaining individuals, through crossover variation, select two points of variation for the parent and child to produce new offspring.
For example.
For individuals (4 10 2 1 9 5 7 6 8 3), the seventh coding exchange of the third and seventh individuals from the parent individuals is selected, resulting in a variant new individual (4 10 7 1 9 5 2 6 8 3).
The number of mutation operations is determined by the mutation probability. Setting the initial value of the mutation probability to a smaller value can better preserve individuals of good quality.
And finally judging whether the maximum iteration times are reached, and outputting an optimal result.
As shown in fig. 2.
And S400, sending the inspection instruction, namely, adopting 5G communication and realizing sending the inspection instruction through a robot terminal device (CPE).
From the above, it can be seen that the 5G-based inspection robot cluster task allocation method in this embodiment adopts 5G, which satisfies the communication requirements of high speed, low delay and wide link in the multi-task allocation of the robot cluster, and solves the problem of unbalanced task allocation caused by single-dimension evaluation of the current robot cluster task allocation algorithm by improving the genetic algorithm, thereby realizing efficient allocation of tasks in three dimensions of time, path and utility.
Meanwhile, the embodiment of the invention also discloses a task allocation system of the inspection robot cluster, which is used for allocating tasks to the robot cluster,
the method comprises the following modules:
the inspection task planning module is used for planning the inspection task of the robot cluster;
the task cost calculation module is used for calculating the cost of the inspection robot in the task execution process from three dimensions of time, distance and utility;
the inspection task distribution module is used for distributing inspection tasks;
and the inspection instruction issuing module is used for issuing an inspection instruction to the robot cluster through the 5G base station.
The step of carrying out inspection task planning on the robot cluster by the inspection task planning module specifically comprises the following steps:
let it contain n patrol tasks to be executed: t= { T 1 ，t 2 ，…，t n One patrol point corresponding to each task: l= { L 1 ，l 2 ，…，l n }；
The inspection robot cluster comprises m robot clusters capable of performing inspection tasks: r= { R 1 ，r 2 ，…，r m }。
The task cost calculation module calculates the cost of the inspection robot in the task execution process from three dimensions of time, distance and utility;
comprising the following steps:
setting:
inspection task t i And inspection task t j The distance cost between the two is c ij ；
Robot r i And inspection task t j Is the distance cost d ij ；
Robot executes inspection task t i The own journey cost is w i ；
The inspection tasks are divided into m groups: t= { T 1 ，T 2 ，…，T m }，T i Representation robot r i Distributing the task; robot r i There are k tasks: t (T) i1 ＝{t i1 ，t i2 ，...，t ik }；
T i The sum of the journey costs of all the tasks in the network is W (r) i )＝w i1 +w i2 +...+w ik ；
The total path cost of a single robot is D { r } i ，T i }＝Dr i t i1 +∑k-1 j＝1ct ij t i(j+1) +W(r i ) Wherein Dr is i t i Representation robot r i From the initial position to the first inspection task t i1 Required path cost Σk-1 j =1ct ij t i(j+1) Representing the total path cost between the other k-1 tasks;
then:
the time cost is: tt=max iD { r i ，T i }
The path cost is: dd= Σ m i =1d { r i ，T i }
The utility cost is: ee=min i D{r i ，T i }/max i D{r i ，T i }。
The patrol task allocation module allocates the patrol task, which comprises the following steps:
(1) Firstly, coding a robot cluster, dividing n tasks into m robots, adding m-1 virtual tasks, and dividing the whole tasks;
(2) Secondly, designing a fitness function, defining A, B as two constants related to the number of inspection tasks, wherein the fitness function is F (x) =A/TT+B/DD+EE;
(3) Then carrying out selection, crossing and mutation operations;
(4) The setting algorithm selects the individuals in the robot cluster according to the fitness value, and the individuals with higher fitness are selected to enter the next step;
(5) Setting an algorithm to generate new individuals through crossover, directly copying the former 10% elite individuals to the next generation, not participating in crossover operation, and generating two new offspring through exchanging the two father-encoded fragments of the rest individuals;
(6) The mutation operation generates a new individual by changing the gene value of a certain individual, and adds new characteristics to the individual to maintain the diversity of the population; the first 10% elite individuals are directly copied to the next generation without participating in mutation operation, and the rest individuals randomly select, and new offspring are generated by exchanging coding mutation of the parent and the offspring;
and finally judging whether the maximum iteration times are reached, and outputting an optimal result.
It may be understood that the system provided by the embodiment of the present invention corresponds to the method provided by the embodiment of the present invention, and explanation, examples and beneficial effects of the related content may refer to corresponding parts in the above method.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (3)
1. A5G-based routing inspection robot cluster task allocation method is based on a robot cluster and a 5G base station and is characterized in that:
the method comprises the following steps:
s100, carrying out inspection task planning on a robot cluster; the robot cluster is subjected to inspection task planning; the method specifically comprises the following steps:
let it contain n patrol tasks to be executed: t= { T 1 ,t 2 ,…,t n One patrol point corresponding to each task: l= { L 1 ,l 2 ,…,l n }；
The inspection robot cluster comprises m robot clusters capable of performing inspection tasks: r= { R 1 ,r 2 ,…,r m }；
S200, calculating the cost of the inspection robot in the task execution process from three dimensions of time, distance and utility; calculating the cost of the inspection robot in the task execution process according to the three dimensions of the slave time, the path and the utility;
comprising the following steps:
setting:
inspection task t i And inspection task t j The cost of the journey between them is
Robot r i And inspection task t j At the cost of (a) distance
Robot executes inspection task t i The own journey cost is w i ；
The inspection tasks are divided into m groups: t= { T 1 ,T 2 ,…,T m }，T i Representation robot r i Distributing the task; robot r i There are k tasks: t (T) i1 ＝{t i1 ,t i2 ,…,t ik }；
T i The sum of the journey costs of all the tasks in the network is W (r) i )＝w i1 +w i2 +…+w ik ；
The total path cost of a single robot isWherein->Representation robot r i From the initial position to the first inspection task t i1 The required journey cost->Representing the total path cost between the other k-1 tasks;
then:
the time cost is: tt=maxid { r i ，T i }
The path cost is:
the utility cost is: ee=min i D{r i ，T i }/max i D{r i ，T i }；
S300, distributing the inspection tasks; s300, distributing the inspection tasks;
comprising the following steps:
(1) Firstly, coding a robot cluster, dividing n tasks into m robots, adding m-1 virtual tasks, and dividing the whole tasks;
(2) Secondly, designing a fitness function, defining A, B as two constants related to the number of inspection tasks, wherein the fitness function is F (x) =A/TT+B/DD+EE;
(3) Then carrying out selection, crossing and mutation operations;
(4) The setting algorithm selects the individuals in the robot cluster according to the fitness value, and the individuals with higher fitness are selected to enter the next step;
(5) Setting an algorithm to generate new individuals through crossover, directly copying the former 10% elite individuals to the next generation, not participating in crossover operation, and generating two new offspring through exchanging the two father-encoded fragments of the rest individuals;
(6) The mutation operation generates a new individual by changing the gene value of a certain individual, and adds new characteristics to the individual to maintain the diversity of the population; the first 10% elite individuals are directly copied to the next generation without participating in mutation operation, and the rest individuals randomly select, and new offspring are generated by exchanging coding mutation of the parent and the offspring;
finally judging whether the maximum iteration times are reached or not, and outputting an optimal result;
s400, sending a routing inspection instruction to the robot cluster through the 5G base station.
2. The 5G-based inspection robot cluster task allocation method according to claim 1, wherein: s400 issues a routing inspection instruction to the robot cluster through the 5G base station;
comprising the following steps:
and 5G communication is adopted, and a robot cluster inspection instruction is issued through a robot terminal device (CPE), so that task allocation of the robot cluster is realized.
3. The utility model provides a patrol and examine robot cluster task distribution system for carry out task distribution to robot cluster, its characterized in that:
the method comprises the following modules:
the inspection task planning module is used for planning the inspection task of the robot cluster; the step of the inspection task planning module for carrying out inspection task planning on the robot cluster specifically comprises the following steps:
let it contain n patrol tasks to be executed: t= { T 1 ,t 2 ,…,t n One patrol point corresponding to each task: l= { L 1 ,l 2 ,…,l n }；
The inspection robot cluster comprises m robot clusters capable of performing inspection tasks: r= { R 1 ,r 2 ,…,r m }；
The task cost calculation module is used for calculating the cost of the inspection robot in the task execution process from three dimensions of time, distance and utility; the task cost calculation module calculates the cost of the inspection robot in the task execution process from three dimensions of time, distance and utility;
comprising the following steps:
setting:
inspection task t i And inspection task t j The cost of the journey between them is
Robot r i And inspection task t j At the cost of (a) distance
Robot executes inspection task t i The own journey cost is w i ；
The inspection tasks are divided into m groups: t= { T 1 ,T 2 ,…,T m }，T i Representation robot r i Distributing the task; robot r i There are k tasks: t (T) i1 ＝{t i1 ,t i2 ,…,t ik }；
T i The sum of the journey costs of all the tasks in the network is W (r) i )＝w i1 +w i2 +…+w ik ；
The total path cost of a single robot isWherein->Representation robot r i From the initial position to the first inspection task t i1 The required journey cost->Representing the total path cost between the other k-1 tasks;
then:
the time cost is: tt=maxid { r i ，T i }
The path cost is:
the utility cost is: ee=min i D{r i ，T i }/max i D{r i ，T i }；
The inspection task distribution module is used for distributing inspection tasks; the patrol task allocation module allocates the patrol task, which comprises the following steps:
(1) Firstly, coding a robot cluster, dividing n tasks into m robots, adding m-1 virtual tasks, and dividing the whole tasks;
(2) Secondly, designing a fitness function, defining A, B as two constants related to the number of inspection tasks, wherein the fitness function is F (x) =A/TT+B/DD+EE;
(3) Then carrying out selection, crossing and mutation operations;
(4) The setting algorithm selects the individuals in the robot cluster according to the fitness value, and the individuals with higher fitness are selected to enter the next step;
(5) Setting an algorithm to generate new individuals through crossover, directly copying the former 10% elite individuals to the next generation, not participating in crossover operation, and generating two new offspring through exchanging the two father-encoded fragments of the rest individuals;
(6) The mutation operation generates a new individual by changing the gene value of a certain individual, and adds new characteristics to the individual to maintain the diversity of the population; the first 10% elite individuals are directly copied to the next generation without participating in mutation operation, and the rest individuals randomly select, and new offspring are generated by exchanging coding mutation of the parent and the offspring;
finally judging whether the maximum iteration times are reached or not, and outputting an optimal result;
and the inspection instruction issuing module is used for issuing an inspection instruction to the robot cluster through the 5G base station.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010185558.7A CN111401745B (en) | 2020-03-16 | 2020-03-16 | 5G-based routing inspection robot cluster task allocation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010185558.7A CN111401745B (en) | 2020-03-16 | 2020-03-16 | 5G-based routing inspection robot cluster task allocation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111401745A CN111401745A (en) | 2020-07-10 |
| CN111401745B true CN111401745B (en) | 2024-02-09 |
Family
ID=71413479
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010185558.7A Active CN111401745B (en) | 2020-03-16 | 2020-03-16 | 5G-based routing inspection robot cluster task allocation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111401745B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111784211B (en) * | 2020-08-04 | 2021-04-27 | 中国人民解放军国防科技大学 | Cluster-based group multitask allocation method and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016210156A1 (en) * | 2015-06-23 | 2016-12-29 | Archon Technologies S.R.L. | System for autonomous operation of multiple hybrid unmanned aerial vehicles supported by recharging stations to perform services |
| CN106529674A (en) * | 2016-11-03 | 2017-03-22 | 中国人民解放军信息工程大学 | Multiple-unmanned-aerial-vehicle cooperated multi-target distribution method |
| CN107895225A (en) * | 2017-11-01 | 2018-04-10 | 北京邮电大学 | A kind of cooperation type method for allocating tasks of multi-Agent Lothrus apterus |
| CN109986563A (en) * | 2019-05-01 | 2019-07-09 | 湖南大学 | A kind of multiple mobile robot's work compound method and system |
| CN110610304A (en) * | 2019-08-28 | 2019-12-24 | 广西电网有限责任公司电力科学研究院 | Cross-region scheduling method of inspection robot based on hybrid genetic-ant colony algorithm |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE112013007263T5 (en) * | 2013-09-19 | 2016-04-07 | Intel Corporation | Techniques for allocating task shares in distributed processing |
-
2020
- 2020-03-16 CN CN202010185558.7A patent/CN111401745B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016210156A1 (en) * | 2015-06-23 | 2016-12-29 | Archon Technologies S.R.L. | System for autonomous operation of multiple hybrid unmanned aerial vehicles supported by recharging stations to perform services |
| CN106529674A (en) * | 2016-11-03 | 2017-03-22 | 中国人民解放军信息工程大学 | Multiple-unmanned-aerial-vehicle cooperated multi-target distribution method |
| CN107895225A (en) * | 2017-11-01 | 2018-04-10 | 北京邮电大学 | A kind of cooperation type method for allocating tasks of multi-Agent Lothrus apterus |
| CN109986563A (en) * | 2019-05-01 | 2019-07-09 | 湖南大学 | A kind of multiple mobile robot's work compound method and system |
| CN110610304A (en) * | 2019-08-28 | 2019-12-24 | 广西电网有限责任公司电力科学研究院 | Cross-region scheduling method of inspection robot based on hybrid genetic-ant colony algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 王锐 ; 莫志超 ; 彭向阳 ; 庞小峰 ; 饶章权 ; .基于遗传算法的变电站巡检机器人任务路径规划方法研究.计算机测量与控制.2017,(第04期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111401745A (en) | 2020-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108320057B (en) | Flexible job shop scheduling method based on limited stable pairing strategy | |
| CN107172166B (en) | Cloud and mist computing system for industrial intelligent service | |
| CN102063339B (en) | Resource load balancing method and equipment based on cloud computing system | |
| CN111065103A (en) | Multi-objective optimization wireless sensor network node deployment method | |
| CN111325356A (en) | Neural network search distributed training system and training method based on evolutionary computation | |
| CN111353910A (en) | Distributed intelligent power grid economic dispatching method based on finite time consistency under directed topology | |
| CN112907150B (en) | Production scheduling method based on genetic algorithm | |
| Mahmudy et al. | Solving Part Type Selection and Loading Problem in Flexible Manufacturing System Using Real Coded Genetic Algorithms¿ Part II: Optimization | |
| Mahmudy et al. | Optimization of part type selection and loading problem with alternative production plans in flexible manufacturing system using hybrid genetic algorithms-part 1: Modelling and representation | |
| CN112580259B (en) | Intelligent mine automatic ore blending method and system based on genetic algorithm | |
| CN112001526A (en) | Resource scheduling optimization method based on ecological niche optimization genetic algorithm | |
| Huang et al. | An improved genetic algorithm for job-shop scheduling problem with process sequence flexibility | |
| CN111401745B (en) | 5G-based routing inspection robot cluster task allocation method and system | |
| CN112926896A (en) | Production scheduling method for cigarette cut tobacco production | |
| CN109298930A (en) | A kind of cloud workflow schedule method and device based on multiple-objection optimization | |
| CN112272102A (en) | Method and device for unloading and scheduling edge network service | |
| Rifai et al. | Reentrant FMS scheduling in loop layout with consideration of multi loading-unloading stations and shortcuts | |
| CN115421885A (en) | Distributed multi-target cloud task scheduling method and device and cloud service system | |
| Ławrynowicz | Genetic algorithms for solving scheduling problems in manufacturing systems | |
| CN113347255B (en) | Edge server site selection deployment model and solving method thereof | |
| CN105427058A (en) | Engine test wire station distribution optimization method based on genetic algorithm | |
| CN112990608A (en) | 5G optimization construction method suitable for full coverage of electric power facilities | |
| CN109195222B (en) | Power distribution method based on statistical characteristic reference | |
| KR100986160B1 (en) | System and method for manufacturing mask using genetic algorithm and dna computing | |
| CN114444240B (en) | Delay and service life optimization method for cyber-physical system |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201020 Address after: 230088 No. 5111 Wangjiang West Road, hi tech Zone, Anhui, Hefei Applicant after: Hefei Technological University Intelligent Robot Technology Co.,Ltd. Address before: 230088 No. 5111 Wangjiang West Road, hi tech Zone, Anhui, Hefei Applicant before: Hefei Technological University Intelligent Robot Technology Co.,Ltd. Applicant before: CSG SMART SCIENCE & TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |