CN113657718A - Multi-robot dynamic alliance task allocation method and related device - Google Patents
Multi-robot dynamic alliance task allocation method and related device Download PDFInfo
- Publication number
- CN113657718A CN113657718A CN202110818187.6A CN202110818187A CN113657718A CN 113657718 A CN113657718 A CN 113657718A CN 202110818187 A CN202110818187 A CN 202110818187A CN 113657718 A CN113657718 A CN 113657718A
- Authority
- CN
- China
- Prior art keywords
- task
- robot
- target
- information
- geographic information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 71
- 238000012545 processing Methods 0.000 claims abstract description 39
- 239000000203 mixture Substances 0.000 claims abstract description 37
- 238000004590 computer program Methods 0.000 claims description 10
- 230000000694 effects Effects 0.000 abstract description 19
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 16
- 230000007704 transition Effects 0.000 description 8
- 238000013178 mathematical model Methods 0.000 description 6
- 239000013598 vector Substances 0.000 description 5
- 239000003814 drug Substances 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000006698 induction Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- DMBHHRLKUKUOEG-UHFFFAOYSA-N diphenylamine Chemical compound C=1C=CC=CC=1NC1=CC=CC=C1 DMBHHRLKUKUOEG-UHFFFAOYSA-N 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000011541 reaction mixture Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
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
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- 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
- G06Q10/06315—Needs-based resource requirements planning or analysis
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Databases & Information Systems (AREA)
- Remote Sensing (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Manipulator (AREA)
Abstract
The application discloses a multi-robot dynamic alliance task allocation method, which comprises the following steps: acquiring geographic information of a target area and position information of a target unit; performing target task grouping processing on the target area geographic information and the target unit position information according to a Gaussian mixture model to obtain a plurality of task groups; and performing dynamic task planning processing on the robots distributed by each task group according to the performance information of each robot to obtain a task sequence of each robot. The effect of task allocation of the robot is improved, and the effect of task processing is improved. The application also discloses a multi-robot dynamic alliance task allocation device, a server and a computer readable storage medium, which have the beneficial effects.
Description
Technical Field
The present application relates to the field of multi-robot control technologies, and in particular, to a multi-robot dynamic alliance task allocation method, a multi-robot dynamic alliance task allocation apparatus, a server, and a computer readable storage medium.
Background
With the continuous development of the robot technology, robots are more and more applied in various task fields. For example, when a work requiring a large-scale rapid processing such as a disaster occurs, it is necessary to deal with problems such as an emergency and an accidental, and a robot is used to perform a task, thereby improving the processing effect and efficiency.
In the related art, an earthquake rescue simulator and a two-stage rescue planning algorithm are usually designed, and the earthquake rescue simulator and the two-stage rescue planning algorithm comprise three parts, namely rescue task level planning, rescue airplane level planning and rescue airplane position distribution. In the rescue task level planning, the grid coordinates of each rescue task are used as clustering basis, a K-means clustering method is adopted to cluster the rescue tasks, and the clustering center of each task group is determined; and completing the division of the rescue aircraft groups according to the proportion of the disaster-suffered total number of people of each task group and the distance from each rescue aircraft to the rescue center. However, the applicability of the method is reduced because the mathematical model established in a more complicated way in practice does not take into account various conditions. In addition, the used kmeans clustering method is also fixed in shape and not flexible enough, the probability that a sample belongs to each cluster is qualitative, and a good clustering result cannot be obtained due to the lack of robustness. The effect of assigning results is reduced so that the robot cannot perform tasks more efficiently.
Therefore, how to improve the assignment effect of the robot task is a key issue that the skilled person focuses on.
Disclosure of Invention
The application aims to provide a multi-robot dynamic alliance task allocation method, a multi-robot dynamic alliance task allocation device, a server and a computer readable storage medium, so that the effect of robot task allocation is improved, and the effect of task processing is improved.
In order to solve the above technical problem, the present application provides a multi-robot dynamic alliance task allocation method, including:
acquiring geographic information of a target area and position information of a target unit;
performing target task grouping processing on the target area geographic information and the target unit position information according to a Gaussian mixture model to obtain a plurality of task groups;
and performing dynamic task planning processing on the robots distributed by each task group according to the performance information of each robot to obtain a task sequence of each robot.
Optionally, the obtaining of the geographic information of the target area and the position information of the target unit includes:
and acquiring the geographic information of the target area and the position information of the target unit through infrared sensing equipment and geographic information equipment.
Optionally, the infrared sensing equipment is unmanned aerial vehicle infrared sensing equipment, the geographic information equipment is GPS equipment and/or big dipper navigation satellite equipment.
Optionally, the target task grouping processing is performed on the target area geographic information and the target unit location information according to a gaussian mixture model to obtain a plurality of task groups, and the method includes:
performing Gaussian mode initialization according to the total number of the robots to obtain a Gaussian mixture model;
and solving the Gaussian mixture model by adopting an EM algorithm according to the geographic information of the target area and the position information of the target unit to obtain the plurality of task groups.
Optionally, the solving of the gaussian mixture model by using an EM algorithm according to the target area geographic information and the target unit location information to obtain the plurality of task groups includes:
coordinate processing is carried out on the geographic information of the target area and the position information of the target unit to obtain all target unit coordinates;
and solving the Gaussian mixture model by adopting an EM algorithm according to all the target unit coordinates to obtain the plurality of task groups.
Optionally, the dynamic task planning processing is performed on the robots allocated to each task group according to the performance information of each robot, so as to obtain a task sequence of each robot, and the method includes:
determining a multi-constraint condition of each robot according to the performance information of each robot;
determining a plurality of robots distributed by each task group according to the number of the target units of each task group, and using the robots as a robot alliance of each task group;
establishing a task sequence distribution model for each robot alliance according to the multi-constraint condition of each robot;
and solving the task sequence distribution model according to a linear planner to obtain the task sequence of each robot.
Optionally, the method further includes:
and sending the task sequence to a corresponding robot so that the robot can execute tasks according to the task sequence.
The present application further provides a multi-robot dynamic alliance task assigning device, comprising:
the information acquisition module is used for acquiring geographic information of a target area and position information of a target unit;
the task grouping module is used for performing target task grouping processing on the target area geographic information and the target unit position information according to a Gaussian mixture model to obtain a plurality of task groups;
and the task planning module is used for performing dynamic task planning processing on the robots distributed by each task group according to the performance information of each robot to obtain a task sequence of each robot.
The present application further provides a server, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the multi-robot dynamic federation task allocation method as described above when executing the computer program.
The present application further provides a computer-readable storage medium having stored thereon a computer program that, when executed by a processor, performs the steps of the multi-robot dynamic federation task allocation method as described above.
The application provides a multi-robot dynamic alliance task allocation method, which comprises the following steps: acquiring geographic information of a target area and position information of a target unit; performing target task grouping processing on the target area geographic information and the target unit position information according to a Gaussian mixture model to obtain a plurality of task groups; and performing dynamic task planning processing on the robots distributed by each task group according to the performance information of each robot to obtain a task sequence of each robot.
The method comprises the steps of grouping target tasks through the acquired geographic information of a target area and the position information of a target unit to obtain a plurality of task groups, performing dynamic task planning processing on the plurality of task groups according to the performance information of each robot to obtain a task sequence to be executed by each robot, adding the performance information of the robots in the task allocation process, and improving the applicability of the method by considering various conditions in the task allocation process. And moreover, the Gaussian mixture model is adopted for grouping, so that the clustering effect is improved, the result distribution effect is further improved, and the robot can execute tasks more efficiently.
The application further provides a multi-robot dynamic alliance task allocation device, a server and a computer readable storage medium, which have the above beneficial effects and are not described herein again.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a multi-robot dynamic alliance task allocation method according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a multi-robot dynamic alliance task allocation apparatus according to an embodiment of the present application.
Detailed Description
The core of the application is to provide a multi-robot dynamic alliance task allocation method, a multi-robot dynamic alliance task allocation device, a server and a computer readable storage medium, so as to improve the effect of robot task allocation and improve the effect of task processing.
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, 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 some embodiments of the present application, but not all 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.
In the related art, an earthquake rescue simulator and a two-stage rescue planning algorithm are usually designed, and the earthquake rescue simulator and the two-stage rescue planning algorithm comprise three parts, namely rescue task level planning, rescue airplane level planning and rescue airplane position distribution. In the rescue task level planning, the grid coordinates of each rescue task are used as clustering basis, a K-means clustering method is adopted to cluster the rescue tasks, and the clustering center of each task group is determined; and completing the division of the rescue aircraft groups according to the proportion of the disaster-suffered total number of people of each task group and the distance from each rescue aircraft to the rescue center. However, the applicability of the method is reduced because the mathematical model established in a more complicated way in practice does not take into account various conditions. In addition, the used kmeans clustering method is also fixed in shape and not flexible enough, the probability that a sample belongs to each cluster is qualitative, and a good clustering result cannot be obtained due to the lack of robustness. The effect of assigning results is reduced so that the robot cannot perform tasks more efficiently.
Therefore, the application provides a multi-robot dynamic alliance task allocation method, target tasks are grouped through the obtained target area geographic information and the target unit position information to obtain a plurality of task groups, dynamic task planning processing is carried out on the plurality of task groups according to the performance information of each robot to obtain a task sequence required to be executed by each robot, the performance information of the robot is added in the task allocation process, and the applicability of the method is improved by considering various conditions in the task allocation process. And moreover, the Gaussian mixture model is adopted for grouping, so that the clustering effect is improved, the result distribution effect is further improved, and the robot can execute tasks more efficiently.
The following describes a multi-robot dynamic federation task allocation method provided by the present application by an embodiment.
Referring to fig. 1, fig. 1 is a flowchart illustrating a multi-robot dynamic federation task allocation method according to an embodiment of the present disclosure.
In this embodiment, the method may include:
s101, acquiring geographic information of a target area and position information of a target unit;
this step is intended to obtain the geographic information of the target area and the position information of the target unit. The target area is the geographical area where the target unit is located.
The target area geographic information is geographic information of an area where the target unit is located. The geographic information includes, but is not limited to, latitude and longitude information, area size, altitude, geographic environment, weather information, and the like. The target unit location information is location information of each target unit in the target area. The location information may be latitude and longitude information and altitude information.
Correspondingly, in the step, the geographic information of the target area and the position information of the target unit can be obtained in various ways. The judgment can be carried out by GPS acquisition, network position acquisition or manual experience. It can be seen that, in this embodiment, the manner of acquiring the geographic information of the target area and the location information of the target unit is not unique, and is not specifically limited herein.
Further, the step may include:
and acquiring geographic information of a target area and position information of a target unit through the infrared sensing equipment and the geographic information equipment.
Therefore, in the alternative, how to acquire the geographic information of the target area and the position information of the target unit is mainly explained. Further, in the alternative, the information can be obtained through an infrared sensing device and a geographic information device. The geographic information equipment can be GPS or Beidou navigation equipment.
Furthermore, the infrared sensing equipment is unmanned aerial vehicle infrared sensing equipment, and the geographic information equipment is GPS equipment and/or big dipper navigation satellite equipment.
S102, performing target task grouping processing on target area geographic information and target unit position information according to a Gaussian mixture model to obtain a plurality of task groups;
and on the basis of S101, performing target task grouping processing on the target area geographic information and the target unit position information according to a Gaussian mixture model to obtain a plurality of task groups.
Since the present embodiment mainly controls a plurality of robots, not a single task execution device performs all tasks. In order to improve the efficiency of the robot in processing tasks, all robots may be configured to execute simultaneously, i.e., to process tasks in parallel. However, not all robots are equally divided to each task. Mainly because the distance between the target units is closer or farther, the closer units can be set as a group for processing so as to save resources. Therefore, all the target tasks are grouped in this step.
Specifically, a gaussian mixture model is used for grouping. The gaussian model is a model formed based on a gaussian probability density function (normal distribution curve) by accurately quantizing objects by using the gaussian probability density function (normal distribution curve) and decomposing one object into a plurality of objects. The principle and process of establishing a Gaussian model for an image background are as follows: the image gray level histogram reflects the frequency of occurrence of a certain gray level in an image, and may also be an estimate of the probability density of the image gray level. If the difference between the target area and the background area contained in the image is large and the background area and the target area have a certain difference in gray level, the gray level histogram of the image is in a double-peak-valley shape, wherein one peak corresponds to the target and the other peak corresponds to the central gray level of the background.
Further, the step may include:
step 1, initializing a Gaussian mode according to the total number of the robots to obtain a Gaussian mixture model;
and 2, solving the Gaussian mixture model by adopting an EM algorithm according to the geographic information of the target area and the position information of the target unit to obtain a plurality of task groups.
It can be seen that the present alternative is mainly to group tasks under the limit of the total number of robots. In the alternative, a Gaussian mode is initialized according to the total number of the robots to obtain a Gaussian mixture model; and then solving the Gaussian mixture model by using an EM algorithm according to the geographic information of the target area and the position information of the target unit to obtain a plurality of task groups. The EM algorithm is an Expectation-Maximization (EM) algorithm, is a type of optimization algorithm for maximum likelihood estimation through iteration, and is generally used as a substitute for a newton iteration method for parameter estimation of a probability model containing hidden variables or missing data.
Therefore, the total number of the robots is adopted for constraint in the alternative scheme, so that the task grouping better meets the requirement of the actual situation, and the effectiveness of the application of the scheme is improved.
Further, step 2 in the last alternative may include:
step 1, coordinate processing is carried out on geographic information of a target area and position information of a target unit to obtain coordinates of all the target units;
and 2, solving the Gaussian mixture model by adopting an EM algorithm according to all target unit coordinates to obtain a plurality of task groups.
It can be seen that this alternative is primarily illustrative of step 2 in the previous alternative. In the alternative scheme, coordinate processing is carried out on geographic information of a target area and position information of target units to obtain all target unit coordinates, and the Gaussian mixture model is solved according to all the target unit coordinates by adopting an EM algorithm to obtain a plurality of task groups. The method mainly comprises the steps of firstly realizing coordinate transformation and then grouping tasks. This alternative describes a way to convert geographic information and location information to improve the accuracy of location processing.
And S103, performing dynamic task planning processing on the robots distributed by each task group according to the performance information of each robot to obtain a task sequence of each robot.
On the basis of S102, this step is intended to perform dynamic task planning processing on the robots assigned to each task group according to the actual performance of the robots, so as to obtain a sequence of each robot. First, it is necessary to determine how many robots are assigned to each task group according to all robots and all task groups. Each robot then faces multiple tasks in each task group. Therefore, how each robot cooperates with other robots, when a certain task is executed, needs to be optimized so as to improve the execution efficiency of the robots. That is, a task sequence of each robot is obtained.
It can be seen that, in this embodiment, a corresponding task sequence is set for each robot, and each robot can cooperate with other robots according to the task sequence to complete a plurality of tasks.
Further, the step may include:
step 1, determining a multi-constraint condition of each robot according to the performance information of each robot;
step 2, determining a plurality of robots distributed by each task group according to the number of target units of each task group, and using the robots as a robot alliance of each task group;
step 3, establishing a task sequence distribution model for each robot alliance according to the multi-constraint condition of each robot;
and 4, solving the task sequence distribution model according to the linear planner to obtain the task sequence of each robot.
It can be seen that the present alternative is mainly described how to obtain a task sequence for each robot. In the alternative scheme, the multi-constraint condition of each robot is determined according to the performance information of each robot, the multiple robots distributed by each task group are determined according to the number of target units of each task group and serve as the robot alliances of each task group, a task sequence distribution model is established for each robot alliance according to the multi-constraint condition of each robot, and the task sequence distribution model is solved according to a linear planner to obtain the task sequence of each robot. Namely, the robot corresponding to each task group is used as a robot alliance, and then the task is distributed in each robot alliance through the multi-constraint condition of each robot. Wherein the multi-constraint condition comprises performance requirements and resource requirements of the task. Wherein the performance requirements include sensing capabilities of the robot and motion capabilities of the robot. The resource requirements comprise the requirements of the robot for conveying food resources and medicine resources and the energy requirements of the robot in the process of completing tasks.
Further, this embodiment may further include:
and sending the task sequence to the corresponding robot so that the robot executes the task according to the task sequence.
It can be seen that in this alternative, the task sequence of each robot is sent to the corresponding robot.
In summary, in this embodiment, target tasks are grouped according to the obtained target area geographic information and the target unit location information to obtain a plurality of task groups, then the plurality of task groups are subjected to dynamic task planning processing according to the performance information of each robot to obtain a task sequence that each robot needs to execute, the performance information of the robot is added in the task allocation process, and the applicability of the method is improved by considering various conditions in the task allocation process. And moreover, the Gaussian mixture model is adopted for grouping, so that the clustering effect is improved, the result distribution effect is further improved, and the robot can execute tasks more efficiently.
The multi-robot dynamic federation task allocation method provided by the present application is further described below by another specific embodiment.
In this embodiment, the method of the previous embodiment is applied in a disaster relief scenario. By the multi-robot dynamic alliance task allocation method, the disaster relief efficiency and effect can be improved.
In this embodiment, the method may include: the method comprises the steps of obtaining geographical information and information of trapped persons in a disaster area by using an unmanned aerial vehicle and a GPS, grouping the trapped persons by using a Gaussian mixture model to calculate clustering, estimating the number of the robots invested in each task group, establishing a mathematical model under a multi-constraint condition, and obtaining a robot rescue allocation sequence by using a linear planner.
Specifically, the multi-robot dynamic alliance task allocation method may include:
step 1, acquiring disaster area geographic information and trapped personnel position information by using unmanned aerial vehicle infrared induction and a GPS (global positioning system), and acquiring robot information according to tasks;
step 2, solving clusters for the rescue tasks by using a Gaussian mixture model according to the obtained disaster area geographic information and the position information of the trapped personnel, and grouping the clusters;
step 3, estimating the number of robots invested in each task group according to the ratio of the number of the disaster suffered people to the total number of the disaster suffered people of each task group;
step 4, the robot establishes a dynamic robot alliance according to the distributed rescue tasks to complete the rescue tasks;
step 4.1, establishing a task sequence distribution mathematical model of the heterogeneous multi-robot dynamic alliance considering the time schedule under the multi-constraint condition;
4.2, solving the mathematical model by using a linear planner to obtain a task sequence of each robot, and sending the task sequence to the corresponding robot so that the robot can execute tasks;
and 4.3, checking whether the targets to be rescued are all rescued successfully, otherwise, repeating the steps 4.1 to 4.2.
Wherein, in step 1, the u th trapped person coordinate p is obtained according to disaster area geographic information and trapped person position information acquired by unmanned aerial vehicle infrared induction and GPSuBelongs to P, and P is the coordinate set P ═ P of all trapped persons1，p2,…,pu}; obtaining rescue robot information, wherein each robot has two groups of capacity vectors, namely an induction vector and a motion vector, and the kth robot RKE.g. R, with a sensing vector of
And a motion vector of
In step 2, the K value is initially set to [2, K ]max]Is a random integer of (1), KmaxThe value is the total number of the input robots, and is corresponding to pi in each Gaussian componentk、μk、ΣkCarrying out initialization, whereinkIs a mixing coefficient, represents the weight of the kth Gaussian model and satisfies
μkMean, sigma, representing the kth Gaussian modelkA covariance matrix representing a kth gaussian model; then, using EM algorithm to solve the Gaussian mixture model, and in step E, according to the current pik、μk、ΣkCalculating gamma (z)nk)，γ(znk) Representing the posterior probability that point n belongs to cluster k,
znkis an implicit variable, znk∈{0,1}，
Wherein z isnk1 indicates that point n belongs to the kth cluster, znk0 means that the point n does not belong to the kth cluster, p (x)n|μk,Σk) Representing the probability density of the kth gaussian model associated with point n, the formula is calculated as follows:
wherein D is 3, which represents 3-dimensional Gaussian distribution, and in M steps, according to gamma (z)nk) Calculating to obtain new pik、μk、ΣkThe method comprises the following steps:
wherein x isnRepresenting the point N, N representing the number of points, NkRepresents the number of points belonging to the k-th cluster; and finally, converging the parameters in the model, meeting the capability and resource requirements of corresponding tasks in clustering, obtaining a proper clustering result, and taking the result as a clustering scheme.
Setting the total number of people suffered from the disaster to be M and the number of people in the D-th rescue group to be M in step 3, and then adding the number of robots to the D-th rescue group
When D is presentRWhen the decimal part is included, the decimal part is removed and one is added. In addition, in the divided clustering, the robot can flexibly form different machines by considering the capability and resource requirement of corresponding tasksAnd (5) carrying out rescue by the alliance of people. Wherein the rescue group is a task group.
In step 4, each task is completed by a robot alliance consisting of a plurality of heterogeneous robots, the composition of the robot alliance is not fixed and is flexibly composed of different robots in divided clustering areas according to task requirements, and the robots belong to different alliances in different time through time scheduling to complete different tasks. The establishment of the dynamic robot alliance not only enables the robot to complete the rescue task more effectively, but also improves the utilization rate of the rescue robot. In addition, in the divided clustering, the capability requirements and resource requirement parameters of the tasks are specified according to the obtained disaster area geographic information and experience, wherein the capability requirements comprise the requirements on the sensing capability and the movement capability of the robot alliance, and the different types of robots are assigned corresponding to different terrains; the resource requirements comprise the requirements of food resources and medicine resources of the robot alliance and also comprise the energy requirements needed by the robot in the process of completing tasks.
In step 4.1, the objective function and the constraint function are as follows:
in the formula 1, the first and second groups,
in the formula 2, the first and second groups,
in the formula 3, the first and second phases,
wherein, in formula 1
And f (x) represents the time for the robot to complete the task.
In equation 2, variables
Is a robot RkStarting pointThe point is a starting point, the end point is a subtask TiThe transition variables of (1) are assumed to all start from the starting point, and the sum of the transition variables of each robot from the starting point to the end point is ensured to be 1.
In the formula 3, the logic of modeling is ensured, each robot automatically enters a virtual terminal without consuming cost after finishing all tasks,
is a robot RkThe starting point is a subtask TiAnd the terminal point is a transition variable of the virtual terminal point, and the sum of the transition variables of each robot from the starting point to the terminal point is ensured to be 1.
In the case of the formula 4,
in the case of the formula 5,
in formula 4, each robot is guaranteed to start from at most one task point at a time.
In formula 5, each robot is guaranteed to reach at most one task point at a time.
In the case of the formula 6,
in the formula (6), the reaction mixture is,
is a robot RkSlave subtask TiTravel to subtask TjThe transition variable of (a) is,
is a robot RkSlave subtask TjTravel to subtask ThTo ensure the robot RkEntering a task and completing it must leave to the next task point or end point.
In the formula 7, the first and second groups,
in the case of the formula 8,
in the equations 7 and 8 of the above-described embodiments,
is a robot RkSlave subtask TiTravel to subtask TjThe transition variable ensures that each task is executed by the robot.
In the formula 9, the first and second groups,
in the formula 9, giAs a subtask TiThe starting time is a real decision variable, so that the starting time and the task starting time are more than or equal to 0.
In the formula 10, the process is described,
in equation 9, tjIndicates the execution duration of task j, djhRepresenting subtasks TjAnd subtask ThThe distance between the robots is that each robot needs to complete the previous task and then transition to the next task. It is ensured that the start time of the next task cannot be earlier than the time when the robot reaches the task point.
In the formula 11, the first and second groups,
in equation 11, if the subtask T is TjPriority higher than subtask ThThen p isjh1 is ═ 1; otherwise pjh0. And ensuring that the robot preferentially executes the tasks with high priority.
In the formula 12, the process is described,
in the formula 13, the first and second groups,
in the formula 12, it is ensured that the sensing capability of the robot alliance corresponding to the task is greater than the requirement of the sensing capability of the task; in the formula 13, it is ensured that the joint movement capability of the robot corresponding to the task is greater than the requirement of the movement capability of the task.
In the case of the formula 14,
in the formula 14, it is ensured that the medicine resource carried by the robot corresponding to the task is greater than the requirement of the task medicine resource.
In the formula 15, the process is described,
in the formula 15, it is ensured that the food resource carried by the robot corresponding to the task is greater than the task food resource requirement.
In the formula 16, the process is described,
in the formula 16, it is ensured that the energy carried by the robot is greater than the energy requirement consumed on the transition route.
In step 4.2, the established mathematical model is solved by using a linear planner, and then a robot rescue allocation sequence is obtained.
It can be seen that, in the embodiment, the target tasks are grouped according to the obtained target area geographic information and the target unit location information to obtain a plurality of task groups, then the plurality of task groups are subjected to dynamic task planning processing according to the performance information of each robot to obtain a task sequence to be executed by each robot, the performance information of the robot is added in the task allocation process, and the applicability of the method is improved by considering various conditions in the task allocation process. And moreover, the Gaussian mixture model is adopted for grouping, so that the clustering effect is improved, the result distribution effect is further improved, and the robot can execute tasks more efficiently.
In the following, the multi-robot dynamic alliance task allocation device provided in the embodiment of the present application is introduced, and the multi-robot dynamic alliance task allocation device described below and the multi-robot dynamic alliance task allocation method described above may be referred to in a corresponding manner.
Referring to fig. 2, fig. 2 is a schematic structural diagram of a multi-robot dynamic alliance task allocation device according to an embodiment of the present application.
In this embodiment, the apparatus may include:
an information obtaining module 100, configured to obtain geographic information of a target area and location information of a target unit;
the task grouping module 200 is configured to perform target task grouping processing on target area geographic information and target unit location information according to a gaussian mixture model to obtain a plurality of task groups;
and the task planning module 300 is configured to perform dynamic task planning processing on the robots allocated to each task group according to the performance information of each robot, so as to obtain a task sequence of each robot.
Optionally, the information obtaining module 100 is specifically configured to obtain geographic information of a target area and location information of a target unit through an infrared sensing device and a geographic information device.
Optionally, the infrared sensing device is an unmanned aerial vehicle infrared sensing device, and the geographic information device is a GPS device and/or a beidou navigation device.
Optionally, the task grouping module 200 is specifically configured to perform gaussian mode initialization according to the total number of the robots to obtain a gaussian mixture model; and solving the Gaussian mixture model by adopting an EM algorithm according to the geographic information of the target area and the position information of the target unit to obtain a plurality of task groups.
Optionally, the task grouping module 200 is specifically configured to perform coordinate processing on the target area geographic information and the target unit location information to obtain all target unit coordinates; and solving the Gaussian mixture model by adopting an EM algorithm according to all target unit coordinates to obtain a plurality of task groups.
Optionally, the task planning module 300 is specifically configured to determine multiple constraint conditions of each robot according to the performance information of each robot; determining a plurality of robots distributed by each task group according to the number of the target units of each task group, and using the robots as a robot alliance of each task group; establishing a task sequence distribution model for each robot alliance according to the multi-constraint condition of each robot; and solving the task sequence distribution model according to the linear planner to obtain the task sequence of each robot.
Optionally, the apparatus may further include:
and the sequence sending module is used for sending the task sequence to the corresponding robot so that the robot can execute the task according to the task sequence.
An embodiment of the present application further provides a server, including:
a memory for storing a computer program;
a processor for implementing the steps of the multi-robot dynamic federation task allocation method as described in the above embodiments when executing the computer program.
Embodiments of the present application further provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the multi-robot dynamic federation task allocation method according to the above embodiments are implemented.
The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The multi-robot dynamic alliance task allocation method, the multi-robot dynamic alliance task allocation device, the server and the computer readable storage medium provided by the application are described in detail above. The principles and embodiments of the present application are explained herein using specific examples, which are provided only to help understand the method and the core idea of the present application. It should be noted that, for those skilled in the art, it is possible to make several improvements and modifications to the present application without departing from the principle of the present application, and such improvements and modifications also fall within the scope of the claims of the present application.
Claims (10)
1. A multi-robot dynamic alliance task allocation method is characterized by comprising the following steps:
acquiring geographic information of a target area and position information of a target unit;
performing target task grouping processing on the target area geographic information and the target unit position information according to a Gaussian mixture model to obtain a plurality of task groups;
and performing dynamic task planning processing on the robots distributed by each task group according to the performance information of each robot to obtain a task sequence of each robot.
2. The multi-robot dynamic alliance task assignment method as claimed in claim 1, wherein obtaining target area geographic information and target unit location information comprises:
and acquiring the geographic information of the target area and the position information of the target unit through infrared sensing equipment and geographic information equipment.
3. The multi-robot dynamic alliance task allocation method as claimed in claim 2, wherein the infrared sensing device is an unmanned aerial vehicle infrared sensing device, and the geographic information device is a GPS device and/or a beidou navigation device.
4. The multi-robot dynamic alliance task allocation method as claimed in claim 1, wherein performing target task grouping processing on the target area geographic information and the target unit location information according to a gaussian mixture model to obtain a plurality of task groups comprises:
performing Gaussian mode initialization according to the total number of the robots to obtain a Gaussian mixture model;
and solving the Gaussian mixture model by adopting an EM algorithm according to the geographic information of the target area and the position information of the target unit to obtain the plurality of task groups.
5. The multi-robot dynamic alliance task allocation method as claimed in claim 4, wherein solving the gaussian mixture model using an EM algorithm according to the target area geographic information and the target unit location information to obtain the plurality of task groups comprises:
coordinate processing is carried out on the geographic information of the target area and the position information of the target unit to obtain all target unit coordinates;
and solving the Gaussian mixture model by adopting an EM algorithm according to all the target unit coordinates to obtain the plurality of task groups.
6. The multi-robot dynamic alliance task allocation method as claimed in claim 1, wherein performing dynamic task planning processing on the robots allocated to each task group according to performance information of each robot to obtain a task sequence of each robot comprises:
determining a multi-constraint condition of each robot according to the performance information of each robot;
determining a plurality of robots distributed by each task group according to the number of the target units of each task group, and using the robots as a robot alliance of each task group;
establishing a task sequence distribution model for each robot alliance according to the multi-constraint condition of each robot;
and solving the task sequence distribution model according to a linear planner to obtain the task sequence of each robot.
7. The multi-robot dynamic federation task allocation method of claim 1, further comprising:
and sending the task sequence to a corresponding robot so that the robot can execute tasks according to the task sequence.
8. A multi-robot dynamic federation task assignment device, comprising:
the information acquisition module is used for acquiring geographic information of a target area and position information of a target unit;
the task grouping module is used for performing target task grouping processing on the target area geographic information and the target unit position information according to a Gaussian mixture model to obtain a plurality of task groups;
and the task planning module is used for performing dynamic task planning processing on the robots distributed by each task group according to the performance information of each robot to obtain a task sequence of each robot.
9. A server, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the multi-robot dynamic federation task allocation method of any one of claims 1 to 7 when executing said computer program.
10. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, carries out the steps of the multi-robot dynamic federation task allocation method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110818187.6A CN113657718B (en) | 2021-07-20 | 2021-07-20 | Multi-robot dynamic alliance task allocation method and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110818187.6A CN113657718B (en) | 2021-07-20 | 2021-07-20 | Multi-robot dynamic alliance task allocation method and related device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113657718A true CN113657718A (en) | 2021-11-16 |
| CN113657718B CN113657718B (en) | 2024-04-19 |
Family
ID=78489607
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110818187.6A Active CN113657718B (en) | 2021-07-20 | 2021-07-20 | Multi-robot dynamic alliance task allocation method and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113657718B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116167595A (en) * | 2023-04-25 | 2023-05-26 | 天信达信息技术有限公司 | Method for determining personnel group decision variables, electronic equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180326583A1 (en) * | 2017-05-11 | 2018-11-15 | King Fahd University Of Petroleum And Minerals | Dynamic multi-objective task allocation |
| CN109190985A (en) * | 2018-09-07 | 2019-01-11 | 江苏师范大学 | A kind of multirobot rescue task distribution method |
| CN110084512A (en) * | 2019-04-26 | 2019-08-02 | 河海大学常州校区 | A kind of multi-robot Task Allocation towards intelligent warehousing system |
| CN110264026A (en) * | 2019-04-22 | 2019-09-20 | 北京邮电大学 | The online method for allocating tasks of rescue aircraft based on two-stage planning in earthquake rescue |
| CN110826915A (en) * | 2019-11-07 | 2020-02-21 | 中国联合网络通信集团有限公司 | Resource scheduling method, device and computer readable storage medium |
| CN110852486A (en) * | 2019-10-16 | 2020-02-28 | 中国人民解放军国防科技大学 | Task planning method for autonomous cooperation of unmanned aerial vehicle cluster |
| CN111716356A (en) * | 2020-06-18 | 2020-09-29 | 南京邮电大学 | Method for cooperation of humanoid multi-robot |
| CN111928849A (en) * | 2019-12-20 | 2020-11-13 | 陕西科技大学 | Multi-medical delivery robot real-time path planning method |
| CN112633654A (en) * | 2020-12-15 | 2021-04-09 | 哈尔滨工程大学 | Multi-unmanned aerial vehicle task allocation method based on improved cluster expansion consistency bundle algorithm |
-
2021
- 2021-07-20 CN CN202110818187.6A patent/CN113657718B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180326583A1 (en) * | 2017-05-11 | 2018-11-15 | King Fahd University Of Petroleum And Minerals | Dynamic multi-objective task allocation |
| CN109190985A (en) * | 2018-09-07 | 2019-01-11 | 江苏师范大学 | A kind of multirobot rescue task distribution method |
| CN110264026A (en) * | 2019-04-22 | 2019-09-20 | 北京邮电大学 | The online method for allocating tasks of rescue aircraft based on two-stage planning in earthquake rescue |
| CN110084512A (en) * | 2019-04-26 | 2019-08-02 | 河海大学常州校区 | A kind of multi-robot Task Allocation towards intelligent warehousing system |
| CN110852486A (en) * | 2019-10-16 | 2020-02-28 | 中国人民解放军国防科技大学 | Task planning method for autonomous cooperation of unmanned aerial vehicle cluster |
| CN110826915A (en) * | 2019-11-07 | 2020-02-21 | 中国联合网络通信集团有限公司 | Resource scheduling method, device and computer readable storage medium |
| CN111928849A (en) * | 2019-12-20 | 2020-11-13 | 陕西科技大学 | Multi-medical delivery robot real-time path planning method |
| CN111716356A (en) * | 2020-06-18 | 2020-09-29 | 南京邮电大学 | Method for cooperation of humanoid multi-robot |
| CN112633654A (en) * | 2020-12-15 | 2021-04-09 | 哈尔滨工程大学 | Multi-unmanned aerial vehicle task allocation method based on improved cluster expansion consistency bundle algorithm |
Non-Patent Citations (4)
| Title |
|---|
| NI, JIANJUN等: "DYNAMIC BIOINSPIRED NEURAL NETWORK FOR MULTI-ROBOT FORMATION CONTROL IN UNKNOWN ENVIRONMENTS", INTERNATIONAL JOURNAL OF ROBOTICS & AUTOMATION, vol. 30, no. 3, pages 256 - 266 * |
| 林林;孙其博;王尚广;杨放春;: "基于时间窗的多无人机联盟任务分配方法研究", 电子与信息学报, no. 08, pages 209 - 214 * |
| 梁志伟;沈杰;杨祥;刘娟;朱松豪;: "RoboCup机器人救援仿真中基于拍卖的任务分配算法", 机器人, no. 04 * |
| 许可;宫华;秦新立;张博渊;: "基于分布式拍卖算法的多无人机分组任务分配", 信息与控制, no. 03 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116167595A (en) * | 2023-04-25 | 2023-05-26 | 天信达信息技术有限公司 | Method for determining personnel group decision variables, electronic equipment and storage medium |
| CN116167595B (en) * | 2023-04-25 | 2023-08-11 | 天信达信息技术有限公司 | Method for determining personnel group decision variables, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113657718B (en) | 2024-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107343025B (en) | Delay optimization method under distributed satellite cloud and mist network architecture and energy consumption constraint | |
| Abd Latiff | A checkpointed league championship algorithm-based cloud scheduling scheme with secure fault tolerance responsiveness | |
| CN109884897B (en) | Unmanned aerial vehicle task matching and calculation migration method based on deep reinforcement learning | |
| CN109829636A (en) | emergency task scheduling planning method based on dynamic priority | |
| CN112561395A (en) | Unmanned aerial vehicle cooperation method, system, device, electronic equipment and storage medium | |
| Xu et al. | Data-driven resilient fleet management for cloud asset-enabled urban flood control | |
| CN111967656A (en) | Resource scheduling method and system for multi-disaster-point emergency rescue command and control organization | |
| CN109697637B (en) | Object type determination method and device, electronic equipment and computer storage medium | |
| CN111460621A (en) | Modularized simulation modeling method and system | |
| Deng et al. | A two-phase coordinated planning approach for heterogeneous earth-observation resources to monitor area targets | |
| CN115134371A (en) | Scheduling method, system, equipment and medium containing edge network computing resources | |
| CN112230677B (en) | Unmanned aerial vehicle group task planning method and terminal equipment | |
| CN107103388B (en) | Robot scheduling system and method based on demand prediction | |
| CN109709985B (en) | Unmanned aerial vehicle task optimization method, device and system | |
| CN113657718A (en) | Multi-robot dynamic alliance task allocation method and related device | |
| CN108845886A (en) | Cloud computing energy consumption optimization method and system based on phase space | |
| CN101452541A (en) | Method for optimizing dynamic lattice work stream by employing particle cluster algorithm | |
| Sahu et al. | Heuristic search based localization in mobile computational grid | |
| CN111199440A (en) | Event prediction method and device and electronic equipment | |
| CN115454654B (en) | Adaptive resource matching obtaining method and device | |
| Moskal et al. | Adaptive unmanned aerial vehicle surveillance using a prize-collecting vertex routing model | |
| Kononov et al. | Control of a Complex of Works in Multiprocessor Real-time ACS | |
| CN114118645A (en) | Order distribution method and device, readable storage medium and electronic equipment | |
| CN113822455A (en) | Time prediction method, device, server and storage medium | |
| US10776406B2 (en) | System for multi-criteria decision analysis |
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 |