CN106126245A - A kind of multi-Agent cooperation method and system under dynamic environment - Google Patents
A kind of multi-Agent cooperation method and system under dynamic environment Download PDFInfo
- Publication number
- CN106126245A CN106126245A CN201610492787.7A CN201610492787A CN106126245A CN 106126245 A CN106126245 A CN 106126245A CN 201610492787 A CN201610492787 A CN 201610492787A CN 106126245 A CN106126245 A CN 106126245A
- Authority
- CN
- China
- Prior art keywords
- agent
- action
- language
- current
- module
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/20—Software design
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses the multi-Agent cooperation method and system under a kind of dynamic environment, method comprises the following steps: S1, is described language by multi-Agent field and describes the current environment of Agent system；S2, the problem to be solved of reception user's input are also described；S3, cook up the optimal case of this problem to be solved of a solution；In S4, Agent system, each Agent is sequentially completed the action distributing to oneself according to this optimal case, until completing everything, solves this problem to be solved；S5, when determining that current action cannot complete, current environment carried out perception again and redescribe, then switching into step S3.The beneficial effect comprise that: when causing each Agent cannot continue executing with action owing to the current environment of Agent system changes, each Agent can plan to ensure completing of task again.
Description
Technical field
The present invention relates to multi-Agent technology field, particularly relate to a kind of multi-Agent cooperation method under dynamic environment and be
System.
Background technology
Agent system (Multi-Agent System, MAS) is important point of distributed artificial intelligence research
, wherein the cooperation problem of Agent is then always the key problem of MAS research.
The cooperation of multi-Agent mainly includes following several traditional method: classical contract net protocol (Contract Net
Protocol, CNP), organizational structure cooperation, blackboard model etc..The environment of MAS is open from being closed to, uncertain from foreseeing
Change so that considering while Agent cooperation problem, it is necessary to consider the situation of change of whole system environment.But pass
System method is all only applicable to the MAS that environment is constant, the most applicable for the MAS under dynamic environment.The environment of MAS is constantly to become
Changing, therefore along with environment and the change of Agent state, the cooperation relation between Agent also can change therewith, in design
Time preset coordination mechanism operationally may cannot complete task or cooperation efficiency step-down.
Summary of the invention
The technical problem to be solved in the present invention is for realizing multi-Agent association in prior art under dynamic environment
The defect made, it is provided that the multi-Agent cooperation method and system under a kind of dynamic environment.
The technical solution adopted for the present invention to solve the technical problems is:
A kind of multi-Agent cooperation method under dynamic environment, comprises the following steps:
S1, described language by multi-Agent field and describe the current environment of Agent system；
S2, receive the problem to be solved of user's input, and describe language by multi-Agent field and be described；
S3, according to the current environment of Agent system after describing and this problem to be solved, this waits to solve to cook up a solution
The certainly optimal case of problem, this optimal case includes several actions that needs perform, is respectively allocated to many by several actions
Agent system is able to carry out the Agent of corresponding actions；
S4, Agent system have each Agent of execution task be sequentially completed according to this optimal case and distribute to oneself
Everything, when determining that current action normally completes, each Agent continues next action, until completing everything, solves
Certainly this problem to be solved；
S5, when determining that current action cannot complete, stop each Agent current action, Agent system worked as front ring
Border carries out perception again by the perceptive function of each Agent, and describes language by multi-Agent field and redescribe, with
After go to step S3.
In method of the present invention, the current environment of described Agent system includes in Agent system all
Cooperation relation between information and all Agent of Agent；The information of described Agent includes the current location of Agent, target
Position and the everything being able to carry out.
In method of the present invention, the information of the Agent with mobile task also includes the target location of this Agent.
In method of the present invention, it is that the planning field for multi-Agent defines that described multi-Agent field describes language
Language.
In method of the present invention, the description of the action that Agent is able to carry out by language is described by multi-Agent field
Including to this Agent, planning and the description of action subject again of this Agent.
The present invention provides the multi-Agent cooperation system under a kind of dynamic environment, including:
Describing module, describes the current environment of Agent system for describing language by multi-Agent field；
Receiver module, for receiving the problem to be solved of user's input, and describes language by multi-Agent field and retouches
State；
Planning module, for the current environment according to the Agent system after describing and this problem to be solved, cooks up one
Solving the optimal case of this problem to be solved, this optimal case includes several actions that needs perform, and several actions is divided
Do not distribute to Agent system is able to carry out the Agent of corresponding actions；
Completing module, in Agent system, each Agent is sequentially completed the institute distributing to oneself according to this optimal case
Having action, when determining that current action normally completes, each Agent continues next action, until completing everything, solving should
Problem to be solved；
Again planning module, for when determining that current action cannot complete, stops each Agent current action, to many
The current environment of Agent system carries out perception again by the perceptive function of each Agent, and describes language by multi-Agent field
Speech is redescribed, and then switches into planning module；
Wherein, the outfan of describing module and the outfan of receiver module are all connected with the input of planning module, planning
The outfan of module is connected with the input completing module, and the input of the outfan and planning module again that complete module connects
Connecing, the outfan of planning module is connected with the input of planning module again.
In system of the present invention, the current environment of described Agent system includes in Agent system all
Cooperation relation between information and all Agent of Agent；The information of described Agent includes the current location of Agent, target
Position and the everything being able to carry out.
In system of the present invention, the information of the Agent with mobile task also includes the target location of this Agent.
In system of the present invention, it is that the planning field for multi-Agent defines that described multi-Agent field describes language
Language.
In system of the present invention, the description of the action that Agent is able to carry out by language is described by multi-Agent field
Including to this Agent, planning and the description of action subject again of this Agent.
The beneficial effect comprise that: causing the Agent cannot owing to the environment of Agent system changes
When continuing executing with action, Agent can the current environment of perception again plan problem to be solved to ensure to ask again
The solution of topic, thus avoid under traditional method environment during tasks carrying to there occurs change and cause the failed feelings of Resolving probiems
Condition, but also planning language (MA-PDDL) can be used to facilitate the succinct cooperation relation being depicted between Agent and whole
The planning of task, facilitates computer to make optimal case for task.
Accompanying drawing explanation
Below in conjunction with drawings and Examples, the invention will be further described, in accompanying drawing:
Fig. 1 is the schematic flow sheet of the multi-Agent cooperation method under a kind of dynamic environment of the embodiment of the present invention；
Fig. 2 is the schematic diagram of the description to Agent execution action in the embodiment of the present invention；
Fig. 3 is the structural representation of the multi-Agent cooperation system under a kind of dynamic environment of the embodiment of the present invention；
Fig. 4 is the scenario simulation figure of the multi-Agent cooperation method under a kind of dynamic environment in the embodiment of the present invention.
Detailed description of the invention
In order to make the purpose of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, right
The present invention is further elaborated.Should be appreciated that specific embodiment described herein only in order to explain the present invention, not
For limiting the present invention.
In the embodiment of the present invention, as it is shown in figure 1, a kind of multi-Agent cooperation method under dynamic environment, including following step
Rapid:
S1, described language by multi-Agent field and describe the current environment of Agent system；
S2, receive the problem to be solved of user's input, and describe language by multi-Agent field and be described；
S3, according to the current environment of Agent system after describing and this problem to be solved, this waits to solve to cook up a solution
The certainly optimal case of problem, this optimal case includes several actions that needs perform, is respectively allocated to many by several actions
Agent system is able to carry out the Agent of corresponding actions；
In S4, Agent system, each Agent is sequentially completed the everything distributing to oneself according to this optimal case, when
Determining when current action normally completes, each Agent continues next action, until completing everything, solving this and to be solved asking
Topic；
S5, when determining that current action cannot complete, stop each Agent current action, Agent system worked as front ring
Border carries out perception again by the perceptive function of each Agent, and describes language by multi-Agent field and redescribe, with
After go to step S3.
In above-described embodiment, a MAS (Multi-agent System, Agent system) includes multiple Agent, its
Knowledge, data and control equal distribution are on multiple node processor (NP)s.Each Agent has certain problem solving ability, as pushed away
Manage, plan, consult, the ability such as communication and coordination.The present invention is improved on the basis of MA-PDDL, in original grammer
Adding the thought of planning continuously, knowledge that is unknown to surrounding as Agent or that grasp has been not enough in planning process
Action time, Agent can postpone the execution of planning action, then by self perception or by with other
Agent communicates, and obtains information more accurately, is continuously updated knowledge, until Agent has enough knowledge to complete to connect
Followed by execution during the planning tasks got off.
(such as during a point moves to b point, action is detected at Agent when current action cannot complete when determining
Certain barrier occurs on path), stop each Agent current action, by the sensing module of each Agent to this multi-Agent system
The current environment of system carries out perception again, describes language by multi-Agent field and redescribes, then according to problem and weight
The new current environment that describes is planned again, obtains a new optimal case, allows each Agent perform new optimum side the most again
Case.
In above-described embodiment, dynamic programming algorithm, greedy algorithm, genetic algorithm, simulated annealing can be passed through, climb the mountain
Algorithm, particle cluster algorithm and ant group algorithm etc. obtain optimal case.
In the embodiment of the present invention, the current environment of described Agent system includes all Agent in Agent system
Cooperation relation between information and all Agent；The information of described Agent includes the current location of Agent, target location and energy
Enough everythings performed.
In the embodiment of the present invention, the information of the Agent with mobile task also includes the target location of this Agent.
In the embodiment of the present invention, it is the planning field definitional language (MA-for multi-Agent that multi-Agent field describes language
PDDL)。
The definition of planning problem is the premise that planning problem solves, if a planning problem can not be come by planning language
Represent, then it all can not be solved by any one planner.After being only described by planning field language, calculate
Machine could identify that professional etiquette of going forward side by side is drawn.PDDL can solve the changeless single Agent system of environment, solves the rule of single Agent
The problem of drawing；MA-PDDL is to improve on PDDL, and the cooperation that can solve between the multiple Agent in Agent system is asked
Topic, is only applicable to the system that environment is constant；In MA-PDDL, add the method again planned could solve under dynamic environment many
Agent cooperates problem, is the MA-PDDL of a kind of improvement.MA-PDDL after improvement can also allow to add to the action of Agent
Numerical attribute and carry out addition subtraction multiplication and division computing etc..
In the embodiment of the present invention, as in figure 2 it is shown, describe, by multi-Agent field, the action that Agent is able to carry out by language
Description include to this Agent, this Agent again planning and the description of action subject.
In the embodiment of the present invention, as it is shown on figure 3, the multi-Agent cooperation system under a kind of dynamic environment, including:
Describing module, describes the current environment of Agent system for describing language by multi-Agent field；
Receiver module, for receiving the problem to be solved of user's input, and describes language by multi-Agent field and retouches
State；
Planning module, for the current environment according to the Agent system after describing and this problem to be solved, cooks up one
Solving the optimal case of this problem to be solved, this optimal case includes several actions that needs perform, and several actions is divided
Do not distribute to Agent system is able to carry out the Agent of corresponding actions；
Completing module, in Agent system, each Agent is sequentially completed the institute distributing to oneself according to this optimal case
Having action, when determining that current action normally completes, each Agent continues next action, until completing everything, solving should
Problem to be solved；
Again planning module, for when determining that current action cannot complete, stops each Agent current action, to many
The current environment of Agent system carries out perception again by the perceptive function of each Agent, and describes language by multi-Agent field
Speech is redescribed, and then switches into planning module；
Wherein, the outfan of describing module and the outfan of receiver module are all connected with the input of planning module, planning
The outfan of module is connected with the input completing module, and the input of the outfan and planning module again that complete module connects
Connecing, the outfan of planning module is connected with the input of planning module again.
In the embodiment of the present invention, the current environment of described Agent system includes all Agent in Agent system
Cooperation relation between information and all Agent；The information of described Agent includes the current location of Agent, target location and energy
Enough everythings performed.
In the embodiment of the present invention, the information of the Agent with mobile task also includes the target location of this Agent.Have
The Agent of mobile task is and is assigned to mobile task and has the Agent of locomotive function.
In the embodiment of the present invention, it is that the planning field for multi-Agent defines language that described multi-Agent field describes language
Speech.
In the embodiment of the present invention, the description being described the action that Agent is able to carry out by language by multi-Agent field is included
To this Agent, planning and the description of action subject again of this Agent.
In a specific embodiment, as shown in Figure 4, in a certain layer of a hospital, there are 4 AGV (Automatic
Guilded Vehicle, automatic guided vehicle) and 12 medical wastes deposit a little, use Agent that hospital system is modeled,
Obtain the Agent system (MAS) being made up of Cart, Cart_sensor, AGV and Decision Agent.Wherein, Cart
It is used to fill the container of medical waste；Cart_sensor is fixed on the parking place of Cart.By reading the RFID label tag of Cart
Information the release tasks (problem to be solved) such as the weight obtaining Cart；AGV (performing Agent) is to be specifically used to transport Cart
Dolly, there is different loading capacity；Decision Agent (decision agent) can select optimal according to task description
AGV performs, and cooks up an optimum mobile route for AGV simultaneously.The task (problem to be solved) of whole system is exactly profit
With AGV, the medical waste deposited inside Cart is transported hospital, put into appointed place (destination) and process.
First, according to MAS current environment, use the MA-PDDL after improving to describe each Agent and may hold inside system
The cooperation relation of possible needs between the action of row and each Agent (including performing Agent and decision agent).Then, when
Cart_sensor perceives when having medical waste to need to process inside Cart, is released in quality and the position of this Cart,
And issue transport task, and the MA-PDDL after improvement is used to describe this transport task (problem to be solved).Decision Agent
Position and weight according to Cart select a most suitable AGV to perform task, and plan an optimum by planning algorithm
Path (optimal case).The AGV chosen is by the path transporting medical rubbish planned, if environment changes during Zhi Hanging
Become, then can be successfully completed task；If finding during Zhi Hanging to there is barrier on the action path of AGV, then the holding of stopping action
OK, Decision Agent selects new most suitable AGV to lay equal stress on new planning optimal path according to transport task and current environment, so
The newest most suitable AGV is by new optimal path transporting medical rubbish.
It should be appreciated that for those of ordinary skills, can be improved according to the above description or be converted,
And all these modifications and variations all should belong to the protection domain of claims of the present invention.
Claims (10)
1. the multi-Agent cooperation method under a dynamic environment, it is characterised in that comprise the following steps:
S1, described language by multi-Agent field and describe the current environment of Agent system；
S2, receive the problem to be solved of user's input, and describe language by multi-Agent field and be described；
S3, according to the current environment of Agent system after describing and this problem to be solved, this to be solved is asked to cook up a solution
The optimal case of topic, this optimal case includes several actions that needs perform, several actions is respectively allocated to multi-Agent
System is able to carry out the Agent of corresponding actions；
Each Agent in S4, Agent system with execution task is sequentially completed the institute distributing to oneself according to this optimal case
Having action, when determining that current action normally completes, each Agent continues next action, until completing everything, solving should
Problem to be solved；
S5, when determining that current action cannot complete, stop each Agent current action, the current environment of Agent system led to
Cross the perceptive function of each Agent and carry out perception again, and describe language by multi-Agent field and redescribe, turn subsequently
To step S3.
2. multi-Agent cooperation method as claimed in claim 1, it is characterised in that the current environment bag of described Agent system
Include the cooperation relation between the information of all Agent in Agent system and all Agent；The information of described Agent includes this
The current location of Agent and the everything being able to carry out.
3. multi-Agent cooperation method as claimed in claim 2, it is characterised in that there is the information of Agent of mobile task also
Target location including this Agent.
4. multi-Agent cooperation method as claimed in claim 1, it is characterised in that it is pin that described multi-Agent field describes language
Planning field definitional language to multi-Agent.
5. multi-Agent cooperation method as claimed in claim 1, it is characterised in that describe language pair by multi-Agent field
The description of the action that Agent is able to carry out includes this Agent, planning and the description of action subject again of this Agent.
6. the multi-Agent cooperation system under a dynamic environment, it is characterised in that including:
Describing module, describes the current environment of Agent system for describing language by multi-Agent field；
Receiver module, for receiving the problem to be solved of user's input, and describes language by multi-Agent field and is described；
Planning module, for the current environment according to the Agent system after describing and this problem to be solved, cooks up a solution
The optimal case of this problem to be solved, this optimal case includes several actions that needs perform, several actions is divided respectively
Dispensing Agent system is able to carry out the Agent of corresponding actions；
Completing module, each Agent in Agent system with execution task is sequentially completed distribution according to this optimal case
To the everything of oneself, when determining that current action normally completes, each Agent continues next action, until completing to own
Action, solves this problem to be solved；
Again planning module, for when determining that current action cannot complete, stops each Agent current action, to multi-Agent system
The current environment of system carries out perception again by the perceptive function of each Agent, and describes language by multi-Agent field and carry out heavily
New description, then switches into planning module；
Wherein, the outfan of describing module and the outfan of receiver module are all connected with the input of planning module, planning module
Outfan be connected with the input completing module, the input of the outfan and planning module again that complete module is connected, weight
The outfan of new planning module is connected with the input of planning module.
7. multi-Agent cooperation system as claimed in claim 6, it is characterised in that the current environment bag of described Agent system
Include the cooperation relation between the information of all Agent in Agent system and all Agent；The information of described Agent includes this
The current location of Agent and the everything being able to carry out.
8. multi-Agent cooperation system as claimed in claim 7, it is characterised in that there is the information of Agent of mobile task also
Target location including this Agent.
9. multi-Agent cooperation system as claimed in claim 6, it is characterised in that it is pin that described multi-Agent field describes language
Planning field definitional language to multi-Agent.
10. multi-Agent cooperation system as claimed in claim 6, it is characterised in that describe language pair by multi-Agent field
The description of the action that Agent is able to carry out includes this Agent, planning and the description of action subject again of this Agent.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610492787.7A CN106126245A (en) | 2016-06-28 | 2016-06-28 | A kind of multi-Agent cooperation method and system under dynamic environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610492787.7A CN106126245A (en) | 2016-06-28 | 2016-06-28 | A kind of multi-Agent cooperation method and system under dynamic environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106126245A true CN106126245A (en) | 2016-11-16 |
Family
ID=57285193
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610492787.7A Pending CN106126245A (en) | 2016-06-28 | 2016-06-28 | A kind of multi-Agent cooperation method and system under dynamic environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106126245A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106598590A (en) * | 2016-12-12 | 2017-04-26 | 华东师范大学 | Software architecture modeling and simulation method |
| CN109885010A (en) * | 2019-03-20 | 2019-06-14 | 中南大学 | The health combined based on multi-Agent and Internet of Things sees maintaining method, device and storage medium |
| CN110086350A (en) * | 2019-05-30 | 2019-08-02 | 南京邮电大学 | It is a kind of to be climbed the mountain the isolation type bidirectional DC-DC efficiency optimization method of hybrid algorithm based on simulated annealing- |
| CN110162400A (en) * | 2019-05-21 | 2019-08-23 | 湖南大学 | The method and system of intelligent body cooperation in MAS system is realized under complex network environment |
| CN110597093A (en) * | 2019-09-05 | 2019-12-20 | 武汉工程大学 | Dynamic cooperation system and cooperation method for intelligent sensing and controlling equipment of self-adaptive parking lot |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020062334A1 (en) * | 1998-08-19 | 2002-05-23 | Qiming Chen | Dynamic agents for dynamic service provision |
| CN101448285A (en) * | 2008-12-31 | 2009-06-03 | 西安交通大学 | Energy conservation oriented method for allocating tasks with multi-step negotiation of mobile Agent |
| CN101964019A (en) * | 2010-09-10 | 2011-02-02 | 北京航空航天大学 | Against behavior modeling simulation platform and method based on Agent technology |
| CN104239594A (en) * | 2014-06-13 | 2014-12-24 | 中国人民解放军装备学院 | Artificial environment model, Agent model and modeling method of Agent model |
-
2016
- 2016-06-28 CN CN201610492787.7A patent/CN106126245A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020062334A1 (en) * | 1998-08-19 | 2002-05-23 | Qiming Chen | Dynamic agents for dynamic service provision |
| CN101448285A (en) * | 2008-12-31 | 2009-06-03 | 西安交通大学 | Energy conservation oriented method for allocating tasks with multi-step negotiation of mobile Agent |
| CN101964019A (en) * | 2010-09-10 | 2011-02-02 | 北京航空航天大学 | Against behavior modeling simulation platform and method based on Agent technology |
| CN104239594A (en) * | 2014-06-13 | 2014-12-24 | 中国人民解放军装备学院 | Artificial environment model, Agent model and modeling method of Agent model |
Non-Patent Citations (2)
| Title |
|---|
| 李明等: "基于改进合同网协议的多Agent动态任务分配", 《山东大学学报（工学版）》 * |
| 陶雪丽等: "多Agent层次任务分配方法", 《计算机工程与设计》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106598590A (en) * | 2016-12-12 | 2017-04-26 | 华东师范大学 | Software architecture modeling and simulation method |
| CN106598590B (en) * | 2016-12-12 | 2020-10-02 | 华东师范大学 | Software architecture modeling and simulation method |
| CN109885010A (en) * | 2019-03-20 | 2019-06-14 | 中南大学 | The health combined based on multi-Agent and Internet of Things sees maintaining method, device and storage medium |
| CN110162400A (en) * | 2019-05-21 | 2019-08-23 | 湖南大学 | The method and system of intelligent body cooperation in MAS system is realized under complex network environment |
| CN110086350A (en) * | 2019-05-30 | 2019-08-02 | 南京邮电大学 | It is a kind of to be climbed the mountain the isolation type bidirectional DC-DC efficiency optimization method of hybrid algorithm based on simulated annealing- |
| CN110597093A (en) * | 2019-09-05 | 2019-12-20 | 武汉工程大学 | Dynamic cooperation system and cooperation method for intelligent sensing and controlling equipment of self-adaptive parking lot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106126245A (en) | A kind of multi-Agent cooperation method and system under dynamic environment | |
| Zaeh et al. | A holistic approach for the cognitive control of production systems | |
| Gajsek et al. | Using maturity model and discrete-event simulation for industry 4.0 implementation | |
| Erol et al. | A multi-agent based approach to dynamic scheduling of machines and automated guided vehicles in manufacturing systems | |
| CN106483943A (en) | The dispatching method of robot, device and computer-readable recording medium | |
| CN104487947B (en) | The unknowable resource allocation frame in domain | |
| Zhang et al. | Self-organizing manufacturing: Current status and prospect for Industry 4.0 | |
| Guo et al. | An agent-oriented approach to resolve scheduling optimization in intelligent manufacturing | |
| Ho et al. | Federated deep reinforcement learning for task scheduling in heterogeneous autonomous robotic system | |
| CN110134081A (en) | Control system based on robot capability model | |
| CN110231993A (en) | Battery management method, device, electronic equipment, storage medium | |
| JP2021504809A (en) | Methods for processing article sorting scheduling requests, and related devices | |
| Strang et al. | Dynamic, adaptive worker allocation for the integration of human factors in cyber-physical production systems | |
| Bai et al. | Smart mobile robot fleet management based on hierarchical multi-agent deep Q network towards intelligent manufacturing | |
| US20220398528A1 (en) | System and method for order processing | |
| CN111308995A (en) | Method, device, medium, and electronic apparatus for scheduling transfer robot | |
| CN109190900A (en) | A kind of method that distribution Constraint Anchored Optimization solves AGV scheduling system task distribution | |
| Avhad et al. | A framework for multi-robot control in execution of a Swarm Production System | |
| Van Brussel et al. | Design of holonic manufacturing systems | |
| Harjes et al. | Autonomous control in closed dynamic logistic systems | |
| Zhang et al. | A digital twin-driven flexible scheduling method in a human–machine collaborative workshop based on hierarchical reinforcement learning | |
| CN103034528B (en) | A kind of examination & approval of the multi-Agent based on body task data disposal route | |
| CN106201847A (en) | Consider method for allocating tasks, device and the system of the decay of cloud platform host performance | |
| Tripathi et al. | Multi agent system in job shop scheduling using contract net protocol | |
| AU2020101681A4 (en) | Centralized cloud laundry logistic management system using iot enabled laundry terminals in residential locations |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161116 |
|
| RJ01 | Rejection of invention patent application after publication |