CN113313420A - AGV intelligence system of putting in storage - Google Patents
AGV intelligence system of putting in storage Download PDFInfo
- Publication number
- CN113313420A CN113313420A CN202110703709.8A CN202110703709A CN113313420A CN 113313420 A CN113313420 A CN 113313420A CN 202110703709 A CN202110703709 A CN 202110703709A CN 113313420 A CN113313420 A CN 113313420A
- Authority
- CN
- China
- Prior art keywords
- agv
- module
- task
- stack
- warehouse
- 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
- 238000012549 training Methods 0.000 claims abstract description 23
- 230000007246 mechanism Effects 0.000 claims abstract description 22
- 238000004891 communication Methods 0.000 claims abstract description 18
- 238000000034 method Methods 0.000 claims abstract description 17
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 230000008569 process Effects 0.000 claims abstract description 9
- 239000013598 vector Substances 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000010801 machine learning Methods 0.000 claims description 11
- 238000007637 random forest analysis Methods 0.000 claims description 8
- 238000012706 support-vector machine Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 abstract description 7
- 238000012360 testing method Methods 0.000 description 6
- 230000004044 response Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002650 habitual effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 238000012163 sequencing technique Methods 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
- G06Q10/06316—Sequencing of tasks or work
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
-
- G06Q50/40—
Abstract
The invention discloses an AGV intelligent warehousing system, which belongs to the technical field of warehouse scheduling and comprises an input module, a bin selection module, a priority determination module, a stacking module and an AGV; the input module is in communication connection with the bin selection module, the bin selection module is in communication connection with the priority determination module, the priority determination module is in communication connection with the stack module, and the stack module is in communication connection with the AGV; the input module is used for inputting the length, width and height of the pallet to be warehoused and the type of goods, and transmitting the length, width and height of the pallet and the type of the goods to the warehouse selection module; the bin selection module is used for constructing a decision model and inputting the length, width and height of the received pallet and the type of goods into the decision model. The invention can automatically obtain the bin according with the storage habit, introduces a method for acquiring the characteristic parameters of basic data, preprocessing the data and training to obtain an automatic bin selection decision model, designs a flexible robust transportation scheduling mechanism, standardizes and optimizes the transportation scheduling process, and ensures that the AGV trolley quickly responds to the prior transportation task and completely conforms the plan and execution.
Description
Technical Field
The invention relates to the technical field of warehouse scheduling, in particular to an AGV intelligent warehousing system.
Background
The stereoscopic warehouse is widely applied to logistics companies and manufacturing enterprises in combination with AGV trolleys. Currently, allocation of positions to goods and pallets generally employs manual experience or rule-based heuristic algorithms. Although the heuristic algorithm can automatically calculate a feasible bin, the heuristic algorithm is often different from an ideal bin that an operator is accustomed to. By utilizing an artificial intelligence method based on machine learning, the bin which is relatively in accordance with the requirements of operators can be automatically selected. The support vector machine and the random forest are two typical algorithms for machine learning, however, how to design and collect the characteristic parameters and how to preprocess the characteristic parameters are the key to applying the typical algorithm for machine learning to bin intelligent allocation.
The position of a bin obtained by the current rule-based automatic bin selection method is often deviated from a customary storage position, and the dispatching response of the AGV is not flexible enough and the planning and execution are inconsistent when an emergency warehouse-in and warehouse-out transportation task is inserted.
Therefore, those skilled in the art provide an AGV intelligent warehousing system to solve the problems set forth in the background art.
Disclosure of Invention
The embodiment of the application can automatically obtain the bin according with the storage habit by providing the AGV intelligent warehousing system, introduces a method for acquiring the characteristic parameters of basic data, preprocessing the data and training to obtain an automatic bin selection decision model, designs a flexible robust transportation scheduling mechanism, standardizes and optimizes the transportation scheduling process, enables the AGV trolley to quickly respond to a prior transportation task and enables the plan to be completely consistent with the execution, and solves the problems in the background technology.
The embodiment of the application provides an AGV intelligent warehousing system which comprises an input module, a bin selection module, a priority determination module, a stacking module and an AGV;
the input module is in communication connection with a bin selection module, the bin selection module is in communication connection with a priority determination module, the priority determination module is in communication connection with a stack module, and the stack module is in communication connection with an AGV;
the input module is used for inputting the length, the width and the height of the pallet to be warehoused and the type of goods, and transmitting the length, the width and the height of the pallet and the type of the goods to the warehouse selection module; the warehouse selection module is used for constructing a decision model, inputting the length, width and height of the received pallet and the type of goods into the decision model, reading state vectors of all current warehouse positions from a database, and outputting warehouse-in recommended warehouse positions; the priority determining module adopts a flexible robust scheduling mechanism, puts the warehousing tasks and the ex-warehouse tasks corresponding to the warehousing recommended positions into a task pool stack together, sorts the tasks according to the priority, and sends the sorted task pool stack to the stack module; the stack module receives the task pool stack and conveys the task pool stack to an AGV; the AGV trolley is used for reading the most prior task in the task pool stack and then immediately responding to and executing the task, and the record in the task pool stack is immediately deleted.
The AGV intelligent warehousing system can automatically obtain the bin according with the storage habit, introduces a method for acquiring basic data characteristic parameters, preprocessing data and training to obtain an automatic bin selection decision model, designs a flexible robust transportation scheduling mechanism, standardizes and optimizes the transportation scheduling process, enables the AGV trolley to quickly respond to a prior transportation task, and enables the plan and the execution to be completely consistent.
Further, the specific construction process of the decision model is as follows:
s1: collecting the states of all bin positions during each bin selection as characteristic parameters for machine learning;
s2: selecting and preprocessing characteristic parameters and labels, and training comparison prediction accuracy;
s3: and taking the model with the highest prediction accuracy as a decision model.
The bin according with the storage habit can be automatically obtained through the decision model.
Further, when the states of all bins are collected in S1, a field is added to the database, a binary code composed of the states of all bins at that time is stored each time a bin is selected, and the code is used as a feature vector of the machine learning training model.
Further, the S2 specifically includes: and taking the cargo type, the length, the width and the height of the pallet and the state characteristic vectors of all the bins as input parameters, changing the length, the width and the height of the pallet into binary parameters through one-hot coding, taking the selected bins as labels, and training the preprocessed data by using a support vector machine and a random forest algorithm respectively.
Further, the flexible robust scheduling mechanism specifically includes: after the position of a warehouse where the pallet is stored is determined, the carrying tasks do not need to be immediately distributed to the AGV, the priority of each warehouse in and out task is selected firstly and put into a task pool stack, the system sorts the warehouse in and out tasks according to the priority, and the AGV actively reads information in the transportation task pool stack after executing the current task each time; if the information in the stack is empty, the AGV trolley is switched to a standby state; otherwise, reading and executing the priority task arranged at the top in the task pool stack, and deleting the task in the task pool. Under this scheduling mechanism, the AGV may not receive any subsequent tasks until it completes the current transfer task. Compared with the mode that the AGV trolleys are assigned to carry after the bin position is selected every time, when emergency pieces are inserted or some AGV trolley breaks down and other emergency conditions occur, the flexible robust transport scheduling mechanism provided by the invention can meet all emergency priority tasks and is reasonably distributed to all AGV trolleys to quickly finish all transport tasks.
Furthermore, AGV intelligence warehouse entry system still includes awakening module, awakening module and AGV dolly communication connection, when the task pool has had new task, and the AGV dolly is in standby state, and the operator accessible awakens up the module initiative and calls and awakens up the AGV dolly this moment. This setting makes things convenient for the operator to awaken up the AGV dolly fast.
Furthermore, after the recommended bin is obtained through the decision model, an operator can modify the storage position according to the preference, the priority of each task is set by combining a flexible robust scheduling mechanism, and the warehousing and ex-warehousing tasks are distributed to each AGV. The operator can modify the transport priority sequence for multiple times as required, so that the emergency task can be processed conveniently and preferentially.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
the invention can automatically obtain the bin according with the storage habit, introduces a method for acquiring the characteristic parameters of basic data, preprocessing the data and training to obtain an automatic bin selection decision model, designs a flexible robust transportation scheduling mechanism, standardizes and optimizes the transportation scheduling process, and ensures that the AGV trolley quickly responds to the prior transportation task and completely conforms the plan and execution.
Drawings
Fig. 1 is a block diagram of the overall structure of a warehousing system in the embodiment of the present application;
FIG. 2 is a flow chart of a newly added entry in the embodiment of the present application;
FIG. 3 is a flowchart illustrating AGV cart task execution according to an embodiment of the present application.
Detailed Description
Through the decision model and the flexible robust transportation scheduling mechanism, the technical problems that the bin position obtained in the prior art often deviates from a habitual storage position and the scheduling response of the AGV trolley is not flexible enough when an emergency warehouse-in and warehouse-out transportation task is inserted are solved, the bin position conforming to the storage habit is automatically obtained, the AGV trolley can quickly respond to the prior transportation task and the plan and the execution are completely consistent.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
Referring to fig. 1 to 3, in the embodiment of the application, an AGV intelligent warehousing system includes an input module, a bin selection module, a priority determination module, a stacking module and an AGV; the input module is in communication connection with the bin selection module, the bin selection module is in communication connection with the priority determination module, the priority determination module is in communication connection with the stack module, and the stack module is in communication connection with the AGV; the input module is used for inputting the length, width and height of the pallet to be warehoused and the type of goods, and transmitting the length, width and height of the pallet and the type of the goods to the warehouse selection module; the warehouse selection module is used for constructing a decision model, inputting the length, width and height of the received pallet and the type of the goods into the decision model, reading state vectors of all current warehouse positions from a database, and outputting warehouse-in recommended warehouse positions; the priority determining module adopts a flexible robust scheduling mechanism, puts the warehousing tasks and the ex-warehouse tasks corresponding to the warehousing recommended positions into a task pool stack together, sorts the tasks according to the priority, and sends the sorted task pool stack to the stacking module; the stack module receives the task pool stack and transmits the task pool stack to the AGV; the AGV trolley is used for reading the most prior task in the task pool stack and then immediately responding to and executing the task, and the record in the task pool stack is immediately deleted. The AGV intelligent warehousing system can automatically obtain the bin according with the storage habit, introduces a method for acquiring basic data characteristic parameters, preprocessing data and training to obtain an automatic bin selection decision model, designs a flexible robust transportation scheduling mechanism, standardizes and optimizes the transportation scheduling process, enables the AGV trolley to quickly respond to a prior transportation task, and enables the plan and the execution to be completely consistent.
The invention is suitable for the configuration mode of the goods shelf and the AGV trolley widely adopted by the stereoscopic warehouse. The warehouse is provided with a plurality of rows of multi-layer goods shelves, each layer is provided with a plurality of bin positions, the bin positions have specifications with various lengths, widths and heights, and various goods have habitually storage areas. Be furnished with many AGV dollies in the warehouse, the AGV dolly is from taking navigation, can automatic handling goods pallet to appointed position in storehouse.
In this embodiment: the specific construction process of the decision model comprises the following steps:
s1: collecting the states of all bin positions during each bin selection as characteristic parameters for machine learning;
s2: selecting and preprocessing characteristic parameters and labels, and training comparison prediction accuracy;
s3: and taking the model with the highest prediction accuracy as a decision model.
The bin according with the storage habit can be automatically obtained through the decision model.
In this embodiment: and S1, when the states of all the bins are collected, adding a field in the database, storing a binary code consisting of the states of all the bins at that time when the bins are selected each time, and using the code as a feature vector of the machine learning training model. Specifically, a field for storing the states of all current bins is added in the database, when the bins are selected each time, the states of all current bins are respectively represented by 0 for availability and 1 for occupation, and the states of all bins form a binary code and are stored in the field.
In this embodiment: s2 specifically includes: and taking the cargo type, the length, the width and the height of the pallet and the state characteristic vectors of all the bins as input parameters, changing the length, the width and the height of the pallet into binary parameters through one-hot coding, taking the selected bins as labels, and training the preprocessed data by using a support vector machine and a random forest algorithm respectively. And the states of all the positions are combined into a binary code and stored in the field, and the length, the width and the height of the current pallet, the cargo type information and the position information of the selected position are stored. After ten thousand bin selections, ten thousand records are stored in the database as historical basic data. Because the support vector machine and the random forest algorithm of machine learning can only recognize binary basic data parameters, data needs to be preprocessed after the data of the database is read. And performing one-hot coding on the length, width and height data and the cargo type of the pallet, and converting the length, width and height values and the cargo type into binary parameter vectors. And simultaneously converting the binary code of the bin state into a parameter vector, and taking the selected bin information as the label quantity. After the historical basic data is preprocessed, the data is averagely divided into five equal parts, wherein four equal parts are used as training data, the rest equal parts are used as test data, the five equal parts are respectively used as training data and test data in turn, the training data and the test data are respectively input into a typical support vector machine and a random forest algorithm, and the average value of the accuracy is calculated through five rounds of training operation. And taking the prediction model with the highest average accuracy as a decision model for automatically selecting the bin.
In this embodiment: the flexible robust scheduling mechanism specifically comprises: after the position of a warehouse where the pallet is stored is determined, the carrying tasks do not need to be immediately distributed to the AGV, the priority of each warehouse in and out task is selected firstly and put into a task pool stack, the system sorts the warehouse in and out tasks according to the priority, and the AGV actively reads information in the transportation task pool stack after executing the current task each time; if the information in the stack is empty, the AGV trolley is switched to a standby state; otherwise, reading and executing the priority task arranged at the top in the task pool stack, and deleting the task in the task pool. Under this scheduling mechanism, the AGV may not receive any subsequent tasks until it completes the current transfer task. Compared with the mode that the AGV trolleys are assigned to carry after the bin position is selected every time, when emergency pieces are inserted or some AGV trolley breaks down and other emergency conditions occur, the flexible robust transport scheduling mechanism provided by the invention can meet all emergency priority tasks and is reasonably distributed to all AGV trolleys to quickly finish all transport tasks.
In this embodiment: the AGV intelligent warehousing system further comprises a wake-up module, the wake-up module is in communication connection with the AGV, when a new task exists in the task pool, the AGV is in a standby state, and at the moment, an operator can actively call the wake-up AGV through the wake-up module. This setting makes things convenient for the operator to awaken up the AGV dolly fast. In this embodiment: after the recommended bin is obtained through the decision model, an operator can modify the storage position according to the preference, the priority of each task is set by combining a flexible robust scheduling mechanism, and the warehousing and ex-warehousing tasks are distributed to each AGV. The operator can modify the transport priority sequence for multiple times as required, so that the emergency task can be processed conveniently and preferentially.
The working principle is as follows: when the AGV intelligent warehousing system is used, firstly, a warehouse selection module builds a decision model. The method specifically comprises the following steps: firstly, designing characteristic parameters to be collected and recording basic data. And adding a field for storing the states of all current bins in the database, wherein when the bins are selected, the states of all the current bins are respectively represented by 0 for availability and 1 for occupation, and the states of all the bins form a binary code and are stored in the field. And storing the length, width, height, cargo type information and the selected position information of the warehouse of the current pallet. After ten thousand bin selections, ten thousand records are stored in the database as historical basic data. Because the support vector machine and the random forest algorithm of machine learning can only recognize binary basic data parameters, data needs to be preprocessed after the data of the database is read. And performing one-hot coding on the length, width and height data and the cargo type of the pallet, and converting the length, width and height values and the cargo type into binary parameter vectors. And simultaneously converting the binary code of the bin state into a parameter vector, and taking the selected bin information as the label quantity. After the historical basic data is preprocessed, the data is averagely divided into five equal parts, wherein four equal parts are used as training data, the rest equal parts are used as test data, the five equal parts are respectively used as training data and test data in turn, the training data and the test data are respectively input into a typical support vector machine and a random forest algorithm, and the average value of the accuracy is calculated through five rounds of training operation. And taking the prediction model with the highest average accuracy as a decision model for automatically selecting the bin.
Then, as shown in fig. 2, when a pallet needing to be newly added and put in storage appears, the bin positions are automatically allocated and put into the transportation task pool stack. The input module inputs the length, width and height of the warehouse-in pallet and the type of the goods, wherein the length, width and height of the pallet are automatically detected through a sensor, the parameters can be added manually, and the type of the goods is input. The current use states of all the bins can be read from a database, the parameters are input into a decision model together, and the bin selection module can automatically obtain the recommended bins.
After the bin selection module obtains the recommended bin through the decision model, an operator can modify the storage position according to the preference, and the bin selection module then outputs the modified recommended bin to the priority determination module. The priority determining module is used for putting the warehousing tasks and the ex-warehouse tasks corresponding to the warehousing recommended positions into a task pool stack according to a flexible robust scheduling mechanism, sequencing the tasks according to the priority, sending the sequenced task pool stack to a stack module, receiving the task pool stack by the stack module, conveying the task pool stack to an AGV trolley, reading the most prior task in the task pool stack by the AGV trolley, immediately responding to and executing, and immediately deleting the record in the task pool stack. Before each task is actually loaded on the AGV, the transportation priority sequence of each task can be modified for multiple times, and when an emergency warehousing/ex-warehousing task exists, the tasks can be automatically arranged in front of other tasks as long as a higher task priority is set.
Finally, as shown in fig. 3, under the scheduling of a flexible robust scheduling mechanism, the AGV intelligent warehousing system does not need to immediately allocate the transport tasks to the AGV after determining the storage bay of the pallet, but first selects the priority of each warehousing-in/out task, puts the priority into the warehousing-in/out transport task pool stack, and sorts the warehousing-in/out tasks according to the priority. After the AGV car finishes the current task each time, the AGV car actively reads the information in the transportation task pool stack. If the information in the stack is empty, the AGV trolley is switched to a standby state; otherwise, reading and executing the priority task arranged at the top in the task pool stack, and deleting the task in the task pool. When the task pool has a new task and the AGV car is in a standby state, the operator can actively call the AGV car to wake up through the wake-up module.
The invention can automatically obtain the bin according with the storage habit, introduces a method for acquiring the characteristic parameters of basic data, preprocessing the data and training to obtain an automatic bin selection decision model, designs a flexible robust transportation scheduling mechanism, standardizes and optimizes the transportation scheduling process, and ensures that the AGV trolley quickly responds to the prior transportation task and completely conforms the plan and execution.
Therefore, the present invention is not limited to the above embodiments, and any person skilled in the art can substitute or change the technical solutions and concepts of the present invention within the technical scope of the present disclosure.
Claims (7)
- The AGV intelligent warehousing system is characterized by comprising an input module, a bin selection module, a priority determination module, a stacking module and an AGV;the input module is in communication connection with a bin selection module, the bin selection module is in communication connection with a priority determination module, the priority determination module is in communication connection with a stack module, and the stack module is in communication connection with an AGV;the input module is used for inputting the length, the width and the height of the pallet to be warehoused and the type of goods, and transmitting the length, the width and the height of the pallet and the type of the goods to the warehouse selection module; the warehouse selection module is used for constructing a decision model, inputting the length, width and height of the received pallet and the type of goods into the decision model, reading state vectors of all current warehouse positions from a database, and outputting warehouse-in recommended warehouse positions; the priority determining module adopts a flexible robust scheduling mechanism, puts the warehousing tasks and the ex-warehouse tasks corresponding to the warehousing recommended positions into a task pool stack together, sorts the tasks according to the priority, and sends the sorted task pool stack to the stack module; the stack module receives the task pool stack and conveys the task pool stack to an AGV; the AGV trolley is used for reading the most prior task in the task pool stack and then immediately responding to and executing the task, and the record in the task pool stack is immediately deleted.
- 2. The AGV intelligent warehousing system of claim 1, wherein the specific construction process of the decision model is:s1: collecting the states of all bin positions during each bin selection as characteristic parameters for machine learning;s2: selecting and preprocessing characteristic parameters and labels, and training comparison prediction accuracy;s3: and taking the model with the highest prediction accuracy as a decision model.
- 3. The AGV intelligent warehousing system of claim 2, wherein when S1 collects the statuses of all bins, the database adds a field, and stores a binary code composed of the statuses of all bins at that time each time a bin is selected, and uses the code as a feature vector of the machine learning training model.
- 4. The AGV intelligent warehousing system of claim 2, wherein the S2 is specifically: and taking the cargo type, the length, the width and the height of the pallet and the state characteristic vectors of all the bins as input parameters, changing the length, the width and the height of the pallet into binary parameters through one-hot coding, taking the selected bins as labels, and training the preprocessed data by using a support vector machine and a random forest algorithm respectively.
- 5. The AGV intelligent warehousing system of claim 1, wherein the flexible robust scheduling mechanism is specifically: after the position of a warehouse where the pallet is stored is determined, the carrying tasks do not need to be immediately distributed to the AGV, the priority of each warehouse in and out task is selected firstly and put into a task pool stack, the system sorts the warehouse in and out tasks according to the priority, and the AGV actively reads information in the transportation task pool stack after executing the current task each time; if the information in the stack is empty, the AGV trolley is switched to a standby state; otherwise, reading and executing the priority task arranged at the top in the task pool stack, and deleting the task in the task pool.
- 6. The AGV intelligent warehousing system of claim 5, further comprising a wake-up module communicatively connected to the AGV, wherein when the task pool has a new task and the AGV is in a standby state, an operator can actively call to wake up the AGV through the wake-up module.
- 7. The AGV intelligent warehousing system of claim 1, wherein after the recommended bin is obtained through the decision model, an operator can modify the storage position according to preference, and set the priority of each task and allocate warehousing and ex-warehousing tasks to each AGV in combination with a flexible robust scheduling mechanism, the transportation priority sequence of each task can be modified for many times before being actually loaded on the AGV, and when an emergency warehousing and ex-warehousing task is available, the tasks can be automatically arranged in front of other tasks as long as a higher task priority is set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110703709.8A CN113313420A (en) | 2021-06-24 | 2021-06-24 | AGV intelligence system of putting in storage |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110703709.8A CN113313420A (en) | 2021-06-24 | 2021-06-24 | AGV intelligence system of putting in storage |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113313420A true CN113313420A (en) | 2021-08-27 |
Family
ID=77380025
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110703709.8A Pending CN113313420A (en) | 2021-06-24 | 2021-06-24 | AGV intelligence system of putting in storage |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113313420A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117094499A (en) * | 2023-08-08 | 2023-11-21 | 矿冶科技集团有限公司 | Distribution trolley optimal scheduling method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107341629A (en) * | 2017-05-24 | 2017-11-10 | 国网北京市电力公司 | Bay assignment method and device |
| CN110264120A (en) * | 2019-05-06 | 2019-09-20 | 盐城品迅智能科技服务有限公司 | A kind of intelligent storage route planning system and method based on more AGV |
| CN112036667A (en) * | 2020-09-29 | 2020-12-04 | 劢微机器人科技(深圳)有限公司 | Warehouse goods location optimization method, equipment, storage medium and device |
| CN112036773A (en) * | 2020-09-29 | 2020-12-04 | 劢微机器人科技(深圳)有限公司 | AGV trolley task allocation method, AGV trolley task allocation equipment, storage medium and device |
-
2021
- 2021-06-24 CN CN202110703709.8A patent/CN113313420A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107341629A (en) * | 2017-05-24 | 2017-11-10 | 国网北京市电力公司 | Bay assignment method and device |
| CN110264120A (en) * | 2019-05-06 | 2019-09-20 | 盐城品迅智能科技服务有限公司 | A kind of intelligent storage route planning system and method based on more AGV |
| CN112036667A (en) * | 2020-09-29 | 2020-12-04 | 劢微机器人科技(深圳)有限公司 | Warehouse goods location optimization method, equipment, storage medium and device |
| CN112036773A (en) * | 2020-09-29 | 2020-12-04 | 劢微机器人科技(深圳)有限公司 | AGV trolley task allocation method, AGV trolley task allocation equipment, storage medium and device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117094499A (en) * | 2023-08-08 | 2023-11-21 | 矿冶科技集团有限公司 | Distribution trolley optimal scheduling method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110084471B (en) | Sorting scheduling method and device, warehousing system and readable storage medium | |
| CN111409997A (en) | Transfer robot picking task scheduling method for mobile shelf warehousing system | |
| KR20130038884A (en) | System and method for process management in a materials handling facility | |
| KR20190048674A (en) | Intelligent logistics robot | |
| CN111027902B (en) | Unmanned warehouse goods transportation matching method and device | |
| Gotthardt et al. | Digitalized milk-run system for a learning factory assembly line | |
| CN104835022A (en) | Logistics center dump intelligent decision control system based on RFID and batch flow technologies and method | |
| CN112016811A (en) | AGV intelligent scheduling system and method based on reinforcement learning | |
| CN111222819A (en) | Method for determining cargo vehicle, warehouse management device, system, equipment and medium | |
| CN113313420A (en) | AGV intelligence system of putting in storage | |
| CN114580996A (en) | Method for discharging bin | |
| CN115689439A (en) | Warehouse material storage position distributing and selecting system based on genetic algorithm | |
| CN112434875B (en) | Equipment path management method, system and server for intelligent warehousing | |
| CN116151741B (en) | Warehouse management method and system for warehouse goods | |
| WO2023226756A1 (en) | Device scheduling method, electronic device, and storage medium | |
| Kahraman et al. | Warehouse location design using AS/RS technologies: An interval valued intuitionistic fuzzy AHP approach | |
| CN112875123A (en) | Intelligent warehouse logistics flow method | |
| CN116307433B (en) | Material guarantee supply method and electronic equipment | |
| CN116777328A (en) | Logistics line and loading management method, device, equipment and storage medium | |
| CN110577048B (en) | Method and system for warehousing scheduling | |
| Takvir | Milkrun 4.0” for Smart Manufacturing | |
| CN113674051A (en) | Goods delivery method and device, electronic equipment and storage medium | |
| CN114662853A (en) | Distribution method, equipment, product and medium of transport vehicle | |
| CN113233070B (en) | Online stacker control method and system based on Internet of things | |
| CN114358680A (en) | Task allocation method, electronic device and computer program product |
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 |