Traveling vehicle system

Abstract

The present invention provides a transport vehicle system including a plurality of transport vehicles that travel along a transport path, and a transport vehicle controller that controls traveling of the transport vehicles. The transport vehicle controller includes: a route determination unit that determines traveling routes of the transport vehicles on the basis of a link cost of each of a plurality of links; a selection unit that selects, from among the plurality of links, a target link that is predicted to have a future use degree exceeding a predetermined reference; and a cost change unit that calculates an index value indicating likelihood of congestion of the transport vehicles for each of a plurality of upstream links present within a predetermined upstream side range starting from an upstream side merge section closest to the target link, preferentially selects upstream links having high index values as one or more bottleneck links, and increases the link costs of the one or more bottleneck links.

Description

Vehicle System

[0001] The present disclosure relates to a vehicle system.

[0002] Conventionally, there has been known a traveling vehicle system that controls the traveling of a traveling vehicle that transports articles such as FOUPs (Front Opening Unified Pods) that house semiconductor substrates in, for example, a semiconductor manufacturing factory (see Patent Document 1). Patent Document 1 describes a method for setting a traveling route for the traveling vehicle based on link costs set for each link on a specified travelable route.

[0003] Patent No. 7059999

[0004] In the above-described method, by increasing the link cost of a link that is predicted to be highly utilized (hereinafter referred to as a "target link"), it is possible to make it easier to select a route that bypasses the target link, thereby suppressing the occurrence of congestion on the target link. However, there are cases where simply increasing the link cost of the target link as described above is not enough to appropriately suppress the occurrence of congestion in the traveling vehicle system.

[0005] Therefore, an object of the present disclosure is to provide a traveling vehicle system that can effectively suppress the occurrence of traffic congestion.

[0006] The present disclosure includes the vehicle systems [1] to [5].

[0007] [1] A traveling vehicle system comprising: a plurality of traveling vehicles traveling along a predetermined traveling path; and a controller that controls the traveling of the traveling vehicles by assigning a traveling command to a traveling vehicle selected from the plurality of traveling vehicles to instruct the traveling vehicle to head to a predetermined point on the traveling path, wherein the traveling path includes a plurality of nodes including branching sections and merging sections, and a plurality of links connecting the nodes; the controller comprising: a storage unit that stores a layout of the traveling path and link costs associated with each of the plurality of links; a route determination unit that, based on the link costs of each of the plurality of links, determines, with priority, as the traveling route of the traveling vehicle, a candidate route having a small sum of the link costs of a plurality of links included in the candidate route, from a plurality of candidate routes for executing the traveling command; and a selection unit that selects, from the plurality of links, a target link whose future utilization is expected to exceed a predetermined standard. a cost change unit that acquires an index value indicating the likelihood of the traveling vehicles concentrating for each of a plurality of upstream links that are present within a predetermined upstream range starting from an upstream junction closest to the target link among the plurality of links, preferentially selects the upstream links with high index values ​​as one or more bottleneck links, and increases the link cost of the one or more bottleneck links.

[0008] According to the traveling vehicle system of [1] above, rather than simply increasing the link cost of the target link, the system increases the link cost of a bottleneck link, which is a link that is likely to attract a large number of vehicles and is located within a predetermined upstream range starting from the upstream junction closest to the target link. This can prevent congestion at the bottleneck link. In other words, it can prevent a significant increase in the number of vehicles using the bottleneck link to reach the target link in the future (i.e., the occurrence of congestion at the bottleneck link). As a result, congestion in the traveling vehicle system can be effectively prevented.

[0009] [2] The traveling vehicle system of [1], wherein the cost change unit calculates the index value for each of the plurality of upstream links based on graph theory.

[0010] According to the configuration [2] above, the bottleneck link in the cost change unit can be efficiently selected by a relatively simple calculation process.

[0011] [3] The selection unit repeatedly executes the process of selecting the target link at predetermined time intervals, and the cost change unit executes the process of selecting the one or more bottleneck links and increasing the link costs of the one or more bottleneck links each time the selection unit selects the target link. [4] The traveling vehicle system of [1] or [2].

[0012] According to the configuration [3] above, the combination of the target link and the bottleneck link can be appropriately updated at predetermined time intervals, so that the occurrence of congestion in the traveling vehicle system can be appropriately suppressed in accordance with changes in the overall system situation.

[0013] [4] A traveling vehicle system according to any one of [1] to [3], wherein the selection unit obtains a maximum allowable number indicating the maximum number of traveling vehicles that can be present within the link at the same time for each of the plurality of links, and selects, from among the plurality of links, a link in which the number of traveling vehicles present within the link is equal to or greater than a predetermined percentage of the maximum allowable number for that link as the target link.

[0014] According to the above configuration [4], target links can be selected relatively easily based on the index of the maximum allowable number of each link.

[0015] [5] A traveling vehicle system according to any of [1] to [4], wherein the traveling command is associated with a destination included in one of the plurality of links, the controller controls the traveling of the traveling vehicle to which the traveling command is assigned so that the traveling vehicle heads toward the destination, and the selection unit calculates, for each of the plurality of links, the number of traveling commands associated with each of the plurality of links that are predicted to occur in the future based on the number of past traveling commands in which a point included in the link was set as the destination, and selects the target link based on the number of traveling commands calculated for each of the plurality of links.

[0016] According to the configuration [5] above, it is possible to select with high accuracy target links where traveling vehicles are likely to concentrate in the future based on the number of future traveling commands to be issued for each link predicted from the number of past traveling commands related to each link.

[0017] According to the present disclosure, it is possible to provide a traveling vehicle system that can effectively suppress the occurrence of traffic congestion.

[0018] FIG. 1 is a diagram showing an example of the layout of a guided vehicle system. FIG. 2 is a block diagram showing the functional configuration of the guided vehicle system. FIG. 3 is a block diagram showing an example of the hardware configuration of a guided vehicle controller. FIGS. 4(a) and 4(b) are schematic diagrams for explaining an example of processing by a selection unit. FIGS. 5(a) and 5(b) are schematic diagrams for explaining an example of processing by a cost modification unit. FIG. 6 is a diagram showing an example of a transport log. FIG. 7 is a diagram showing an example of aggregated data of transport logs for each period. FIG. 8 is a diagram showing an example of learning data and verification data used for learning a prediction model. FIG. 9 is a diagram showing an example of prediction processing using a prediction model. FIG. 10 is a flowchart showing an example of processing by a guided vehicle system.

[0019] Hereinafter, an embodiment of the present disclosure will be described with reference to the drawings. In the description of the drawings, the same or equivalent elements are denoted by the same reference numerals, and redundant description may be omitted.

[0020] As shown in FIG. 1 , a guided vehicle system 1 (traveling vehicle system) according to this embodiment includes a transport path 4 (a predetermined travel path) and a plurality of guided vehicles 2 (traveling vehicles) that travel along the transport path 4. The transport path 4 is, for example, a rail (track) laid in a factory. The guided vehicle 2 is, for example, an automated guided vehicle that transports an article. The guided vehicle 2 is, for example, an overhead traveling vehicle, a tracked carriage, or the like. As an example, the guided vehicle 2 is an overhead traveling automated guided vehicle that is capable of traveling along the transport path 4. For example, the guided vehicle 2 is an overhead traveling automated guided vehicle (OHT). As an example, the article transported by the guided vehicle 2 is a cassette (a so-called FOUP (Front Opening Unified Pod)) that accommodates a plurality of semiconductor wafers.

[0021] The transport path 4 is divided into multiple (three in the example of FIG. 1 ) bays (sections) B. The transport path 4 includes an intra-bay route 5, which is a route within a bay B, and an inter-bay route 6, which is a route connecting different bays B. Along the transport path 4, processing equipment 7, a stocker (not shown), and the like are provided. The processing equipment 7 is equipment that performs processing on semiconductor wafers. The stocker is a point where the transport vehicle 2 can temporarily store items and serves as a buffer.

[0022] The transport path 4 includes a plurality of nodes 10 and a plurality of links 11 connecting adjacent nodes 10. The plurality of nodes 10 indicate specific points such as a branching section 8 and a merging section 9. In this embodiment, each link 11 is a unidirectional link. That is, the transport vehicle 2 can travel in a predetermined traveling direction (the direction of the arrow shown in FIG. 1 ) for each link 11. The branching section 8 is a node 10 connected to one upstream link (the link 11 upstream of the branching section 8) and multiple downstream links (the links 11 downstream of the branching section 8). The merging section 9 is a node 10 connected to multiple upstream links (the links 11 upstream of the merging section 9) and one downstream link (the link 11 downstream of the merging section 9).

[0023] The processing device 7 is provided with an inlet port for carrying in articles (i.e., a point where the transport vehicle 2 unloads articles) and an outlet port for carrying out articles (i.e., a point where the transport vehicle 2 picks up (loads) articles). The inlet port and outlet port are located below the transport path 4. The inlet port may also serve as an outlet port.

[0024] 2, the guided vehicle system 1 includes a plurality of guided vehicles 2 and a guided vehicle controller 20 (controller). The guided vehicle controller 20 receives a transport command (travel command) from a host controller 12.

[0025] The transport vehicle controller 20 controls the travel of the transport vehicle 2 so that the transport vehicle 2 to which the transport command is assigned heads toward the destination. Specifically, the transport vehicle controller 20 receives a transport command from the upper controller 12 instructing the transport vehicle 2 to head toward the destination (predetermined point) on the transport path 4. The transport vehicle controller 20 controls the travel of the transport vehicle 2 by assigning the transport command received from the upper controller 12 to a transport vehicle 2 selected from the multiple transport vehicles 2.

[0026] A transport command is associated with a destination included in any one of the multiple links 11. Examples of destinations include the above-mentioned processing device 7 (incoming port, outgoing port), a stocker, etc. In this embodiment, a transport command is associated with a "From point" indicating a point where the item to be transported is to be picked up (i.e., the origin of the item to be transported) and a "To point" indicating a point where the item to be transported is to be unloaded (i.e., the destination of the item to be transported). That is, one transport command is associated with the From point as a first destination and the To point as a second destination. A transport vehicle 2 to which such a transport command is assigned first travels toward the From point, which is the first destination. Next, the transport vehicle 2 picks up the item to be transported at the From point, transports the item to the To point, which is the second destination, and unloads the item at the To point.

[0027] The upper controller 12 has, for example, an MES (Manufacturing Execution System) and an MCS (Material Control System). The MES is managed by a manufacturer or the like. The MES is capable of communicating with the processing device 7. For example, the processing device 7 transmits a transport request (item grab request, item unloading request) for an item for which processing has been completed to the MES. The MES transmits the transport request received from the processing device 7 to the MCS. When the MCS receives a transport request from the MES, it converts the transport request into a transport command as described above and transmits the transport command to the guided vehicle controller 20. As a result, the transport command is assigned to a specific guided vehicle 2 via the guided vehicle controller 20.

[0028] The transport vehicle controller 20 determines a transport vehicle 2 to which the transport command is to be assigned based on predetermined selection criteria. For example, the transport vehicle controller 20 determines the transport vehicle 2 closest to the From point and to which no other transport commands are assigned (an available transport vehicle) as the transport command destination. The transport vehicle controller 20 also executes a predetermined route search algorithm (e.g., a shortest path search algorithm such as Dijkstra's algorithm) based on the link cost associated with each link 11 to determine a transport route for executing the transport command (i.e., a travel route from the current position of the transport vehicle 2 to the To point via the From point), and notifies the transport vehicle 2 of the transport route. As a result, the transport vehicle 2 travels on the transport path 4 based on the transport route.

[0029] The guided vehicle controller 20 may be configured to distribute the above-described processing among multiple sub-controllers. For example, the transport path 4 may be divided into multiple areas (modules), with one sub-controller provided for each area. In this case, the transport route within each area may be determined by the sub-controller corresponding to each area. For example, if the transport route for executing a transport command passes through three areas a, b, and c in this order, the sub-controller managing area a may determine the sub-transport route within area a, the sub-controller managing area b may determine the sub-transport route within area b, and the sub-controller managing area c may determine the sub-transport route within area c. Furthermore, when the transport route is divided into multiple sub-transport routes for each area in this manner, the timing for determining the sub-transport route for each area (i.e., the timing for calculating the optimal sub-transport route using the above-described path search algorithm) may differ for each area. For example, the sub-controller managing area c may determine the sub-transport route within area c immediately before the guided vehicle 2 enters area c and notify the guided vehicle 2 of the determined sub-transport route. Furthermore, the transport vehicle controller 20 may once determine a transport route for a transport vehicle 2, and then update the route by recalculating the transport route for the transport vehicle 2 while the transport vehicle 2 is traveling along the determined transport route. In either case, the transport route for the transport vehicle 2 is determined based on the link cost of each link 11.

[0030] The link cost associated with a link 11 is, for example, a value related to the time required for a guided vehicle 2 to pass through the link 11 (hereinafter referred to as the "passing time"). A first example of the link cost is the length of the link 11 (the distance from the upstream node to the downstream node of the link 11). A second example of the link cost is the value obtained by dividing the length of the link 11 by the average speed of the guided vehicles 2 (i.e., the theoretical average passing time). A third example of the link cost is the average passing time of the link 11 (e.g., the average passing time of a predetermined number of guided vehicles 2 that have most recently passed through the link 11). However, the link cost may be in a form other than the first to third examples described above. In this embodiment, the link cost of each link 11 is the third example described above. In this case, the guided vehicle controller 20 may update the link cost of a link 11 each time a guided vehicle 2 passes through the link 11, or may update the link costs of each link 11 collectively at a predetermined time step interval (15-minute intervals in this embodiment).

[0031] The transport vehicle controller 20 (the route determination unit 22 described later) preferentially determines, as the transport route of the transport vehicle 2, a candidate route having a small sum of link costs of the multiple links 11 included in the candidate route among multiple candidate routes for the transport vehicle 2 to perform transport (transport corresponding to a predetermined transport command). For example, when a shortest path search algorithm such as the Dijkstra algorithm described above is used, the candidate route having the smallest sum of link costs of the multiple links 11 included in the candidate route is determined as the transport route. Note that the transport vehicle controller 20 does not necessarily determine the shortest path in the strict sense as the transport route. For example, when the transport path 4 is divided into multiple areas as described above and a route search is performed for each area, the route formed by connecting the shortest paths (sub-transport paths) determined for each area may not match the shortest path when viewed as the entire transport path 4. Furthermore, even when the transport vehicle controller 20 performs a route search within a limited calculation time in order to improve the response speed of notifying the transport route to the transport vehicle 2, the determined transport route may not match the shortest path when viewed as the entire transport path 4.

[0032] 3, the transport vehicle controller 20 may be configured as a computer system including one or more processors 201 such as CPUs (Central Processing Units), one or more RAMs (Random Access Memories) 202 and one or more ROMs (Read Only Memories) 203 as main storage devices, an input device 204 such as a keyboard for an operator to input operations, an output device 205 such as a display that presents information to the operator, a communication module 206 for communicating with the transport vehicle 2, and an auxiliary storage device 207 such as an HDD and SSD. The transport vehicle controller 20 may be configured as a single computer device or may be configured as a plurality of computer devices (for example, a plurality of sub-controllers as described above).

[0033] Each function of the transport vehicle controller 20 is realized, for example, by loading a predetermined program into a memory such as RAM 202, operating the input device 204 and output device 205 under the control of the processor 201, operating the communication module 206, and reading and writing data in RAM 202 and the auxiliary storage device 207.

[0034] Next, the functions of the guided vehicle controller 20 will be described with reference to Fig. 2. The guided vehicle controller 20 has a storage unit 21, a route determination unit 22, a selection unit 23, and a cost change unit 24.

[0035] The storage unit 21 is a database that stores various information related to the guided vehicle system 1. The storage unit 21 may be configured with a single database device or multiple database devices. In this embodiment, the storage unit 21 stores the layout of the transport path 4 as shown in FIG. 1 and the link costs associated with each of the multiple links 11. Furthermore, when a correction is made by the processing of the cost change unit 24 (described later) to temporarily increase the link cost of a certain link 11 (a link selected as a bottleneck link), the storage unit 21 temporarily stores the corrected link cost of the link 11.

[0036] The route determination unit 22 determines a transport route for the transport vehicle 2 based on the link costs of each of the multiple links 11 stored in the storage unit 21. For example, when a transport command is assigned to a transport vehicle 2, the route determination unit 22 determines a transport route for the transport vehicle 2 to execute the transport command (i.e., a route from the current location of the transport vehicle 2 to the To location of the transport command via the From location of the transport command). As described above, the route determination unit 22 preferentially determines, as the transport route for the transport vehicle 2, a candidate route having a small sum of link costs of the multiple links 11 included in the candidate route, from among multiple candidate routes for the transport vehicle 2 capable of executing the transport command. For example, the route determination unit 22 determines the transport route for the transport vehicle 2 to which the transport command is assigned by using a shortest path search algorithm such as Dijkstra's algorithm. The transport vehicle controller 20 notifies the corresponding transport vehicle 2 of the transport route determined by the route determination unit 22. As a result, the transport vehicle 2 can travel on the transport path 4 according to the transport route determined by the route determination unit 22.

[0037] The selection unit 23 selects, from among the plurality of links 11, a target link 11a (see FIG. 4B) whose future utilization is expected to exceed a predetermined standard.

[0038] The cost modification unit 24 calculates index values ​​v1 to v12 indicating the likelihood of concentration of guided vehicles 2 for each of a plurality of upstream links 11b1 to 11b12 (see FIG. 5) that exist within a predetermined upstream range starting from the upstream junction 9a (see FIG. 5) that is closest to the target link 11a among the plurality of links 11. Then, the cost modification unit 24 preferentially selects upstream links with high index values ​​as one or more bottleneck links 11c (see FIG. 5), and increases the link costs of the one or more bottleneck links 11c.

[0039] In this embodiment, the processes of the selection unit 23 and the cost modification unit 24 are repeatedly executed at predetermined time intervals (for example, the above-mentioned time step intervals). That is, the selection unit 23 repeatedly executes the process of selecting the target link 11a at predetermined time intervals. Every time the selection unit 23 selects a target link 11a, the cost modification unit 24 selects (updates) one or more bottleneck links 11c and increases the link costs of the one or more bottleneck links 11c.

[0040] As an example, the link costs of one or more bottleneck links 11c determined by the selection unit 23 and the cost modification unit 24 at a certain time t (the modified (increased) link costs) are temporarily stored in the storage unit 21 and applied to the period from time t to the time t+1 following time t (i.e., the time after a predetermined time interval has elapsed since time t). That is, when the route determination unit 22 executes a process of determining a transport route for the transport vehicle 2 during the period from time t to the next time t+1 (e.g., shortest route search), it uses the link costs of one or more bottleneck links 11c determined at time t. Note that the link costs of one or more bottleneck links 11c determined at time t are reset after the above-mentioned period has elapsed (i.e., after time t+1 has passed) and deleted from the storage unit 21.

[0041] Specific examples of the processing of the selection unit 23 and the cost modification unit 24 will be described in order with reference to Fig. 4 and Fig. 5. Fig. 4 is a diagram for explaining an example of the processing of the selection unit 23, and Fig. 5 is a diagram for explaining an example of the processing of the cost modification unit 24.

[0042] First, specific examples (first and second examples) of the processing by the selection unit 23 will be described with reference to Fig. 4. Fig. 4(a) is a diagram showing a part of a schematic conveyance path 4 for this description. Fig. 4(b) is a diagram showing a target link 11a selected by the selection unit 23.

[0043] (First Example) In the first example, the selection unit 23 first acquires, for each of the multiple links 11, a maximum allowable number indicating the maximum number of guided vehicles 2 that can be present in the link 11 at the same time. The maximum allowable number n for each link 11 is obtained by, for example, calculating the largest n that satisfies "n×y+(n−1)×z≦x" based on the length x of each link 11, the total length y of one guided vehicle 2, and the minimum inter-vehicle distance z (i.e., a distance previously set as the minimum inter-vehicle distance that must be maintained to avoid collisions between adjacent guided vehicles 2 in the front and rear). The selection unit 23 may calculate (acquire) the maximum allowable number n for each link 11 by performing the calculation described above. Alternatively, the maximum allowable number n for each link 11 may be stored in the storage unit 21 in advance. In this case, the selection unit 23 may acquire the maximum allowable number n for each link 11 by referring to the storage unit 21.

[0044] Next, the selection unit 23 selects, as a target link 11a, a link 11 in which the number of guided vehicles 2 simultaneously present in the link 11 is equal to or greater than a predetermined percentage (e.g., 70%) of the maximum allowable number for the link 11. As an example, the guided vehicle controller 20 is configured to continuously monitor whether the number of guided vehicles in each link 11 is equal to or greater than the predetermined percentage, and, when detecting that the number of guided vehicles in a certain link 11 is equal to or greater than the predetermined percentage, issue a predetermined signal GL1 (Grid Lock Level 1) for the link 11. Furthermore, the guided vehicle controller 20 is configured to issue a signal GL2 (Grid Lock Level 2) for the link 11 when detecting a link 11 in which the number of guided vehicles in the link 11 has reached the maximum allowable number for the link 11. In this case, the link 11 in which the signal GL1 is detected is said to be a link 11 in which the number of guided vehicles 2 using the link 11 is likely to continue to exceed a predetermined standard (in this example, the standard for issuing the signal GL1) even in a future period (i.e., a predetermined period after the time when the signal GL1 is detected). Therefore, the selection unit 23 may select the link 11 for which such a signal GL1 has been issued as a target link 11a whose future utilization is predicted to exceed a predetermined standard.

[0045] (Second Example) In a second example, first, the selection unit 23 calculates the number of transport commands related to each of the multiple links 11 that are predicted to occur in the future (in this embodiment, the period from the current time point t to the next time point t+1) based on the number of past transport commands in which a point included in the link 11 (e.g., a processing device 7, a stocker, etc.) was set as the destination (in this embodiment, the From point or the To point) for each of the multiple links 11. Here, a transport command related to a certain link (hereinafter simply referred to as a "transport command for a certain link") means a transport command in which a point included in the link is set as the destination (the From point or the To point).

[0046] Next, the selection unit 23 selects a target link 11a based on the number of transport commands calculated for each of the multiple links 11 (i.e., the predicted number of transport commands to be generated in the future). In this embodiment, the selection unit 23 acquires the predicted number of transport commands to be generated in the future for each link 11 by using a prediction model M, which will be described later. The prediction model M is a trained model configured to input the number of past transport commands for each link 11 (for example, the number of transport commands issued in each period of the past three time steps) and output the predicted number of transport commands to be generated for each link 11 in the period of the next one time step (i.e., the period from time t to time t+1).

[0047] An example of the prediction model M will be described with reference to FIGS. 6 to 9. FIG. 6 shows an example of the transport log for each of a plurality of transports that arrived at the From point during a certain period (two time steps TS1 and TS2). Information in one record (row) in FIG. 6 shows a transport log corresponding to one transport command. As an example, the transport log includes information on the From arrival date and time, the transport completion date and time, the From link, and the To link. The "From arrival date and time" is information indicating the date and time when the transport vehicle 2 arrived at the From point. The "Transport completion date and time" is information indicating the date and time when the transport vehicle 2 arrived at the To point and completed unloading of the items (FOUP). The "From link" is information (link ID) that identifies the link 11 that includes the From point. The "To link" is information (link ID) that identifies the link 11 that includes the To point.

[0048] The aggregated data for each period shown in Fig. 7 is data obtained by aggregating the multiple transport logs shown in Fig. 6 for each period (time step) and for each link. More specifically, by aggregating for each link the number of transport commands with each link as the From link (number of From transport commands) and the number of transport commands with each link as the To link (number of To transport commands), data is obtained that correlates a predetermined past period, a link (link ID), and the total number of transport commands (number of From transport commands + number of To transport commands; hereinafter simply referred to as the "number of transport commands").

[0049] The number of From transport commands for the link with link ID "1001" in time step TS1 can be obtained by counting the number of transport logs (see FIG. 6) whose From arrival dates and times are included in the period of time step TS1 (here, the period from "January 1st, 00:00 to 00:14:59") in which the From link is "1001". Similarly, the number of To transport commands for the link with link ID "1001" in time step TS1 can be obtained by counting the number of transport logs whose To link is "1001" in which the transport completion dates and times are included in the period of time step TS1.

[0050] Here, it is considered that there is a certain relationship (pattern) between the number of transport commands for each link in the most recent past period and the number of transport commands for each link in the future period (next time step). Therefore, in this embodiment, a prediction model M is used that inputs the number of transport commands for each link in the past period and outputs a prediction result of the number of transport commands for each link in the future period corresponding to the next time step.

[0051] In this embodiment, vectors (data V1 and V2 in the example of FIG. 7 ) containing as elements the number of transport commands for each of a plurality of links (links 11 with link IDs "1001" to "9990" in the example of FIG. 7 ) at each time step (time steps TS1 and TS2 in the example of FIG. 7 ) are used as data for training the prediction model M (training data or validation data, which will be described later). The prediction model M is created, for example, by a gradient boosting decision tree (GBDT), which is a type of supervised learning. However, the learning method for creating the prediction model M is not limited to the above-described GBDT.

[0052] FIG. 8 illustrates an example of training data and validation data used in training the prediction model M. In the example of FIG. 8 , the prediction model M is configured to output a prediction result of the number of transport commands for each link in a future period (15 minutes, or one time step) immediately following a past period (three time steps, or 45 minutes) based on data on the number of transport commands for each link (data V1 and V2 in FIG. 7 ). In the example of FIG. 8 , past periods corresponding to time steps with time step IDs "350" to "364" are displayed. As shown in FIG. 8 , data on the number of transport commands for multiple past time steps is divided into training data and validation data. Furthermore, it is preferable that the training data period (time steps prior to ID "355" in the example of FIG. 8 ) and the validation data period (time steps after ID "358" in the example of FIG. 8 ) are not contiguous in time. In the example of FIG. 8 , a 30-minute interval is set between the training data period and the validation data period.

[0053] In FIG. 8 , one row of data corresponds to one piece of training data or validation data. The data for the hatched period (a period of three time steps) corresponds to the input data for the prediction model M, and the data for the black period (a period of one time step) corresponds to the output (correct label) of the prediction model M. In this way, by acquiring data for four consecutive time steps from data for a past period including multiple time steps while sliding the time steps one by one, multiple training data and validation data can be efficiently obtained. The prediction model M is trained using multiple training data, for example, so that the difference between the output result obtained by inputting the first three time steps of data for each validation data into the prediction model M and the last one time step of data for each validation data is minimized. The length of the input data period for the prediction model M (three time steps in this embodiment), as well as the number of training data and validation data, are appropriately set based on the results of accuracy evaluation of the prediction model M, etc.

[0054] FIG. 9 is a diagram schematically illustrating an example of prediction processing using a prediction model M (trained model) created by machine learning as described above. As shown in FIG. 9 , when data (V1, V2, V3) from the past period (t-2, t-1, t) corresponding to the most recent three time steps is input to the prediction model M, the prediction model M outputs data X from the future period (t+1) corresponding to the next time step. The data X indicates the number of transport commands for each link in the future period (the number of transport commands predicted to be issued). In this manner, in the present embodiment, the selection unit 23 uses the prediction model M to obtain the predicted number of transport commands to be issued in the future period (data X output from the prediction model M) as information regarding the future utilization of each link, based on the number of past transport commands in which a location included in each link was set as the destination (in this embodiment, data V1, V2, V3 from the most recent three time steps input to the prediction model M).

[0055] Next, the selection unit 23 selects, for example, the link 11 for which the predicted number of transport commands to be generated in the future period is equal to or greater than a predetermined threshold as the target link 11a. The threshold may be set individually for each link 11. Alternatively, the selection unit 23 may select, as the target link 11a, the link 11 for which the rate of increase in the number of transport commands is equal to or greater than a predetermined standard. For example, the selection unit 23 may select, as the target link 11a, the link 11 for which the average value n of the number of transport commands in the most recent three time steps ＡＶＥ The predicted number of transport orders in the future period for Ｐ The proportion of (n Ｐ / n ＡＶＥ ) is equal to or greater than a predetermined threshold (for example, 1.2 (20% increase)). As described above, according to the second example, the selection unit 23 can select a target link 11a whose future utilization is predicted to exceed a predetermined standard based on the predicted number of transport commands to be generated in the future period.

[0056] The first and second examples may be used in combination. For example, the selection unit 23 may periodically execute the process of the second example at a predetermined time step interval (15 minutes in this embodiment) and may irregularly execute the process of the first example triggered by the detection of a link 11 for which the signal GL1 is issued. Furthermore, the target link 11a selected in the first example (and the corrected link cost of the bottleneck link 11c selected based on the target link 11a) may be reset when the signal GL1 of the target link 11a is no longer issued, or may be reset after a predetermined time has elapsed since the issuance of the signal GL1 was detected.

[0057] Next, with reference to FIG. 5 , a specific example of the processing of the cost modification unit 24 after the target link 11a is selected will be described. First, as shown in FIG. 5A , the cost modification unit 24 selects multiple upstream links within a predetermined upstream range, starting from the upstream junction 9a closest to the target link 11a. The upstream junction 9a is the junction 9 closest to the target link 11a among multiple junctions 9 located upstream of the target link 11a. In this embodiment, as an example, the above-mentioned "predetermined upstream range" is a subgraph G consisting of a range reachable upstream from the upstream junction 9a by N or fewer links 11 (for example, "N = 4") upstream. That is, in this embodiment, the cost modification unit 24 selects multiple (12 in this embodiment) upstream links 11b1 to 11b12 included in the subgraph G.

[0058] Next, the cost modification unit 24 acquires index values ​​v1 to v12 indicating the likelihood of guided vehicles 2 concentrating on each of the selected upstream links 11b1 to 11b12. For example, the cost modification unit 24 may calculate the index values ​​v1 to v12 based on graph theory. For example, the cost modification unit 24 may employ an index related to centrality in graph theory as the index values ​​v1 to v12. As an example, the cost modification unit 24 may calculate a betweenness centrality (BC) value for each of the upstream links 11b1 to 11b12 as the index values ​​v1 to v12. Here, the BC value of a given link 11 is a value indicating the frequency with which the link 11 exists on the shortest path between all node pairs in the graph of the entire transport path 4 (a graph composed of multiple nodes 10 and multiple links 11). It can be said that a link 11 with a larger BC value is a link 11 that is qualitatively more likely to attract guided vehicles 2 in terms of the layout of the transport path 4. The BC value of each link 11 can be calculated in advance because it depends on the layout of the conveying path 4. For example, the BC value of each link 11 may be calculated in advance and stored in the storage unit 21. In this case, the cost modification unit 24 may acquire the index values ​​v1 to v12 (BC values) of each of the upstream links 11b1 to 11b12 by referring to the storage unit 21.

[0059] Next, the cost modification unit 24 preferentially selects upstream links 11b with high index values ​​as one or more bottleneck links 11c. For example, when the index values ​​v1 to v12 of the upstream links 11b1 to 11b12 are sorted in descending order, the cost modification unit 24 selects the top m upstream links (in this example, the top three) as bottleneck links 11c. As an example, it is assumed here that the index values ​​v1, v3, and v5 of the three upstream links 11b1, 11b3, and 11b5 are in the top three. In this case, as shown in FIG. 5B, each of the three upstream links 11b1, 11b3, and 11b5 with the top three index values ​​v1, v3, and v5 is selected as a bottleneck link 11c.

[0060] Next, the cost modification unit 24 increases the link cost of each bottleneck link 11c selected as described above. The amount of increase in the link cost can be determined arbitrarily. For example, the cost modification unit 24 may increase the link cost of the bottleneck link 11c by multiplying the original link cost of the bottleneck link 11c by a predetermined cost multiplier K (e.g., K = 1.2). Alternatively, the cost modification unit 24 may display each bottleneck link 11c on a screen of an operator terminal and determine the amount of increase in the link cost of each bottleneck link 11c based on an instruction from the operator. As another example, the cost modification unit 24 may increase the link cost of one bottleneck link 11c so that the shortest route from the current positions of at least a predetermined number of guided vehicles 2 to the target link 11a is changed from a first route that uses the bottleneck link 11c to a second route that does not use (detours) the bottleneck link 11c. This method is expected to reduce the number of guided vehicles 2 heading toward the target link 11a by using the bottleneck link 11c. Also, by adjusting the "predetermined number" described above, it is possible to adjust the extent of increase in link cost. Specifically, by increasing the "predetermined number" described above, it is possible to increase the extent of increase in link cost.

[0061] Next, an example of the processing of the guided vehicle system 1 (the guided vehicle controller 20) will be described with reference to Fig. 10. As shown in Fig. 10, the processing of the route determination unit 22 and the processing of the selection unit 23 and the cost change unit 24 are executed independently of each other.

[0062] First, the processing flows of the selection unit 23 and the cost modification unit 24 will be described. When the timing (trigger) for performing calculation arrives (step S11: YES), the selection unit 23 executes processing to select a target link 11a (see FIG. 4B) (step S12). In this embodiment, the trigger has a first timing and a second timing. The first timing is the timing when a signal GL1 is issued for a certain link 11. In this case, in step S12, the selection unit 23 executes the processing of the first example described above. The second timing is the timing that occurs repeatedly at predetermined time steps (15 minutes in this embodiment). When the second timing arrives, the selection unit 23 executes the processing of the second example described above.

[0063] 5A and 5B, the cost modification unit 24 selects one or more bottleneck links 11c based on the target links 11a selected by the selection unit 23 (step S13). The cost modification unit 24 then increases the link cost of the selected bottleneck links 11c (step S14). The corrected (increased) link cost of the bottleneck link 11c is stored in the storage unit 21.

[0064] Next, the processing flow of the route determination unit 22 will be described. When the timing for performing a route search arrives (e.g., when the transport vehicle controller 20 receives a transport command from the upper controller 12) (step S21: YES), the route determination unit 22 acquires the link costs of each of the multiple links 11 from the storage unit 21 (step S22). At this time, the route determination unit 22 acquires the link costs originally set for each link 11 and also acquires the corrected link cost of the bottleneck link 11c (i.e., the link cost of the bottleneck link 11c corrected by the latest processing in step S14). As a result, the route determination unit 22 can perform a route search, described below, for the bottleneck link 11c by using the corrected link cost. Next, the route determination unit 22 performs a route search (e.g., a shortest route search such as Dijkstra's algorithm) based on the link costs of each of the multiple links 11 to determine a transport route for the transport vehicle 2 (step S23).

[0065] [Effects] According to the guided vehicle system 1 described above, rather than simply increasing the link cost of the target link 11a, the link cost of the bottleneck link 11c, where guided vehicles 2 are likely to congregate, among the upstream links 11b1 to 11b12 existing within a predetermined upstream range (subgraph G in FIG. 5 ) starting from the upstream junction 9a closest to the target link 11a can be increased, thereby preventing congestion at the bottleneck link 11c. In other words, a significant increase in the number of guided vehicles using the bottleneck link 11c to reach the target link 11a in the future (i.e., the occurrence of congestion at the bottleneck link 11c) can be suppressed. As a result, congestion in the guided vehicle system 1 can be effectively suppressed.

[0066] The above-mentioned effect will be supplemented. According to the inventor's findings, since guided vehicles 2 heading toward the target link 11a always pass through the link 11 upstream of the target link 11a, the link 11 upstream of the upstream junction 9a closest to the target link 11a (upstream link) is likely to become a bottleneck. According to the guided vehicle system 1, among such upstream links, a link 11 that is thought to be particularly likely to attract guided vehicles 2 is selected as the bottleneck link 11c, and the link cost of the bottleneck link 11c is increased to induce a decrease in the number of guided vehicles using the bottleneck link 11c, thereby achieving the above-mentioned effect.

[0067] The cost modification unit 24 obtains the index values ​​v1 to v12 of each of the upstream links 11b1 to 11b12 based on graph theory. According to the above configuration, the bottleneck link 11c can be efficiently selected through relatively simple calculation processing. Furthermore, in this embodiment, by calculating the BC value of each link 11 in advance and storing it in the storage unit 21 as described above, the index values ​​v1 to v12 of each of the upstream links 11b1 to 11b12 can be obtained easily and quickly.

[0068] The selection unit 23 repeatedly executes the process of selecting the target link 11 a at predetermined intervals, and the cost change unit 24 executes the process of selecting one or more bottleneck links 11 c and increasing the link costs of the one or more bottleneck links 11 c each time the selection unit 23 selects a target link 11 a. According to the above configuration, the combination of the target link 11 a and the bottleneck link 11 c can be appropriately updated at predetermined time intervals, and therefore, the occurrence of congestion in the guided vehicle system 1 can be appropriately suppressed in accordance with changes in the status of the entire system.

[0069] The selection unit 23 acquires a maximum allowable number indicating the maximum number of guided vehicles 2 that can be present simultaneously within each of the multiple links 11, and selects, from among the multiple links 11, a link 11 in which the number of guided vehicles present within the link 11 is equal to or greater than a predetermined percentage of the maximum allowable number for the link 11, as the target link 11a. For example, the selection unit 23 executes the processing of the first example described above. With the above configuration, the target link 11a can be selected relatively easily based on the index of the maximum allowable number for each link 11.

[0070] The selection unit 23 calculates the number of transport commands related to each of the multiple links 11 that are predicted to be generated in the future based on the number of past transport commands in which a point included in the link 11 is set as a destination (in this embodiment, the From point or the To point) for each of the multiple links 11, and selects a target link 11a based on the number of transport commands calculated for each of the multiple links 11. For example, the selection unit 23 executes the processing of the second example described above. According to the above configuration, it is possible to accurately select a target link 11a where guided vehicles 2 are likely to concentrate in the future based on the number of future transport commands to be generated for each link 11 predicted from the number of past transport commands related to each link 11.

[0071] [Modifications] Although the embodiments of the present disclosure have been described above, the present disclosure is not limited to the above-described embodiments, and various modifications are possible without departing from the spirit of the present disclosure.

[0072] For example, the index values ​​v1 to v12 of the upstream links 11b1 to 11b12 acquired by the cost modification unit 24 may be index values ​​based on graph theory other than the BC value (for example, index values ​​indicating the centrality of the link in the graph other than the BC value). Alternatively, the index values ​​v1 to v12 may be index values ​​obtained by a method other than graph theory.

[0073] The selection unit 23 does not need to repeatedly execute the process of selecting the target link 11a at predetermined intervals, but may execute the process at any timing. For example, if the selection unit 23 is configured to execute only the process of the first example described above, the process of the selection unit 23 (and the subsequent process of the cost modification unit 24) is executed irregularly. The selection unit 23 may also select the target link 11a by processes other than the first and second examples described above. In the above embodiment, the target link 11a and the bottleneck link 11c (including the increased link cost) selected at a certain time point are reset after a certain period of time has elapsed from that time point. However, they may also be reset based on a predetermined condition other than the elapse of a certain period of time. An example of the predetermined condition is when the utilization of the target link 11a (the number of transport vehicles in the link, the number of transport commands issued, etc.) falls below a predetermined standard.

[0074] In the above embodiment, a FOUP containing multiple semiconductor wafers is exemplified as an item (carried object) transported by the transport vehicle 2, but the item is not limited to this and may be, for example, other containers containing glass wafers, reticles, etc., or other items. Furthermore, the location where the transport vehicle system 1 is installed is not limited to a semiconductor manufacturing factory, and the transport vehicle system 1 may be installed in other facilities.

[0075] Furthermore, in the above embodiment, a configuration has been described in which multiple transport vehicles 2 transport articles on the transport path 4, but the mechanism of the present disclosure can also be applied to a traveling vehicle system in which multiple traveling vehicles that do not transport articles travel along a preset travel path. That is, in the above embodiment, it is not essential that the transport vehicles 2 travel based on a transport command that assumes the transport of articles, and the transport vehicles 2 may be configured to travel based on a travel command that does not involve the transport of articles.

[0076] 1...Transport vehicle system (traveling vehicle system), 2...Transport vehicle (traveling vehicle), 4...Transport path (traveling path), 8...Branch, 9...Merge, 9a...Upstream merge, 10...Node, 11...Link, 11a...Target link, 11b1 to 11b12...Upstream link, 11c...Bottleneck link, 20...Transport vehicle controller (controller), 21...Memory unit, 22...Route determination unit, 23...Selection unit, 24...Cost change unit.

Claims

1. A traveling vehicle system comprising: a plurality of traveling vehicles traveling along a preset traveling path; and a controller that controls the traveling of the traveling vehicles by assigning a traveling command to a traveling vehicle selected from the plurality of traveling vehicles instructing the traveling vehicle to head to a specified point on the traveling path, wherein the traveling path includes a plurality of nodes including branching sections and merging sections, and a plurality of links connecting the nodes, and the controller comprises: a memory unit that stores a layout of the traveling path and a link cost associated with each of the plurality of links; a route determination unit that determines, based on the link cost of each of the plurality of links, from a plurality of candidate routes for the traveling vehicle for executing the traveling command, with priority as the traveling route of the traveling vehicle, a candidate route having a small sum of the link costs of a plurality of the links included in the candidate route; and a selection unit that selects, from the plurality of links, a target link whose future utilization is expected to exceed a specified standard. a cost changing unit that obtains an index value indicating the likelihood of the traveling vehicles concentrating for each of a plurality of upstream links that are present within a predetermined upstream range starting from an upstream junction closest to the target link among the plurality of links, preferentially selects the upstream links with high index values ​​as one or more bottleneck links, and increases the link costs of the one or more bottleneck links.

2. The traveling vehicle system according to claim 1, wherein the cost modification unit calculates the index value for each of the plurality of upstream links based on graph theory.

3. The traveling vehicle system of claim 1, wherein the selection unit repeatedly executes the process of selecting the target link at a predetermined time interval, and the cost change unit executes the process of selecting the one or more bottleneck links and increasing the link costs of the one or more bottleneck links each time the selection unit selects the target link.

4. The traveling vehicle system of claim 1, wherein the selection unit obtains a maximum allowable number indicating the maximum number of traveling vehicles that can exist simultaneously within the link for each of the plurality of links, and selects as the target link a link among the plurality of links in which the number of traveling vehicles existing within the link is equal to or greater than a predetermined percentage of the maximum allowable number for that link.

5. The traveling command is associated with a destination included in one of the multiple links, the controller controls the traveling of the traveling vehicle to which the traveling command is assigned so that the traveling vehicle heads toward the destination, and the selection unit calculates, for each of the multiple links, the number of traveling commands associated with each of the multiple links that are predicted to occur in the future based on the number of past traveling commands in which a point included in the link was set as the destination, and selects the target link based on the number of traveling commands calculated for each of the multiple links.

Images