WO2022113222A1 - Transportation route determination method, transportation route determination device, and computer program - Google Patents

Abstract

Provided are a transportation route determination method, transportation route determination device, and computer program.　In this transportation route determination method, a transportation network is defined in which a plurality of goods collection/delivery points, transportation hubs that a transportation device for transporting the goods is to pass through, and each point in a traffic network are assigned to nodes disposed in a geometric pattern having a prescribed unit pattern that repeats periodically and routes connecting adjacent points or transportation hubs are assigned to edges between nodes, and a transportation route connecting the transportation hubs for the transportation device is determined as a data sequence of identification data for the nodes of the transportation network.

Description

Transport route determination method, transport route determination device, and computer program

INDUSTRIAL APPLICABILITY The present invention relates to a transportation route determining method, a transportation route determining device, which determines a route for transporting a distribution member on which an article such as a pallet, a small container, or a cardboard box is loaded, in order to improve the distribution efficiency of the article. And computer programs.

In order to improve the efficiency of the entire physical distribution, it is necessary to optimize the routes of the physical distribution members on which the goods to be transported are loaded and the transportation equipment on which the physical distribution members are loaded.

The method of setting a route for delivery has been proposed for some time. Patent Document 1 discloses a method for solving a delivery planning problem assuming that a loaded load is transported in one travel of one transport vehicle from a delivery base to a delivery destination. Patent Document 1 uses a plurality of delivery vehicles to deliver a cargo from a distribution base to a plurality of delivery destinations, and a delivery plan is made by a different algorithm so that the mileage to the route returning to the original base is the shortest. By repeating the creation, I try to select the plan that has the shortest total mileage.

Patent Document 2 discloses a method using an insertion method in which a step of inserting a delivery destination and selecting the route having the shortest mileage is repeated in a tentatively determined delivery route. Patent Document 2 provides a provisional solution in which a customer is inserted in the middle of a closed route from a distribution base to a plurality of delivery destinations under the constraint conditions that the upper limit of the traveling time and the maximum load capacity of the vehicle are not exceeded. Generate and reduce mileage or travel time.

Japanese Unexamined Patent Publication No. 2001-188984 Japanese Patent Application Laid-Open No. 2015-038429

In all the methods for setting the delivery route from the base to the delivery destination as disclosed in Patent Documents 1 and 2, it is premised that each transport vehicle delivers the goods collected at the base center to the final delivery destination. It is supposed to be. It does not assume that the transport vehicle will transfer the cargo to another vehicle on the way.

Designing based on simulations is being promoted in various fields such as production technology, goods or buildings, but it is difficult to design delivery routes in logistics because there are many uncertain conditions. In the case of logistics, the starting and ending points of goods are not fixed, the starting and ending points of goods are geographically mixed, and the requirements for pickup and delivery times are not fixed, and the transportation equipment The number is also not constant. In addition, if the goods are allowed to be transshipped to another vehicle on the way, indefinite conditions overlap. If these indefinite conditions are divided into a plurality of patterns and each is calculated, the amount of calculation becomes enormous. Since the arrival and departure of goods and road conditions change from moment to moment, it becomes unrealistic to automatically derive a delivery route by simulation if the plan is reviewed and recalculated one by one.

The present invention has been made in view of such circumstances, and provides a transportation route determination method, a transportation route determination device, and a computer program that enable mechanical derivation of a transportation route to be more practical. The purpose is to do.

In the method for determining a transportation route according to an embodiment of the present disclosure, a predetermined unit pattern cycles between a point where a plurality of articles are collected and delivered, a transportation base via which a transportation device for transporting the articles passes, and each point in a transportation network. A transportation network is defined in which nodes are assigned to nodes arranged in a geometrically repeated geometric pattern, and a route connecting adjacent points or transportation bases is assigned to an edge between the nodes, and transportation connecting the transportation bases of the transportation equipment is defined. The route is determined as a data string of identification data of the node in the transportation network.

The transport route determining device according to the embodiment of the present disclosure has a predetermined unit pattern cycled between a point at which a plurality of articles are collected and delivered, a transportation base via which a transportation device for transporting the articles passes, and each point in a transportation network. A transportation network is defined in which nodes are assigned to nodes arranged in a geometrically repeated geometric pattern, and a route connecting adjacent points or transportation bases is assigned to an edge between the nodes, and transportation connecting the transportation bases of the transportation equipment is defined. A processing unit for determining a route as a data string of identification data of the node in the transportation network is provided.

The computer program of the embodiment of the present disclosure has a predetermined unit pattern of a point at which a plurality of articles are collected and delivered to a computer, a transportation base via which a transportation device for transporting the articles passes, and each point in a transportation network. A transportation network is defined in which nodes are assigned to nodes arranged in a periodically repeated geometric pattern, and a route connecting adjacent points or transportation bases is assigned to the edges between the nodes, and the transportation bases of the transportation equipment are connected. A process of determining a transportation route as a data string of identification data of the node in the transportation network is executed.

In the transportation route determination method, the transportation route determination device, and the computer program of the present disclosure, the points and the roads between the points constituting the transportation route are approximated to the transportation network represented by the geometric pattern, and simple data. It is converted to and used. By associating the distance as separate data without reflecting the length that reflects the actual distance in the route connecting the points, it is easy to process agent-based modeling that probabilistically selects the route to the adjacent node. Become.

According to the present disclosure, since the transportation route in a certain area is converted into a geometric pattern network including a grid and used, network analysis or image analysis becomes possible. It becomes easier to apply existing analysis methods of network analysis or image analysis, learning methods can also be applied, and it becomes possible to narrow down for deriving the optimum transportation route.

It is a schematic diagram of the distribution system of this disclosure. It is a schematic diagram which shows an example of the transportation equipment. It is a schematic diagram which shows an example of the transportation equipment. It is a block diagram which shows the structure of the transportation route determination apparatus. It is a block diagram which shows the structure of the terminal apparatus used by an operator. It is explanatory drawing of conversion from map data to a transportation network. It is a flowchart which shows an example of the processing procedure of the route calculation in advance. It is a flowchart which shows an example of the processing procedure of the route calculation in advance. It is a figure which shows the content example of the derivation method of the optimum route. It is a figure which shows the content example of the derivation method of the optimum route. It is a figure which shows the content example of the derivation method of the optimum route. It is a flowchart which shows an example of the transport route determination processing procedure by a transport route determination apparatus. It is a flowchart which shows an example of the transport route determination processing procedure by a transport route determination apparatus. The relationship between the overall pallet route and the partitioned transportation network is shown. It is a flowchart which shows an example of the processing procedure of the prior route calculation in Embodiment 2. It is a flowchart which shows an example of the processing procedure of the prior route calculation in Embodiment 2. It is explanatory drawing of the pixel representation of the transportation network in Embodiment 3. FIG. A schematic diagram of learning of a transportation network expressed in pixels is shown. It is a figure which shows other representations of a transportation network. It is a figure which shows the transportation network including the bypass edge. It is a figure which shows an example of the pixel representation of the transport network including a bypass edge.

The present disclosure will be specifically described with reference to the drawings showing the embodiments thereof. In the following embodiment, a physical distribution system to which the transportation route determination method of the present disclosure is applied will be described.

FIG. 1 is a schematic diagram of the distribution system 100 of the present disclosure. The distribution system 100 includes a transportation device 1 for transporting goods, for example, agricultural products, a base center (base) 2 which is a transfer center where the transportation device 1 stops, a collection / delivery center 3 which is a distribution center for collecting and delivering goods, and a control center 400. And include. The distribution system 100 is operated based on the route information determined by the transportation route determination device 4. The transportation route determining device 4 can be connected to the transportation device 1, the device in the base center 2, and the device in the collection / delivery center 3 by communication. Further, the transportation route determining device 4 can be connected to a terminal device 5 used by operators at various locations such as a producer or a manufacturer, a base center 2, a collection and delivery center 3, and the like.

The transport device 1 is a vehicle such as a transport truck, a train, a transport aircraft, or a ship. The transport device 1 may be a transport robot that travels by automatic operation.

The base center 2 is a transit center provided on a so-called trunk line in logistics, and is installed at a place that serves as a base for transportation equipment 1, such as a port, an airport, a freight station, and an interchange (IC) in a road network. The base center 2 is provided, for example, at predetermined distances. The base center 2 is provided with a group of devices for receiving the warehousing of the transport device 1 at the base center 2 and carrying in / out the pallet P from the transport device 1, and a base controller 20 for controlling the device group. The base controller 20 is capable of communication connection with the transportation route determination device 4, and controls the device group based on the instruction from the transportation route determination device 4.

In the distribution system centered on the base center 2, the objects to be transported are loaded on the distribution members and transported. Specifically, the physical distribution members are the pallet P and the small container C. In the following description, the description will be focused on the pallet P, but the small container C may be treated in the same manner. Further, the distribution member may be a flexible container, a so-called flexible container, an iron container, or a cardboard box. In addition, bags, plates, and box materials used for placing and accommodating goods in physical distribution are included in physical distribution members.

The pallet center 22 should be installed side by side in the base center 2. Pallets P are collected and delivered at the pallet center 22. The pallet center 22 is equipped with a pallet controller 23 that controls a device for carrying in and out the pallet P. The pallet controller 23 is capable of communication connection with the transport route determination device 4, and controls the device group based on the instruction from the transport route determination device 4.

The collection and delivery center 3 collects the goods to be transported from the producer or the manufacturer's base and transports them to the base center 2, or conversely, receives and stores the load from the base center 2 and stores the end user. It is a base for transporting goods to. The collection and delivery center 3 corresponds to a wholesale or distribution center. A plurality of collection and delivery centers 3 may be provided for the base center 2. The collection and delivery center 3 may be managed by a consignee who is a retailer. When the collection / delivery center 3 collects the goods to be transported to the base center 2, the goods may be loaded on the pallet P at the collection / delivery center 3. The collection / delivery center 3 is equipped with a collection / delivery site device 30 that receives instructions from the transportation route determination device 4. The collection / delivery site device 30 accepts the input of the shipped goods and the pallet P from the operator at the collection / delivery center 3, and accepts the input of the arrived goods. The collection / delivery site device 30 corresponds to the correspondence between the pallet identification information of the pallet P on which the goods to be shipped are loaded and the identification information of the goods, and the identification information of the arriving goods and the pallet identification of the pallets P on which the goods are loaded. The correspondence with the information is stored and transmitted to the transportation route determination device 4.

There is one or more base centers 2 in the area, and there are a plurality of collection and delivery centers 3. The area is not limited to administrative divisions, but is defined to be divided into arbitrary units, and is stored in latitude / longitude information, identification data of the base center 2 and the collection / delivery center 3, and identification data of the area to which the area belongs. Regions may overlap. The collection and delivery center 3 may belong to different areas. The base center 2 and the collection / delivery center 3 are both collection points and distribution points for transportation within the region (corresponding to "collection / delivery points"). Each of the plurality of collection and delivery centers 3 in the area is both a collection point and a distribution point. Any collection and delivery center 3 may function only as a collection point, and similarly any other collection and delivery center 3 may function only as a collection point.

The transport route determination device 4 sequentially acquires the position of the transport device 1, and sequentially collects the information of the pallet P housed in the transport device 1 and the information of the pallet P waiting to be shipped at the collection / delivery center 3. The transport route determination device 4 sequentially acquires the position from the transport device 1, the position information including the existence position of each pallet P, the destination information of the collection / delivery center 3 to which each pallet P should be delivered, and the time to be delivered. From the information, the movement route of the pallet P and the transportation route of the transportation device 1 are sequentially determined.

The transportation route determination device 4 instructs the transportation equipment 1 to stop at the base center 2 based on the determined transportation routes of the transportation equipment 1 and the movement route of the pallet P. The transport route determining device 4 instructs the base center 2 the pallet P to be carried out from the arrived transport device 1 and the pallet P to be carried into the transport device 1. Based on the determined transportation route and movement route, the transportation route determining device 4 instructs each center to send the pallet P to be shipped from the collection / delivery center 3 and the pallet center 22, and sends the pallet P to be carried out to the transportation equipment 1. Instruct.

In the present disclosure, a process of sequentially optimizing the movement route of the pallet P and the transportation route of the transportation equipment 1 from the information of the goods to be transported, the position information of the transportation equipment 1, and the like by the transportation route determining device 4 will be described. ..

The pallet P will be explained. The pallet P is a physical distribution member having a size of 90 cm square, similar to the pallet widely used in the field of physical distribution, and is more preferably made of resin. The pallet P may be made of various materials such as wood, stainless steel, and corrugated cardboard, and may be provided with a lift hole suitable for transportation by a forklift. As the pallet P, it is preferable to use a pallet made of a material conforming to the import / export regulations. A tag storing pallet identification information is attached to the pallet P. The tag is preferably a wireless tag using RFID or the like.

In the tag, the palette identification information of the palette P assigned in advance is readable and stored by the wireless reader. Although the pallet identification information of the pallet P in the tag is not rewritable, information on one or more articles loaded on the pallet P by the writer can be written in the tag. The goods information includes the type and item of the goods, the weight, the date of collection, the delivery number of the goods, the base identification information of the base center 2 that has recently passed through, the base center 2 of the destination, the consignee information, the sender information, etc. Is. It may be a predetermined medium on which a one-dimensional code or a two-dimensional code corresponding to the palette identification information of the palette P given in advance instead of the tag is printed. A one-dimensional code or a two-dimensional code may be printed on the tag. The information of the article is stored in association with the pallet identification information on the transportation route determining device 4 side.

The transport device 1 is a transport truck in the present embodiment. 2A and 2B are schematic views showing an example of the transportation device 1. FIG. 2A shows an example of a loading platform having a side-opening door, and FIG. 2B shows an example of a loading platform having a rear door. In both cases of the examples shown in FIGS. 2A and 2B, the transport device 1 is provided with a pallet frame 11 inside the loading platform in order to transport articles in units of pallets P. Specifically, the pallet frame 11 is a table that divides the loading platform from the floor surface to the ceiling in half in two stages, upper and lower. The loading platform has an internal dimension that allows two pallets P to be juxtaposed in the vehicle width direction. The accommodation position of the pallet P can be specified by the top and bottom and the left and right divided by the pallet frame 11.

As shown in FIG. 2B, the pallet frame 11 may have a configuration in which the entire pallet frame 11 can be pulled out from the rear door of the loading platform. In this case, if the pallet frame 11 is considered to be a huge pallet, the pallet frame 11 is also managed in a nested state in which a plurality of pallets P are loaded on the pallets as distribution members and a plurality of small containers C are loaded on each of the pallets P. It is also possible to do. The pallet frame 11 may be in the form of a plate laid on the floor of the loading platform, instead of the platform divided into two stages as shown in FIGS. 2A and 2B.

When the transport device 1 is a vehicle such as a train, a transport aircraft, or a ship, a large container having the same structure as the loading platform portion of FIG. 2A or FIG. 2B may be used, and the large container may be configured to include the pallet frame 11.

The transportation device 1 includes a reader that reads pallet identification information from the on-board unit 10 and the tag of the pallet P. The on-board unit 10 has a GPS receiver, sequentially acquires the position information of the transportation device 1, and transmits the position information to the transportation route determination device 4. When the pallet P is carried into the loading platform of the transport device 1, the on-board unit 10 reads the pallet identification information from the tag of the pallet P with a reader. The pallet identification information of the pallet P being accommodated and the accommodation unit identification information for identifying the accommodation position in the pallet frame 11 are transmitted to the transport route determination device 4 in association with the identification information of the transport device 1 stored in advance. .. The on-board unit 10 reads the pallet identification information from the tag of the pallet P carried out from the loading platform of the transport device 1 with a reader, and the pallet identification information of the carried out pallet P is stored in advance as the identification information of the transport device 1. It is associated and transmitted to the transportation route determination device 4. The on-board unit 10 may notify the transport route determination device 4 that the pallet P to be carried out is to be carried out by associating it with the accommodating portion identification information of the accommodating portion in which the pallet P is accommodated.

As a result, the position information of the pallet P can be constantly grasped by the transportation route determination device 4. The transport route determination device 4 associates the position information of the transport device 1 transmitted from each transport device 1 with the device identification information of the transport device 1 and stores it as the transport device information 413 (see FIG. 3). The transport route determining device 4 is associated with the pallet identification information of the pallet P, and the device identification information and the accommodating portion identification information of the transport device 1 on which the pallet P is loaded, or the pallet P is placed. The identification information of the base center 2 or the collection / delivery center 3 is stored as pallet information 412 (see FIG. 3).

FIG. 3 is a block diagram showing the configuration of the transportation route determination device 4. The transportation route determination device 4 is a server computer, and includes a processing unit 40, a storage unit 41, and a communication unit 42. The transport route determination device 4 may be configured not only by using one server computer (hardware) but also by distributing processing among a plurality of server computers, or a plurality of server computers virtually generated by a large computer. It may be one of (instances). The transportation route determination device 4 may execute the calculation by the quantum computer except for the processing of updating the information of the distribution DB 410 of the storage unit 41.

The processing unit 40 is a processor using a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit). The processing unit 40 executes processing using the built-in memory such as ROM (Read Only Memory) and RAM (Random Access Memory). The processing unit 40 can sequentially acquire time information by a built-in timer.

The storage unit 41 includes a hard disk or a non-volatile storage medium such as an SSD (Solid State Drive). The storage unit 41 stores the control program 40P. The processing unit 40 executes a process of deriving an optimum route by an operation described later based on the control program 40P stored in the storage unit 41.

A Web server program is stored in the storage unit 41, and the processing unit 40 exerts a Web server function, and the terminal device 5 may receive a request for sharing the loading platform of the transportation device 1 or the like from the terminal device 5 by this Web server function. ..

A distribution DB (DataBase) 410 is constructed in the storage unit 41 or an external storage device. The processing unit 40 can read / write to / from the distribution DB410 by the database operation module. For example, user information 411, pallet information 412, and transportation equipment information 413 are stored in the distribution DB410, as will be described later. Further, the physical distribution DB 410 stores the transportation route information 414 derived in advance by the calculation described later.

The communication unit 42 realizes communication on the public communication network N1 or the carrier network N2. The processing unit 40 can transmit and receive information to and from the terminal device 5 via the public communication network N1 or the carrier network N2 by the communication unit 42. Further, the processing unit 40 can transmit / receive information to / from the in-vehicle device mounted on the transportation device 1 via the carrier network N2 by the communication unit 42. The processing unit 40 can communicate with the base controller 20 of the base center 2 and the collection / delivery area device 30 of the collection / delivery center 3 via the public communication network N1, the carrier network N2, or the leased line by the communication unit 42.

FIG. 4 is a block diagram showing the configuration of the terminal device 5 used by the operator. The terminal device 5 uses a desktop type, laptop type, or tablet type personal computer. The terminal device 5 may be a smartphone. The terminal device 5 includes a processing unit 50, a storage unit 51, a communication unit 52, a display unit 53, and an operation unit 54.

The processing unit 50 is a processor using a CPU or GPU. The processing unit 50 executes processing based on the program stored in the storage unit 51 using the built-in memory such as ROM and RAM.

The storage unit 51 includes a non-volatile storage medium such as a hard disk or SSD. The storage unit 51 stores the terminal program 50P. The processing unit 50 receives an operator's operation based on the terminal program 50P stored in the storage unit 51, and executes a process of displaying data.

The communication unit 52 realizes communication in the public communication network N1 or the carrier network N2. The processing unit 50 can transmit and receive information to and from the transportation route determination device 4 via the public communication network N1 or the carrier network N2 by the communication unit 52.

The display unit 53 is a display such as a liquid crystal display or an organic EL (ElectroLuminescence) display. The display unit 53 displays a screen based on the data stored in the storage unit 51.

The operation unit 54 is a user interface such as a keyboard and a pointing device capable of input / output to / from the processing unit 50. The operation unit 54 may be a voice input unit. The operation unit 54 may be a touch panel of the display unit 53.

In the distribution system 100 configured in this way, the transportation route determination device 4 is based on the position of each transportation device 1 and the position of the pallet P, and the delivery conditions such as the shipping schedule and the required arrival time of the goods. The transportation route of 1 and the movement route of the pallet P are determined. The transportation route of the transportation equipment 1 connects the waypoints that sequentially approach for collection or unloading from the base center 2 or collection / delivery center 3 at the departure point (shipping point) to the base center 2 or collection / delivery center 3 at the end point. Contains data. The movement route of the pallet P is the history of the accommodating portion of one or a plurality of transportation devices 1 accommodated during the period from the departure point to the end point of the pallet P. The pallet P may be transported to the final destination by one transport device 1, but from one transport device 1 to another at a transit point which is a collection and delivery center 3 in the base center 2 or the delivery destination area. It is possible to transfer to the transportation equipment 1.

The transport route determination device 4 is given actual delivery conditions (position of transport device 1, position of pallet P, shipping schedule and arrival time) when determining the transport route of the transport device 1 and the movement route of the pallet P. In addition to starting the calculation from, the optimum route within the target range is derived in advance. When the actual delivery conditions are given, the transportation route determination device 4 extracts a matching or similar route from the optimum routes derived for various conditions derived in advance, and uses the extracted route as the extracted route. Based on this, a simulation is executed to derive the actual transportation route and movement route. The optimum route may be completed by selecting a partial route for each area.

Explain the derivation of the optimum route to be executed in advance. The derivation of the route in advance is first executed from the process of creating a transportation network from the geographical information of the target range. Second, the process of route calculation is performed by simulation of agent-based modeling using the transformed transport network.

FIG. 5 is an explanatory diagram of conversion from map data to a transportation network. The image of A in FIG. 5 shows an example of the original map data, the image of B shows the transportation network created from the map data, and the image of C shows the divided transportation network. As shown in A and B, the transportation network is a grid of intersections, branch points, or waypoints (base center 2, collection and delivery center 3, and pallet P supply area) from a road network that is never in a grid pattern. It is created by assigning it to the vertices (nodes) arranged in a grid pattern. The geographical length between each point does not adapt to the length in the transportation network, and it is better to have it as separate data simply as the distance between the nodes. The transportation network of B is divided into sizes that can be calculated (FIG. 5 (C)). As will be described later, the size that can be calculated may be appropriately set based on the processing capacity of the transport route determining device 4 based on the trial of the calculation time. As shown in the images of B and C, if there is no corresponding road on the map, the edge is eliminated. By converting to such a transportation network, the road transportation network can be converted into standard data.

The transportation route can be represented as a column of node identification data (rows and columns). For example, the transportation route of the transportation device 1 starting from the central point in FIG. 5C can be expressed as a point (i, j) → a point (i, j + 1) → a point (i-1, j + 1) → ...

The transportation network shown in FIG. 5 may be automatically created by the processing unit 40 of the transportation route determination device 4 based on the map data acquired from the communication unit 42. Alternatively, the temporarily created transportation network is displayed on the display unit 53 of the terminal device 5 by the processing unit 40 of the transportation route determination device 4 or another arithmetic unit, and the operator of the terminal device 5 deletes the edge or removes the edge. It may be created by accepting additional modifications.

The transportation route determination device 4 divides the grid-like transportation network as shown in FIG. 5 as necessary to the extent that calculation can be performed, gives delivery conditions to each transportation network, and executes the second simulation. .. The unit of classification may be set according to the processing capacity of the transport route determining device 4. It is preferable that the divided range partially overlaps, for example, centering on the base center 2. For example, it has been found that when the transportation network grows from a size of 3 × 3 to a size of 5 × 5, the calculation time described later increases by 20 times.

Next, the route calculation by agent-based modeling simulation using the transportation network will be explained in advance. 6 and 7 are flowcharts showing an example of the processing procedure of the prior route calculation. The transportation route determination device 4 (or another arithmetic unit may be used) repeats the following processing for each transportation network by changing the delivery conditions, and derives the optimum route for each delivery condition.

The processing unit 40 sets delivery conditions for the target transportation network, including the initial position and number of the transportation equipment 1, the initial position and number of the pallets P, and the transportation destination in the network of each pallet P (S101). The delivery condition is, for example, that the transportation device 1 is located at the node corresponding to the base center 2 in the transportation network, 100 pallets P exist at the specific node, and the pallets P are transferred to the other three nodes. Transporting 40, 30, and 20 pieces. The number of transport devices 1 may be one or more, or may be a delivery condition that they are located at different nodes. The type of pallet P may be one or more.

The processing unit 40 sets the number of executions to the initial value (S102). The processing unit 40 executes the following processes a plurality of times, and among the multiple executions, the pallet P existing at the specific node as the departure point is distributed to the distribution points in the transportation network. The route with the least number of executions (the number of steps from the state where the transport device 1 exists in one node to the state of moving to the next node) required to complete, or the route with the shortest transport travel distance of the transport device 1. Derived.

The processing unit 40 sets the number of steps to the initial value (S103). As shown below, the processing unit 40 distributes the processing based on the agent-based modeling using the transportation device 1 as an agent to each transportation destination in the network by the pallet P existing at the specific node as the departure point. Run until is complete.

In that step, the processing unit 40 acquires the number of pallets P (loaded pallets P) associated with the agent (transport equipment 1) (S104). The processing unit 40 acquires the number of palettes P existing in the node where the agent is located (S105). The processing unit 40 determines and stores the number of pallets P to be stacked at the node where the agent is located (S106).

In S106, if the node in which the agent is located is the departure point, the processing unit 40 determines to load the pallet P existing in the departure point so as to fill the vacant storage section of the transport device 1 which is the agent. do. If the node in which the agent exists is a stopover or a destination, the processing unit 40 compares the number of pallets P accommodated in the accommodation unit with the number of pallets P required for the node, and is required for the node. The number of pallets P is determined so as to reduce the remaining number of pallets P.

The processing unit 40 probabilistically selects an edge to the adjacent node to proceed (S107). Here, of course, edges that do not exist in the transportation network are not selected.

In the selection process of S107, the processing unit 40 basically selects stochastically by a random number (solution A). As will be described later, it may be selected with a probability based on the weight for the node to be advanced in the next step, or when the number of pallets (loading number) associated with the agent becomes zero, the starting point (or the number of loads) becomes zero. You may select it with the condition that you return to the supply area) (Solution B). The processing unit 40 may learn a weighting coefficient for selecting a node by reinforcement learning that gives a reward such as loading efficiency each time one step is advanced (solution C). In this case, the processing unit 40 is more likely to reach the optimum solution sooner. In addition, the processing unit 40 may greatly change the parameter (for example, probability) by one, like any mutation (solution D). This reduces the possibility of falling into a local solution.

The processing unit 40 calculates the number of pallets P existing in the node when the pallet P being loaded is dropped onto the node moved via the selected edge (S108). In S108, the processing unit 40 calculates the total of the number of palettes P existing in the node before the movement of the agent and the number associated with the agent.

The processing unit 40 adds and stores the number of steps (S109), stores the identification data of the node to which the agent is moved, and stores the number of palettes P in each node (S110). The processing unit 40 may treat and store the state at each node after the movement of the agent as a multidimensional matrix (vector).

The processing unit 40 determines whether or not delivery matching the delivery conditions has been completed in the transportation network based on the number of pallets P in each node (S111).

If it is determined that the delivery has not been completed (S111: NO), the number of steps and the distance associated with the edge are added to the cumulative travel distance (S112), and the process is returned to S104. In S112, the processing unit 40 may add only one of the number of steps and the cumulative movement distance in the execution times.

When it is determined that the delivery is completed (S111: YES), the processing unit 40 stores the history (transport route) of the identification data of the node via which the agent has passed and the number of steps (S113).

The processing unit 40 determines whether or not the processing of S104-S113 has been executed a predetermined number of times or more (S114). If it is determined that the number of times is less than the predetermined number (S114: NO), the processing unit 40 adds the number of executions (S115) and returns the processing to S103.

In S114, the processing unit 40 may not determine whether or not the execution is performed more than a predetermined number of times, but whether or not it is determined that the optimum solution (minimum number of steps or the shortest cumulative distance) has been obtained by the execution up to that point. It may be executed further to determine whether or not the optimum solution can be derived.

When it is determined in S114 that the execution has been performed a predetermined number of times or more (S114: YES), the processing unit 40 extracts the transportation route having the minimum number of steps or the shortest cumulative travel distance in the predetermined number of times (S116). The processing unit 40 stores the extracted transportation route as the optimum solution under the delivery conditions (S117), and ends the processing.

The optimum route for each transportation network derived by the processing procedure shown in the flowcharts of FIGS. 6 and 7 is stored in the storage unit 41 of the transportation route determination device 4 as transportation route information 414 for each delivery condition.

FIGS. 8, 9A and 9B are diagrams showing an example of the content of the method for deriving the optimum route. FIG. 8 is a schematic diagram of a transportation network. The identification information of the matrix number is attached to each node. The agent (transport equipment 1) initially located at i and j stochastically selects the adjacent node. Here, the probability is completely random, preset weight, or the number of pallets P remaining at the departure point, the number of pallets P not enough at the destination, the number of pallets loaded by the agent, etc. It may be described by a function in the state described.

An example of applying a reinforcement learning method is shown. 9A and 9B are schematic views of the transportation network. The transportation networks of FIGS. 9A and 9B are given numerical values for evaluation (reward) for the condition. FIG. 9A shows the initial state, and FIG. 9B shows the selection history of the node of the agent in the time series. In FIGS. 9A and 9B, each node is attached with identification information of a matrix number, and it is assumed that the starting point is the node (i + 1, j) and there are two pallets P, respectively, and the nodes (i, j-1). And the delivery conditions to be delivered to the node (i + 1, j + 1).

In FIG. 9A, in the initial state, the starting point is given a negative evaluation reward for the number of pallets P, the positive evaluation reward is given for the number of pallets P loaded on the agent, and the pallet P that has arrived at the destination. It is assumed that a reward for positive evaluation is given for each number. By executing reinforcement learning with profit as the sum of rewards, learning of selection of each edge is realized.

Next, the processing procedure for determining the movement route of the pallet P and the transportation route of the transportation equipment 1 based on the actual ordering of goods and the transportation request will be described. The transportation route determining device 4 sequentially updates the distribution DB410 based on the information obtained from the vehicle-mounted device 10 by moving the transportation device 1, the shipping of the goods, and the location information of the goods obtained from the base center 2 and the collection / delivery center 3. The transportation route determination device 4 determines the movement routes of the transportation equipment 1 and the pallet P of the transportation equipment 1 together with the update of the distribution DB410, and based on this, the transportation equipment 1, the base center 2, and the collection and delivery center 3 transport, carry in, and carry out. Control carry-out.

10 and 11 are flowcharts showing an example of the transportation route determination processing procedure by the transportation route determination device 4.

The processing unit 40 of the transportation route determination device 4 acquires the arrangement of the pallets P from the pallet information 412 and the transportation equipment information 413 (S201).

The processing unit 40 acquires a condition indicating where the pallet P must be transported after a predetermined time or at a specific time based on the destination and the desired arrival time of each pallet P (S202). In S202, the processing unit 40 totals the number of pallets P for each base center 2 or collection / delivery center 3, which should be, for example, 3 hours after the processing of S201.

The processing unit 40 is based on the current position of the pallet P and the position of the transport device 1 acquired in the process of S201, and the conditions that the pallet P and the transport device 1 after a predetermined time should be acquired in the process of S202. , The transportation conditions in the transportation network are determined (S203).

In the processing of S203, the processing unit 40 obtains the transportation conditions of where the pallet P is located and how far it should be reached in the transportation network for each time zone. FIG. 12 shows the relationship between the overall pallet P route and the partitioned transport network. The base center 2 is connected in a net shape. As shown in FIG. 12, each pallet P passes through a plurality of partitioned transportation networks extending from the base center 2 at the departure point to the collection / delivery center 3 at the final destination. In the example of FIG. 12, one pallet P departs from the base center 2 in Nagano prefecture and destinations at the collection and delivery center 3 in Shiga prefecture. From the position of the pallet P at each time point, it is decided where to be transported thereafter, and by superimposing multiple pallet Ps, how many pallets P are gathered in the base center 2 for each divided transportation network, and others. It is possible to determine the transportation conditions of whether or not the material must be transported to the base center 2 or the collection and delivery center 3.

The processing unit 40 selects one transportation network (S204), extracts the optimum route of the delivery condition similar to the transportation condition for the transportation network from the one stored in the storage unit 41, and stores it (S205). In S205, the processing unit 40 derives the delivery condition and the Euclidean distance as a vector having the identification information of the node of the departure point that describes the transportation condition, the identification information of the node of the destination, the type of pallet, and the number of pallets as dimensions. Then, those with a shorter distance are extracted as those with a higher degree of similarity.

In S205, the processing unit 40 executes route calculation (FIGS. 6 and 7) based on agent-based modeling for the optimum route under similar delivery conditions only by the difference from the transportation condition, and derives the optimum route under each condition. do. At this time, when selecting a node stochastically, the simulation may be performed by selecting an edge similar to the optimum route with similar delivery conditions. Reinforcement learning techniques may be incorporated and implemented so that the cumulative travel distance is the shortest.

The processing unit 40 determines whether or not all transportation networks have been selected (S206), and if it determines that all networks have not been selected (S206: NO), returns the processing to S204.

When it is determined that all the transportation networks have been selected (S206: YES), the processing unit 40 determines the number of transportation devices 1 required for each transportation network, the optimum transportation route for each of the required number of transportation devices, and the optimum transportation route. The delivery conditions (type, number of pallets P to be transported, number of pallet accommodating units) are acquired and stored (S207).

The processing unit 40 assigns and stores pallet identification information based on the information of the pallet P already loaded and the information acquired in the processing of S207 to the pallet accommodating unit of the loading platform of the transportation equipment 1 in each place (). S208).

The processing unit 40 selects a transportation route in the divided transportation network as a partial route for each transportation device 1 and determines the entire transportation route (S209). In S209, the processing unit 40 may determine the route in the transportation network for the transportation equipment 1 as the entire transportation route.

The processing unit 40 determines (updates) the movement route of the pallet P for each pallet P, that is, the pallet accommodating unit of the transportation equipment 1 to be transferred to the destination (S210).

The processing unit 40 is based on the movement route of each pallet P, and for each transport device 1, the pallet identification information of the pallet P to be carried out at the base center 2 which is a transit point, and the storage unit in which the pallet P is housed. The storage unit identification information is listed (S211).

Based on the movement route of each pallet P, the processing unit 40 has pallet identification information of the pallet P to be carried in at the base center 2 which is a transit point, and a pallet storage unit in which the pallet P should be accommodated. The accommodation unit identification information of the above is listed (S212).

The processing unit 40 outputs a list of the determined transport route of the transport device 1, the movement route of the pallet P, and the pallet P to be carried in / out at each base center 2 (S213). The processing unit 40 transmits an instruction to the on-board unit 10, the base controller 20, the collection / delivery site device 30, and the pallet controller 23 (S214) based on the output content, and ends the processing.

In this way, it is possible to refer to the optimum route calculated in the divided transportation network, determine the transportation route of the transportation equipment 1 and the movement route of the pallet P, and control the movement of the entire pallet P based on this.

Of the processing procedures shown in the flowcharts of FIGS. 10 and 11, in the processing of S205, the optimum route derived in advance is not simply selected, but the optimum route with conditions similar to those already derived. It is preferable to add an operation related to the difference condition based on. For example, for delivery conditions that specify the departure point, destination, and type and number of pallets P in a 5x5 transportation network, in addition to the information on the number of transportation equipment and the transportation route for which calculation results have already been calculated, additional collection and delivery Calculate and integrate the number of transport equipment and transport routes that correspond only to the land, destination, and number of pallets. By accumulating the calculation result of the route in advance, the calculation time requires only the time to access the data, and the calculation time can be shortened.

(Embodiment 2)
In the second embodiment, the process of probabilistically moving the arrangement of the agent and the pallet P one step at a time from the initial state is repeated a predetermined number of times, and the route is better than the transportation route with the shortest number of steps so far. The search is terminated at the timing when it is unlikely that the search can be derived.

13 and 14 are flowcharts showing an example of the processing procedure of the prior route calculation in the second embodiment. Of the processing procedures shown in the flowcharts of FIGS. 13 and 14, the procedures common to the procedures shown in the flowcharts of FIGS. 9 and 10 are designated by the same reference numerals and detailed description thereof will be omitted.

In the second embodiment, the processing unit 40 uses the adjacent base center 2 or collection / delivery center centered on the selected base center 2 as a node, the route between the nodes as an edge, and associates the distance information with the edge. A distance transportation network within the region is defined (S121).

When the processing unit 40 calculates the number of palettes P existing in the node at the node to which the agent is moved (S108), not only the number of steps is added but also the distance associated with the moved edge is cumulatively moved. It is added and stored as a distance (S129).

When the processing unit 40 determines that the delivery within the transportation network is completed by the processing of S111 (S111: YES), the processing unit 40 determines the history (transportation route) of the identification data of the node via which the agent has passed, the cumulative travel distance, and the number of steps. Remember (S132). As a result, the number of steps required to complete the delivery at each time, the travel distance, and the transportation route are stored.

When it is determined in the processing of S111 that the delivery within the transportation network is not completed (S111: NO), the processing unit 40 adds the number of steps and the cumulative travel distance (S112), and the progress of delivery in the entire transportation network. Calculate the rate (S133). In S133, the processing unit 40 calculates the ratio of the number of pallets P that have reached the destination in the area to the total number of pallets P as the progress rate. In S133, the processing unit 40 may calculate the ratio of the number of undelivered pallets P to the whole as the progress rate as the progress rate.

In the processing of S133, the processing unit 40 may derive a standard for determining the timing for determining whether or not the route being calculated in S137, which will be described later, is likely to derive the shortest path. Therefore, it is not limited to the progress rate, and may be the number of calculations or the time.

The processing unit 40 determines whether or not the progress rate calculated in the processing of S133 satisfies the condition (S134). In S134, the processing unit 40 determines, for example, whether or not the progress rate (%) is a multiple of 10. In addition, if it is the number of calculations instead of the progress rate, it may be judged whether it is a multiple of 5, or if it is time, it may be judged whether the elapsed time is a multiple of 5. good.

If it is determined that the conditions are not satisfied in the processing of S134 (S134: NO), the processing unit 40 returns the processing to S104 and proceeds to the next step.

When it is determined in S134 that the condition is satisfied (S134: YES), the processing unit 40 stores the travel distance so far this time in association with the progress rate calculated in the processing of S133 (S135). The processing unit 40 gives the memorized travel distance and the transport route with the shortest travel distance among the travel distances for which the calculation of the transport routes is executed a plurality of times, with the distance at the progress rate calculated by the processing of S333 and the width. Compare (S136).

In S136, the processing unit 40 calculates, for example, as in the following equation (1). Assuming that the travel distance up to that point is k and the travel route at the progress rate (prog) of the shortest transport route among the transport routes obtained so far is kmin prog, the equation (1) is k <kmin + kmin. × (1-Progress rate) ... (1)
kprog <kmin prog + kmin prog × (1-progress rate (prog)) ... (1)
Is. The travel distance k10 when the progress rate is 10% is compared with 1.9 times the travel distance kmin 10 at the progress rate of 10% of the shortest transportation route. The travel distance k20 when the progress rate is 20% is compared with 1.8 times the travel distance kmin 20 at the progress rate of 20% of the shortest transportation route. When the progress rate is 90%, the travel distance k90 is compared with 1.1 times the travel distance kmin 90 at the progress rate 90% of the shortest transportation route. When the travel distance k obtained so far is equal to or greater than the comparison value, it can be determined that there is no possibility that the shortest transportation route can be derived.

As a result of the comparison processing in S136, the processing unit 40 determines whether or not there is a possibility that the shortest distance transportation route can be derived by proceeding with the delivery simulation (S137). When it is determined that there is no possibility (S137: NO), the processing unit 40 ends the current calculation in the middle and proceeds to the processing to S114.

If it is determined in S137 that there is a possibility (S137: YES), the processing unit 40 continues the calculation and returns the processing to S104.

As a result, if it is unlikely that the shortest path will be derived even if the calculation is further advanced, the calculation can be interrupted and the calculation time can be shortened.

(Embodiment 3)
In the third embodiment, the transportation network is further converted into a pixel representation from the aspect shown in FIG. 5 and used for the calculation. Since the hardware configuration of the distribution system 100 in the second embodiment is the same as the configuration of the first embodiment, the common configurations are designated by the same reference numerals and detailed description thereof will be omitted.

FIG. 15 is an explanatory diagram of the pixel representation of the transportation network according to the third embodiment. The upper left image in FIG. 15 shows a two-dimensional image corresponding to the pixel representation of the transport network, and the middle left image in FIG. 15 shows a two-dimensional image showing delivery conditions for the pixel representation. The upper left image and the middle left image of FIG. 15 are checkered images of the same size.

As shown in the upper left image of FIG. 15, in the second embodiment, the transportation network is represented by a two-dimensional image of a grid pattern. Every other square in the vertical and horizontal directions corresponds to a node in the transportation network. The squares that are vertically and horizontally adjacent to the squares corresponding to the nodes correspond to the edges between the nodes, that is, the roads between the points. The squares corresponding to the nodes and the squares corresponding to the edges are represented by different colors. When there is no road connecting the nodes, it is expressed as transparent or colorless (white). Not limited to color, it is preferable to express it by squares having different attributes such as patterns and marks. The pixel representation of the transportation network consists of a departure point image showing the squares of the starting point under the placement condition shown on the left side of the middle row of FIG. 15 by specific hatching, and a destination showing the distribution point under the placement condition shown on the right side of the middle row of FIG. The image can be separated into a road image corresponding to the geographical information shown in the lower right image of FIG. In the departure place image, the pixel range corresponding to the node where the pallet P is first accumulated, for example, the collection point such as the base center 2 and the supply point, is represented by specific hatching.

As shown in the upper left image of FIG. 15, a transportation network including a node that is a candidate for a waypoint and an edge that is a road between nodes can be easily created by a pixel representation that combines a departure image, a destination image, and a road image. Can be described.

Further, in the two-dimensional image on the upper left of FIG. 15, the geographical distance of the edge may be expressed by the shade of color and the brightness in the pixel range, and in the two-dimensional image on the left side of the middle of FIG. 15, the palette is displayed. The number of palettes P may be expressed by the shade or the intensity of the pixel range corresponding to the point where P is arranged.

By standardizing the data in this way, it becomes easy to carry out processing for transportation networks in different regions with the same computer program. Geographical information about the location on the map is approximated at the top of the transport network. Represents a road that exists in geographic information as the edge of a transportation network. Diagonal roads, three-way junctions, junctions, corners, etc. may also be approximated in the vertical and horizontal directions of the transportation network. Such standardization facilitates handling in the usage described below.

The usage of the pixel expression shown in FIG. 15 will be described. These pixel representations may be displayed on the display unit 53 of the terminal device 5 and used to display the state during the search for the route or the optimum route. Further, it may be used as input data and output data for deep learning for deriving the optimum route. In order for the operator to visually recognize the result of deriving the shortest path in the first embodiment, it may be displayed on the display unit 53 of the terminal device 5.

Explain the derivation of the optimum route when deep learning is adopted. As shown in FIG. 15, the transportation network and its delivery conditions can be handled as image data. Therefore, learning using a convolutional neural network that has a proven track record in image processing enables learning such as outputting data representing weighting of edges to be selected (FIG. 16).

FIG. 16 shows a schematic diagram of learning of a transportation network expressed in pixels. For example, as shown in FIG. 16, when an image of a transport network represented by pixels (upper left image in FIG. 15) is input to a model using a neural network, the number of transport devices 1 and the transport route are vectorized (transport devices). It is also possible to output as a sequence of identification data of numbers and vertices of the transportation route).

As shown in FIG. 15, the transportation route determination device 4 separates the departure point image, the destination image, and the road image and inputs each of them into a model using a neural network, and the transportation device 1 is used. It may be learned to output as a vector indicating the number of vehicles and the transportation route.

In this way, by using a transportation network that expresses delivery conditions and road conditions in pixel representation, it is possible to apply it to the techniques cultivated in neural networks such as image recognition and pattern recognition.

Further, by using the pixel representation as shown in FIG. 15, the operator who operates the terminal device 5 can visually recognize the transportation network displayed on the display unit 53 and intuitively understand the transportation network. .. Further, the operator can intuitively determine the delivery conditions of which node the pallet P exists in and which node should be transported by visually recognizing the transportation network as shown in FIG. 15 displayed on the display unit 53. I can understand. Therefore, it becomes easy to judge the validity of the calculation result and to automate at least a part of the correction of the number of transportation devices 1 and the transportation route, which has conventionally relied on the intuition of a skilled person.

In the above-mentioned embodiments 1 to 3, the transportation network had a grid pattern, a grid pattern, and a checkered pattern. However, the definition of transportation network is not limited to these vertical and horizontal grids. FIG. 17 is a diagram showing another representation of the transportation network. As shown in FIG. 17, a transportation network is defined by nodes arranged in a shape in which equilateral triangles are periodically repeated, and edges connecting the nodes. May be assigned. Further, as shown in FIG. 17, the transport network may be defined not only by the checkered pattern but also by a two-dimensional image including a geometric pattern region. In FIG. 17, the corresponding areas of the nodes arranged at predetermined intervals in arbitrary two directions in the pattern are represented by dark gray (hatching) in the figure, and the areas corresponding to the edges between the nodes correspond to the nodes. It is expressed with a dot pattern that is different from the area to be used. By defining the transportation network with such a simple shape, the processing of route calculation becomes easy. The geometric pattern is not limited to an equilateral triangle, but may be a honeycomb-shaped network consisting of regular hexagons.

The transportation network may be represented in a plurality of three dimensions based on the actual condition of the transportation network. What is the actual state of the transportation network? Here, if it is a road, it is a highway network, an automobile-only road, and if transportation by different types of transportation equipment 1 is mixed, there are routes such as railroads, aviation, and ships. These different paths may be defined as bypass edges. FIG. 18 is a diagram showing a transportation network including a bypass edge. In FIG. 18, the bypass edge is shown by a thick dashed line regardless of its type. It may be divided into different layers according to the type of transportation equipment 1 such as railroad, aviation, and ship. The transportation network may include a representation of the bypass edge in layers of the highway network only. By targeting these bypass edges in the selection process of S107, it becomes possible to perform route calculation in a complicated system even in a simplified transportation network.

The transportation network including the bypass edge may be defined by superimposing a checkered two-dimensional image. FIG. 19 is a diagram showing an example of pixel representation of a transportation network including a bypass edge. As shown in FIG. 19, a transportation network is defined by superimposing two checkered two-dimensional images. In FIG. 19, the image superimposed on the top is the same as the pixel representation of the transport network of FIG. The squares corresponding to the nodes and the squares corresponding to the roads are indicated by pixel representations of attributes such as different colors, patterns or marks. In FIG. 19, the image shown at the bottom shows an example of an image of the bypass edge. In the pixel representation of the bypass edge, the square corresponding to the node to which the bypass edge is connected is represented by a specific attribute. In the image of the bypass edge, the bypass edge, which is a highway, is represented by a grid having the same attribute as the road, and the bypass edge, which is a water transport, is represented by a grid having a different attribute from the road. In this way, by expressing pixels for different types of transportation networks, the operator can visually recognize them in a simplified state on the display unit 53, and the techniques cultivated in neural networks such as image recognition and pattern recognition can be used. It can be applied and used for route calculation, etc.

The embodiments disclosed as described above are exemplary in all respects and are not restrictive. The scope of the present invention is indicated by the scope of claims and includes all modifications within the meaning and scope equivalent to the scope of claims.

1 Transportation equipment P pallet 4 Transportation route determination device 40 Processing unit 41 Storage unit 410 Logistics DB
414 Transport route information 40P control program

Claims (14)

A node in which a point for collecting and delivering a plurality of articles, a transportation base via which a transportation device for transporting the article passes, and each point in a transportation network are arranged in a geometric pattern in which a predetermined unit pattern is periodically repeated. Define a transportation network that assigns to the edge between the nodes with a route connecting the adjacent points or transportation bases.
A transportation route determination method for determining a transportation route connecting transportation bases of the transportation equipment as a data string of identification data of the node in the transportation network. The transportation route determination method according to claim 1, wherein the transportation network is defined by nodes and edges arranged in a grid pattern. The transportation route determination method according to claim 1 or 2, wherein each point in the transportation network includes a branch point in the transportation network. Display the transportation network and
Accepts deletion or additional correction of the node or edge for the displayed transport network,
The transportation route determination method according to any one of claims 1 to 3, wherein the transportation route is determined on the corrected transportation network. The transportation route determination method according to any one of claims 1 to 4, wherein geographical distance data is associated with each of the edges. The transport network is defined as a two-dimensional image of a geometric pattern.
The nodes of the transport network are represented by regions in the geometric pattern having attributes containing predetermined colors, patterns or marks arranged at predetermined intervals in any two directions, and the edges between the nodes are the predetermined. The transportation route determination method according to any one of claims 1 to 5, which is located between the regions of the attribute of the above and is represented by the region of the attribute different from the predetermined attribute. The transport network is defined as a two-dimensional image of a grid pattern.
The nodes of the transport network are represented by the grids of attributes including a predetermined color, pattern, or mark every other vertical and horizontal direction in the two-dimensional image, and the edges between the nodes are the vertical rows of the squares of the predetermined attributes. The transportation route determination method according to any one of claims 1 to 5, which is next to each other and is represented by squares having attributes different from the predetermined attributes. In the two-dimensional image of the transportation network, the starting point image representing the square corresponding to the node of the pick-up point of the article with a specific attribute and the square corresponding to the node of the delivery point of the article are defined as the predetermined squares. The transportation route determination method according to claim 7, wherein the destination image represented by the attribute and the road image representing the squares corresponding to the edges with the different attributes are superimposed. The transportation route determination method according to any one of claims 1 to 8, wherein the transportation network includes a bypass edge different from the edge connecting specific nodes. The transportation network is defined by superimposing two-dimensional images of a plurality of geometric patterns.
A node of the transport network is represented by a region in a two-dimensional image that requires an attribute containing predetermined colors, patterns, or marks arranged at predetermined intervals in any two directions in the geometric pattern. The edge between them is located between the regions of the predetermined attribute and is represented by the region of the attribute different from the predetermined attribute.
The transport route determination method according to claim 9, wherein the bypass edge is represented by a region having a specific attribute between regions corresponding to a specific node in another two-dimensional image. Define the transportation network based on the map data,
From the transportation base or collection point corresponding to the node of the defined transportation network, the selection process of sequentially and probabilistically selecting the node of the transportation base or distribution point to which the transportation equipment passes next is performed at the distribution point of the goods. Simulation process that repeats until transportation to is completed,
A step of calculating a predetermined evaluation amount for a transportation route obtained in the simulation step, and a step of calculating a predetermined evaluation amount, and
From claim 1 including a step of determining a transport route based on the predetermined evaluation amount from a plurality of transport routes obtained by repeating the simulation step and the calculation step of the predetermined evaluation amount within a predetermined range. The transportation route determination method according to any one of 10. When the image data of the transportation network is input, a learning model that is trained to output vector data indicating the transportation route of the article in the transportation network is created.
The transportation route determination method according to claim 7 or 8, wherein the transportation route is determined based on the vector data output from the learning model when an image showing the collection point and the distribution point of the article is input. A node in which a point for collecting and delivering a plurality of articles, a transportation base via which a transportation device for transporting the article passes, and each point in a transportation network are arranged in a geometric pattern in which a predetermined unit pattern is periodically repeated. Define a transportation network that assigns to the edge between the nodes with a route connecting the adjacent points or transportation bases.
A transportation route determination device including a processing unit that determines a transportation route connecting transportation bases of the transportation equipment as a data string of identification data of the node in the transportation network. On the computer
A node in which a point for collecting and delivering a plurality of articles, a transportation base via which a transportation device for transporting the article passes, and each point in a transportation network are arranged in a geometric pattern in which a predetermined unit pattern is periodically repeated. Define a transportation network that assigns to the edge between the nodes with a route connecting the adjacent points or transportation bases.
A computer program that executes a process of determining a transportation route connecting transportation bases of the transportation equipment as a data string of identification data of the node in the transportation network.

Images