Mobile object management system and mobile object management method

Abstract

To provide a technique capable of avoiding the competition of routes caused by unexpected fluctuations in travel even if a difference occurs between a planned route and an actual travel route of a mobile body.SOLUTION: A mobile object management system of the present invention includes, in a storage unit, actual route information indicating an actual route for a mobile object moving within a specified area, optimal route information indicating an optimal route that is a premise of the actual route, and map information indicating positions of obstacles in the specified area. And in a memory, the system includes processing instructions for causing a processor to function as a prediction-actual difference learning unit that calculates a prediction-actual difference of a route which is a difference between the actual route information and the optimal route based on the actual route information and the optimal route information, and generates a prediction-actual difference model, a travelable route prediction unit that predicts a travelable route based on the prediction-actual difference model, and a probability threshold determination unit that calculates a route that avoids the competition of routes according to a probability threshold based on the input probability threshold.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present invention relates to a mobile object management system and a mobile object management method. [Background technology]

[0002] In a warehouse or the like, multiple mobile objects such as robots and people move around the warehouse to perform picking tasks, and at that time, other robots and people may become obstacles to their movement. For this reason, in order to perform picking tasks efficiently without the robot or human colliding with each other, it is important to select a rational movement route. In such an environment where the locations of moving objects such as robots and people change dynamically, technology is being developed to dynamically assign work tasks, including movement routes, to each moving object as a technology to optimize the operation of multiple moving objects such as robots and people. Furthermore, in fields where multiple robots, people, and other mobile objects work while moving, resource conflicts such as workspace and movement routes are likely to occur, adversely affecting work efficiency, making cooperative route optimization that can resolve resource conflicts necessary.

[0003] For example, in Patent Document 1, it is described that "in order to reduce the constraints on the route along which the autonomous mobile body travels and to enable the setting of the shortest route, and to prevent collisions and congestion even when multiple autonomous mobile bodies travel at the same time, when the loading and unloading locations of the workpieces W are specified via a wireless transmission path, the autonomous mobile body 1 creates a travel plan including a route from the loading location to the unloading location, and when an instruction to transport the workpieces W is received, the autonomous mobile body transports the workpieces W according to the planned route." The centralized control device 4 is capable of communicating with multiple autonomous mobile bodies 1 via wireless transmission paths to acquire the position of each autonomous mobile body 1, and notifies the autonomous mobile body 1 that is not transporting work W and is closest to the loading location of the loading location and unloading location to plan a route. Furthermore, a technology is disclosed in which the centralized control device 4 evaluates the relationship between the routes planned by each autonomous moving body 1, and when there is a possibility of interference between the routes of each autonomous moving body 1, causes the autonomous moving body 1 to re-plan a driving plan.

[0004] Furthermore, Patent Document 2 discloses a technology in which "a system and method for robot congestion management includes a robot monitoring server configured to track the locations of a plurality of robots in a navigation space, and a plurality of robots in communication with the robot monitoring server. Here, each robot includes a processor and a memory, and the memory stores instructions that, when executed by the processor, cause the autonomous robot to determine a first pose location corresponding to a first task from a task list assigned to the robot, receive congestion information associated with the first pose location from the robot monitoring server, identify a congested state at the first pose location indicated by the congestion information, and in response to the identification of the congested state, select a second task from the task list, and navigate to the second pose location corresponding to the second task." [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2005-242489 A [Patent Document 2] Special Publication No. 2022-519054 Summary of the Invention [Problem to be solved by the invention]

[0006] When planning a route for a certain mobile object, it has been a common practice to register the planned routes of other mobile objects on a time axis as dynamic obstacles, and to search for and generate a planned route that can avoid these obstacles. However, in actual operation, deviations from the planned route due to the accuracy of the control of the mobile object, or deviations from the planned route due to the mobile object autonomously detecting obstacles on-site, can cause fluctuations in travel due to the mobile object traveling off the planned route, which can become the cause of new conflicts (traffic jams or deadlocks).

[0007] In Patent Document 1, route planning for multiple moving objects and avoidance of route conflicts are considered, but conflicts caused by fluctuations in actual driving are not taken into consideration. Furthermore, in Patent Document 2, in order to prevent the effects of traffic congestion from spreading after it has occurred, the robot monitoring server takes measures such as updating the navigation rules and navigation parameters for each robot. However, this does not prevent traffic congestion from occurring, and only has the effect of preventing the effects of traffic congestion from spreading after the fact. Therefore, an object of the present invention is to provide a technology that can avoid route conflicts caused by unplanned fluctuations in travel even if a difference occurs between the planned route and the actual travel route of a moving object. [Means for solving the problem]

[0008] In order to solve the above problems, one of the representative robot movement management systems of the present invention is as follows: The system is equipped with a processor, a memory, and a storage unit, and the storage unit can include actual route information indicating an actual route for a moving object moving in a specified area, optimal route information indicating an optimal route that is the premise of the actual route, and map information indicating the positions of fixed obstacles as information regarding obstacles in the specified area. The memory can include processing instructions for causing the processor to function as a predictive / actual difference learning unit that calculates a route predictive / actual difference (hereinafter sometimes referred to as a "route predictive / actual difference"), which is the difference between the actual route information and the optimal route based on the actual route information and the optimal route information, and generates a predictive / actual difference model, a drivable route prediction unit that predicts a drivable route based on the predictive / actual difference model, and a probability threshold determination unit that calculates a route that avoids route conflicts according to an input probability threshold based on the probability threshold. Effect of the Invention

[0009] According to the present invention, it is possible to provide a technology that can avoid route conflicts caused by unplanned fluctuations in travel even if a difference occurs between the planned route and the actual travel route of a moving object. Problems, configurations and effects other than those described above will become apparent from the following description of the preferred embodiment of the invention. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a schematic diagram illustrating an example of a warehouse and an autonomous moving body for explaining an embodiment of the present disclosure. [Diagram 2] FIG. 2 is an example of a work task for explaining an embodiment of the present disclosure. [Diagram 3] FIG. 3 illustrates a computer system for implementing an embodiment of the present disclosure. [Figure 4] FIG. 4 is a diagram illustrating an example of a configuration of a mobile object management system according to an embodiment of the present disclosure. [Diagram 5] FIG. 5 is a diagram illustrating an example of a processing flow in the optimum route searching unit according to the embodiment of the present disclosure. [Figure 6] FIG. 6 is a diagram illustrating an example of a processing flow of the moving object control unit according to an embodiment of the present disclosure. [Figure 7] FIG. 7 is a diagram illustrating an example of a processing flow of the predicted / actual difference learning unit according to the embodiment of the present disclosure. [Figure 8]FIG. 8 is a diagram illustrating an example of a flow of processing by the travelable route prediction unit according to the embodiment of the present disclosure. [Figure 9] FIG. 9 is a diagram illustrating an example of a processing flow of the probability threshold determination unit according to an embodiment of the present disclosure. [Figure 10] FIG. 10 is a diagram illustrating an example of a dynamic obstacle information management unit according to an embodiment of the present disclosure. [Figure 11] FIG. 11 is a diagram illustrating an example of an overall flow according to an embodiment of the present disclosure. [Figure 12] FIG. 12 is a diagram illustrating an example of a route display and a display when a probability threshold value is input according to an embodiment of the present disclosure. [Figure 13] FIG. 13 is a diagram illustrating an example of a route display and a display when a probability threshold value is input according to an embodiment of the present disclosure. [Figure 14] FIG. 14 is a diagram illustrating an example of a route display and a display when a probability threshold value is input according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. Note that the present invention is not limited to the embodiment. In addition, in the description of the drawings, the same parts are denoted by the same reference numerals. When there are multiple components having the same or similar functions, they may be described by using the same reference numerals with different subscripts, or when there is no need to distinguish between these multiple components, the subscripts may be omitted. In addition, although terms such as "first," "second," and "third" may be used in the present disclosure to describe various elements or components, it will be understood that these elements or components should not be limited by these terms. These terms are used only to distinguish one element or component from another element or component. Thus, a first element or component discussed below can also be referred to as a second element or component without departing from the teachings of the inventive concept. In order to facilitate understanding of the invention, the position, size, shape, range, etc. of each component shown in the drawings may not represent the actual position, size, shape, range, etc. Therefore, the present invention is not necessarily limited to the position, size, shape, range, etc. disclosed in the drawings.

[0012] First, an overview of a mobile object management system according to the present disclosure will be described with reference to Fig. 1. Fig. 1 is a schematic diagram showing an example of a warehouse and an autonomous mobile object for explaining an embodiment of the present disclosure. In a warehouse 1 shown in FIG. 1, multiple autonomous mobile objects A, B, C, etc. travel autonomously while avoiding fixed obstacles such as shelves and walls, and pick up items given by work tasks described below. For example, the arrows in the example of Figure 1 indicate that autonomous mobile object A follows a work task, picks up an item at the black circle on shelf 3, then picks up an item at the black triangle on another shelf, and then returns to the designated location. In such a system, the shortest travel route is first searched for and set for the autonomous moving body that moves first. Then, for the autonomous moving body that moves next, the travel route of the previously determined autonomous moving body is regarded as a dynamic obstacle, and the shortest travel route is searched for and set so that the travel route does not conflict with the travel route of the previous autonomous moving body. Since the travel route of each autonomous mobile body can be recognized as its location at each time, it is possible to determine the travel route of each autonomous mobile body for all tasks, eliminating temporal and spatial conflicts. Therefore, when an autonomous mobile unit completes one task, the next task is automatically assigned to it in sequence according to the plan, and the work of the autonomous mobile unit is repeated until all work tasks are completed, thereby accomplishing all tasks.

[0013] Next, an example of a work task given to an autonomous moving body will be described with reference to Fig. 2. Fig. 2 is an example of a work task for explaining an embodiment of the present disclosure. Generally, work tasks are organized into groups of item numbers to be picked up on one route, and the items and quantities to be picked up in each group are stored in a list format, as shown in Figure 2. The relationship between the item number and the shelf position in the warehouse is linked in another table, and the autonomous mobile entity can recognize which shelf the item should be picked up from by specifying the item number.

[0014] These work tasks are automatically assigned in sequence to the autonomous moving bodies that have completed the previous work task, so that task assignment and the work of the autonomous moving bodies continues until all work tasks are completed. Note that the work tasks shown in FIG. 2 are explained in a simplified table for the purpose of explanation, and the work tasks dealt with in this disclosure are not limited to these.

[0015] A representative example of a method for searching routes for autonomous vehicles is the "Space-Time A * "Space-Time A*" is a graph search algorithm for finding a reasonable route to perform picking tasks efficiently without colliding with other moving objects or obstacles such as people. * The algorithm is extended to apply it to space-time planning problems. * In , a route is selected using an evaluation function that incorporates both time and space elements, which makes it possible to find the shortest route while satisfying time constraints. Specifically, each node contains location information and time information, and the evaluation function calculates the priority of the node by taking into account both location and time elements.

[0016] The mobile management system according to the present disclosure also uses such a known route search algorithm to perform efficient route search.

[0017] (Hardware configuration) Next, referring to Fig. 3, a computer system 100 for implementing an embodiment of the present disclosure will be described. The mechanisms and devices of the various embodiments disclosed herein may be applied to any suitable computing system. The main components of the computer system 100 include one or more processors 102, memory 104, a terminal interface 112, a storage interface 113, an I / O (input / output) device interface 114, and a network interface 115. These components may be interconnected via a memory bus 106, an I / O bus 108, a bus interface unit 109, and an I / O bus interface unit 110.

[0018] Computer system 100 may include one or more general purpose programmable central processing units (CPUs) 102A and 102B, collectively referred to as processors 102. In some embodiments, computer system 100 may include multiple processors, while in other embodiments, computer system 100 may be a single CPU system. Each processor 102 executes instructions stored in memory 104 and may include an on-board cache.

[0019] In one embodiment, memory 104 may include random access semiconductor memory, storage devices, or storage media (either volatile or non-volatile) for storing data and programs. Memory 104 may store all or a portion of the programs, modules, and data structures that implement the functions described herein. For example, memory 104 may store a mobility management application 150. In one embodiment, mobility management application 150 may include instructions or descriptions that execute on processor 102 the functions described below.

[0020] In some embodiments, mobility management application 150 may be implemented in hardware via semiconductor devices, chips, logic gates, circuits, circuit cards, and / or other physical hardware devices instead of or in addition to a processor-based system. In some embodiments, mobility management application 150 may include data other than instructions or descriptions. In some embodiments, cameras, sensors, or other data input devices (not shown) may be provided to communicate directly with bus interface unit 109, processor 102, or other hardware of computer system 100.

[0021] Computer system 100 may include a bus interface unit 109 that provides communication between processor 102, memory 104, display system 124, and I / O bus interface unit 110. I / O bus interface unit 110 may couple to an I / O bus 108 for transferring data to and from various I / O units. I / O bus interface unit 110 may communicate via I / O bus 108 with multiple I / O interface units 112, 113, 114, and 115, also known as I / O processors (IOPs) or I / O adapters (IOAs).

[0022] Display system 124 may include a display controller, a display memory, or both. The display controller may provide video, audio, or both data to display device 126. Computer system 100 may also include one or more sensors or other devices configured to collect data and provide the data to processor 102.

[0023] For example, computer system 100 may include motion sensors, etc. that collect acceleration data, movement data, etc. Other types of sensors may also be used. Display system 124 may be connected to a display device 126, such as a standalone display screen, a television, a tablet, or a handheld device.

[0024] The I / O interface unit provides the ability to communicate with various storage or I / O devices. For example, the terminal interface unit 112 may be attached to user I / O devices 116, such as user output devices, such as a video display, a television with speakers, and user input devices, such as a keyboard, a mouse, a keypad, a touchpad, a trackball, buttons, a light pen, or other pointing device. A user may use a user interface to enter input data or instructions to the user I / O devices 116 and the computer system 100, and receive output data from the computer system 100, by manipulating the user input devices. The user interface may be displayed on a display, played through speakers, or printed via a printer, for example, via the user I / O devices 116.

[0025] Storage interface 113 allows attachment of one or more disk drives or direct access storage device 117 (usually a magnetic disk drive storage device, but may be an array of disk drives or other storage devices configured to appear as a single disk drive). In some embodiments, storage device 117 may be implemented as any secondary storage device. Contents of memory 104 may be stored in storage device 117 and retrieved from storage device 117 as needed. I / O device interface 114 may provide an interface to other I / O devices such as printers, fax machines, etc. Network interface 115 may provide a communications path to allow computer system 100 and other devices to communicate with each other. This communications path may be, for example, network 130.

[0026] In one embodiment, computer system 100 may be a device that receives requests from other computer systems (clients) without a direct user interface, such as a multi-user mainframe computer system, a single-user system, or a server computer, etc. In other embodiments, computer system 100 may be a desktop computer, a portable computer, a laptop, a tablet computer, a pocket computer, a telephone, a smartphone, or any other suitable electronic device.

[0027] Next, a mobile management system according to an embodiment of the present disclosure will be described with reference to FIG.

[0028] (Mobile Management System) FIG. 4 is a diagram illustrating an example of a configuration of a mobile object management system 200 according to an embodiment of the present disclosure. The mobile object management system 200 is a system that can present a travelable route, together with a probability threshold, for an autonomous moving object, which is a route that can avoid a route conflict caused by an unplanned fluctuation in travel even if a difference occurs between the planned route and the actual travel route of another autonomous moving object. As shown in FIG. 4, the mobile object management system 200 includes a mobile object management device 210, a communication network 250, and a user terminal 260. In the mobile object management system 200, the mobile object management device 210 and the user terminal 260 may be connected to each other via the communication network 250.

[0029] (Mobile object management device) The mobile object management device 210 can present a route derived by the optimal route search unit using a known route search method, in a selectable form together with a probability threshold, by the travelable route prediction unit, which can avoid route conflicts caused by fluctuations in the travel of the autonomous mobile object, based on the results of the predicted / actual difference learning unit. Then, when a travel route based on a desired probability threshold is selected, the travel route is registered in the dynamic obstacle information management unit as a dynamic obstacle, and the travel route of the mobile object is determined. As shown in FIG. 4, the device mainly includes a memory 220, a storage unit 230, a processor 244, and an input / output unit 246. In one embodiment, the mobility management device 210 may be implemented by the computer system 100 shown in FIG.

[0030] The memory 220 may be a memory for storing a mobile object management application 150 for implementing the functions of the mobile object management means according to an embodiment of the present disclosure. The mobile object management application 150 may include processing instructions for implementing the functions of software modules such as an optimal route search unit 222, a mobile object control unit 223, a predicted / actual difference learning unit 224, a drivable route prediction unit 225, a probability threshold determination unit 226, and a dynamic obstacle information management unit 227, as shown in FIG.

[0031] (Optimal route search section) The optimum route search unit 222 is a functional unit that calculates an optimum route using a known route search method based on map data 234, which is information about obstacles, a dynamic obstacle DB 231, and further, a work task 235. The details of the operation of the optimum route searching unit 222 will be described later, and therefore will not be described here.

[0032] (Mobile unit control unit) The mobile object control unit 223 is a functional unit that transmits driving instructions to mobile objects such as autonomous mobile objects and robots, collects the position history of the mobile objects, and records the results as an actual driving route, which is the route actually traveled. The details of the operation of the optimum route searching unit 222 will be described later, and therefore will not be described here.

[0033] (Prediction and Actual Difference Learning Department) The predicted-actual difference learning unit 224 is a functional unit that statistically learns the difference between a travel route instructed to a moving body such as an autonomous moving body or a robot and an actual travel route, which is the route actually traveled, and generates a predicted-actual difference model DB 233. The details of the operation of the predicted / actual difference learning unit 224 will be described later, and therefore will not be described here.

[0034] (Drivable route prediction unit) The drivable route prediction unit 225 is a functional unit that refers to the predicted / actual difference model DB 233 and calculates a drivable route taking into account past driving fluctuations together with its probability threshold for the optimal route calculated by the optimal route search unit 222. The details of the operation of the travelable route prediction unit 225 will be described later, and therefore will not be described here.

[0035] (Probability threshold determination unit) The probability threshold determination unit 226 is a functional unit that displays the drivable route calculated by the drivable route prediction unit 225 and its probability threshold on the user terminal 260, displays possible routes based on the selected threshold, and confirms the drivable route selected by the user. The details of the operation of probability threshold determination unit 226 will be described later, and therefore will not be described here.

[0036] (Dynamic Obstacle Information Management Unit) The dynamic obstacle information management unit 227 is a functional unit that registers the travelable route selected by the probability threshold determination unit 226 as dynamic obstacle information, which is a type of information on obstacles, and generates a dynamic obstacle DB. The details of the operation of the moving obstacle information management unit 227 will be described later, and therefore will not be described here.

[0037] (Storage part) The storage unit 230 stores data used by the mobile object management application 150 for implementing the functions of the mobile object management means according to the embodiment of the present disclosure and data generated by the mobile object management application 150, and stores a data DB 231 relating to dynamic obstacles, a position history DB 232, a predicted / actual difference model DB 233, map data 234, work tasks 235, a time-space graph 236, mobile object information 237, optimal route information 239, and actual route information 240. The storage unit 230 may store information other than the above, and may store data generated by the mobile object management application 150 in the course of processing, or other information. Here, the time-space graph 236 is a type of data used when calculating an optimal route using a known route search method, and may not be necessary when a different method is used for route search. Also, the mobile unit information 237 is information used to manage robots and autonomous mobile units.

[0038] Next, a processing flow in each functional unit included in the mobility management system according to an embodiment of the present disclosure will be described with reference to FIGS.

[0039] (Processing flow of optimal route search unit) FIG. 5 is a diagram showing a processing flow of the optimum route searching unit 222 according to an embodiment of the present disclosure. The optimum route search unit 222 calculates the optimum route using a known route search method. Specifically, a time-space graph 236 is generated based on map data 234 and data on dynamic obstacles, and an optimal route is searched for (S503) by associating this with work tasks 235 and mobile object information 237. If the route search (S505) is successful, the result is stored as an optimal route 238, and if the route search (S505) is unsuccessful, the movement start time of the mobile object is delayed (S507) and the optimal route search (S503) is performed again, and this is repeated until the optimal route is searched for.

[0040] (Processing flow of the mobile unit control unit) FIG. 6 is a diagram showing a processing flow of the moving object control unit 223 according to an embodiment of the present disclosure. The mobile object control unit 223 generates driving instructions for the mobile object based on the optimal route 238 calculated by the optimal route search unit 222, with reference to the map data 234 and the mobile object information 237 (S601). The mobile object control unit 223 transmits the generated driving instructions to the target mobile object (S603), and thereafter continues to detect the position information of the mobile object, and when the position information of the mobile object is updated, stores the information in the position history DB 232 as appropriate. This process continues until the mobile object arrives at the destination. When the mobile object arrives at the destination, the mobile object control unit 223 reads out the position history information of the mobile object from the position history DB, generates it as an actual driving route (S609), and stores it as the actual driving route 638. The difference between the actual route 638 stored here and the initial optimum route 238 becomes route predicted / actual difference data 738, which will be described next.

[0041] (Processing flow of prediction-actual difference learning unit) FIG. 7 is a diagram showing a processing flow of the predicted / actual difference learning unit 224 according to the embodiment of the present disclosure. As described above, the predicted / actual difference learning unit 224 calculates the difference between the actual route 638 and the optimal route 238 as the predicted / actual difference (S701). Then, the calculated route predicted / actual difference data 738 is statistically learned together with the map data 234 to learn at which point and to what extent the predicted / actual difference occurs, a predicted / actual difference model is generated, and is stored as the predicted / actual difference model DB 233. Regarding the statistical learning (S703) here, it is possible to use not only statistical results related only to positional relationships, but also learning results that take into account factors other than positional relationships by utilizing AI, etc., as a model for the learning results.

[0042] FIG. 8 is a diagram showing a processing flow of the travelable route prediction unit 225 according to the embodiment of the present disclosure. The drivable route prediction unit 225 performs drivable route prediction (S801) from the optimal route 238 and map data 234 using the predicted / actual difference model generated by the predicted / actual difference learning unit 224, and calculates a drivable route 838 and a probability threshold value 858 for the drivable route. A drivable route 838 and a probability threshold value 858 of the drivable route indicate a route along which a moving body actually travels, together with a probability threshold value. For example, even if the optimal route 238 is instructed to the moving body, in actual operation, the moving body will deviate from the optimal route 238 at some probability threshold value due to deviation from the planned route caused by the accuracy of the control of the moving body, deviation from the planned route caused by the moving body autonomously detecting an obstacle on-site, and the like. Specifically, when the optimal route 238 is set as the drivable route 838, the probability threshold 858 of the drivable route is 100%. On the other hand, when the probability threshold 858 of the drivable route is successively decreased to 90%, 80%, and 70%, the drivable route 838 becomes a bulging route based on past route forecast-actual difference data. The deviation from this planned route, which is the optimal route, is shown together with the probability threshold, which becomes the drivable route 838 and the probability threshold 858 of the drivable route. This situation will be described later with reference to Figs. 12 to 14.

[0043] (Processing flow of the probability threshold determination unit) FIG. 9 is a diagram showing a process flow of the probability threshold determination unit 226 according to an embodiment of the present disclosure. In the probability threshold determination unit 226, a display screen is generated (S901) using the map data 234 for the drivable route 838 and the probability threshold 858 for the drivable route generated by the drivable route prediction unit 225. Output examples of the screen display output (S903) are shown in Figs. 12 to 14. When the user inputs a probability threshold 858 for the drivable route as a threshold based on the screen display output or taking into account other information (S905), the drivable route is identified (S907) and specified as the selected drivable route 938. Here, when the probability threshold value 858 of the drivable route is selected as a threshold value of 100%, the selected drivable route 938 is the narrowest route that does not assume deviation from the planned route. On the other hand, when the probability threshold value 858 of the drivable route is successively decreased to 90%, 80%, and 70%, the selected drivable route 938 becomes a bulging road. In other words, when the travelable route expands, other moving bodies will not be able to use the expanded route thereafter, and the travel distance of the other moving bodies will increase.

[0044] (Processing flow of the dynamic obstacle information management unit) FIG. 10 is a diagram showing a processing flow of the dynamic obstacle information management unit 227 according to an embodiment of the present disclosure. In the dynamic obstacle information management unit 227, when the probability threshold determination unit 226 determines the selected drivable route 938, the selected drivable route 938 is generated as dynamic obstacle information together with the map data 234 (S1001). Then, the generated dynamic obstacle information is stored in the dynamic obstacle DB 231 as registration data. This is because the selected travelable route 938 corresponds to a dynamic obstacle when viewed from another moving object that searches for a travel route later.

[0045] (Action and effect) In this way, for a moving body whose travel route has been determined earlier, a possible travel route is determined taking into account the deviation in actual travel and is registered as a dynamic obstacle, so that a moving body that travels later is not affected by the deviation in actual travel of a moving body that travels earlier. This makes it possible to avoid route conflicts caused by unexpected fluctuations in travel even if a difference occurs between the planned route and the actual travel route of a moving body.

[0046] (Overall flow) Next, an overall flow for implementing the mobile object management system and mobile object management method of the present disclosure will be described with reference to Fig. 11. Fig. 11 shows an overview of the flow including "a stage before the forecast-actual difference model DB233 is constructed" to "a stage after the forecast-actual difference model DB233 is constructed." At the "stage before the prediction-actual difference model DB233 is constructed", the travel route of the moving body is set so that the moving body travels along the optimal route 238 searched for by the optimal route search unit, and the travel route is recognized as a dynamic obstacle for the moving body that travels thereafter. On the other hand, in the "stage after the predicted / actual difference model DB233 is constructed", the drivable route prediction unit 225 predicts a drivable route for the optimal route 238 searched for by the optimal route search unit based on the predicted / actual difference model, and the drivable route based on the probability threshold selected by the probability threshold determination unit 226 is recognized as a dynamic obstacle for the moving body that will travel thereafter, and is registered in the dynamic obstacle DB231. This makes it possible to avoid route conflicts caused by unscheduled travel fluctuations. It should be noted that the flow in FIG. 11 does not cover all possible flows, but shows only a rough outline of the flows.

[0047] First, it is determined whether or not there is any task that has not been assigned to any mobile object among the set work tasks 235 (S1101). If there is no unassigned task, the flow as the mobile object management system ends. On the other hand, if there is an unassigned task, the next step is to determine whether there is a mobile object that does not have a task (an available mobile object) (S1103). If there is no available mobile object, that is, if all the mobile objects are performing other tasks, the presence or absence of an available mobile object is determined again after a certain period of time has elapsed. In addition, this re-check for available mobile objects may be performed at regular intervals, or the mobile object itself may transmit a signal indicating that an available mobile object has been found, and the availability of an available mobile object may be confirmed upon receiving a signal indicating that an available mobile object has been found.

[0048] When the presence of an available mobile object is confirmed, a task is assigned to the available mobile object (S1105). Then, for the task assigned to the moving object, the optimum route search unit 222 performs an optimum route search (S503).

[0049] Next, after the shortest route is searched for, it is confirmed whether or not there is a predicted / actual difference model DB 233 (S1107). The predicted / actual difference model DB233 for a specific area does not exist from the beginning, but a highly accurate predicted / actual difference model is established at a stage where a certain amount of actual driving data is accumulated. Therefore, when the mobile object management system of the present disclosure is introduced into a specific area, the predicted / actual difference model DB233 does not exist at the initial stage, but becomes available at a stage where actual driving data of the mobile object is accumulated. For this reason, in S1107, the existence of a usable predicted / actual difference model DB233 is confirmed, and if there is no predicted / actual difference model DB, the result of the optimal route search (S503) is stored in the dynamic obstacle DB231 by the dynamic obstacle information management unit, and then the process proceeds to actual driving (S1115).

[0050] On the other hand, in S1107, if the predicted / actual difference model DB exists, in S1109, the drivable route prediction unit performs drivable route prediction. Then, after calculating the drivable route 838 and the probability threshold 858 of the drivable route, in S1111, the probability threshold determination unit determines the threshold, and the selected drivable route 938 is determined. Then, in S1113, the selected drivable route 938 is stored in the dynamic obstacle DB 231 by the dynamic obstacle information management unit, and then the process proceeds to actual driving (S1115). In the above example, the data is stored in the dynamic obstacle DB 231 and then the actual traveling (S1115) is started. However, since the dynamic obstacle DB 231 is used to plan the traveling route of the moving body that starts moving next, the data may be stored in the dynamic obstacle DB 231 after the actual traveling (S1115) starts, and it is sufficient that the data is stored before the traveling route of the moving body that starts moving next is planned.

[0051] (Example of route display) 12-14, route display and probability threshold input according to an embodiment of the present disclosure will now be described. Fig. 12 is a diagram showing an example of a route display according to an embodiment of the present disclosure, displayed on the display device 126. In Fig. 12, a target area is shown in the center of the screen, and a slide bar for selecting a probability threshold for predicting a drivable route is shown at the bottom. The target area has eight shelves arranged within it, and the routes that two moving objects will travel through it are shown diagrammatically. In addition, a button for determining the probability threshold selected with the slide bar is displayed in the lower right corner. In the example of Fig. 12, the optimum route 238 calculated by the optimum route search unit 222 is shown as a planned route in a solid line. In addition, the control bar for selecting the probability threshold value of the drivable route prediction is placed at the 80% position, and the route is shown wide on the route of the moving body together with the notation of 80%. This indicates that when the probability threshold value selection of the drivable route prediction is set to 100%, the route of the moving body is the optimum route 238 itself shown in a solid line, which is a drivable route, whereas when the probability threshold selection of the drivable route prediction is set to 80%, the route of the moving body is a route wider than the solid line. That is, the display device 126 displays the area of ​​the travelable route in conjunction with the probability threshold. If a low value is selected as the probability threshold, the possible route for the moving body will be set wide and the wide portion will be set as a dynamic obstacle, thereby preventing the moving body, whose route is calculated later, from colliding with the wide portion and causing traffic jams and the like.

[0052] Next, a display example when the probability threshold is lowered to 40% will be described with reference to Fig. 13. In Fig. 13, the overall screen configuration is the same as in Fig. 12, so the description of the same or equivalent components as in Fig. 12 will be simplified or omitted. In FIG. 13, the probability threshold is lowered to 40%, so that the possible routes of the moving object become thicker, and possible routes of different moving objects overlap, which are displayed as a diagonal striped pattern. In this way, when a conflict occurs between possible routes for different mobile bodies, it is necessary to consider a detour route that does not conflict.

[0053] Next, another display example in the case where the probability threshold is lowered to 40% will be described with reference to Fig. 14. In Fig. 14, the overall screen configuration is similar to Figs. 12 and 13, so the description of the same or equivalent components as Figs. 12 and 13 will be simplified or omitted. In FIG. 14, the threshold is lowered to 40%, resulting in a thicker band of possible travel routes, and a detour route that does not cause a conflict when a conflict occurs between possible travel routes of different mobile objects is displayed. In this way, by selecting a detour as a possible route, it is possible to avoid congestion caused by competing routes. On the other hand, when a detour is selected as a possible route, the travel distance of the mobile object increases, and the time required to complete the task increases.

[0054] (Recommendation function) For this reason, the probability threshold value must be determined by comparing and balancing the possibility of route conflicts occurring and the estimated overall delay time caused by the resulting congestion, and the estimated increase in travel distance due to the provision of detours and the resulting delay in task completion time. For this reason, the mobile management system of the present disclosure is equipped with a work data storage unit and a work time calculation unit as part of the mobile management application 150 shown in Figure 4, and is therefore able to present an optimal or preferred probability threshold based on a given work task and the target time required to complete the task.

[0055] For example, the task data storage unit calculates the average task time by tallying up the time from when the mobile unit starts to finish a task for each probability threshold from past task data of the mobile unit in the same or similar area. The task time calculation unit calculates the expected task time for each probability threshold by multiplying the number of tasks indicated in the task by the average task time. The threshold setting that is closest to the target task time can then be presented as a recommendation.

[0056] Furthermore, based on information on the frequency of route conflicts in a target area, it is possible to change the width of routes within the area, the arrangement of shelves, and the arrangement of items placed on shelves, etc., and make recommendations to level out the frequency of route travel within the target area, or to optimize the travel distance of mobile objects and target work times.

[0057] The present disclosure includes the following aspects. (Aspect 1) A mobile management system, A processor, a memory, and a storage unit are provided, The storage unit is Actual route information indicating an actual route of a moving object moving in a predetermined area, and optimal route information indicating an optimal route that is a premise of the actual route; Contains information about obstacles in a given area; The memory includes: a prediction-actual difference learning unit that calculates a prediction-actual difference of a route, which is a difference between the actual route information and the optimal route, based on the actual route information and the optimal route information, and generates a prediction-actual difference model; A travelable route prediction unit that predicts a travelable route based on the route prediction-actual difference model; A probability threshold determination unit that calculates a route that avoids a conflict between routes according to an input probability threshold. and a processing instruction for causing the processor to function as a mobile management system.

[0058] (Aspect 2) In the mobile object management system according to aspect 1, The memory includes: A mobile object management system comprising: a dynamic obstacle information management unit that registers the drivable route selected by the probability threshold determination unit as a dynamic obstacle.

[0059] (Aspect 3) In the mobile object management system according to the first or second aspect, The prediction-actual difference learning unit generates a prediction-actual difference model by statistically learning the prediction-actual difference of the calculated route.

[0060] (Aspect 4) In the mobile object management system according to any one of aspects 1 to 3, The mobile management system is characterized in that the drivable route prediction unit predicts a drivable route using the prediction-actual difference model, and calculates a drivable route and a probability threshold value for the drivable route.

[0061] (Aspect 5) In the mobile object management system according to any one of aspects 1 to 4, The mobile management system includes a display device, A mobile management system characterized in that the display device displays the area of ​​a drivable route in conjunction with a probability threshold.

[0062] (Aspect 6) In the mobile object management system according to any one of aspects 1 to 5, The memory includes: a task data storage unit that calculates an average task time by tallying up the time from when a mobile object starts to when a task ends for each probability threshold from past task data; a task time calculation unit that calculates an expected task time for each probability threshold by multiplying the number of tasks indicated in the task by an average task time; A mobility management system that presents a preferred probability threshold based on a given work task and a target time to complete the task.

[0063] (Aspect 7) In the mobile object management system according to aspect 1, The mobile management system includes an optimal route search unit, a step of searching for an optimal route by the optimal route search unit by referring to information about the obstacle; A step in which a travelable route prediction unit predicts a travelable route based on a prediction-actual difference model; recognizing the drivable route as a dynamic obstacle for a moving object that will travel thereafter; A mobile object management method comprising:

[0064] (Aspect 8) In the mobile object management method according to aspect 7, The mobile management system includes: a task data storage unit that calculates an average task time by tallying up the time from when a mobile object starts a task to when it finishes the task for each probability threshold from past task data; a task time calculation unit that calculates an expected task time for each probability threshold by multiplying the number of tasks indicated in the task by an average task time, The task time calculation unit includes a step of presenting an optimal probability threshold based on a given task and a target time until completion of the task. A mobile object management method comprising:

[0065] Although the embodiment of the present invention has been described above, the present invention is not limited to the above-described embodiment, and various modifications are possible without departing from the gist of the present invention. For example, the screen configuration of the display device is not limited to that shown in the figure, and various expression and display formats can be adopted. In addition, the method of calculating the optimal probability threshold in the recommendation function can be modified in various ways, and it is also possible to change the calculation so as to associate it with factors such as the characteristics of the target area and seasonal fluctuation factors. [Explanation of symbols]

[0066] 100: Computer system 150: Mobility management application 200: Mobile object management system 210: Mobile object management device 220: Memory 222: Optimal route search unit 223: Mobile object control unit 224: Prediction / actual difference learning unit 225: Driving path prediction unit 226: Probability threshold determination unit 227: Dynamic obstacle information management unit 230: Memory unit 244: Processor 246: Input / Output section 250: communication network 260: user terminal

Claims

1. A mobile management system, A processor, a memory, and a storage unit are provided, The storage unit is Actual route information indicating an actual route of a moving object moving in a predetermined area, and optimal route information indicating an optimal route that is a premise of the actual route; Contains information about obstacles in a given area; The memory includes: a prediction-actual difference learning unit that calculates a prediction-actual difference of a route, which is a difference between the actual route information and the optimal route, based on the actual route information and the optimal route information, and generates a prediction-actual difference model; A travelable route prediction unit that predicts a travelable route based on the prediction-actual difference model; A probability threshold determination unit that calculates a route that avoids a conflict between routes according to an input probability threshold. and a processing instruction for causing the processor to function as a mobile management system.

2. 2. The mobile object management system according to claim 1, The memory includes: A mobile object management system comprising: a dynamic obstacle information management unit that registers the drivable route selected by the probability threshold determination unit as a dynamic obstacle.

3. 3. The mobile object management system according to claim 2, The prediction-actual difference learning unit generates a prediction-actual difference model by statistically learning the prediction-actual difference of the calculated route.

4. 4. The mobile object management system according to claim 3, The mobile management system is characterized in that the drivable route prediction unit predicts a drivable route using the prediction-actual difference model, and calculates a drivable route and a probability threshold value for the drivable route.

5. 5. The mobile object management system according to claim 4, The mobile management system includes a display device, A mobile management system characterized in that the display device displays the area of ​​a drivable route in conjunction with a probability threshold.

6. 6. The mobile object management system according to claim 5, The memory includes: a task data storage unit that calculates an average task time by tallying up the time from when a mobile object starts to when a task ends for each probability threshold from past task data; a task time calculation unit that calculates an expected task time for each probability threshold by multiplying the number of tasks indicated in the task by an average task time; A mobility management system that presents a preferred probability threshold based on a given work task and a target time to complete the task.

7. 2. The mobile object management system according to claim 1, The mobile management system includes an optimal route search unit, a step of searching for an optimal route by the optimal route search unit by referring to information about the obstacle; A step in which the travelable route prediction unit predicts a travelable route based on a prediction-actual difference model; recognizing the drivable route as a dynamic obstacle for a moving object that will travel thereafter; A mobile object management method comprising:

8. The mobile object management method according to claim 7, The mobility management system includes: a task data storage unit that calculates an average task time by tallying up the time from when a mobile object starts to when a task ends for each probability threshold from past task data; a task time calculation unit that calculates an expected task time for each probability threshold by multiplying the number of tasks indicated in the task by an average task time, The task time calculation unit includes a step of presenting an optimal probability threshold based on a given task and a target time until completion of the task. A mobile object management method comprising:

Images