Operation plan generation device, operation plan generation method, and program

Abstract

To make it possible to automatically generate an operation plan that increases the number of autonomous mobile devices capable of being operated in the same time zone in a fixed space.SOLUTION: An operation plan generation device 1 includes: a control unit 1a for generating an operation plan including a plurality of passing points for an autonomous mobile device in response to an operation plan generation request including operation desire information; and a storage unit 1b. The storage unit 1b stores a relation between an execution operation plan and operation achievements at the time of execution. The control unit 1a generates an operation plan candidate including the plurality of passing points based on the operation desire information to predict a positional and temporal deviation that may occur when the operation is performed according to the operation plan candidate based on the relation with respect to the operation plan candidate. The control unit 1a sets an exclusive area for prohibiting competition of another autonomous mobile device based on predicted results with respect to the operation plan candidate. The control unit 1a determines the operation plan candidate that does not compete with the operation plan that has been generated and has not been completed with respect to the other autonomous mobile device to be the operation plan to be responded.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an operation plan generation device, a learning device, an operation plan generation method, a learning method, and a program. [Background technology]

[0002] In recent years, autonomously moving devices (autonomous mobile devices), such as drones and self-driving cars, have been actively researched and are already being used in some areas. Furthermore, due to the declining labor force, cost reductions, and operational efficiency, autonomous mobile devices are expected to become even more widespread in the future. For example, as tasks such as transporting and delivering packages are replaced by autonomous mobile devices from people and human-driven cars, it is expected that autonomous mobile devices will be used in situations closely related to people's lives. As this happens, autonomous mobile devices will be operated in people's living spaces, and therefore they will be required to operate safely and stably, such as by operating reliably and on time.

[0003] Patent Document 1 describes a traffic control support system that aims to improve the accuracy of ship route control while reducing the amount of calculations. The system includes a memory unit, an instruction responsiveness estimation unit, a geographic E-map generation unit, and a movement prediction unit. The memory unit includes behavioral data related to the behavior of a moving object, geographical data in which each meshed map section is assigned geographic attribute information, which is information related to the moving object's movement criteria, and responsiveness data related to the moving object's responsiveness to instructions. The instruction responsiveness estimation unit estimates the ideal behavior of the moving object based on the responsiveness data, calculates the difference between the estimated behavior and the behavior in the behavior data, and updates the responsiveness data based on the calculation result. The geographic E-map generation unit estimates the likelihood that the moving object will exist at a certain coordinate at each time based on the behavioral data, geographical data, and responsiveness data, and generates a geographic E-map. The movement prediction unit predicts the future coordinates of the moving object based on the geographic E-map. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2018-36958 Summary of the Invention [Problem to be solved by the invention]

[0005] The present inventors have considered how to operate an autonomous mobile device safely and stably. First, autonomous mobile devices are often operated by autonomously controlling their routes to move along given routes and operating times, i.e., to follow a route plan. Even if an external disturbance occurs during movement, the autonomous mobile device autonomously corrects its trajectory to follow the route and operating times, i.e., the operating plan. For example, for devices that operate in the air, such as drones, or devices that move on the ocean, a typical example of an external disturbance that can cause the device to deviate from its route is wind. Even if an external disturbance such as wind occurs, the autonomous mobile device autonomously controls its vehicle and moves to follow the operating plan as much as possible.

[0006] A typical example of an autonomous mobile device is a drone that flies autonomously beyond visual line of sight. An autonomously flying drone does not receive sequential instructions from an operator, but rather can move while making its own decisions to follow a given route. However, although an autonomous mobile device has a certain degree of autonomous navigation function, in order to respond to unforeseen circumstances and ensure safe operation, it is desirable for it to be operated while being monitored remotely by a traffic management device, such as by determining its current location via communication. It is also desirable for route monitoring to be one of the functions of the traffic management device.

[0007] Furthermore, while some autonomous mobile devices are equipped with the ability to avoid collisions using sensors, etc., collisions between autonomous mobile devices are unacceptable when they are used in urban areas. Therefore, even when multiple autonomous mobile devices are operating simultaneously, it is desirable to coordinate and plan routes and times in advance to prevent collisions between the autonomous mobile devices and prevent contact between the autonomous mobile devices. The adjusted and planned operation routes and passing times can be referred to as an operation plan, and formulating such an operation plan is one of the functions of the operation management device.

[0008] After considering methods for formulating operation plans for autonomous mobile devices, we found two main problems. The first problem is that there is no automated method for the series of procedures of simply setting a start point and an end point, designing a route, and generating an operation plan that is coordinated with the routes of other autonomous mobile devices; the procedure is carried out manually via the web. When there are few drones in operation and the operation density in a certain airspace is not high, it is possible to adjust the operation plan manually, but this method breaks down as the number of drones in operation increases.

[0009] The second problem is that when operation plans are created manually, the efficiency of spatial and temporal utilization deteriorates, making it impossible to operate a large number of autonomous mobile devices efficiently within the same space. For example, it is possible to handle route design and collision detection using a uniform, fixed-width route (protected airspace), but even when such a uniform protected airspace is taken into account, it is difficult to say that efficient operation is possible.

[0010] Specifically, as mentioned above, even if an autonomous mobile device determines a route, it may temporarily deviate from the planned route due to disturbances or other factors. Therefore, it is common to design routes with a large margin of error to avoid collisions with other autonomous mobile devices. For example, in the horizontal direction of an autonomous mobile device flying in the air, such as a drone, a sufficient margin of error is required to prevent the device from straying into other operational zones even if it is blown away by the wind at the maximum wind speed permitted for operation. This large margin of error must also be ensured in terms of time. For example, in the case of an autonomous mobile device flying in the air, such as a drone, collisions will occur if multiple drones enter the same spatial zone at the same time. Therefore, the time period during which a drone can occupy a certain space must be extended to account for delays. However, if this margin of error is too large, the efficiency of space utilization will decrease, limiting the number of autonomous mobile devices that can simultaneously operate in a given space at the same time.

[0011] Due to these problems, when formulating operation plans for autonomous mobile devices, it is necessary to increase the number of autonomous mobile devices that can operate simultaneously within a certain space at the same time, and to automate the formulation of such plans.

[0012] On the other hand, the technology described in Patent Document 1 is designed with human-crewed vessels in mind, and allows multiple vessels to enter one large mesh section. This is because, since humans are on board, even if a collision is imminent within the section, it can be avoided by human judgment. Therefore, it is desirable to automatically generate an operation plan that increases the number of autonomous mobile devices that can operate simultaneously in the same time period within a certain space, without requiring human judgment to avoid collisions.

[0013] The object of the present disclosure is to provide an operation plan generation device, a learning device, and methods and programs thereof that are capable of automatically generating an operation plan that increases the number of autonomous mobile devices that can operate within a certain space during the same time period, in order to solve the above-mentioned problems. [Means for solving the problem]

[0014] An operation plan generation device according to a first aspect of the present disclosure includes: a control unit that, in response to an operation plan generation request including operation desire information, generates an operation plan including multiple pass points for an autonomous mobile device included as an operation target in the operation desire information, and a storage unit that stores a relationship between an execution operation plan, which is an executed operation plan, and an operation record at the time of execution of the execution operation plan. The control unit generates operation plan candidates including multiple pass points based on the operation desire information, predicts positional and time deviations that may occur when operating according to the operation plan candidate based on the relationship, sets an exclusive area for the operation plan candidate as an area where other autonomous mobile devices are prohibited from competing with each other to operate, and determines, from among the operation plan candidates, a candidate that does not conflict with operation plans that have been generated but are incomplete for other autonomous mobile devices as the operation plan to be responded to the operation plan generation request.

[0015] A learning device according to a second aspect of the present disclosure includes: an acquisition unit that, in response to an operation plan generation request including operation desire information, acquires information including an executed operation plan from among operation plans generated to include multiple pass points for an autonomous mobile device included as an operation target in the operation desire information, and operation results during the execution of the executed operation plan; and a control unit that generates a trained model that predicts, based on the information acquired by the acquisition unit, positional and temporal deviations that may occur when operating according to a candidate operation plan generated to include multiple pass points based on another operation desire information. The operation plan is a plan in which, for each section route connecting adjacent pass points among multiple pass points included in the operation plan, an exclusive area is set to surround the section route as an area in which other autonomous mobile devices are prohibited from competing with each other to operate.

[0016] An operation plan generation method according to a third aspect of the present disclosure includes a process of generating, in response to an operation plan generation request including operation desire information, an operation plan including multiple pass points for an autonomous mobile device included as an operation target in the operation desire information. The process generates operation plan candidates including multiple pass points based on the operation desire information, predicts positional and time deviations that may occur when operating according to the operation plan candidates based on a relationship between an actual operation plan, which is an executed operation plan, and operation results at the time of execution of the actual operation plan, sets an exclusive area for the operation plan candidate as an area in which other autonomous mobile devices are prohibited from competing with the operation of the operation plan candidate based on the prediction result, and determines, from the operation plan candidates, a candidate that does not compete with operation plans that have been generated but are incomplete for other autonomous mobile devices as the operation plan to be responded to the operation plan generation request.

[0017] A learning method according to a fourth aspect of the present disclosure, in response to an operation plan generation request including operation request information, acquires information including an executed operation plan from among operation plans generated to include multiple pass points for an autonomous mobile device included as an operation target in the operation request information, and operation results during the execution of the executed operation plan, and generates a trained model that predicts, based on the acquired information, positional and temporal deviations that may occur when operating according to a candidate operation plan generated to include multiple pass points based on other operation request information. The operation plan is a plan in which, for each section route connecting adjacent pass points among the multiple pass points included in the operation plan, an exclusive area is set to surround the section route as an area in which other autonomous mobile devices are prohibited from competing with each other to operate.

[0018] A program according to a fifth aspect of the present disclosure causes a computer to execute the following processing: in response to an operation plan generation request including operation desire information, generate an operation plan including multiple pass points for an autonomous mobile device included as an operation target in the operation desire information, based on the operation desire information; for the candidate operation plan, predict positional and time deviations that may occur when operating according to the candidate operation plan based on a relationship between an executed operation plan, which is an operation plan that has already been executed, and operation performance at the time of execution of the executed operation plan; for the candidate operation plan, set an exclusive area as an area where other autonomous mobile devices are prohibited from competing with each other to operate, based on the predicted result; and determine, from among the candidate operation plan, a candidate that does not compete with operation plans that have been generated but are not yet completed for other autonomous mobile devices as the operation plan to respond to the operation plan generation request.

[0019] A program according to a sixth aspect of the present disclosure causes a computer to execute a process of, in response to an operation plan generation request including operation request information, acquiring information including an executed operation plan from among operation plans generated to include multiple pass points for an autonomous mobile device included as an operation target in the operation request information and operation results during the execution of the executed operation plan, and generating a trained model that predicts, based on the acquired information, positional and temporal deviations that may occur when operating according to a candidate operation plan generated to include multiple pass points based on other operation request information. The operation plan is a plan in which, for each section route connecting adjacent pass points among multiple pass points included in the operation plan, an exclusive area is set to surround the section route as an area in which other autonomous mobile devices are prohibited from competing with each other to operate the section route. [Effects of the Invention]

[0020] The present disclosure makes it possible to provide an operation plan generation device, a learning device, and methods and programs thereof that are capable of automatically generating an operation plan that increases the number of autonomous mobile devices that can operate within a certain space during the same time period. [Brief explanation of the drawings]

[0021] [Figure 1] 1 is a block diagram showing an example of the configuration of an operation plan generation device according to a first embodiment. [Figure 2] 2 is a block diagram showing an example of the configuration of an autonomous mobile device that is to be operated in an operation plan generated by the operation plan generation device of FIG. 1. FIG. [Figure 3] 4 is a flowchart illustrating a processing example in the operation plan generation device according to the first embodiment. FIG. [Figure 4] FIG. 1 is a block diagram showing an example configuration of a learning device that generates a trained model that can be used in the operation plan generation device according to the first embodiment. [Figure 5] FIG. 5 is a flowchart illustrating an example of processing in the learning device of FIG. [Figure 6] FIG. 10 is a schematic diagram showing a configuration example of an operation control system according to a second embodiment. [Figure 7] FIG. 10 is a block diagram showing an example of the configuration of an operation management device according to a second embodiment. [Figure 8] FIG. 10 is a schematic diagram for explaining section management according to a comparative example. [Figure 9] FIG. 8 is a schematic diagram for explaining an example of management in the traffic management device of FIG. 7. [Figure 10] FIG. 10 is a conceptual diagram for explaining the relationship between waypoints, edges, and route deviations, as well as exclusive areas. [Figure 11] FIG. 10 is a diagram illustrating an example of a data format of an operation plan issuance request. [Figure 12] 12 is a diagram illustrating an example of a format of data stored in an operation plan issuance request storage unit in response to the request in FIG. 11. FIG. [Figure 13] FIG. 10 is a diagram illustrating an example of a data format of an operation plan candidate created during the formulation of an operation plan. [Figure 14] 14 is a diagram illustrating an example of a data format of an operation plan issued for the operation plan candidate in FIG. 13. FIG. [Figure 15] FIG. 10 is a diagram illustrating an example of a data format of an issued operation plan. [Figure 16] 16 is a diagram illustrating an example of a data format in which a plurality of issued operation plans in FIG. 15 are arranged. FIG. [Figure 17] FIG. 10 is a diagram illustrating an example of a data format of coordinate information of a waypoint. [Figure 18] FIG. 10 is a diagram illustrating an example of a data format of edge information. [Figure 19] FIG. 8 is a sequence diagram showing an example of operation in the traffic management device of FIG. 7. [Figure 20] This is a sequence diagram continuing from FIG. 19. [Figure 21] FIG. 10 is a flowchart illustrating an example of a registration process of an operation plan issuance request. [Figure 22] FIG. 10 is a diagram illustrating an example of a data format of parameters of an operation plan request. [Figure 23] FIG. 10 is a flowchart illustrating an example of a process for determining a spatial information acquisition range. [Figure 24] FIG. 10 is a schematic diagram showing an example of a spatial information acquisition range. [Figure 25] FIG. 10 is a diagram illustrating an example of a data format of a spatial information acquisition request parameter. [Figure 26] FIG. 10 is a flowchart illustrating an example of a process for determining a spatial information acquisition range. [Figure 27] FIG. 10 is a diagram illustrating an example of a data format of acquisition range space information. [Figure 28] FIG. 10 is a schematic diagram illustrating an example of acquisition range space information. [Figure 29] FIG. 10 is a flowchart illustrating an example of a process for formulating a candidate operation plan. [Figure 30] This is a flow chart continuing from FIG. 29. [Figure 31] FIG. 10 is a diagram illustrating an example of a data format of a predicted value. [Figure 32] FIG. 10 is a schematic diagram for explaining a prediction result. [Figure 33] FIG. 10 is a diagram illustrating an example of a data format of a calculated exclusive area. [Figure 34] FIG. 10 is a diagram illustrating an example of a data format of an issued operation plan acquisition range. [Figure 35] FIG. 35 is a schematic diagram showing an example of the spatial information acquisition range determined in FIG. 34. [Figure 36] 10 is a diagram illustrating an example of a data format of an operation plan candidate to which an exclusive region calculation result of the operation plan candidate is added. FIG. [Figure 37] FIG. 10 is a schematic diagram illustrating an example of a conflict state. [Figure 38] FIG. 10 is a schematic diagram illustrating another example of a conflict state. [Figure 39] FIG. 10 is a schematic diagram illustrating another example of a conflict state. [Figure 40] FIG. 10 is a diagram illustrating a contention of an area. [Figure 41] FIG. 10 is a diagram illustrating an example of a data format of an operation plan. [Figure 42] FIG. 10 is a diagram illustrating an example of a data format of an operation plan. [Figure 43] FIG. 10 is a diagram illustrating an example of a data format of an operation plan. [Figure 44] FIG. 2 illustrates an example of a hardware configuration of the apparatus. DETAILED DESCRIPTION OF THE INVENTION

[0022] Hereinafter, embodiments will be described with reference to the drawings. In the embodiments, the same or equivalent elements may be denoted by the same reference numerals, and redundant description will be omitted as appropriate.

[0023] <Embodiment 1> An operation plan generation device according to embodiment 1 will be described with reference to Fig. 1 and Fig. 2. Fig. 1 is a block diagram showing an example of the configuration of the operation plan generation device according to embodiment 1, and Fig. 2 is a block diagram showing an example of the configuration of an autonomous mobile device that is to be operated in an operation plan generated by the operation plan generation device of Fig. 1.

[0024] 1, an operation plan generation device 1 according to this embodiment includes a control unit 1a that controls the entire device and a storage unit 1b, and generates operation plans for autonomous mobile devices. Operation plans are usually generated for multiple autonomous mobile devices, but it is sufficient that an operation plan generation request for a certain autonomous mobile device is received and the operation plans are generated in response to the operation plan generation request; operation plans do not necessarily have to be generated for all autonomous mobile devices under management at the same time.

[0025] Before describing the configuration of the operation plan generation device 1, we will explain an example of the configuration of an autonomous mobile device that is to be operated in the generated operation plan. As shown in Fig. 2, an autonomous mobile device (autonomous mobile equipment) 2 that is to be operated in the operation plan can include multiple sensors (sensor group) 2a, a communication unit 2b, a movement control unit 2c, and a drive unit 2d.

[0026] The autonomous mobile device 2 has information processing capabilities, controls actuators and the like, moves autonomously, and can be any device that carries or moves.

[0027] Examples of the autonomous mobile device 2 include self-driving automobiles, self-driving trains, self-navigating ships, autonomously flying aircraft, drones, AGVs (automated guided vehicles) used in factories, warehouses, etc., robots with running or leg-based mobility, robotic electric wheelchairs, motorcycles, etc. Here, drones are not limited to unmanned aerial vehicles that fly in the sky, but can operate in any environment, such as on the ground, in the sky, on water, underwater, or in space. Furthermore, robots can move by any method, such as running or walking. Furthermore, examples of the autonomous mobile device 2 include construction vehicles such as forklifts, construction machinery, and heavy machinery, railroad vehicles, vehicles used in logistics such as taxis and trucks, police vehicles, and fire engines. Here, railroad vehicles can be any type of locomotion, such as light rail, steel wheel systems, new transit systems, monorails, and magnetic levitation systems. The autonomous mobile device 2 also includes devices that can switch modes, sometimes operating autonomously and sometimes operating in response to human instructions or operations, and devices that move in coordination with human operations or instructions for part of their autonomous operation. In other words, the autonomous mobile device 2 only needs to be capable of moving autonomously, and can also have the function of moving under control from an external controller or under the operation of a passenger.

[0028] The sensor group 2a is a plurality of sensors provided at various locations on the autonomous mobile device 2. The results detected by each sensor are passed to the mobile control unit 2c and can be used to control the movement. In other words, the autonomous mobile device 2 is a device capable of autonomous movement and can detect its state (current state) while moving (in operation) based on the detection results (sensor data) output from the sensor group 2a. Here, the current state refers to the sensor values ​​obtained by measuring the detection target at the installation location of each sensor included in the sensor group 2a, or the state indicated by the sensor values, and mainly includes the moving state (operating state). The moving state can include the tilt and position of the autonomous mobile device 2. Note that the installation location and the detection target generally differ depending on the type and shape of the autonomous mobile device 2. Furthermore, the sensor group 2a can be composed of a plurality of sensors necessary for controlling the autonomous mobile device 2, and can include not only a sensor group that collects the state of the autonomous mobile device 2 itself, but also a sensor group that collects the state of the surroundings (surrounding environment).

[0029] An example of the sensor group 2a will be described using a drone, a type of autonomous mobile device, as an example. The sensor group 2a may include a speed sensor that observes the speed of the aircraft, an acceleration sensor that observes the acceleration of the aircraft, a gyro sensor that observes the roll, pitch, and yaw of the aircraft, and a rotation sensor that observes the rotation speed of each rotor used in flight. The sensor group 2a may also include a barometric pressure sensor or altitude sensor that observes the altitude of the aircraft, a geomagnetic sensor that observes the direction from the aircraft, and a temperature sensor that detects heat generation in the circuitry and rotors. Of course, the sensor group 2a does not need to include all of these examples and may include only some of them, and may also include other types of sensors without being limited to these examples.

[0030] For example, other sensors included in the sensor group 2a include sensors that acquire position information in a Global Navigation Satellite System (GNSS). GNSS is a general term for satellite positioning systems such as the Global Positioning System (GPS), the Global Navigation Satellite System (GLONASS), Galileo, and the Quasi-Zenith Satellite System (QZSS). The Quasi-Zenith Satellite System (QZSS) is the Quasi-Zenith Satellite System (QZSS). Using this sensor, the autonomous mobile device 2 can receive GNSS signals, determine its own position in space, and obtain position information. The sensors included in the sensor group 2a may be optical cameras or stereo cameras, and the position and attitude of the autonomous mobile device may be determined by processing images acquired by the cameras. The sensors included in the sensor group 2a may also be sonic sensors, ultrasonic sensors, 2D-LiDAR, 3D-LiDAR, or the like. In this case, the autonomous mobile device 2 can process waveform data and point cloud data obtained from a sensing device using sound waves or lasers to determine its own position, attitude, surrounding conditions, etc., and the information obtained in this way can also be considered sensor information. Therefore, sensors that require information processing such as these can also be included in the sensor group 2a.

[0031] Furthermore, the operating mode of the autonomous mobile device 2 (mode On / Off, current mode, etc.), the status of other mounted devices (for example, the rotor), and log data of the control device used for autonomous control can also be considered sensor information, so devices that provide such information can also be included in the sensor group 2a. Here, examples of the rotor status include valid / invalid, normal / abnormal, rotation speed, output, temperature, etc.

[0032] The communication unit 2b is a part that communicates with external devices such as the operation plan generation device 1, receives data of the operation plan generated by the operation plan generation device 1, and passes it to the movement control unit 2c. The communication unit 2b can be at least one of a wireless communication unit and a wired communication unit depending on the type of autonomous mobile device 2, the timing of data communication with the outside, etc.

[0033] The movement control unit 2c is a control unit that controls the movement of the autonomous mobile device 2, and can also be called a drive control unit. The movement control unit 2c is the brain that controls the drive unit 2d (for example, an actuator such as a rotor) mounted on the autonomous mobile device 2 based on sensing information provided by the sensor group 2a, in accordance with the operation plan data received by the communication unit 2b. The autonomous mobile device 2 performs autonomous control so that it moves along the route, coordinates, attitude, and speed provided as an operation plan at the start of operation. Therefore, even if the autonomous mobile device 2 shifts its position slightly due to control errors or external disturbances such as wind, it can control the actuators based on the sensing information and maintain its original position, attitude, and speed by itself.

[0034] In this way, the movement control unit 2c controls the driver 2d in accordance with the detection results of the sensor group 2a to move the autonomous moving device 2. Alternatively, the movement control unit 2c transmits some or all of the detection results of the sensor group 2a to an external server device (which may be the operation plan generation device 1 as long as it has a function for performing movement control) via the communication unit 2b. The movement control unit 2c then receives information for movement control from the server device via the communication unit 2b, and controls the driver 2d in accordance with this information. The driver 2d drives the autonomous moving device 2 in accordance with the control from the movement control unit 2c to move the autonomous moving device 2.

[0035] The movement control unit 2c can be configured as a control unit (not shown) that controls the entire autonomous moving device 2. This control unit can be realized, for example, by a CPU (Central Processing Unit), a working memory, and a non-volatile storage device that stores a program. This program can be a program that executes processing related to autonomous movement control. Furthermore, this control unit can also be realized, for example, by an integrated circuit.

[0036] Next, each component of the operation plan generation device 1 that generates an operation plan for an autonomous mobile device such as the autonomous mobile device 2 will be described.

[0037] The operation plan generation device 1 functions as a server device that provides operation plans and can be implemented as a server computer. The control unit 1a controls the entire operation plan generation device 1. Therefore, the control unit 1a can be realized, for example, by a CPU, a working memory, and a non-volatile storage device that stores a program. This program can be a program that executes processing related to the generation of an operation plan. Furthermore, the control unit can also be realized, for example, by an integrated circuit.

[0038] In response to an operation plan generation request including desired operation information received from an external device, the control unit 1a generates an operation plan including multiple passing points for the autonomous mobile devices included as operation targets in the desired operation information. The desired operation information can include, for example, a departure point, a destination, and a departure (possible or desired) time, and can also include a desired arrival time.

[0039] The storage unit 1b stores the relationship between an executed operation plan, which is an executed operation plan, and the operation results at the time of execution of the executed operation plan. Here, the executed operation plan is basically a plan generated by the control unit 1a, but it may also be a plan generated by another device, or it may include both of these plans. The relationship may be stored in a state that allows for prediction of deviations (for example, a calculation formula indicating the relationship), as described below, but it is preferable that it be stored as a trained model, as described below.

[0040] If the actual operation plan is a plan generated by the control unit 1a, it can be stored in the storage unit 1b when it is generated. If not, it can be obtained externally via communication or a portable recording medium. The operation results can be obtained by direct communication from the autonomous mobile device 2, but the timing does not matter, and they can also be received via another device or obtained via a portable recording medium. However, it is sufficient that the storage unit 1b stores the above-mentioned relationships obtained from them, and it is not necessary for it to store either the actual operation plan or the operation results.

[0041] The control unit 1a first generates a candidate operation plan including multiple passing points based on the desired operation information, and then predicts the positional and time deviations that may occur when operating according to this candidate operation plan based on the above relationships.

[0042] For this prediction, for example, a trained model can be used. In other words, the above relationship can be a trained model generated by machine learning based on the actual operation plan and operation results, and can be a trained model that predicts positional and time deviations that may occur when operating according to the operation plan candidate. In this case, this trained model is stored in the memory unit 1b, and the control unit 1a performs the above prediction using this trained model at the time of prediction. This trained model is a model that has learned the deviations in arrival locations and arrival times between past operation plans and actual results. The arrival location here can include not only the destination but also multiple set passing points.

[0043] Based on the predicted results for the operation plan candidates, the control unit 1a sets an exclusive area as an area where other autonomous mobile devices are prohibited from competing with each other to operate. This exclusive area can be set as an area where operation of other autonomous mobile devices for which operation plans have not yet been generated or autonomous mobile devices for which operation plans have been generated but are incomplete is prohibited. Therefore, this exclusive area corresponds to a margin range for the operation route of the autonomous mobile device, determined based on the deviation prediction results.

[0044] Then, the control unit 1a determines, from among the operation plan candidates, a candidate that does not conflict with operation plans that have been generated but are not yet completed for other autonomous mobile devices, as the operation plan to be sent in response to the operation plan generation request. The operation plan generation device 1 can return the operation plan determined in this manner as a response to the operation plan generation request. Note that the determined operation plan can also be sent to the autonomous mobile device 2, for example, sequentially while the autonomous mobile device 2 is operating, only as much as is necessary for control at that time.

[0045] Furthermore, as described above, this embodiment can be constructed as an autonomous mobile system including the operation plan generation device 1 and the autonomous mobile device 2 that is equipped with a group of sensors that collect information to be included in the operation record and is capable of communicating with the operation plan generation device 1. Furthermore, the operation plan generation device 1 can be configured as a single device, or its functions can be distributed among multiple devices to configure it as a system.

[0046] Next, an operation plan generation method executed in the operation plan generation device 1 will be described with reference to Fig. 3. Fig. 3 is a flow diagram illustrating an example of processing in the operation plan generation device according to the first embodiment.

[0047] As described above, in response to an operation plan generation request including desired operation information, the operation plan generation device 1 performs processing to generate an operation plan including multiple passing points for the autonomous mobile devices 2 included as operation targets in the desired operation information.

[0048] In this process, first, the operation plan generation device 1 generates an operation plan candidate including multiple passing points based on the desired operation information (step S1). Next, for the operation plan candidate, the operation plan generation device 1 predicts positional and time deviations that may occur when operating according to the operation plan candidate based on the relationship between an actual operation plan and the operation performance at the time of execution of the actual operation plan (step S2).

[0049] Next, the operation plan generation device 1 sets an exclusive region for the operation plan candidate based on the prediction result (step S3). Then, the operation plan generation device 1 determines, from the operation plan candidates, a candidate that does not conflict with operation plans that have been generated but are incomplete for other autonomous mobile devices, as the operation plan to respond to the operation plan generation request (step S4), and ends the processing. The operation plan determined here is set for the autonomous mobile device 2 that is specified as the device to be operated in the operation plan generation request. Furthermore, as described above, the operation plan generation device 1 can be configured by a computer, and in that case, the program can be a program that causes the computer to execute the above-mentioned processing.

[0050] As described above, in this embodiment, an exclusive area is set for a candidate operation plan based on a predicted deviation based on past performance, so the set exclusive area is variable and based on performance. Therefore, according to this embodiment, an operation plan can be automatically generated that increases the number of autonomous mobile devices that can operate in the same time period within a certain space, thereby increasing the accommodation density and the number of simultaneous operations of autonomous mobile devices in the space while avoiding collisions between the autonomous mobile devices. In other words, this embodiment can achieve both collision prevention and improved space utilization efficiency. Furthermore, in this embodiment, the exclusive area can be assumed not only as a two-dimensional space such as the ground, but also as a three-dimensional space such as the airspace.

[0051] Furthermore, in this embodiment, as explained as an exclusive area where other operations are prohibited, the autonomous mobile device 2 can be operated based on the concept of an operation zone where only one vehicle can be allowed in one zone. From this perspective, this embodiment can be said to be safe and useful as a concept for route design in areas where collision avoidance is difficult for the autonomous mobile device itself or where there are limits to its avoidance capabilities, including judgment and detection, such as for small drones flying beyond visual line of sight without a human on board. Furthermore, according to this embodiment, an operation plan can be automatically generated simply by specifying desired operation information.

[0052] Next, a learning device that generates a trained model that can be used in the operation plan generation device 1 will be described with reference to Fig. 4. Fig. 4 is a block diagram showing an example configuration of a learning device that generates a trained model that can be used in the operation plan generation device 1.

[0053] 4, the learning device 4 may include an acquisition unit 4a and a control unit 4b. Here, the control unit 4b may include a storage unit 4c.

[0054] The acquisition unit 4a acquires information including an effective operation plan and operation results of operations performed based on the effective operation plan. If the effective operation plan is a plan generated by the control unit 1a, it can be acquired via communication or a portable recording medium from the operation plan generation device 1 after generation or from the autonomous mobile device 2 that has acquired the generated plan. The operation results can also be acquired, for example, via the operation plan generation device 1 or directly from the autonomous mobile device 2 via communication or a portable recording medium. In addition, various types of environmental data acquired from the sensor group 2a, weather information websites, etc. can also be included as other learning data in the learning.

[0055] The control unit 4b generates the trained model described above based on the information acquired by the acquisition unit 4a. Specifically, the control unit 4b inputs the information acquired by the acquisition unit 4a as training data into the untrained model 4d stored in the memory unit 4c, performs machine learning, obtains the trained model 4e, and stores it in the memory unit 4c. Alternatively, the untrained model 4d is updated to become the trained model 4e. The algorithm, etc., of this untrained model 4d is not important as long as the generated trained model 4e can perform the predictions described above. Note that the learning algorithm (learner) can be determined arbitrarily by the analyst. Then, the trained model resulting from the learning can be used and an appropriate one can be selected by the analyst, or it can be automatically selected to meet specified conditions deemed appropriate.

[0056] The learning device 4 can be configured as a computer. Therefore, the control unit 4b can be realized by, for example, a CPU, a working memory, and a non-volatile storage device that stores a program. This program can be a trained model generation program.

[0057] Furthermore, the learning device 4 can be configured as a single device, or its functions can be distributed among multiple devices to configure it as a system. The learning device 4 can be provided in the operation plan generation device 1 or connected to the operation plan generation device 1. However, the learning device 4 can also be configured as an independent device that is not connected to the operation plan generation device 1. In that case, for example, the trained model generated by the learning device 4 can be copied or moved to the operation plan generation device 1 using a portable recording medium or the like.

[0058] Next, a learning method executed by the learning device 4 will be described with reference to Fig. 5. Fig. 5 is a flow diagram for explaining an example of processing by the learning device 4 of Fig. 4. First, the learning device 4 acquires information including an actual operation plan and operation results of operations performed based on the actual operation plan (step S11). Then, the learning device 4 generates a trained model based on the acquired information (step S12).

[0059] Such a learning device 4 can generate a trained model that can be used as the above relationship in the operation plan generation device 1, and the operation plan generation device 1 can obtain appropriate prediction results based on machine learning, and based on the prediction results, can determine an exclusive area that corresponds to the actual deviation.

[0060] <Embodiment 2> The second embodiment will be described with reference to Figures 6 to 43, focusing on the differences from the first embodiment, but the various examples described in the first embodiment can also be applied. The following description will be given with an example in mind where the operation plan generated by the operation plan generation device according to this embodiment is a plan generated for a drone, but the present invention will not be essentially different even if the drone is replaced with another type of autonomous mobile device.

[0061] This embodiment will be described with reference to FIG. 6, taking as an example a case where a delivery company (transportation business) Tr uses a drone for parcel delivery. FIG. 6 is a schematic diagram showing an example configuration of a traffic management system according to this embodiment. However, this embodiment can be similarly applied to autonomous mobile devices other than drones, and can also be similarly applied for purposes other than parcel delivery. For example, drones can be used for purposes other than parcel delivery, such as mediating, managing, and allocating routes, as performed by the Ministry of Land, Infrastructure, Transport and Tourism, for businesses that fly beyond visual line of sight (BVL) for tasks such as parcel transport, photography, and monitoring. Furthermore, this embodiment is not limited to drone operation management and tasks using drones, but can also be applied to operation management of autonomous mobile devices in general, such as robots, self-driving cars, automated guided vehicles in factories, and ships and aircraft with automatic navigation functions, and tasks using these. Additionally, this embodiment can also be applied to the transportation industry, manufacturing industry, infrastructure inspection and maintenance, construction and civil engineering, public services (flood control, dam management, disaster prevention, disaster response, police, firefighting), and security.

[0062] As shown in Fig. 6, the operation management system according to this embodiment includes an operation management device 10 that performs operation management, and a delivery company Tr that receives an order from a shipper sh becomes a requester for issuance of an operation plan, requests issuance of an operation plan to the operation management device 10, and obtains an operation plan. The operation management device 10 functions as a server device that provides operation plans.

[0063] The operation management device 10 is an example of the operation plan management device 1 according to the first embodiment, and in this example, has a mechanism for managing the operation of the drone 3 and an aircraft control function. The operation management device 10 has a function for issuing an operation plan in response to a request from an operation management issuance requester Tr, and a function for collecting and managing the operation history when the drone 3 operates, either continuously via communication or online or offline after the operation is completed.

[0064] The shipper sh requests the operation plan issuer Tr to transport cargo (operate drone 3). The shipper sh provides the operation plan issuer Tr with requests regarding operation conditions (operation start time (time or time zone when cargo is loaded), operation end time (desired time or time zone when delivery is made), operation start location (location where cargo is loaded), operation end location (destination of cargo)), etc. The shipper sh is depicted with a person icon in Figure 6, but the work performed by this component may be replaced with a computer system or the like and automated. For example, the shipper sh can place an order to a server device or the like used by the delivery company Tr using a terminal device such as a PC (Personal Computer), smartphone, or dedicated terminal.

[0065] The operation plan issuance requester Tr requests the operation management device 10 to issue an operation plan based on an order from the shipper sh, and has the operation plan issued. The requester Tr has the role of registering the received issued plan in the operating drone 3 and operating the drone 3 in accordance with the operation plan.

[0066] The operation plan issuance requester Tr is depicted with a person icon in Figure 6, but it simply mediates the exchange of information between the shipper sh, the drone 3, and the operation management device 10, and the work performed by this component may be automated by replacing it with a computer system or the like. For example, the delivery company Tr uses a terminal device such as a PC, smartphone, or dedicated terminal to access the server device used by the delivery company Tr, send an operation plan issuance request to the operation management device 10, and receive the operation plan in response. This operation plan is generated and issued by the operation management device 10 based on the operation plan issuance request from the delivery company Tr.

[0067] The drone 3 transports the cargo of the shipper sh in accordance with the registered operation plan. Note that, although the present embodiment will be described in terms of a transportation use case, the present invention can be similarly applied to passenger transportation, photography, and other cases in which the drone 3 is operated.

[0068] Next, a configuration example of the traffic management device 10 according to this embodiment will be described in outline with reference to Fig. 7 to Fig. 9. Fig. 7 is a block diagram showing a configuration example of the traffic management device according to the second embodiment, Fig. 8 is a schematic diagram for explaining section management according to a comparative example, and Fig. 9 is a schematic diagram for explaining an example of management in the traffic management device of Fig. 7.

[0069] As shown in FIG. 7, the traffic management device 10 according to this embodiment may include a performance learning unit 100, a performance management unit 200, a plan formulation unit 300, a plan management unit 400, and a space management unit 500. Each component shown in FIG. 7 may be configured as a computer program, an electrical / electronic circuit, or a combination of a program and an electrical / electronic circuit. Information can be exchanged between the components connected by lines in FIG. 7. If the components are programs, information can be exchanged between elements via shared memory or storage, or if the units are separate in implementation, information can be exchanged via communications.

[0070] In general, the operation management device 10 according to this embodiment can include an operation plan formulation unit 304 in the plan formulation unit 300 that sets an exclusive area based on deviation prediction and formulates an operation plan. The deviation prediction can refer to learning the route deviation between the actual operation plan and the operation record, and predicting the deviation between the route and the passage time using the learned results. The operation plan formulation unit 304 can automatically generate an operation plan based on the prediction results. Note that, in the case of the drone 3, the operation plan can be referred to as a flight plan.

[0071] Furthermore, the traffic management device 10 according to this embodiment manages the travel route of an autonomous mobile device 2 such as a drone 3 as follows, rather than managing exclusion by zone as in the comparative example shown in Fig. 8. That is, the traffic management device 10 manages exclusion by using waypoints (passage points) and edges (section routes connecting the pass points) connecting them, as shown by circles in Fig. 9, and variable exclusion areas set around the edges.

[0072] Specifically, in this embodiment, the deviations in destination locations and arrival times between past plans and actual results are learned, and based on the learning results, predictions of these deviations are used when formulating an operation plan to determine the margin of safety (hereinafter referred to as the danger zone in this embodiment) for the operation route of the autonomous mobile device.

[0073] Furthermore, in this embodiment, when designing a route, the method of selecting from a space in which the margin range of the entire space (all sections) is defined as a continuous arrangement of rectangular parallelepipeds of fixed uniform size is not adopted, and the exclusion time of the danger zone is not set to exclude the entire section from the start to the end of operation of a certain autonomous mobile device.

[0074] In the route design according to the comparative example, a rectangular parallelepiped (cube) larger than the danger zone is defined in advance to fill the space, as shown in Fig. 8, and the cube is selected as the shaded area in Fig. 8 to set the route for the autonomous mobile device, with the autonomous mobile device trying to move along the center of the cube as much as possible. In the comparative example, this type of route design is used to set a route that will prevent collisions between autonomous mobile devices.

[0075] In contrast, in this embodiment, as shown in Fig. 9, a plurality of points called waypoints are densely defined in space, and a route is set by selecting waypoints to be passed through. A waypoint is a passing point, and is a point that defines a location to be passed through and a time or time period to be passed through in an operation plan. Furthermore, in this embodiment, a danger zone (exclusion zone where routes for other autonomous mobile devices are not set) where routes for other autonomous mobile devices are not set is set around a line connecting waypoints, in a range according to a predicted value of route deviation.

[0076] More specifically, in locations where the predicted deviation from the route in the operation plan is small based on actual operation records, the exclusive space called the danger zone is made smaller, and conversely, if the deviation from the predicted value is large, the exclusive space of the danger zone is made larger.

[0077] Furthermore, in the traffic management device 10, when there is a large discrepancy between the planned arrival time and the actual arrival time at the waypoint and an advance or delay in the arrival time is predicted, the device processes as follows: That is, the traffic management device 10 extends the time for which the section is excluded as a danger zone (lifespan of the danger zone) depending on the magnitude of the discrepancy, and conversely, if the discrepancy is small, it shortens the exclusion time (lifespan of the danger zone).

[0078] In this way, in this embodiment, a route can be designed so as to pass through smaller partitioned sections (or conversely, larger sections) rather than through large sections of a fixed size.

[0079] In this way, the traffic management device 10 can set routes for autonomous mobile devices more flexibly. In particular, the traffic management device 10 can reduce the range and time that the danger zone occupies space compared to the comparative example, making it possible to set more traffic routes and increase the number of autonomous mobile devices that can be accommodated in a space.

[0080] In this manner, in this embodiment, instead of partitions in space, high-density waypoints are defined, and a travel route is set and designed to pass through those waypoints. In particular, in this embodiment, not only is a danger zone (a zone that excludes other autonomous mobile devices) set to surround the travel route, but it can also be set as follows. That is, its size (the size of the plane perpendicular to the edge of the exclusion zone) and exclusion time (exclusion period) can be determined and set based on a predicted deviation value predicted from learning past route deviation information. Here, the danger zone can be set to a different size for each edge between waypoints on the design route based on the prediction.

[0081] In other words, the size of the plane perpendicular to the direction of travel (plane perpendicular to the route) in the exclusive area is set to be different for at least two edges connecting adjacent waypoints. In this way, in this embodiment, the exclusive area is set according to the predicted deviation, and the set size is allowed to be different, so it is possible to create uneven divisions with different sizes depending on the section.

[0082] Furthermore, the exclusion time (exclusion period) can also be set to be different for at least two edges, which makes it possible to realize non-uniform partitioning in which the temporal sizes of the partitions are different.

[0083] Next, a description will be given of each component in Fig. 7. Note that the cooperation between the components will be described later as the operation of the traffic management device 10 with reference to Figs. 19 and 20, etc.

[0084] As described with reference to Fig. 6, the traffic management device 10 has a mechanism for managing the operation of the drone 3 and an aircraft control function. Specifically, the traffic management device 10 has a function for issuing a traffic plan in response to a request from the traffic management issuance requester Tr, and a function for collecting and managing the operation history of the drone 3 when it is operating, either continuously via communication or online or offline after the operation is completed. To achieve this, as described above, the traffic management device 10 has a performance learning unit 100, a performance management unit 200, a plan formulation unit 300, a plan management unit 400, and a space management unit 500.

[0085] (Actual Learning Section 100) When the drone 3 is actually operated, deviations occur between the operation plan and the actual operation route. Therefore, the performance learning unit 100 learns the operation performance information collected from the drone 3 by the performance management unit 200. This provides a trained model that can be used to predict deviations in the route of the drone 3 from the operation plan. To achieve this, the performance learning unit 100 includes a trained model management unit 101, an operation performance learning unit 102, and a trained model holding unit 103.

[0086] The trained model management unit 101 manages the trained model data stored in the trained model holding unit 103 (such as inputting and outputting data and searching).

[0087] The operation record learning unit 102 mainly learns the differences (positional differences, time differences) between the operation plan and operation records of the drone 3. The trained model obtained by learning is stored in the trained model holding unit 103 via the trained model management unit 101.

[0088] The trained model holding unit 103 holds the trained model trained by the operation record learning unit 102. This trained model is used by the plan formulation unit 300 (described later) when formulating an operation plan, to predict the generated operation plan and positional and time deviations that may occur when operating in accordance with that operation plan.

[0089] The operation record learning unit 102 reads out information about the drone's operation record stored in the operation record storage unit 202 of the record management unit 200 via the operation record management unit 201. The information about the drone's operation record can be information indicating the history of how the drone actually operated between waypoints, such as the route deviation (dashed line) in the left diagram of Fig. 10. Fig. 10 is a conceptual diagram for explaining the relationship between waypoints, edges, and route deviations, as well as exclusive regions.

[0090] The operation record learning unit 102 compares this information with the issued operation plan stored in the issued operation plan storage unit 402, which is read in via the issued operation plan management unit 401 of the plan management unit 400. Then, the operation record learning unit 102 learns the route deviation and the deviation of the arrival time at the waypoint between the plan and the actual operation obtained by the comparison, the time period in which the deviation occurred, and each edge (and the waypoints at both ends) in which the deviation occurred, and constructs a trained model. The route deviation may be the maximum value or the most frequent value of the deviation for the section. Furthermore, since the deviation is significantly affected by the season, temperature, climate, and weather, the time period in which the deviation occurred can be, for example, a tag representing the month, a tag representing each week in which a year is divided into weeks, a tag representing each time period into six parts of a day, or a combination of these. In other words, the time period in which the deviation occurred means a time period divided into units in which the same tendency for deviation can be obtained.

[0091] The operation record learning unit 102 stores the constructed trained model in the trained model holding unit 103 via the trained model management unit 101. When the location (edge ​​(or both end waypoints)) where a deviation is to be predicted and the planned time of travel at that location are given to the trained model stored in the trained model holding unit 103, a predicted deviation value is obtained. The obtained predicted value is the predicted deviation value for the route deviation and the end point passing time (the time at which the end of the edge is passed) that will occur at that time and place. However, in this embodiment, the explanation will be given assuming that this trained model is transferred to the plan formulation unit 300 and used.

[0092] (Performance Management Department 200) When the drone 3 operates, the performance management unit 200 collects, stores, and manages the operation history via communication either continuously or online or offline after the operation is completed. To achieve this, the performance management unit 200 includes an operation performance storage unit 202 and an operation performance management unit 201.

[0093] The operation record storage unit 202 stores the operation history collected and accumulated by the drone 3 during operation and the information collected from it. The operation record management unit 201 manages the operation history stored in the operation record storage unit 202. In addition, in response to a request from the record learning unit 100, the operation record management unit 201 searches for and extracts operation records from the operation record storage unit 202 and passes them to the record learning unit 100.

[0094] (Planning Department 300) The plan formulation unit 300 formulates an operation plan in cooperation with other functional units in response to a request from an operation plan issuance requester Tr. To achieve this, the plan formulation unit 300 includes a trained model holding unit 103, an exclusive region calculation unit 301, an operation plan issuance request management unit 302, an operation plan issuance request holding unit 303, an operation plan formulation unit 304, and an operation plan candidate temporary holding unit 305.

[0095] The trained model holding unit 103 of the plan formulation unit 300 holds the trained model generated by the performance learning unit 100. The trained model held here may be the trained model itself generated by the performance learning unit 100, or a copy obtained via the trained model management unit 101. The trained model is used to predict an operation plan and an expected deviation from the plan when formulating an operation plan.

[0096] The exclusive region calculation unit 301 calculates an exclusive region to be set around the operation plan. The exclusive region calculation unit 301 predicts positional and temporal deviations that will occur on the designed operation route using the trained model managed by the trained model storage unit 103, and calculates the exclusive region by adding a safety margin range (risk range) to the predicted range.

[0097] An exclusive area calculation unit 301 is provided to design a flight route so that other drones 3 do not enter this exclusive area. The plan formulation unit 300 designs a flight route so that the exclusive area of ​​one drone 3 does not overlap with the exclusive area of ​​another drone 3, as there is a risk of collision if the two areas overlap.

[0098] An operation plan issuance request management unit 302 receives a request from an operation plan issuance requester Tr, registers the request in an operation plan issuance request holding unit 303, and requests an operation plan formulation unit 304 to formulate an operation plan.

[0099] The operation plan issuance request holding unit 303 holds the contents of the request from the operation plan issuance requester Tr, and also holds the status of whether or not an operation plan has been issued in response to the request. The operation plan issuance request holding unit 303 can hold this information in a format that allows searching by any item, like a relational database.

[0100] Here, an example of the data format (information items) held in the operation plan issuance request holding unit 303 will be described with reference to Fig. 11 and Fig. 12. Fig. 11 is a diagram showing an example of the data format of an operation plan issuance request (an operation plan generation request including desired operation information), and Fig. 12 is a diagram showing an example of the data format held in the operation plan issuance request holding unit 303 in response to the request in Fig. 11.

[0101] 11, a request from an operation plan issuance requester Tr can include desired operation information such as a departure point (latitude, longitude, altitude), an arrival point (latitude, longitude, altitude), a possible departure time (year, month, day, hour, minute, second), and a desired arrival time (year, month, day, hour, minute, second). Note that the request can also be configured so that the operation plan issuance requester Tr accesses the operation management device 10 from a PC or the like and makes a request by, for example, specifying the departure point and the arrival point using a waypoint ID.

[0102] Then, when the operation plan issuance request management unit 302 receives a request from an operation plan issuance requester Tr, it registers the request management number and the operation route issue number in addition to the information included in the request in the operation system threat issuance request holding unit 303, as shown in Fig. 12. That is, when a request is received, the operation plan issuance request holding unit 303 registers the request management number, departure point (latitude, longitude, altitude), arrival point (latitude, longitude, altitude), possible departure time (year, month, day, hour, minute, second), desired arrival time (year, month, day, hour, minute, second), and operation route issue number.

[0103] In addition, when the operation plan issuance request management unit 302 completes the generation of the operation plan and returns a response to the operation plan issuance requester Tr, it updates the operation plan issuance request holding unit 303 by adding an issued flag and an operation route issuance number to the row with the matching request management number.

[0104] As described above, the plan formulation unit 300 formulates an operation plan in cooperation with other functional units in response to a request from the operation plan issuance requester Tr. This formulation is executed by the operation plan formulation unit 304. The operation plan formulation unit 304 designs an operation route so that other drones 3 do not enter the exclusive area calculated by the exclusive area calculation unit 301. If the exclusive area of ​​one drone 3 overlaps with the exclusive area of ​​another drone 3, there is a risk of collision, so the operation plan formulation unit 304 designs an operation route so that the two drones do not overlap.

[0105] The operation plan candidate temporary storage unit 305 temporarily stores operation plan candidates created during the formulation of an operation plan. The operation plan candidate temporary storage unit 305 can store information indicating operation plan candidates in a format that allows searching by any item, such as a relational database.

[0106] Here, an example of the data format (information items) stored in the operation plan candidate temporary storage unit 305 will be described with reference to Fig. 13 and Fig. 14. Fig. 13 is a diagram showing an example of the data format of an operation plan candidate created during the formulation of an operation plan, and Fig. 14 is a diagram showing an example of the data format of an operation plan issued for the operation plan candidate of Fig. 13.

[0107] 13, the operation plan candidate temporary storage unit 305 temporarily stores a list of operation routes, including the waypoint ID of the departure point, the possible departure time (year, month, day, hour, minute, second), the waypoint ID of the arrival point, and the arrival deadline time (year, month, day, hour, minute, second). Here, the list of operation routes has columns for the section sequence number, the starting waypoint ID, the ending waypoint ID, the target end point passing time, and the edge ID.

[0108] Furthermore, the operation plan candidate temporary storage unit 305 also temporarily stores a conflict flag indicating whether or not this candidate conflicts with other candidates. The conflict flag item can be used when determining whether the operation plan candidate conflicts with other candidates, that is, whether or not there is any problem with adopting the operation plan as an operation plan. Then, if there is no problem with adopting the operation plan as an operation plan, the operation plan formulation unit 304 determines it as an operation plan by removing the conflict flag item stored in the operation plan candidate temporary storage unit 305, as shown in FIG. 14 .

[0109] In this way, when formulating an operation plan, the operation plan formulation unit 304 first generates a draft (candidate) of the operation plan and temporarily stores it in the operation plan candidate temporary storage unit 305. Then, the operation plan formulation unit 304 obtains an exclusive area for the stored operation plan, calculates whether the exclusive area overlaps with the exclusive area of ​​an operation plan that has already been issued, and if there is no overlap, issues it as a formal operation plan. On the other hand, if there is an overlap, the operation plan formulation unit 304 operates to generate another operation plan draft again, and therefore includes a mechanism for temporarily storing the operation plan draft, such as the operation plan candidate temporary storage unit 305.

[0110] (Planning and Management Department 400) The plan management unit 400 holds and manages issued operation plans. The issued operation plans managed here are used to learn discrepancies between the operation plans and actual operation results, and when formulating an operation plan, to check whether the exclusive area of ​​the formulated operation plan overlaps with the exclusive area of ​​an operation plan that has already been issued. To achieve this, the plan management unit 400 includes an issued operation plan management unit 401 and an issued operation plan holding unit 402.

[0111] The issued operation plan management unit 401 manages, that is, inserts and extracts, and searches, issued operation plans in the issued operation plan holding unit 402. The issued operation plan management unit 401 provides issued operation plans to the performance learning unit 100 and handles the exchange of issued operation plans with the plan formulation unit 300.

[0112] The issued operation plan storage unit 402 stores the issued operation plans and the exclusive areas for those operation plans. The issued operation plan storage unit 402 can store information about the issued operation plans and the exclusive areas for those operation plans in a format that allows searching by any item, like a relational database.

[0113] Here, an example of the data format (information items) stored in the issued operation plan storage unit 402 will be described with reference to Fig. 15 and Fig. 16. Fig. 15 is a diagram showing an example of the data format of an issued operation plan, and Fig. 16 is a diagram showing an example of the data format in which a plurality of the issued operation plans of Fig. 15 are arranged.

[0114] The issued operation plan storage unit 402 can store information such as that shown in Fig. 15 as an issued operation plan. That is, an issued operation plan can include waypoint IDs of the departure point and arrival point, possible departure times (year, month, day, hour, minute, second), arrival deadline times (year, month, day, hour, minute, second), a request management number, a route issue number, a route, and an exclusive area (exclusive area radius and exclusive end time). This information can then be grouped together and added to each issued operation plan, resulting in a data format such as that shown in Fig. 16.

[0115] (Space Management Department 500) The space management unit 500 manages information about the space in which the drone 3 is operated. This information (spatial information) can be composed of coordinate information of points in space called waypoints, which are rough estimates of the route the drone 3 will take when operating, and edge information, which are lines (vectors) connecting these points. As a configuration for managing spatial information, the space management unit 500 includes a space information management unit 501 and a waypoint (WP) information storage unit 502.

[0116] The spatial information management unit 501 manages and searches for waypoint and edge information. The waypoint information storage unit 502 stores coordinate information of spatial points called waypoints, which serve as a guide for the route along which the drone 3 is operated and as a waypoint during operation. The waypoint information storage unit 502 can store coordinate information of waypoints in a format that allows searches by any item, like a relational database.

[0117] An example of the data format (information items) stored in the waypoint information storage unit 502 will now be described with reference to FIG. 17. FIG. 17 is a diagram showing an example of the data format of waypoint coordinate information. As shown in FIG. 17, the waypoint storage unit 502 stores a list of waypoint IDs and waypoint coordinates (latitude, longitude, altitude) as coordinate information of waypoints. For example, it stores coordinates of points in space as shown in FIG. 9. Note that in the example of FIG. 9, the waypoints are arranged evenly vertically, horizontally, and vertically, but the points do not necessarily have to be arranged evenly, and irregular arrangement is acceptable.

[0118] The edge information storage unit 503 stores information on edges, which are lines (vectors) connecting waypoints, and a flag indicating whether the edge can be used as part of the travel route (unusable flag). The edge information storage unit 503 can store edge information in a format that allows searching by any item, like a relational database.

[0119] An example of the data format (information items) stored in the edge information storage unit 503 will now be described with reference to Fig. 18. Fig. 18 is a diagram showing an example of the data format of edge information.

[0120] 18, the waypoint storage unit 502 can store information about edges connecting waypoints, such as edge IDs, starting waypoint IDs that are the starting points of the edges, ending waypoint IDs that are the ending points, and a list of unusable flags. The unusable flag is set to indicate that a section that should not be used as part of a travel route cannot be used, for example, because there is an obstacle on the line connecting the waypoints.

[0121] (Example of operation of the traffic management device 10) An example of the internal operation of the traffic management device 10 will be described with reference to FIGS. First, the operation of the performance learning unit 100 will be described. As described above, the operation record learning unit 102 of the record learning unit 100 reads out information about the drone's operation record stored in the operation record storage unit 202 of the record management unit 200 via the operation record management unit 201. The information about the drone's operation record can be information indicating the history of how the drone actually operated between waypoints, such as the route deviation (dashed line) in the left diagram of FIG. 10. In addition, the operation record learning unit 102 compares this information with the issued operation plan stored in the issued operation plan storage unit 402, which is read in via the issued operation plan management unit 401 of the plan management unit 400.

[0122] The operation record learning unit 102 then learns the route deviations between the planned and actual results obtained by the comparison, the deviations in arrival times at waypoints, the time periods in which the deviations occurred, and the edges (and the waypoints at both ends) in which the deviations occurred, and constructs a trained model. The route deviations may be the maximum or most frequent deviations in a section. Furthermore, the time periods in which deviations occurred refer to time periods divided into units that provide the same tendency for deviations, as described above.

[0123] Next, the operation record learning unit 102 stores the constructed trained model in the trained model holding unit 103 via the trained model management unit 101. When the location (edge ​​(or both end waypoints)) where deviation is to be predicted and the planned time of operation at that location are given to the trained model stored in the trained model holding unit 103, a predicted deviation value can be obtained. The obtained predicted value is the predicted deviation value for the route deviation and the end point passing time (the time of passing the end of the edge) that will occur at that time and place.

[0124] Next, the operation of the planning unit 300 and its surroundings will be described. The cooperation between each element is shown in the sequence diagrams of Figures 19 and 20, and the processing within each functional unit is explained with reference to individual flow diagrams. Figures 19 and 20 show an example of sequential execution of operation plan formulation processing. Figures 19 and 20 are sequence diagrams showing an example of a series of operations in the operation management device 10. Here, the entire sequence is expressed in the notation of UML (Unified Modeling Language) 2.0.

[0125] First, the requester for issuance of an operation plan specifies information of the items in Fig. 11 and requests the issuance of an operation plan to the operation plan issuance request management unit 302 (step S21). As shown in Fig. 11, the items of the specified information (desired operation information) can be the departure point (latitude, longitude, altitude), arrival point (latitude, longitude, altitude), possible departure time (year, month, day, hour, minute, second), and desired arrival time (year, month, day, hour, minute, second).

[0126] The operation plan issuance request management unit 302 registers the received operation plan issuance request in the operation plan issuance request storage unit 303 (step S22). The processing of step S22 will be described with reference to Fig. 21. Fig. 21 is a flow diagram for describing an example of the registration processing of an operation plan issuance request.

[0127] The operation plan issuance request management unit 302 receives an operation plan issuance request including the information shown in Fig. 11 from the operation plan issuance requester (step S51). The operation plan issuance request management unit 302 adds a request management number and an issued flag (False) to the contents of the operation plan issuance request as shown in Fig. 12, and registers and stores the information in the operation plan issuance request holding unit 303 (step S52). Here, a request management number is assigned to the information of Fig. 11 specified in step S21, and the information is added to the operation plan issuance request holding unit 303 as shown in Fig. 12. At this point, the issued flag is set to False, and the operation route issue number is added as a blank.

[0128] Next, the operation plan issuance request management unit 302 sends an operation plan formulation request to the operation plan formulation unit 304 using the parameters of the operation plan formulation request as shown in Fig. 22 as parameters (step S53). This step S53 corresponds to step S23 in Fig. 19. Here, Fig. 22 is a diagram showing an example of the data format of the parameters of the operation plan request.

[0129] As described above, in step S23, the operation plan issuance request management unit 302 specifies parameters and requests the operation plan formulation unit 304 to formulate an operation plan. As parameters of this operation plan request, a request management number, a departure point (latitude, longitude, altitude), an arrival point (latitude, longitude, altitude), a possible departure time (year, month, day, hour, minute, second), and a desired arrival time (year, month, day, hour, minute, second) are specified, as shown in Fig. 22. The request management number is added when responding with the result, so that the operation plan issuance request stored in the operation plan issuance request storage unit 303 can be associated with the responded operation plan.

[0130] Following step S23, an operation plan formulation request is received, and the operation plan formulation unit 304 determines a spatial information acquisition range (step S24). An example of the processing in step S24 will be described with reference to Fig. 23. Fig. 23 is a flow diagram illustrating an example of processing for determining a spatial information acquisition range.

[0131] The operation plan formulation unit 304 receives the operation plan formulation request transmitted in step S23 from the operation plan issuance request management unit 302 using the parameters of the operation plan formulation request in Fig. 22 as parameters (step S61). Next, as shown in Fig. 24, the operation plan formulation unit 304 calculates the start point and end point of the requested range based on the departure point coordinates and arrival point coordinates of the parameters of the operation plan formulation request in Fig. 22 (step S62). Fig. 24 is a schematic diagram showing an example of a spatial information acquisition range.

[0132] Next, the operation plan formulation unit 304 sends a spatial information acquisition request in step S25 to the spatial information management unit 501 using the parameters of the spatial information acquisition request shown in Fig. 25 as parameters (step S63). Fig. 25 is a diagram showing an example of the data format of the spatial information acquisition request parameters.

[0133] As shown in FIG. 24, the operation plan formulation unit 304 determines the spatial information acquisition range as the range that can be taken as the route of the operation plan. Here, as shown in FIG. 24, the spatial information acquisition range is calculated to be a range wider than the range of a rectangular parallelepiped with the departure point and arrival point as diagonal corners. This is because, when a route conflicts with an already issued route, a route that takes a detour to avoid it may be created. In this way, a detour can be secured by setting the spatial information acquisition range to a range that is a predetermined distance wider than the rectangle with the horizontal coordinates of the departure point and arrival point as diagonal corners. Furthermore, since a drone is used as an example here, the upper and lower altitude limits shown in FIG. 24 are not specified because they are legally determined. However, when applied to other autonomous mobile devices, the spatial information acquisition range may be determined by specifying the altitude as well.

[0134] In the spatial information acquisition request in step S25, the operation plan formulation unit 304 requests acquisition of spatial information by providing search parameters to the spatial information management unit 501. As shown in Fig. 25, these search parameters include information on items such as the departure point (latitude, longitude, altitude), arrival point (latitude, longitude, altitude), requested range start point (latitude, longitude), and requested range end point (latitude, longitude).

[0135] The spatial information management unit 501 receives the spatial information acquisition request in step S25 and searches for spatial information (step S26). An example of the processing in step S26 will be described with reference to Fig. 26. Fig. 26 is a flow diagram for describing an example of processing for determining the spatial information acquisition range.

[0136] In step S26, the spatial information management unit 501 receives a spatial information acquisition request with the requested range as a parameter (search parameter) from the operation plan formulation unit 304 (step S71). Next, the spatial information management unit 501 reads spatial information for the requested range (FIG. 25), which is a parameter of the spatial information acquisition request in step S25, from the waypoint information in FIG. 17 and the edge information in FIG. 18 (step S72). The spatial information read here includes the requested range start point, requested range apex end point, waypoints included in the range determined by the upper limit of permitted operation and the lower limit of permitted operation, and edges, as shown in FIG. 27, and this becomes the spatial information of the requested acquisition range. FIG. 27 is a diagram showing an example of the data format of the acquisition range spatial information. The acquisition range spatial information acquired in this way has an image as shown in FIG. 28. FIG. 28 is a schematic diagram showing an example of acquisition range spatial information.

[0137] Then, the spatial information management unit 501 responds to the operation plan formulation unit 304 with the spatial information of the acquisition range shown in FIG. 27 as the spatial information of the acquisition request range (steps S73 and S27).

[0138] The operation plan formulation unit 304 receives spatial information of the requested acquisition range from the spatial information management unit 501 (step S27), formulates an operation plan candidate based on the spatial information (step S28), and sends an exclusive area calculation request to the exclusive area calculation unit 301 (step S29). In the processing of step S28, an operation plan candidate is generated, not an operation plan. In the subsequent processing, it is checked whether there is any conflict of operation routes with operation plans that have already been issued, and therefore, what is generated at this point is an operation plan candidate.

[0139] An example of the processing of steps S27 to S29 will be described with reference to FIGS. 29 and 30. FIGS. 29 and 30 are flow diagrams illustrating an example of the process of formulating an operation plan candidate. First, the operation plan formulation unit 304 receives spatial information within the acquisition request range (FIG. 27) from the spatial information management unit 501 as spatial information of the acquisition request range (step S81). If the formulation of step S28 is the first time it is executed, the operation plan formulation unit 304 registers the information shown in FIG. 13 in the operation plan candidate temporary storage unit 305. That is, the waypoint ID of the departure point, the possible departure time, the waypoint ID of the arrival point, and the arrival deadline time are registered, and an empty table of operation routes and conflict flags is also registered. Every time a candidate is formulated, an empty table of operation routes and conflict flags is generated.

[0140] Next, the operation plan developer 304 performs a loop process between steps S82a and S82b. The loop condition in this loop process is that the process is repeated until the waypoint ID of the arrival point and the end point waypoint ID match.

[0141] In this loop process, first, the operation plan formulation unit 304 determines the starting waypoint as follows (step S83): The first time, it searches for and reads out the waypoint ID of the departure point of the spatial information (FIG. 27) within the acquisition request range received in step S81, and from the second time onwards, it searches for and reads out edges where the end waypoint ID from the previous process matches the starting waypoint ID and the unusable flag is false.

[0142] Next, the operation plan formulation unit 304 determines the target end point passing time for each selected edge as follows (step S84). Using the start point waypoint ID and end point waypoint ID of the multiple edges searched and read in step S83 as keys, the waypoint coordinates of each waypoint whose spatial information within the acquisition request range (Figure 27) matches the waypoint ID are acquired. Then, the required time to travel that edge (route section) is calculated from the distance between the two acquired waypoints and the standard speed of the drone being used. Calculating the required time means that the target end point passing time for the edge is also calculated.

[0143] Next, the operation plan formulation unit 304 selects a route section to proceed to the next waypoint from among the multiple edges searched and read in step S84 (step S85). At this time, edges whose edge ID matches the table (there may be multiple) of operation routes and conflict flags of operation routes in the operation plan candidate temporary storage unit 305 shown in FIG. 13, whose target end time is close, and whose conflict flag is true are excluded from selection. After performing this exclusion, edges are selected according to a route search algorithm such as a greedy algorithm or an A-star algorithm so that the route of the operation plan that is finally created is as short as possible. As a result, the edge IDs for one section and the end waypoint (= next start waypoint ID) are determined.

[0144] Next, the operation plan formulation unit 304 adds a record to the table of operation routes and conflict flags of the operation routes in the operation plan candidate temporary storage unit 305 shown in Fig. 13 (step S86). Here, the assigned section sequence number (a sequential number starting from 0), the start waypoint ID, the end waypoint ID, and the conflict flag value "false" are added as one record.

[0145] In step S82b, if the above-mentioned loop condition is satisfied, the loop processing is terminated, and at the time of termination of the loop processing, one table of operation routes and conflict flags will be completed.

[0146] Next, the operation plan formulation unit 304 requests the exclusive area calculation unit 301 to calculate the exclusive area of ​​the operation plan candidate, using as a parameter the operation plan candidate that was last registered as information in Figure 13 in the operation plan candidate temporary storage unit 305 (steps S87 and S29).

[0147] As a result of this processing, the items shown in FIG. 13 are formulated as candidates for the operation plan. The operation plan candidate generated and added in the operation plan candidate temporary storage unit 305 in this step is stored until the operation plan is determined, exits the loop in FIG. 20, and is registered and issued, and then is deleted.

[0148] The request to calculate the exclusive region of the operation plan candidate in step S29 is made to the exclusive region calculation unit 301 by specifying the items in Fig. 14. The items shown in Fig. 14 are the waypoint ID of the departure point, the possible departure time (year, month, day, hour, minute, second), the waypoint ID of the arrival point, the arrival deadline time (year, month, day, hour, minute, second), and the operation route. This operation route includes the section sequence number, the starting waypoint ID, the end waypoint ID, the target end point passing time, and the edge ID.

[0149] Upon receiving this exclusive region calculation request, the exclusive region calculation unit 301 calculates the exclusive region of the operation plan (step S30). Prior to the processing of step S30, it is assumed that the trained model described above has been stored in the trained model holding unit 103 of the plan formulation unit 300. In other words, when the location (edge ​​(or both end waypoints)) for which a deviation is to be predicted and the planned time of operation at that location are given to this trained model, the trained model is able to obtain predicted values ​​for the deviation in the route that will occur at that time and the deviation relative to the end point passing time. This end point passing time refers to the time at which the end of the edge is passed.

[0150] Step S30 will now be described in detail. 13 one record at a time, and calculates predicted values ​​(predicted route deviation value, predicted end point passing time deviation value) using the trained model stored in the trained model storage unit 103. Then, the exclusive zone calculation unit 301 adds the predicted values ​​(predicted route deviation value, predicted end point passing time deviation value) to each record.

[0151] As a result, information such as that shown in Fig. 31 can be obtained. As shown in Fig. 32, the predicted route deviation value is obtained as a predicted value indicating the maximum deviation in the vertical direction on the line connecting waypoints (section operation route), and the predicted end point passing time deviation value is obtained as a predicted value indicating the deviation from the target end point passing time. The concept of deviation is as explained with reference to Fig. 10. Here, Fig. 31 is a diagram showing an example of the data format of the predicted value, and Fig. 32 is a schematic diagram for explaining the prediction result.

[0152] For each record of the predicted values ​​(predicted route deviation value, predicted end point passing time deviation value) calculated in this way, the safety distance and safety time are added to calculate the exclusive area (exclusive area radius, exclusive end time). The result of calculating the exclusive area is shown in Fig. 33. Fig. 33 is a diagram showing an example of the data format of the calculated exclusive area.

[0153] Next, the exclusive region calculation unit 301 responds to the operation plan formulation unit 304 with the processing result of step S30 shown in FIG. 33 (step S31). The operation plan formulation unit 304 receives this response and determines the range for acquiring an issued operation plan (issued operation plan acquisition range) using the information shown in FIG. 34 as parameters (step S32). FIG. 34 is a diagram showing an example of the data format of the issued operation plan acquisition range. The parameters include a time that is earlier than the reachable time by a safety time, a time that is later than the arrival deadline by a safety time, a point (latitude, longitude) that is wider than the requested range start point by a safety range, and a point (latitude, longitude) that is wider than the requested range end point by a safety range.

[0154] The acquisition range (spatial information acquisition range) determined in this way is the sum of the safety range at the start point of the requested range and the safety range at the end point of the requested range, as shown in Figure 35, and this is determined as the range of the exclusive area acquisition request. Figure 35 is a schematic diagram showing an example of the spatial information acquisition range determined in Figure 34. Past operation plans whose start and end times overlap with the above-mentioned time zones and whose exclusive area overlaps even partially within this section will be read out.

[0155] Next, the operation plan formulation unit 304 requests the issued operation plan management unit 401 to acquire an exclusive area of ​​the issued operation plan, using the exclusive area acquisition request range determined in step S32 as a parameter (step S33).

[0156] The issued operation plan management unit 401 receives this request and searches for and reads out issued operation plans from the operation plans stored in the issued operation plan storage unit 402 and whose data format is shown in FIG. 16, thereby calculating the exclusive area of ​​the issued operation plan (step S34). Here, the issued operation plan management unit 401 searches for and reads out issued operation plans that are included in the requested range shown in FIG. 35 and that fall within the time between the possible departure time of the current operation plan candidate advanced by a safety time and the arrival deadline time delayed by a safety time. Note that there may be multiple applicable operation plans.

[0157] Here, the route issue number, departure waypoint ID, possible departure time, arrival waypoint ID, arrival deadline time, request management number, and the corresponding route and exclusive area list for the operation plan that meets the conditions are read.

[0158] Then, the issued operation plan management unit 401 returns the exclusive areas of the issued operation plans within the acquisition request range as a response to the operation plan formulation unit 304 (step S35). Here, the response includes the operation route issue number, waypoint ID of the departure point, possible departure time, waypoint ID of the arrival point, arrival deadline time, request management number, and a list of the corresponding operation routes and exclusive areas of the operation plans that match the conditions read in step S34. An example of this list is shown in FIG. 36. FIG. 36 is a diagram showing an example of the data format of the operation plan candidate to which the calculation result of the exclusive area of ​​the operation plan candidate is added.

[0159] 36 is information on the operation plan candidate to which the exclusive area calculation result of the operation plan candidate has been added, and includes a list of operation sections including the section sequence number, start waypoint ID, end waypoint ID, target end point passing time, and edge ID as the operation route. In addition, the information shown in FIG. 36 includes a predicted route deviation value and a predicted end point passing time deviation value as exclusive area information.

[0160] The operation plan formulation unit 304 receives this response and checks whether there is a conflict between the exclusive area of ​​the operation plan candidate and the exclusive area of ​​the issued operation plan (Step S36). There are two cases in which a conflict is determined.

[0161] The first case is when the combination of the start waypoint and the end waypoint matches and the exclusive time overlaps between the records of the operation route included in the operation plan candidate and the operation route included in the issued operation plan obtained in step S31. Such a case is shown in FIG. 37. FIG. 37 is a schematic diagram showing an example of a conflict state. Here, a match in the combination of the start waypoint and the end waypoint is considered to match even if the start point and the end point are reversed, regardless of whether it is an uphill or downhill direction. In addition, the above-mentioned exclusive time refers to the period from the exclusive end time of the record having the section sequence number one section sequence number before the section sequence number of the operation route record of interest to the exclusive end time of the operation route record of interest.

[0162] The second case is when the space calculated from the exclusive area radius and the exclusive time overlap at least partially between the operation route records included in the operation plan candidate and the operation route records included in the issued operation plan obtained in step S31. Such a case is as shown in Figures 38 and 39. Figures 38 and 39 are schematic diagrams showing other examples of conflicting states.

[0163] With reference to Figure 40, we will provide a supplementary explanation of area contention. Figure 40 is a diagram for explaining area contention. The space determined from the above-mentioned exclusive area radius refers to a cylindrical space with a radius equal to the exclusive area radius, with both ends hemispherical, surrounding the edges and waypoints of one section of the route, and is a space in which hemispheres of the same radius as the cylinder are attached to both ends of the cylindrical space in Figure 32 (see Figure 10). The above-mentioned exclusive time refers to the period from the exclusive end time of the record with the section sequence number one before the section sequence number of the route record of interest to the exclusive end time of the route record of interest.

[0164] As shown in Fig. 40, whether the areas conflict is determined by comparing the operation plan candidate to which the calculation result of the exclusive area of ​​the operation plan candidate is added with the exclusive area of ​​the issued operation plan of the acquisition request range. Here, when determining the conflict, the section occupancy time is calculated from the time obtained by adding the predicted time deviation value to the addition time of the previous and next target end points, and then a safety time is added, and a safety range is added to the predicted route deviation value.

[0165] If any of the above conflict conditions is met, the operation plan formulation unit 304 considers it to be a route conflict or an exclusive area conflict and sets the conflict flag of the corresponding operation route record of the operation plan candidate stored in the operation plan candidate temporary storage unit 305 to true.

[0166] On the other hand, if an operation plan in which no conflict occurs is obtained, the operation plan formulation unit 304 exits the loop processing in FIG. 20 and proceeds to the next step S37.

[0167] In step S37, the operation plan formulation unit 304 registers, as an operation plan, an operation plan candidate whose exclusive area does not conflict with the issued operation plan in the issued operation plan management unit 401. As described above, when an operation plan candidate that does not conflict with the issued operation plan is obtained, the operation plan formulation unit 304 exits the loop processing shown in FIG. 20 and enters the processing of step S37.

[0168] In step S37, the operation plan formulation unit 304 requests the issued operation plan management unit 401 to register the information of the items shown in FIG. 15 (information on the operation plan that was last generated at this point in time among the operation plan candidates stored in the operation plan candidate temporary storage unit 305) as a parameter.

[0169] The issued operation plan management unit 401 registers the operation plan by adding the information of the operation plan ( FIG. 15 ) provided in step 37 to the issued operation plan storage unit 402 (step S38). When adding the operation plan, an operation route issue number is assigned and added to the operation plan. As a result, the information of the items shown in FIG. 16 is stored in the issued operation plan storage unit 402.

[0170] As shown in Fig. 41, the operation plan formulation unit 304 adds information on the request management number, departure point, and arrival point received in the operation plan formulation request in step S23. Furthermore, the operation plan formulation unit 304 specifies a waypoint ID and queries the spatial information management unit 501, thereby adding corresponding coordinates to the start waypoint ID and end waypoint ID. Then, the operation plan formulation unit 304 responds to the operation plan issuance request management unit 302 with the data of the items shown in Fig. 41 as an operation plan (step S39). Fig. 41 is a diagram showing an example of the data format of an operation plan.

[0171] Upon receiving this response, the operation plan issuance request management unit 302 sets an issued flag in the operation plan issuance request in the operation plan issuance request storage unit 303 (step S40). Here, the operation route issuance number is added to the record (see FIG. 12) whose request management number matches the received operation plan, and the issued flag is set to true. As a result, data of the items shown in FIG. 42 is generated as an operation plan. FIG. 42 is a diagram showing an example of the data format of an operation plan.

[0172] Next, the operation plan issuance request management unit 302 issues the operation plan by responding with the operation plan to the person who requested issuance of the operation plan (step S41). The issued operation plan can have the issued flag removed, and can include, for example, information on the items shown in Fig. 43. Fig. 43 is a diagram showing an example of the data format of the operation plan.

[0173] As described above, the operation management device 10 according to this embodiment has a function of learning route deviations, a function of predicting route and passage time deviations (spatial and temporal deviations), and a function of automatically generating an operation plan.

[0174] Then, based on the prediction results for the operation plan candidate, the operation management device 10 sets an exclusive region to surround each edge connecting adjacent waypoints included in the operation plan candidate. This improves spatial utilization efficiency compared to when settings based on the prediction results are not made, and therefore also improves temporal utilization efficiency.

[0175] In this case, a trained model equivalent to the trained model 4e described in the first embodiment can be generated as follows. Here, an example of training using the learning device 4 in FIG. 4 will be described.

[0176] In response to an operation plan generation request including desired operation information, the acquisition unit 4a acquires information including an executed operation plan that has been executed from among operation plans generated to include multiple waypoints for an autonomous mobile device included as an operation target in the desired operation information, and operation results. The operation results are operation results at the time of execution of the executed operation plan. Here, the operation plan is a plan in which an exclusive area is set to surround each edge connecting adjacent waypoints among the multiple waypoints included in the operation plan. Here, too, the exclusive area is an area in which other autonomous mobile devices are prohibited from competing with each other in operation.

[0177] The control unit 4b generates a trained model that predicts, based on the acquired information, positional and time deviations that may occur when operating according to a candidate operation plan that has been generated to include multiple waypoints based on new desired operation information (i.e., different desired operation information).

[0178] Furthermore, this learning device 4 can execute the learning method as described above. Furthermore, as described above, the learning device 4 can be configured as a computer, and in that case, the program can be a program that causes the computer to execute the processing as described above.

[0179] Furthermore, for the operation plan candidate, based on the above-described prediction result, the operation management device 10 can set, in addition to the exclusive area, an exclusive period as a period during which operations of other autonomous mobile devices for which operation plans have not been generated are prohibited within the exclusive area. Therefore, time utilization efficiency can be further improved compared to when only the exclusive area is set. In particular, the length of the exclusive period for the operation plan candidate can be set to be longer depending on the length of the time difference between the predicted passage times at each waypoint, thereby further improving time utilization efficiency.

[0180] Furthermore, the traffic management device 10 according to this embodiment defines waypoints at a high density rather than dividing the space, and sets and designs a travel route that passes through those waypoints. In this embodiment, a danger zone (a zone that excludes other autonomous mobile devices) is set to surround the travel route, and its size and exclusion period are determined based on a predicted deviation value predicted from learning past route deviation information. As a result, the danger zone can be set to a different size for each section between waypoints on the designed route based on the prediction results.

[0181] Furthermore, in the operation management device 10 according to this embodiment, non-conflicting candidates are determined as candidates that operate in areas excluding the set exclusive areas that are set to surround each edge included in the generated but incomplete operation plan among the operation plan candidates. Therefore, the set exclusive areas can also be determined based on the prediction results, which further improves the temporal and spatial utilization efficiency.

[0182] In the operation plan formulation process, an example has been given in which conflicts are determined each time an operation plan candidate is generated, but the process is not limited to this example. It is also possible to generate multiple operation plan candidates and then determine the candidate with the lowest degree of conflict as the operation plan.

[0183] In this embodiment, the non-conflicting candidates are determined as candidates that operate in an area excluding the set exclusive area during the set exclusive period that is set for the set exclusive area related to the generated but incomplete operation plan among the operation plan candidates. Therefore, this exclusive period can also be determined based on the prediction result, which can further improve the temporal and spatial utilization efficiency.

[0184] Furthermore, when a non-conflicting candidate is determined to be a candidate that operates in an area excluding the set exclusive area for an operation plan that has been generated but not yet completed, among the operation plan candidates, a trained model equivalent to the trained model 4e described in the first embodiment can be generated as follows. Here, an example of training using the learning device 4 in FIG. 4 will be described.

[0185] In response to an operation plan generation request including desired operation information, the acquisition unit 4a acquires information including an executed operation plan that has been executed from among operation plans generated to include multiple waypoints for an autonomous mobile device included as an operation target in the desired operation information, and operation results. The operation results are operation results at the time of execution of the executed operation plan. Here, the operation plan may be any operation plan candidate that includes multiple waypoints and is generated based on the desired operation information, as long as it is capable of operating in an area excluding the following exclusive area. The exclusive area here refers to a set exclusive area that is set to surround each edge connecting adjacent waypoints in multiple waypoints included in an operation plan that has been generated but is incomplete for another autonomous mobile device.

[0186] The control unit 4b generates a trained model that predicts, based on the information acquired by the acquisition unit, positional and time deviations that may occur when operating according to a candidate operation plan that is generated to include multiple waypoints based on other desired operation information.

[0187] Furthermore, the learning device 4 in this example can execute the learning method as described above. As described above, the learning device 4 can be configured as a computer, and in that case, the program can be a program that causes the computer to execute the processing as described above.

[0188] As described above, according to this embodiment, similar to the first embodiment, collision prevention and improved space utilization efficiency can be achieved simultaneously, while also achieving the effects of the individual components. This embodiment solves the first problem described above, namely, the lack of a method for automatically performing a series of procedures, from simply setting a start point and an end point to designing a route and generating an operation plan coordinated with the routes of other drones 3, and enables automatic execution. This embodiment also solves the second problem described above, namely, the poor space utilization efficiency (both spatially and temporally) of existing route design methods, which makes it difficult to operate multiple drones efficiently. That is, according to this embodiment, in locations where the discrepancy between the planned and actual route is small, the number of drones that can be accommodated per space can be increased, thereby improving utilization efficiency in terms of space and time.

[0189] <Embodiment 3> As the third embodiment, various application examples applicable to the first and second embodiments will be described, focusing on the differences from the second embodiment. In the third embodiment, the various examples described in the first and second embodiments can be used as appropriate.

[0190] Although the second embodiment has been described using a drone as an example, it can also be applied to an autonomous mobile device that travels on the ground without flying. In that case, instead of the operation plan in three-dimensional space exemplified in the second embodiment, an operation plan on a two-dimensional plane can be applied for the autonomous mobile device traveling on the ground. In an operation plan on a two-dimensional plane, it is not necessary to use information on the upper and lower altitude limits or the altitudes of the target and actual arrival coordinates for the sections. Furthermore, even when applied to a traveling autonomous mobile device, when used in a situation with a hierarchical structure, such as a multi-story parking lot, a large logistics center or factory that can accommodate vehicles, floor height information can be used in addition to altitude.

[0191] Furthermore, in regard to the placement of waypoints, in Figure 9, for the sake of simplicity, the waypoints are placed at equal intervals, but they do not necessarily have to be placed at equal intervals. For example, if it is clear that a space is impassable due to mountains or buildings, or if it is clear that a space cannot be navigated due to legal restrictions, there may be places where no waypoints are set from the start. In other words, the multiple waypoints included in the operation plan or candidates may be selected and determined from pre-set spatial points.

[0192] Waypoints can also be placed as follows to represent spaces that are clearly impassable due to mountains or buildings, or spaces that are clearly not navigable due to legal restrictions, etc. That is, as shown in Figure 9, waypoints can be set densely and evenly spaced regardless of obstacles, and only in places that cross obstacles can unnavigable spaces be represented by setting the unusable flag of the edges that pass through them to true. The data structure of edges in this case is as shown in Figure 27.

[0193] In other words, the multiple waypoints included in the operation plan or candidates may be determined by selecting from spatial points that have been preset as grid points of an evenly spaced grid, excluding spatial points where obstacles exist and spatial points that are included in areas where operation is not legally permitted.

[0194] As can be seen from these examples, multiple waypoints included in operation plans and candidates can be determined so that the edge lengths between at least two edges are different. This allows a route to be designed so that it passes through smaller (or larger) sections rather than through large sections of a fixed size.

[0195] The exclusive area can also be set by allowing the exclusive line to represent the edge itself.

[0196] In the second embodiment, week number tags, time zone tags, month tags, and season tags are used as explanatory variables for learning in the operation record learning unit 102 and for predicting position and time deviations in the exclusive zone calculation unit 301, but these items may be increased or replaced with other items. Furthermore, as long as the information is expected to correlate with the objective variable, it is possible to use items from other information sources in addition to obtaining learning data from operation records alone.

[0197] For example, when applied to an autonomous mobile device that operates on land, it is possible to add a number indicating the type of ground surface condition for each section (paved, unpaved, gravel, sand, etc.), and when applied to an autonomous mobile device that operates on the ocean, it is possible to add the wave height for each section. Even in the case of an autonomous mobile device that operates in the air, it is possible to add meteorological information for each section. Furthermore, the number of items of information obtained from the operation history described in the second embodiment may be increased. For example, sensors may be installed in the autonomous mobile device, and information such as vibration information, temperature information, fluctuations in the output of the motor or engine used for propulsion, inclination, and fuel consumption status may be added to the explanatory variables. This makes it possible to improve prediction accuracy and build a learning model that is more in line with reality.

[0198] In addition, in the second embodiment, an example was shown in which the distance of the positional deviation was used as the objective variable for learning in the operation record learning unit 102 and for predicting the positional deviation and time deviation in the exclusive area calculation unit 301, but the direction of the positional deviation may also be used as the objective variable. In other words, the operation management device 10 can also be configured to predict the distance deviation and the direction deviation as the prediction of the positional deviation. This makes it possible to make the space exclusive only in a specific direction, which has the effect of further improving the space utilization efficiency.

[0199] Furthermore, in the second embodiment, no mention is made of the machine learning method used for learning in the operation record learning unit 102 and for predicting position deviations and time deviations in the exclusive area calculation unit 301, but multiple regression analysis, for example, can be used. However, other machine learning methods, such as deep learning, may also be used as the learning method.

[0200] <Embodiment 4> The fourth embodiment will be described, focusing on the differences from the first embodiment, with reference again to Fig. 1. In the fourth embodiment, the various examples described in the first to third embodiments can be used as appropriate.

[0201] The operation plan generation device 1 according to this embodiment includes a control unit 1a, and in response to an operation plan generation request including operation request information, the control unit 1a generates an operation plan including multiple pass points for autonomous mobile devices included as operation targets in the operation request information. Note that in this embodiment, the memory unit 1b does not need to store data such as operation results, and can be used to temporarily store intermediate processing data and generated data; however, it is sufficient if the memory unit is provided within the control unit 1a.

[0202] The control unit 1a generates an operation plan candidate that includes multiple pass points based on the operation request information. The control unit 1a sets an exclusive area for the operation plan candidate as an area in which other autonomous mobile devices are prohibited from competing with the operation of the operation plan candidate. Here, as a feature of the present embodiment, the exclusive area is not based on a prediction result, but is set to surround each section route that connects adjacent pass points among the multiple pass points included in the operation plan candidate. Then, the control unit 1a determines, as the operation plan to be sent in response to the operation plan generation request, a candidate from the operation plan candidates that does not compete with operation plans that have been generated but are incomplete for other autonomous mobile devices.

[0203] As described above, in this embodiment, unlike in the first embodiment, the exclusive zones are not set using the prediction results, but an exclusive zone can be set for each section route so as to surround the section route. Because the exclusive zones can be set more precisely than in the comparative example, this embodiment makes it possible to automatically generate an operation plan that increases the number of autonomous mobile devices that can operate in the same time period within a certain space, thereby achieving both collision prevention and improved space utilization efficiency. Although a detailed description thereof will be omitted in this embodiment, such an operation plan generation method and processing program can also be adopted.

[0204] <Other embodiments> [a] In each embodiment, the functions of the operation plan generation device, the functions of the autonomous mobile device, the functions of the learning device, etc. have been described, but each device is not limited to the configuration examples shown, and it is sufficient if each device can realize these functions.

[0205] [b] Each device according to each embodiment may have the following hardware configuration. Figure 44 is a diagram showing an example of the hardware configuration of the device. The same applies to the other embodiment [a] above.

[0206] The device 1000 shown in FIG. 44 may include a processor 1001, a memory 1002, and an interface 1003. The processor 1001 may be, for example, a microprocessor, a microprocessor unit (MPU), or a CPU. The processor 1001 may include multiple processors. The memory 1002 is, for example, configured by a combination of a volatile memory and a non-volatile memory. The functions of each device described in each embodiment are realized by the processor 1001 reading and executing a program stored in the memory 1002. At this time, input and output of information can be performed via an interface 1003 such as a communication interface for communicating with other internal components or other external devices. For example, if the device 1000 is an operation plan generation device or a learning device, the interface 1003 may include at least a communication interface and a user interface for accepting user operations. For example, if the device 1000 is an autonomous mobile device, the interface 1003 may include at least an interface with each sensor and a communication interface.

[0207] In the above examples, the program includes instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more functions described in the embodiments. The program may be stored on a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable medium or tangible storage medium includes random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technology, CD-ROM, digital versatile disc (DVD), Blu-ray disc or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The program may also be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, transitory computer-readable medium or communication medium includes electrical, optical, acoustic, or other forms of propagated signals.

[0208] The present disclosure is not limited to the above-described embodiments, and may be modified as appropriate without departing from the spirit and scope of the present disclosure. In addition, the present disclosure may be implemented by appropriately combining the respective embodiments.

[0209] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes. (Appendix 1) a control unit that, in response to an operation plan generation request including operation request information, generates an operation plan including a plurality of pass points for an autonomous mobile device included as an operation target in the operation request information; a storage unit that stores a relationship between an execution operation plan, which is an executed operation plan, and operation results at the time of execution of the execution operation plan; Equipped with The control unit generating a candidate operation plan including a plurality of passing points based on the desired operation information; For the operation plan candidate, based on the relationship, a prediction is made of positional and time deviations that may occur when an operation is performed according to the operation plan candidate; Based on the predicted results, an exclusive area is set as an area in which other autonomous mobile devices are prohibited from competing with each other to operate the operation plan candidate; determining, from among the operation plan candidates, a candidate that does not conflict with operation plans that have been generated but are not yet completed for other autonomous mobile devices, as an operation plan to be used in response to the operation plan generation request; Operation plan generation device. (Appendix 2) the control unit, based on the prediction result, sets the exclusive region to surround each section route that connects adjacent passing points among a plurality of passing points included in the operation plan candidate, for the operation plan candidate. 2. An operation plan generation device according to claim 1. (Appendix 3) the control unit sets, for the operation plan candidate, the exclusive area and an exclusive period as a period during which other autonomous mobile devices are prohibited from competing with each other to operate in the exclusive area, based on the prediction result. 3. An operation plan generation device according to claim 2. (Appendix 4) the control unit determines, as the responding operation plan, a candidate that operates in an area excluding set exclusive areas that are set to surround each of section routes connecting adjacent pass points among a plurality of pass points included in the generated but incomplete operation plan, as a candidate that does not conflict with the generated but incomplete operation plan; 4. An operation plan generation device according to any one of Supplementary notes 1 to 3. (Appendix 5) the control unit determines, as the responding operation plan, a candidate operation plan candidate that operates in an area excluding the set exclusive area during a set exclusive period that is set for the set exclusive area, as a candidate that does not conflict with the generated but incomplete operation plan. 5. An operation plan generation device according to claim 4. (Appendix 6) The size of a plane perpendicular to the travel direction in the exclusive area is set to be different for at least two section routes connecting adjacent passing points among the plurality of passing points. 6. An operation plan generation device according to any one of Supplementary notes 1 to 5. (Appendix 7) the exclusive area is set by allowing a section route connecting adjacent passing points among the plurality of passing points to be an exclusive line indicating the section route itself; 7. An operation plan generation device according to any one of Supplementary notes 1 to 6. (Appendix 8) the plurality of passing points are determined such that the lengths of at least two of the section routes connecting adjacent passing points are different from each other; An operation plan generation device according to any one of Supplementary notes 1 to 7. (Appendix 9) The plurality of passing points are determined by selecting from spatial points preset as lattice points of an equally spaced grid, excluding spatial points where obstacles exist and spatial points included in areas where operation is not legally permitted. An operation plan generation device according to any one of Supplementary notes 1 to 8. (Appendix 10) The plurality of passing points are selected and determined from among preset spatial points. An operation plan generation device according to any one of Supplementary notes 1 to 8. (Appendix 11) an exclusive period, which is a period during which other autonomous mobile devices are prohibited from competing with one another to operate in the exclusive area, is set so as to be different for at least two section routes connecting adjacent pass points among the plurality of pass points; 6. An operation plan generation device according to claim 3 or 5. (Appendix 12) the control unit sets a length of the exclusive period for the operation plan candidate to be long in accordance with a length of a time difference between predicted passage times at each passage point. 4. An operation plan generation device according to claim 3. (Appendix 13) The control unit predicts a distance deviation and a direction deviation as a positional deviation prediction. 13. An operation plan generation device according to any one of Supplementary notes 1 to 12. (Appendix 14) The relationship is stored in the storage unit as a trained model that predicts positional and time deviations that may occur when operating according to the candidate operation plan, the train being generated by machine learning based on the actual operation plan and the operation record; The control unit performs the prediction using the trained model. 14. An operation plan generation device according to any one of Supplementary notes 1 to 13. (Appendix 15) a control unit that, in response to an operation plan generation request including operation request information, generates an operation plan including a plurality of passing points for an autonomous mobile device included as an operation target in the operation request information; The control unit generating a candidate operation plan including a plurality of passing points based on the desired operation information; for each section route connecting adjacent pass points among a plurality of pass points included in the operation plan candidate, an exclusive area is set to surround the section route as an area in which other autonomous mobile devices are prohibited from competing with each other to operate; determining, from among the operation plan candidates, a candidate that does not conflict with operation plans that have been generated but are not yet completed for other autonomous mobile devices, as an operation plan to be used in response to the operation plan generation request; Operation plan generation device. (Appendix 16) an acquisition unit that, in response to an operation plan generation request including operation request information, acquires information including an executed operation plan that has been executed from among operation plans generated to include a plurality of pass points for an autonomous mobile device included as an operation target in the operation request information, and operation results during the execution of the executed operation plan; a control unit that generates a trained model that predicts, based on the information acquired by the acquisition unit, positional and time deviations that may occur when operating in accordance with a candidate operation plan that is generated to include multiple passing points based on other desired operation information; and Equipped with The operation plan is a plan in which, for each section route connecting adjacent pass points among a plurality of pass points included in the operation plan, an exclusive area is set as an area surrounding the section route in which other autonomous mobile devices are prohibited from competing with each other to operate. Learning device. (Appendix 17) an acquisition unit that, in response to an operation plan generation request including operation request information, acquires information including an executed operation plan that has been executed from among operation plans generated to include a plurality of pass points for an autonomous mobile device included as an operation target in the operation request information, and operation results during the execution of the executed operation plan; a control unit that generates a trained model that predicts, based on the information acquired by the acquisition unit, positional and time deviations that may occur when operating in accordance with a candidate operation plan that is generated to include multiple passing points based on other desired operation information; and Equipped with The operation plan is Among the operation plan candidates including a plurality of passing points generated based on the operation request information, The plan is a plan that allows operation in an area excluding a set exclusive area that is set to surround each section route connecting adjacent pass points among a plurality of pass points included in an operation plan that has been generated but is not yet completed for another autonomous mobile device. Learning device. (Appendix 18) an autonomous mobile device including the operation plan generation device according to Supplementary Note 14, a learning device, and a sensor group that collects information to be included in the operation record and that is capable of communicating with the operation plan generation device; The learning device an acquisition unit that acquires information including the actual operation plan and the operation record; a learning device-side control unit that generates the trained model based on the information acquired by the acquisition unit; Equipped with Autonomous mobility system. (Appendix 19) An autonomous mobile system comprising: an operation plan generation device according to any one of appendices 1 to 14; and an autonomous mobile device equipped with a group of sensors that collects information to be included in the operation record and capable of communicating with the operation plan generation device. (Appendix 20) In response to an operation plan generation request including operation request information, the operation plan includes a plurality of passing points for an autonomous mobile device included as an operation target in the operation request information, The process comprises: generating a candidate operation plan including a plurality of passing points based on the desired operation information; For the operation plan candidate, a prediction of positional and time deviations that may occur when operating according to the operation plan candidate is performed based on a relationship between an actual operation plan, which is an operation plan that has already been executed, and operation results at the time of execution of the actual operation plan; Based on the predicted results, an exclusive area is set as an area in which other autonomous mobile devices are prohibited from competing with each other to operate the operation plan candidate; determining, from among the operation plan candidates, a candidate that does not conflict with operation plans that have been generated but are not yet completed for other autonomous mobile devices, as an operation plan to be used in response to the operation plan generation request; Operation plan generation method. (Appendix 21) In response to an operation plan generation request including operation request information, the operation plan includes a plurality of passing points for an autonomous mobile device included as an operation target in the operation request information, The process comprises: generating a candidate operation plan including a plurality of passing points based on the desired operation information; for each section route connecting adjacent pass points among a plurality of pass points included in the operation plan candidate, an exclusive area is set to surround the section route as an area in which other autonomous mobile devices are prohibited from competing with each other to operate; determining, from among the operation plan candidates, a candidate that does not conflict with operation plans that have been generated but are not yet completed for other autonomous mobile devices, as an operation plan to be used in response to the operation plan generation request; Operation plan generation method. (Appendix 22) In response to an operation plan generation request including desired operation information, acquire information including an executed operation plan that has been executed from among operation plans generated to include a plurality of passing points for an autonomous mobile device included as an operation target in the desired operation information, and operation results at the time of execution of the executed operation plan; A trained model is generated based on the acquired information to predict positional and time deviations that may occur when operating in accordance with a candidate operation plan that is generated to include multiple passing points based on other desired operation information. The operation plan is a plan in which, for each section route connecting adjacent pass points among a plurality of pass points included in the operation plan, an exclusive area is set as an area surrounding the section route in which other autonomous mobile devices are prohibited from competing with each other to operate. How to learn. (Appendix 23) In response to an operation plan generation request including desired operation information, acquire information including an executed operation plan that has been executed from among operation plans generated to include a plurality of passing points for an autonomous mobile device included as an operation target in the desired operation information, and operation results at the time of execution of the executed operation plan; A trained model is generated based on the acquired information to predict positional and time deviations that may occur when operating in accordance with a candidate operation plan that is generated to include multiple passing points based on other desired operation information. The operation plan is Among the operation plan candidates including a plurality of passing points generated based on the operation request information, The plan is a plan that allows operation in an area excluding a set exclusive area that is set to surround each section route connecting adjacent pass points among a plurality of pass points included in an operation plan that has been generated but is not yet completed for another autonomous mobile device. How to learn. (Appendix 24) On the computer, In response to an operation plan generation request including operation request information, a process of generating an operation plan including a plurality of passing points for an autonomous mobile device included as an operation target in the operation request information, generating a candidate operation plan including a plurality of passing points based on the desired operation information; For the operation plan candidate, a prediction of positional and time deviations that may occur when operating according to the operation plan candidate is performed based on a relationship between an actual operation plan, which is an operation plan that has already been executed, and operation results at the time of execution of the actual operation plan; Based on the predicted results, an exclusive area is set as an area in which other autonomous mobile devices are prohibited from competing with each other to operate the operation plan candidate; determining, from among the operation plan candidates, a candidate that does not conflict with operation plans that have been generated but are not yet completed for other autonomous mobile devices, as an operation plan to be used in response to the operation plan generation request; A program that executes a process. (Appendix 25) On the computer, In response to an operation plan generation request including operation request information, a process of generating an operation plan including a plurality of passing points for an autonomous mobile device included as an operation target in the operation request information, generating a candidate operation plan including a plurality of passing points based on the desired operation information; for each section route connecting adjacent pass points among a plurality of pass points included in the operation plan candidate, an exclusive area is set to surround the section route as an area in which other autonomous mobile devices are prohibited from competing with each other to operate; determining, from among the operation plan candidates, a candidate that does not conflict with operation plans that have been generated but are not yet completed for other autonomous mobile devices, as an operation plan to be used in response to the operation plan generation request; A program that executes a process. (Appendix 26) On the computer, In response to an operation plan generation request including desired operation information, acquire information including an executed operation plan that has been executed from among operation plans generated to include a plurality of passing points for an autonomous mobile device included as an operation target in the desired operation information, and operation results at the time of execution of the executed operation plan; Generate a trained model that predicts, based on the acquired information, positional and time deviations that may occur when operating according to a candidate operation plan that is generated based on other desired operation information and includes multiple transit points. Execute the process, The operation plan is a plan in which, for each section route connecting adjacent pass points among a plurality of pass points included in the operation plan, an exclusive area is set as an area surrounding the section route in which other autonomous mobile devices are prohibited from competing with each other to operate. program. (Appendix 27) On the computer, In response to an operation plan generation request including desired operation information, acquire information including an executed operation plan that has been executed from among operation plans generated to include a plurality of passing points for an autonomous mobile device included as an operation target in the desired operation information, and operation results at the time of execution of the executed operation plan; Generate a trained model that predicts, based on the acquired information, positional and time deviations that may occur when operating according to a candidate operation plan that is generated based on other desired operation information and includes multiple transit points. Execute the process, The operation plan is Among the operation plan candidates including a plurality of passing points generated based on the operation request information, The plan is a plan that allows operation in an area excluding a set exclusive area that is set to surround each section route connecting adjacent pass points among a plurality of pass points included in an operation plan that has been generated but is not yet completed for another autonomous mobile device. program. [Explanation of symbols]

[0210] 1. Operation plan generation device 1a Control section 1b Storage section 2 Autonomous Mobile Device 2a Sensor group 2b Communication Department 2c Movement control section 2d Drive unit 3. Drone 4 Learning Device 4a Acquisition part 4b Control section 4c storage section 4d Untrained Model 4e Pre-trained model 10 Traffic control device 101 Trained Model Management Unit 102 Operational Performance Learning Department 103 Trained model storage unit 200 Performance Management Department 201 Operational Performance Management Department 202 Operation Records Department 300 Planning Department 301 Exclusive area calculation unit 302 Operation Plan Issuance Request Management Department 303 Operation plan issuance request storage unit 304 Operation Planning Department 305 Operation plan candidate temporary storage unit 400 Planning and Management Department 401 Issued Operation Planning Management Department 402 Issued Operation Plan Storage Unit 500 Space Management Department 501 Spatial Information Management Department 502 Waypoint (WP) holder 503 Edge information storage unit 1000 devices 1001 processor 1002 memory 1003 Interface

Claims

1. a control unit that, in response to an operation plan generation request including operation request information, generates an operation plan including a plurality of passing points for an autonomous mobile device included as an operation target in the operation request information; The control unit generating a candidate operation plan including a plurality of passing points based on the desired operation information; For the operation plan candidate, an exclusive area is set to surround each section route connecting adjacent pass points among a plurality of pass points included in the operation plan candidate, as an area in which other autonomous mobile devices are prohibited from being located and operating at the same time; Among the operation plan candidates, a candidate that does not conflict with operation plans that have been generated but are not yet completed for other autonomous mobile devices is determined to be an operation plan to be used in response to the operation plan generation request. Operation plan generation device.

2. the control unit determines, as the responding operation plan, a candidate that operates in an area excluding set exclusive areas that are set to surround each of section routes connecting adjacent pass points among a plurality of pass points included in the generated but incomplete operation plan, as a candidate that does not conflict with the generated but incomplete operation plan; The operation plan generation device according to claim 1 .

3. the control unit determines, as the responding operation plan, a candidate operation plan that operates in an area excluding the set exclusive area during a set exclusive period that is set for the set exclusive area, from among the operation plan candidates as a candidate that does not conflict with the generated but incomplete operation plan; The operation plan generation device according to claim 2 .

4. a size of a plane perpendicular to the direction of travel in the exclusive area is set to be different for at least two section routes connecting adjacent passing points among the plurality of passing points; The operation plan generation device according to any one of claims 1 to 3.

5. the exclusive area is set by allowing a section route connecting adjacent passing points among the plurality of passing points to be an exclusive line indicating the section route itself; The operation plan generation device according to any one of claims 1 to 4.

6. In response to an operation plan generation request including operation request information, the operation plan includes a plurality of passing points for an autonomous mobile device included as an operation target in the operation request information, The process comprises: generating a candidate operation plan including a plurality of passing points based on the desired operation information; For the operation plan candidate, an exclusive area is set to surround each section route connecting adjacent pass points among a plurality of pass points included in the operation plan candidate, as an area in which other autonomous mobile devices are prohibited from being located and operating at the same time; Among the operation plan candidates, a candidate that does not conflict with operation plans that have been generated but are not yet completed for other autonomous mobile devices is determined to be an operation plan to be used in response to the operation plan generation request. Operation plan generation method.

7. On the computer, In response to an operation plan generation request including operation request information, a process of generating an operation plan including a plurality of passing points for an autonomous mobile device included as an operation target in the operation request information, generating a candidate operation plan including a plurality of passing points based on the desired operation information; For the operation plan candidate, an exclusive area is set to surround each section route connecting adjacent pass points among a plurality of pass points included in the operation plan candidate, as an area in which other autonomous mobile devices are prohibited from being located and operating at the same time; Among the operation plan candidates, a candidate that does not conflict with operation plans that have been generated but are not yet completed for other autonomous mobile devices is determined to be an operation plan to be used in response to the operation plan generation request. A program that executes a process.

Images