Operation Management Device

Abstract

To prevent water from splashing a pedestrian and reduce the danger of travel of a vehicle.SOLUTION: An operation management device 20 operates a vehicle 30 by automatic driving. The operation management device 20 includes a control unit that acquires precipitation amount data showing an expected precipitation amount in a period to the end of the operation of a vehicle 30, executes determination processing of determining the occurrence state of a puddle for each of multiple candidate links connecting a first node and a second node included in the path where the vehicle is scheduled to travel using the acquired precipitation amount data as an input, selects the link from among the candidate links on the basis of the determination result of the occurrence state of the puddle, and determines the path constituted by the selected link as the operation path of the vehicle 30.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a traffic management device. [Background technology]

[0002] Patent Document 1 discloses a driving assistance device that calculates a predicted position of a small electric vehicle that is predicted to travel while avoiding a puddle in front of the vehicle, and supports the driving of the vehicle in accordance with the calculated predicted position. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2019-98965 Summary of the Invention [Problem to be solved by the invention]

[0004] When a vehicle passes over a puddle, splashed water is likely to hit pedestrians. In addition, when a vehicle passes over a puddle, hydroplaning can occur, which is dangerous.

[0005] The object of the present disclosure is to make it less likely for pedestrians to be splashed with water and to reduce the danger of vehicles passing by. [Means for solving the problem]

[0006] The traffic management device according to the present disclosure includes: An operation management device that operates a vehicle by automatic driving, acquiring precipitation data indicating the amount of precipitation expected during the period until the end of the operation of the vehicle; Using the acquired precipitation data as an input, execute a determination process to determine the occurrence of puddles for each of a plurality of candidate links connecting a first node and a second node included in the route along which the vehicle is scheduled to travel; The control unit selects links from the candidate links based on the determination result of the occurrence of puddles, and determines a route consisting of the selected links as the travel route of the vehicle. [Effects of the Invention]

[0007] According to the present disclosure, pedestrians are less likely to be splashed with water, and the danger of passing vehicles is reduced. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating a configuration of a system according to an embodiment of the present disclosure. [Figure 2] 1 is a block diagram illustrating a configuration of an operation management device according to an embodiment of the present disclosure. [Figure 3] 4 is a flowchart illustrating an operation of the operation management device according to the embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an embodiment of the present disclosure will be described with reference to the drawings.

[0010] In each drawing, the same or corresponding parts are denoted by the same reference numerals. In the description of this embodiment, the description of the same or corresponding parts will be omitted or simplified as appropriate.

[0011] The configuration of a system 10 according to this embodiment will be described with reference to FIG.

[0012] The system 10 according to this embodiment includes an operation management device 20 and one or more vehicles 30. The system 10 is used to provide mobility services such as MaaS. "MaaS" is an abbreviation for Mobility-as-a-Service.

[0013] The operation management device 20 is capable of communicating with the vehicle 30 via a network 40 such as the Internet.

[0014] The traffic management device 20 is installed in a facility such as a data center and operated by a traffic manager who manages the system 10. The traffic management device 20 is, for example, a computer such as a server belonging to a cloud computing system or other computing system. The traffic management device 20 may be installed in a control room of the system 10 and used by the traffic manager. Alternatively, the traffic management device 20 installed in the control room may be shared by two or more traffic managers. In this embodiment, the traffic management device 20 automatically drives the vehicle 30 along a travel route.

[0015] The vehicle 30 may be any type of automobile, such as a gasoline vehicle, a diesel vehicle, a hydrogen vehicle, an HEV, a PHEV, a BEV, or an FCEV. "HEV" is an abbreviation for hybrid electric vehicle. "PHEV" is an abbreviation for plug-in hybrid electric vehicle. "BEV" is an abbreviation for battery electric vehicle. "FCEV" is an abbreviation for fuel cell electric vehicle. In this embodiment, the vehicle 30 is a MaaS-dedicated vehicle, but may also be an AV with automated driving at any level. "AV" is an abbreviation for autonomous vehicle. The level of automation is, for example, any of levels 1 to 5 in the SAE classification. "SAE" is an abbreviation for Society of Automotive Engineers.

[0016] Network 40 may include the Internet, at least one WAN, at least one MAN, or a combination thereof. "WAN" is an abbreviation for wide area network. "MAN" is an abbreviation for metropolitan area network. Network 40 may include at least one wireless network, at least one optical network, or a combination thereof. A wireless network may be, for example, an ad-hoc network, a cellular network, a wireless LAN, a satellite communication network, or a terrestrial microwave network. "LAN" is an abbreviation for local area network.

[0017] An overview of this embodiment will be described with reference to FIG.

[0018] In the system 10, the traffic management device 20 functions as a mobility service platform. In summary, the traffic management device 20 determines a travel route R for the vehicle 30, and causes the vehicle 30 to travel along the determined travel route R by automatic driving.

[0019] In this embodiment, the vehicle 30 is a bus that transports one or more passengers. The vehicle 30 operates as a scheduled bus that automatically drives according to a preset schedule. The vehicle 30 is equipped with a control device. The control device controls the vehicle based on commands from the operation management device 20. For example, the control device controls the operation of the vehicle 30 based on information indicating the operation route R determined by the operation management device 20. As a result, the vehicle 30 runs along the operation route R. The operation route R includes, for example, a starting point P1 where the vehicle 30 starts running and an ending point P2 where the vehicle ends running.

[0020] If puddles occur due to rain or other reasons on the travel route R on which the vehicle 30 is traveling, water may splash as the vehicle 30 passes through the puddle, and the splashed water may land on pedestrians. In addition, it is dangerous for the vehicle 30 to pass through a puddle. Furthermore, it takes time and effort to avoid puddles while the vehicle 30 is traveling. Therefore, it is desirable to determine a route with as few puddles as possible as the travel route R.

[0021] In this embodiment, the traffic management device 20 operates the vehicle 30 in an autonomous driving manner. The traffic management device 20 acquires precipitation data D1 indicating the amount of precipitation expected until the end of the vehicle 30's operation. The traffic management device 20 uses the acquired precipitation data D1 as an input and executes a determination process to determine the occurrence of puddles for each of a plurality of candidate links L1, L2, L3, . . . , Ln connecting a first node N1 and a second node N2 included in the route along which the vehicle 30 is scheduled to travel. In this embodiment, the first node N1 and the second node N2 are selected from two or more nodes N included in the route along which the vehicle 30 is scheduled to travel. The traffic management device 20 selects a link L' from the candidate links L1, L2, L3, . . . , Ln based on the determination result of the occurrence of puddles, and determines a route R' consisting of the selected links L' as the travel route R of the vehicle 30.

[0022] According to this embodiment, locations where puddles will occur are predicted based on the amount of precipitation expected during operation of the vehicle 30, and the travel route R is determined based on the predicted results. For example, a route R' that is likely to produce fewer puddles is selected as the travel route R, so pedestrians are less likely to be splashed with water. This also reduces the risk of danger to the vehicle 30 during operation. Furthermore, this also reduces the time and effort required to avoid puddles while the vehicle 30 is in operation.

[0023] The configuration of the operation management device 20 according to this embodiment will be described with reference to FIG.

[0024] The operation management device 20 includes a control unit 21, a storage unit 22, and a communication unit 23.

[0025] The control unit 21 includes at least one processor, at least one programmable circuit, at least one dedicated circuit, or any combination thereof. The processor is a general-purpose processor such as a CPU or GPU, or a dedicated processor specialized for specific processing. "CPU" is an abbreviation for central processing unit. "GPU" is an abbreviation for graphics processing unit. An example of the programmable circuit is an FPGA. "FPGA" is an abbreviation for field-programmable gate array. An example of the dedicated circuit is an ASIC. "ASIC" is an abbreviation for application specific integrated circuit. The control unit 21 controls each part of the traffic management device 20 and executes processing related to the operation of the traffic management device 20.

[0026] The storage unit 22 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or any combination thereof. The semiconductor memory is, for example, a RAM or a ROM. "RAM" is an abbreviation for random access memory. "ROM" is an abbreviation for read only memory. RAM is, for example, an SRAM or a DRAM. "SRAM" is an abbreviation for static random access memory. "DRAM" is an abbreviation for dynamic random access memory. ROM is, for example, an EEPROM. "EEPROM" is an abbreviation for electrically erasable programmable read only memory. The storage unit 22 functions as, for example, a main storage device, an auxiliary storage device, or a cache memory. The storage unit 22 stores data used in the operation of the traffic management device 20 and data obtained by the operation of the traffic management device 20. In this embodiment, the storage unit 22 stores, for example, precipitation data D1. The precipitation data D1 includes data indicating the amount of precipitation expected until the end of the operation of the vehicle 30.

[0027] The communication unit 23 includes at least one communication interface. The communication interface is, for example, a LAN interface. The communication unit 23 receives data used in the operation of the traffic management device 20 and transmits data obtained by the operation of the traffic management device 20. In this embodiment, the communication unit 23 communicates with the vehicle 30.

[0028] The functions of the traffic management device 20 are realized by executing a program according to this embodiment on a processor serving as the control unit 21. That is, the functions of the traffic management device 20 are realized by software. The program causes a computer to execute the operations of the traffic management device 20, thereby causing the computer to function as the traffic management device 20. That is, the computer functions as the traffic management device 20 by executing the operations of the traffic management device 20 in accordance with the program.

[0029] The program can be stored on a non-transitory computer-readable medium. Examples of non-transitory computer-readable media include flash memory, magnetic recording devices, optical disks, magneto-optical recording media, and ROMs. The program can be distributed by selling, transferring, or lending portable media such as SD cards, DVDs, or CD-ROMs that store the program. "SD" is an abbreviation for Secure Digital. "DVD" is an abbreviation for digital versatile disc. "CD-ROM" is an abbreviation for compact disc read only memory. The program can also be distributed by storing it in the storage of a server and transferring it from the server to another computer. The program can also be provided as a program product.

[0030] A computer temporarily stores a program stored on a portable medium or transferred from a server in its main storage device. The computer then reads the program stored in the main storage device using a processor and executes processing in accordance with the read program. The computer may also read the program directly from a portable medium and execute processing in accordance with the program. The computer may also execute processing in accordance with the received program each time a program is transferred from a server to the computer. Processing may also be executed through a so-called ASP-type service that achieves its functions by issuing execution instructions and obtaining results without transferring the program from the server to the computer. "ASP" is an abbreviation for application service provider. A program is information used for processing by a computer and includes something equivalent to a program. For example, data that is not a direct instruction to a computer but has properties that specify computer processing falls under the category of "something equivalent to a program."

[0031] Some or all of the functions of the traffic management device 20 may be realized by a programmable circuit or a dedicated circuit as the control unit 21. In other words, some or all of the functions of the traffic management device 20 may be realized by hardware.

[0032] The operation of the traffic management device 20 according to this embodiment will be described with reference to Fig. 3. This operation corresponds to the traffic management method according to this embodiment.

[0033] In step S1, the control unit 21 of the traffic management device 20 acquires precipitation data D1 indicating the amount of precipitation expected until the end of the operation of the vehicle 30. The precipitation data D1 may be acquired by any procedure. In this embodiment, for example, the control unit 21 acquires precipitation data D1 registered in advance in the storage unit 22. The precipitation data D1 is data indicating the amount of precipitation predicted based on weather forecast data. The weather forecast data is provided, for example, by the Japan Meteorological Agency. Alternatively, the weather forecast data may be provided from another device connected to the network 40.

[0034] In step S2, the control unit 21 of the traffic management device 20 receives the precipitation data D1 acquired in step S1 as input and executes a determination process to determine whether puddles have occurred. Specifically, the control unit 21 performs the determination process for each of a plurality of candidate links L1, L2, L3, . . . , Ln connecting a first node N1 and a second node N2 selected from two or more nodes N included in the route along which the vehicle 30 is scheduled to travel. In this embodiment, the first node N1 is a starting point P1 where the vehicle 30 starts traveling. The second node N2 is an end point P2 where the vehicle 30 ends traveling. The two or more nodes N may include an intermediate point P3 between the starting point P1 and the end point P2. The intermediate point P3 is, for example, a bus stop through which the vehicle 30 passes. Instead of the second node N2 being the end point P2, the second node N2 may be the intermediate point P3. Alternatively, instead of using the first node N1 as the starting point P1, the first node N1 may be used as the midpoint P3.

[0035] In this embodiment, the control unit 21 of the traffic management device 20 performs a process using a trained model for identifying the positions of puddles that will occur as a determination process. Specifically, the control unit 21 performs a process using a trained model that receives data indicating the amount of precipitation as input and outputs data indicating the positions of puddles that correspond to the amount of precipitation as an input as a determination process. The control unit 21 inputs the precipitation amount data D1 acquired in step S1 into a trained model for determining the positions of puddles that will occur, thereby acquiring a determination result of the positions of puddles from the trained model. The trained model may be generated by any learning method, but in this embodiment, it is generated by the following learning method.

[0036] In a first step, the control unit 21 of the traffic management device 20 detects puddles. Specifically, the control unit 21 detects puddles based on captured images M of the road surfaces of each of the multiple candidate links L1, L2, L3, . . . , Ln. The captured images M may be acquired using any procedure, but for example, may be acquired using the following procedure. The communication unit 23 of the traffic management device 20 receives one or more images acquired by capturing images of the road surface using an imaging device such as a drive recorder mounted on any of multiple vehicles VH under the management of the traffic management device 20. The control unit 21 acquires the images received by the communication unit 23. The multiple vehicles VH may include the vehicle 30. The captured images M may be images captured by a translog of the drive recorder, a roadside unit, or a fixed camera. Alternatively, the captured images M may be still images captured from a video. The control unit 21 of the traffic management device 20 analyzes the one or more captured images M that have been acquired to identify the location where the puddle has occurred, thereby detecting the puddle.

[0037] Alternatively, the control unit 21 of the traffic management device 20 may measure the size of a puddle when detecting it. The size of the puddle may be, for example, the diameter of the puddle. The control unit 21 may then identify the location of a puddle whose measured size is equal to or greater than a threshold value Th1. The threshold value Th1 may be any value, but may be set, for example, as follows: The amount of water splashed when the vehicle 30 passes over the puddle is considered to increase in proportion to the size of the puddle. That is, if the puddle is sufficiently small, it is considered that almost no water splashes when the vehicle 30 passes over it, or that even if water splashes, it is unlikely to splash on pedestrians. Therefore, the threshold value Th1 may be set to a value that is considered to be the diameter of the puddle such that water splashes large enough to splash on pedestrians when the vehicle 30 passes over it. As an example, the threshold value Th1 may be approximately 100 cm. Alternatively, the risk of the vehicle 30 passing over a puddle is considered to increase in proportion to the size of the puddle. Therefore, the threshold value Th1 may be set to a value that is the diameter of the puddle at which hydroplaning is considered unlikely to occur even if the vehicle 30 passes over it.

[0038] In the second step, the control unit 21 of the traffic management device 20 creates training data. Specifically, the control unit 21 creates training data by associating, for each puddle detected in the first step, the amount of precipitation observed when the puddle was detected with the location of the detected puddle. Specifically, the control unit 21 associates the amount of precipitation with the location of the puddle by, for example, mapping the location of the puddle identified in the first step together with the amount of precipitation observed when the puddle was detected.

[0039] The amount of precipitation observed when a puddle is detected may be determined using any procedure, but for example, it is determined using the following procedure. A precipitation sensor mounted on or connected to each vehicle VH observes precipitation such as rain. Data observed by the precipitation sensor is transmitted from each vehicle VH to the traffic management device 20. A communication unit 23 of the traffic management device 20 receives the data transmitted from each vehicle VH. A control unit 21 of the traffic management device 20 acquires the data received by the communication unit 23. The control unit 21 determines the amount of precipitation based on the acquired data. Alternatively, the control unit 21 of the traffic management device 20 may acquire past weather data provided, for example, by the Japan Meteorological Agency, and determine the amount of precipitation observed when a puddle was detected based on the acquired past weather data. Alternatively, the weather data may be provided from another device connected to the network 40.

[0040] The procedure for creating the training data will be described in detail. As an example, assume that puddle X, puddle Y, and puddle Z are detected in the first step described above. Specifically, assume that the occurrence position Px of puddle X, the occurrence position Py of puddle Y, and the occurrence position Pz of puddle Z are identified. Furthermore, assume that the precipitation determined for puddle X is 10 mm, the precipitation determined for puddle Y is 20 mm, and the precipitation determined for puddle Z is 1 mm in the second step described above. The control unit 21 of the traffic management device 20 associates the occurrence position Px of puddle X with the precipitation amount of 10 mm. The control unit 21 associates the occurrence position Py of puddle Y with the precipitation amount of 20 mm. The control unit 21 associates the occurrence position Pz of puddle Z with the precipitation amount of 1 mm.

[0041] In the third step, a trained model is generated. Specifically, by performing machine learning using the training data created in the second step, a trained model is generated that takes data indicating the amount of precipitation as input and outputs data indicating the locations of puddles corresponding to the amount of precipitation indicated by the input data. Machine learning can be performed using known machine learning algorithms such as neural networks or deep learning.

[0042] In this embodiment, the trained model outputs puddle data D2 indicating the location of a puddle corresponding to the input precipitation amount as a determination result. The puddle data D2 is data indicating the location of a puddle using coordinates such as latitude and longitude. As an example, if the trained model is created using the training data described above, when a precipitation amount of 10 mm is input, data indicating the location Px of the puddle is output as the puddle data D2. The control unit 21 of the traffic management device 20 acquires the puddle data D2 output by the trained model as a determination result as a result of the determination process in step S2.

[0043] In step S3, the control unit 21 of the traffic management device 20 determines the travel route R of the vehicle 30 based on the determination result of the puddle occurrence status. Specifically, the control unit 21 selects a link L' from among the candidate links L1, L2, L3, . . . , Ln based on the puddle data D2 acquired as the determination result in step S2. Then, the control unit 21 determines the route R' consisting of the selected link L' as the travel route R of the vehicle 30. In this embodiment, the control unit 21 identifies the positions of puddles for each candidate link by referring to the puddle data D2 acquired in step S2. Then, the control unit 21 selects the link with the fewest identified positions of puddles as the link L' from among the candidate links L1, L2, L3, . . . , Ln. The control unit 21 determines the route R' consisting of the selected link L' as the travel route R of the vehicle 30.

[0044] As described above, the traffic management device 20 according to this embodiment acquires precipitation data D1 indicating the amount of precipitation expected until the end of the operation of the vehicle 30. The traffic management device 20 receives the acquired precipitation data D1 as an input and executes a determination process to determine the occurrence of puddles for each of a plurality of candidate links L1, L2, L3, . . . , Ln connecting a first node N1 and a second node N2 selected from two or more nodes N included in the route along which the vehicle 30 is scheduled to travel. The traffic management device 20 selects a link L' from the candidate links L1, L2, L3, . . . , Ln based on the determination result of the occurrence of puddles, and determines a route R' consisting of the selected links L' as the travel route R of the vehicle 30.

[0045] According to this configuration, locations where puddles will occur during operation of the vehicle 30 are predicted based on the amount of precipitation expected, and the travel route R is determined based on the prediction results. For example, a route R' where the fewest puddles are predicted to occur is selected as the travel route R. As a result, the number of times the vehicle 30 passes through locations where puddles have occurred during operation can be reduced. This reduces the risk of pedestrians being splashed with water, and reduces the risk of vehicle travel. Furthermore, the time and effort required to avoid puddles during operation of the vehicle 30 is reduced.

[0046] In the above-described embodiment, the control unit 21 of the traffic management device 20 may acquire position data D3 indicating the position of the vehicle 30 after the vehicle 30 starts traveling, identify the positions of puddles on the travel route R based on the puddle data D2, and perform control to decelerate the vehicle 30 when it is determined that the distance d from the position indicated by the position data D3 to any of the identified positions of puddles is less than the threshold value Th2. Specifically, the control unit 21 may further perform the processes of the following steps S4 to S6.

[0047] In step S4, the control unit 21 of the traffic management device 20 acquires position data D3 indicating the position of the vehicle 30. The position data D3 may be acquired by any procedure, but is acquired, for example, by the following means. The control unit 21 receives data indicating the position measured by a positioning sensor provided in the vehicle 30 from the vehicle 30 via the communication unit 23. The positioning sensor includes at least one GNSS receiver. GNSS is, for example, GPS, QZSS, BeiDou, GLONASS, or Galileo. "GNSS" is an abbreviation for global navigation satellite system. "GPS" is an abbreviation for Global Positioning System. "QZSS" is an abbreviation for Quasi-Zenith Satellite System. QZSS satellites are called quasi-zenith satellites. "GLONASS" is an abbreviation for Global Navigation Satellite System.

[0048] In step S5, the control unit 21 of the traffic management device 20 identifies a puddle location on the travel route R based on the puddle data D2 acquired as the determination result in step S2. As an example, assume that a puddle X has occurred on the travel route R. The control unit 21 identifies the location Px of the puddle X based on the puddle data D2. The control unit 21 measures the distance d from the position of the vehicle 30 indicated by the position data D3 acquired in step S4 to the location Px and determines whether the measured distance d is less than a threshold value Th2. The threshold value Th2 may be any value, but may be, for example, a braking distance that allows the vehicle 30 to decelerate without sudden braking to a speed V1 that prevents pedestrians from being splashed with water when passing through a puddle. The speed V1 is, for example, approximately 10 km / h. If there are two or more locations where puddles have occurred on the travel route R, the control unit 21 performs the same process for each puddle. If it is determined in step S5 that the distance d is less than the threshold value Th2, the process proceeds to step S6. If it is determined in step S5 that the distance d is equal to or greater than the threshold value Th2, the process returns to step S4, where the control unit 21 acquires the position data D3 indicating the position of the vehicle 30 again, and the process proceeds to step S5 again.

[0049] In step S6, the control unit 21 of the traffic management device 20 controls the vehicle 30 to decelerate. Specifically, the control unit 21 communicates with a control device mounted on the vehicle 30 via the communication unit 23 and transmits a deceleration command to the control device. The control device decelerates the vehicle 30 by applying the brakes of the vehicle 30 based on the deceleration command from the traffic management device 20. In this embodiment, it is desirable to decelerate the vehicle 30 so that the traveling speed when passing through a location where a puddle has occurred is around 10 km / h, for example.

[0050] In this way, by reducing the speed of the vehicle 30 when passing through a puddle-forming area, the amount of water splashing when the vehicle 30 passes through the puddle-forming area can be reduced compared to when the vehicle 30 is not decelerated. Also, hydroplaning and other phenomena are less likely to occur when the vehicle 30 travels through a puddle-forming area. This configuration makes it even more unlikely that water will splash on pedestrians, and further reduces the danger of the vehicle traveling.

[0051] In the above-described embodiment, when the control unit 21 of the traffic management device 20 performs control to decelerate the vehicle 30 in the above-described step S6, the control unit 21 may adjust the deceleration amount W of the vehicle 30 depending on the situation inside the passenger compartment of the vehicle 30. Specifically, the control unit 21 may further perform the processes of the following steps S7 and S8.

[0052] In step S7, the control unit 21 of the traffic management device 20 determines the status of the interior of the vehicle 30. Specifically, the control unit 21 acquires vehicle data D4 indicating the status of the interior of the vehicle 30, and determines the status of the interior of the vehicle 30 based on the status indicated by the acquired vehicle data D4. The vehicle data D4 may be acquired using any procedure, but for example, it is acquired using the following procedure. An arbitrary sensor, such as a camera, installed in the interior of the vehicle 30 captures an image of the interior of the vehicle 30. The image captured by the sensor is transmitted from the vehicle 30 to the traffic management device 20. The control unit 21 of the traffic management device 20 receives the image transmitted from the vehicle 30 via the communication unit 23. The control unit 21 acquires information obtained by analyzing the received image as vehicle data D4. In this embodiment, the control unit 21 determines the congestion status of the interior of the vehicle 30 as the status of the interior of the vehicle 30. Specifically, the control unit 21 determines whether any passengers in the vehicle 30 are standing. Furthermore, the control unit 21 may determine the situation inside the vehicle 30, for example, whether there is someone carrying a stroller, whether there is someone in a wheelchair, or whether there is someone carrying large luggage or a walking stick.

[0053] In step S8, the control unit 21 of the traffic management device 20 performs control to adjust the deceleration width W according to the situation determined in step S7. Specifically, if it is determined in step S7 that there is a standing person, the control unit 21 performs control to reduce the deceleration width W. This is because the larger the deceleration width W, the greater the swaying of the vehicle 30, and if there is a standing person, there is a risk of an accident, such as a fall. Furthermore, if the deceleration width W is large, there is a risk of the vehicle 30 slipping due to sudden deceleration. It is desirable that the deceleration width W be less than 20 km, for example. The control unit 21 may further count the number of standing people in step S7, and further reduce the deceleration width W as the counted number increases. This configuration makes it less likely for pedestrians to be splashed with water, reduces the danger of the vehicle traveling, and improves passenger safety.

[0054] The present disclosure is not limited to the above-described embodiments. For example, two or more blocks shown in the block diagrams may be integrated, or one block may be divided. Two or more steps shown in the flowcharts may be executed in parallel or in a different order, instead of being executed in chronological order as described, depending on the processing capabilities of the device executing each step, or as needed. Other modifications are possible within the scope of the present disclosure. [Explanation of symbols]

[0055] 10 Systems 20 Operation control device 21 Control Unit 22 Memory section 23 Communications Department 30 vehicles 40 Network

Claims

1. An operation management device that operates a vehicle by automatic driving, acquiring precipitation data indicating the amount of precipitation expected during the period until the end of the operation of the vehicle; executing a process using a trained model that uses the acquired precipitation data as input, and executing a determination process to determine the occurrence of puddles for each of a plurality of candidate links connecting a first node and a second node included in a route along which the vehicle is scheduled to travel; As a result of the determination process, puddle data indicating the occurrence position of puddles output from the trained model is acquired; a control unit that selects links from the candidate links based on a result of determining whether a puddle is occurring, and determines a route formed by the selected links as a travel route for the vehicle; The control unit acquiring one or more images obtained by photographing a road surface; Analyzing the one or more images to identify a location where a puddle has occurred, the size of the puddle being measured, and identifying a location where a puddle has occurred where the measured size is equal to or greater than a threshold, thereby detecting the puddle; For each detected puddle, the location of the puddle is associated with the amount of precipitation observed when the puddle was detected to create training data. An operation management device that performs machine learning using the created training data to generate a trained model that takes acquired precipitation data as input and outputs puddle data indicating the location of puddles corresponding to the precipitation indicated by the input data.

2. the first node is a starting point where the vehicle starts traveling, and the second node is a destination point where the vehicle ends traveling; The traffic management device according to claim 1 , wherein the control unit refers to the puddle data and selects, from the candidate links, a link with the fewest number of puddle locations.

3. The operation management device described in claim 1 or claim 2, wherein the control unit acquires position data indicating the position of the vehicle after the vehicle starts operating, identifies the location of each puddle on the operation route based on the puddle data, and controls the vehicle to decelerate if it is determined that the distance from the position indicated by the position data to any of the puddle locations is less than a threshold value.

4. 4. The operation management device according to claim 3, wherein the control unit, when performing control to decelerate the vehicle, further acquires vehicle data indicating a situation inside the vehicle's cabin, and adjusts the deceleration amount of the vehicle according to the situation indicated by the acquired vehicle data.

Images