Inspection method for moving body

Through the inspection method of unmanned mobile objects, maintenance information and machine learning models are used to solve the problem of inability to distinguish the causes of abnormalities of vehicles, inspection devices and servers in the prior art, and achieve high reliability and high precision abnormal determination, simplifying the The detection process was carried out.

CN119024829APending Publication Date: 2024-11-26TOYOTA JIDOSHA KK
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410626196.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2023-05-25
Filing Date
2024-05-20
Publication Date
2024-11-26

Smart Images

  • Figure CN119024829A_ABST
    Figure CN119024829A_ABST
Patent Text Reader

Abstract

The invention provides a technology capable of determining the cause of abnormality of the inspection result with high reliability in the inspection of a moving body capable of moving through remote control. A method for inspecting a moving body that can be moved by remote control includes: a first step of giving an instruction from a remote control device to the moving body to be inspected so as to drive the moving body so that an output value related to movement of the moving body becomes a predetermined target value; a second step in which the output value is measured using an inspection device for inspecting the moving body, and a measured value is acquired; a maintenance information acquisition step for acquiring maintenance information relating to a history of maintenance performed on at least one of the remote control device and the inspection device; and an abnormality determination step in which, when the difference between the target value and the measured value is not within a predetermined reference range, the acquired maintenance information is used to determine which of the remote control device, the inspection device, and the inspection target has an abnormality.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to a method for inspecting a moving object. Background Art

[0002] For example, Japanese Patent Application Laid-Open No. 2020-60459 discloses an inspection system in which an operator causes a vehicle to travel on a roller device and uses a sensor vehicle speed obtained by a vehicle speed sensor of the vehicle and a roller vehicle speed obtained by the roller device to inspect an abnormality of a vehicle speed meter. In this inspection system, if the roller vehicle speed is not within a predetermined reference range, it is determined that the vehicle speed meter is abnormal. Prior art literature Patent Literature

[0003] Patent Document 1: Japanese Patent Application Publication No. 2020-60459 Summary of the invention Problems to be solved by the invention

[0004] However, even if an abnormality is detected by the inspection device, it is not necessarily an abnormality of the vehicle, but may be an abnormality of the inspection device, for example. In addition, when the inspection is performed while the vehicle is running by remote control, it may be an abnormality of the server that performs the remote control. In the conventional technology, when an abnormality occurs, it is impossible to determine whether the cause of the abnormality is the vehicle, the inspection device, or the server. Means for solving problems

[0005] The present disclosure can be implemented as the following aspects.

[0006] (1) According to one aspect of the present disclosure, there is provided a method for inspecting a mobile object that can be moved by unmanned driving. The inspection method comprises: a first step of giving an instruction from a server to drive the mobile object to be inspected so that an output value related to the movement of the mobile object becomes a predetermined target value; a second step of measuring the output value using an inspection device that inspects the mobile object and obtaining a measured value; a maintenance information acquisition step of obtaining maintenance information related to a history of maintenance performed on at least one of the server and the inspection device; and an abnormality determination step of using the maintenance information to determine which of the server, the inspection device, and the mobile object to be inspected has an abnormality when the difference between the target value and the measured value is not within a predetermined reference range. According to this inspection method, in an inspection of a mobile object that can move unmanned using a remote control device and an inspection device, it is possible to determine with high reliability whether the cause of the abnormality is the mobile object, the inspection device, or the remote control device being inspected. (2) In the inspection method of the above aspect, the maintenance information may be information related to a timing at which the maintenance is performed on the target device. According to the inspection method of this aspect, the cause of abnormality can be identified with high reliability by a simple method utilizing the execution timing of maintenance. (3) In the inspection method of the above-mentioned aspect, it may also be that, in the abnormality determination step, when the timing of executing the second step is within a predetermined period from the execution timing included in the maintenance information, a determination is made that there is no abnormality in the object device on which the maintenance is performed. According to the inspection method of this aspect, the abnormality identification process can be simplified based on the maintenance information within a predetermined period from the execution timing of the maintenance. (4) The inspection method of the above aspect may further include: a learning step of causing the machine learning model to learn using past data related to the input and output of the server, past data related to the input and output of the inspection device, past data related to the maintenance information, and past data related to the normality or abnormality of the server, the inspection device, and the movable body of the inspection object, In the abnormality determination step, the machine learning model learned in the learning step is used to determine which of the server, the inspection device, and the moving object of the inspection object has an abnormality. According to the inspection method of this aspect, by using a machine learning model that has been learned using past data, it is possible to improve the productivity of the inspection and the accuracy of identifying the cause of the abnormality. (5) In the inspection method of the above-mentioned manner, it may also be that, in the abnormality determination step, when the second step is performed within a predetermined period from the execution timing of the maintenance performed on the object device, information is output indicating that the probability that there is no abnormality in the object device on which the maintenance is performed is higher than when the maintenance is not performed. (6) In the inspection method of the above aspect, the maintenance information may be information on whether an abnormality of the target device is detected during the maintenance. According to the inspection method of this aspect, the cause of the abnormality can be identified with high reliability by a simple method utilizing the presence or absence of abnormality during maintenance. (7) In the inspection method of the above aspect, in the abnormality identification step, when the maintenance information includes information indicating that an abnormality of the target device is detected during the maintenance, a determination is made that an abnormality exists in the target device in which the abnormality is detected. According to the inspection method of this aspect, the abnormality identification process can be simplified by a simple method of confirming whether there is an abnormality during maintenance. (8) In the inspection method of the above-mentioned manner, it may be that, in the abnormality determination step, when the maintenance information includes information indicating that an abnormality of the object device was detected during the maintenance and also includes information that a component that caused the abnormality of the object device in which the abnormality was detected has been replaced, a determination is made that there is no abnormality in the object device in which the abnormality was detected, or a determination step is performed to determine whether there is an abnormality in the object device in which the abnormality was detected. According to the inspection method of this aspect, it is possible to perform appropriate identification of the cause of the abnormality in consideration of the fact that the abnormality at the time of maintenance has been repaired. (9) In the inspection method of the above aspect, the maintenance information may be information on whether an abnormality of the target device is detected continuously or intermittently during the maintenance. According to the inspection method of this aspect, the cause of the abnormality can be identified with high reliability through a simple method of confirming whether there is a continuous or intermittent abnormality during maintenance. (10) In the inspection method of the above-mentioned manner, it may be that in the abnormality determination step, when the maintenance information includes information that an abnormality of the object device is detected continuously or intermittently during the maintenance, information indicating that an abnormality exists in the object device in which the continuous or intermittent abnormality is detected is output. According to the inspection method of this aspect, the abnormality identification process can be simplified by a simple method of confirming whether there is a continuous or intermittent abnormality during maintenance. The present disclosure can also be implemented in various forms other than the inspection method. For example, it can be implemented in the form of a mobile inspection system, an inspection device, a method for manufacturing a mobile, a control method for an inspection system, a control method for an inspection device, a computer program for implementing the control method, a non-temporary recording medium having the computer program recorded thereon, and the like. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 It is an explanatory diagram showing a schematic configuration of an inspection system as a first embodiment of the present disclosure. Figure 2 It is a block diagram showing the internal functional configuration of the ECU. Figure 3 It is a block diagram showing the internal functional configuration of the inspection control device. Figure 4A This is a flowchart showing the processing procedure of the travel control of the vehicle in the first embodiment. Figure 4BThis is a flowchart showing a processing routine of the inspection method according to the first embodiment. Figure 5 1 is a flowchart showing a processing routine of the abnormality identification process. Figure 6 It is a block diagram showing the internal functional configuration of an inspection control device that executes the inspection method according to the second embodiment. Figure 7 This is a flowchart showing a processing routine of the abnormality identification step according to the second embodiment. Figure 8 This is a flowchart showing a processing routine of the abnormality specifying step of the inspection method according to the third embodiment. Fig. 9 This is a flowchart showing a processing routine of the abnormality specifying step of the inspection method according to the fourth embodiment. Fig.10 This is a flowchart showing a processing routine of the inspection method according to the fifth embodiment. Fig.11 This is a flowchart showing a processing routine of the abnormality specifying step in the inspection method according to the fifth embodiment. DETAILED DESCRIPTION

[0008] A. First Implementation Method: Figure 1 1 is an explanatory diagram showing a schematic configuration of an inspection system 500 as a first embodiment of the present disclosure. The inspection system 500 is used, for example, in a factory that manufactures a vehicle 100 as a mobile body that can travel without human control. The inspection system 500 includes an inspection device 200 and a server 300 as a remote control device. The inspection system 500 inspects whether the vehicle 100 can travel normally at a predetermined travel speed without human control.

[0009] In the present disclosure, "mobile body" means an object that can move, such as a vehicle, an electric vertical take-off and landing aircraft (so-called flying car). A vehicle may be a vehicle that runs on wheels or a vehicle that runs on tracks, such as a passenger car, a truck, a bus, a two-wheeled vehicle, a four-wheeled vehicle, a tank, an engineering vehicle, etc. Vehicles include electric vehicles (BEV: Battery Electric Vehicle), gasoline vehicles, hybrid vehicles, and fuel cell vehicles. In the case where the mobile body is other than a vehicle, the expressions "vehicle" and "car" in the present disclosure can be appropriately replaced with "mobile body", and the expression "running" can be appropriately replaced with "moving".

[0010] The vehicle 100 is configured to be able to travel by unmanned driving. "Unmanned driving" means driving that does not rely on the driving operation of the passengers. The driving operation means an operation related to at least one of "driving", "steering" and "stopping" of the vehicle 100. Unmanned driving is achieved by automatic or manual remote control using a device located outside the vehicle 100, or autonomous control of the vehicle 100. In the vehicle 100 that travels by unmanned driving, there may also be passengers who do not perform driving operations. Passengers who do not perform driving operations include, for example, people who only sit on the seats of the vehicle 100, and people who perform operations other than driving operations such as assembly, inspection, and operation of switch groups while riding in the vehicle 100. In addition, driving based on the driving operation of the passengers is sometimes referred to as "manned driving".

[0011] In the specification, “remote control” includes “full remote control” in which all actions of the vehicle 100 are determined completely from outside the vehicle 100, and “partial remote control” in which part of the actions of the vehicle 100 are determined from outside the vehicle 100. In addition, “autonomous control” includes “full autonomous control” in which the vehicle 100 autonomously controls its own actions without receiving any information from a device outside the vehicle 100, and “partial autonomous control” in which the vehicle 100 autonomously controls its own actions using information received from a device outside the vehicle 100.

[0012] The vehicle 100 is, for example, a passenger car, a truck, a bus, or a construction vehicle. The vehicle 100 is preferably an electric vehicle (BEV: Battery Electric Vehicle). In addition, the vehicle 100 is not limited to an electric vehicle, and may be, for example, a gasoline vehicle, a hybrid vehicle, or a fuel cell vehicle. The vehicle 100 includes a vehicle communication unit 190, a power receiving device 150, a motor 140, a battery 120, a wheel speed sensor 170, and an ECU (Electronic Control Unit: Electronic Control Unit) 180.

[0013] The vehicle communication unit 190 wirelessly communicates with devices outside the vehicle 100 such as the inspection device 200 and the server 300 connected to the network 72 via the access point 70 in the factory. The vehicle communication unit 190 transmits output values ​​corresponding to the inspection items of the inspection device 200, such as the running speed of the vehicle 100, the braking force of the brakes, the number of revolutions of the wheels 160, and the state of charge (SOC: State Of Charge) of the battery 120, to the server 300 or the inspection device 200.

[0014] The power receiving device 150 includes, for example, a power receiving circuit and a power receiver (not shown). The power receiver is a power supply inlet corresponding to the power supply connector of the charging device. Instead of the power receiver, a power receiving resonance circuit may be provided, which is used to receive power supplied from the charging device via the power transmission resonance circuit by contactless power supply using the electromagnetic induction phenomenon. The power receiving circuit is a rectifier and a DC / DC converter. When AC power is supplied from the power receiver, the power receiving circuit converts the supplied AC power into DC power through the rectifier. The converted DC power is supplied to the battery 120 via the DC / DC converter.

[0015] The motor 140 is, for example, an AC synchronous motor, and functions as an electric motor and a generator. When the motor 140 functions as an electric motor, the motor 140 uses the power stored in the battery 120 as a power source to be driven. The output of the motor 140 is transmitted to the wheels 160 via the speed reducer and the axle. When the vehicle 100 decelerates, the motor 140 functions as a generator using the rotation of the wheels 160, and generates regenerative power.

[0016] The rotation of the wheel 160 is one form of a "moving motion" as an action for the moving body to move. The wheel 160 is one form of a "moving unit" as a part of the moving body that performs the moving motion. The brake 162 that stops the rotation of the wheel 160 is provided by the moving body and is one form of a "stopping unit" that stops the moving motion of the moving body.

[0017] The battery 120 is, for example, a rechargeable secondary battery such as a lithium-ion battery or a nickel-metal hydride battery. The battery 120 stores the power used during the travel of the vehicle 100. When the power supplied from the charging device to the power receiving device 150 and the regenerative power generated by the motor 140 are supplied to the battery 120, the battery 120 is charged and the state of charge of the battery 120 increases. A PCU (Power Control Unit) having an inverter, a boost converter, and a DC / DC converter may be connected between the battery 120 and the motor 140.

[0018] The wheel speed sensor 170 detects the rotation speed of each wheel 160. The wheel speed sensor 170 calculates the running speed of the vehicle 100 using the detected rotation speed of each wheel 160. Specifically, the wheel speed sensor 170 calculates the running speed of the vehicle 100 using the rotation speed per unit time after performing arithmetic processing such as averaging the rotation speed of each wheel 160. In addition, at least a part of the function of calculating the running speed of the vehicle 100 may be performed by the vehicle speed acquisition unit 316 of the server 300 or the ECU 180 that acquires the rotation speed of the wheel 160 from the wheel speed sensor 170.

[0019] A device provided on a moving body and detecting an output value related to the movement of the moving body is also referred to as a "moving body detection unit". The "output value related to the movement of the moving body" may include the moving speed of the moving body and various output values ​​from which the moving speed of the moving body can be derived. The output value detected by the moving body detection unit is also referred to as a "moving body side output value".

[0020] A device provided in the vehicle 100 and detecting an output value related to the travel of the vehicle 100 is also referred to as a “vehicle detection unit”. The wheel speed sensor 170 is one form of a “vehicle detection unit”. The “output value related to the travel of the vehicle 100” may include the travel speed of the vehicle 100 and various output values ​​such as the number of revolutions of the wheel 160, the rotation speed of the wheel 160, and the torque of the wheel 160 from which the travel speed of the vehicle 100 can be derived. The travel speed of the vehicle 100 detected by the vehicle detection unit is also referred to as a “vehicle side speed”.

[0021] Figure 2 1 is a block diagram showing the internal functional structure of ECU 180. ECU 180 is mounted on vehicle 100 and performs various controls of vehicle 100. ECU 180 includes storage device 186 such as HDD (hard disk drive), SSD (solid state drive), optical recording medium, semiconductor memory, and CPU 182 as a central processing unit. Vehicle speed data 188 is stored in the readable and writable area of ​​storage device 186. Vehicle speed data 188 is the vehicle side speed obtained from wheel speed sensor 170. Computer programs for realizing at least part of the functions provided in this embodiment are stored in storage device 186. Functions such as driving control unit 184 are realized by CPU 182 executing various computer programs stored in the memory.

[0022] The driving control unit 184 performs driving control of the vehicle 100. “Driving control” refers to various controls such as adjustment of acceleration, speed, and steering angle for driving various actuators that perform the functions of “driving”, “steering”, and “stopping” of the vehicle 100. In the driving control of the vehicle 100 based on remote control, the driving control unit 184 controls various actuators mounted on the vehicle 100 according to the remote control request received from the server 300 via the vehicle communication unit 190.

[0023] In this embodiment, the actuator includes an actuator of a driving device for accelerating the vehicle 100, an actuator of a steering device for changing the traveling direction of the vehicle 100, and an actuator of a braking device for decelerating the vehicle 100. The driving device includes a battery 120, a motor 140, and a wheel 160. The actuator of the driving device includes the motor 140. In addition, the actuator may also include an actuator for swinging a wiper of the vehicle 100, an actuator for opening and closing an electric window of the vehicle 100, and the like.

[0024] When a driver is on board the vehicle 100, the driving control unit 184 can control the actuator according to the driver's operation, thereby driving the vehicle 100. Regardless of whether there is a driver on board the vehicle 100, the driving control unit 184 can control the actuator according to the control command sent from the server 300, thereby driving the vehicle 100.

[0025] return Figure 1 , the server 300 performs driving control of the vehicle 100 based on remote control. For example, the server 300 performs the transportation of the vehicle 100 in the manufacturing process in the factory by making the vehicle 100 drive automatically. The transportation of the vehicle 100 by automatic driving based on remote control is also called "self-propelled transportation". The server 300 can move the vehicle 100 by remote control without using a transportation device such as a crane or a conveyor. When the inspection device 200 inspects the vehicle 100, the server 300 automatically drives the vehicle 100 according to the request from the inspection device 200.

[0026] The server 300 includes a CPU 310 as a central processing unit, a storage device 320 , and a server communication unit 390 . These are connected to each other via an internal bus or an interface circuit, etc. The server communication unit 390 communicates with the vehicle 100 and the inspection device 200 via the network 72 .

[0027] The storage device 320 is, for example, a RAM, a ROM, a HDD, or an SSD. As described later, the storage device 320 stores vehicle speed data 322 and maintenance information 324. In addition, by executing a computer program stored in the storage device 320 by the CPU 310, the CPU 310 functions as a server control unit 312, a vehicle speed acquisition unit 316, and a vehicle information acquisition unit 318. However, some or all of these functions may be constituted by hardware circuits.

[0028] The vehicle information acquisition unit 318 acquires the vehicle identification information of the vehicle 100 from the process management device or the like provided in each process. "Vehicle identification information" means various information that can individually identify the vehicle 100. Vehicle identification information is, for example, ID information assigned to each vehicle 100 such as a vehicle identification number (VIN: Vehicle Identification Number) and a manufacturing number used in production management. The vehicle identification information may also include specification information of the vehicle 100 such as the model, color, and shape. As vehicle identification information, it is not limited to information for identifying a single vehicle 100, but information such as a batch number for identifying multiple vehicles 100 in each specified unit may also be used. The vehicle identification information may be obtained, for example, from a radio frequency identification (RF-ID: Radio Frequency-Identification) tag attached to the vehicle 100 via short-range wireless communication or the like. The vehicle identification information may also be obtained by reading a two-dimensional code attached to the vehicle 100 using a camera or the like.

[0029] The vehicle speed acquisition unit 316 acquires the running speed of the vehicle 100 detected by the vehicle 100, that is, the vehicle speed. In the present embodiment, the vehicle speed data 188 of the vehicle 100 is acquired via the server communication unit 390. The vehicle speed acquisition unit 316 may also acquire the rotation speed of the wheel 160 from the wheel speed sensor 170 to calculate the running speed of the vehicle 100. The acquired vehicle speed is stored in the storage device 320 as the vehicle speed data 322 associated with the vehicle identification information.

[0030] The maintenance information acquisition unit 314 acquires maintenance information 324 related to the maintenance performed on the server 300. "Maintenance information" means various information related to the history of maintenance of the device for the purpose of repairing, maintaining, servicing, and inspecting the device. The maintenance of the device, for example, does not include minor content that does not affect the function of the device, and preferably includes content that can fully infer that the target device can operate normally or content that can fully infer that the target device has an abnormality. The maintenance information is used in the inspection method of this embodiment.

[0031] The “maintenance history” may include information related to the results of maintenance, such as information on whether an abnormality was detected during maintenance, information on parts and components that were repaired or replaced during maintenance, etc. In addition, the “maintenance history” may include information related to the maintenance history, such as the execution timing of maintenance, and information related to maintenance over time. The maintenance information acquisition unit 314 acquires, as maintenance information 324, information related to maintenance manually input by an operator who has performed maintenance on the server 300. The maintenance information acquisition unit 314 may also acquire the maintenance information 324 from a management device that manages the maintenance information of the server 300 and the inspection device 200 in a unified manner. The acquired maintenance information 324 is stored in the storage device 320.

[0032] The server control unit 312 transmits a control signal requesting remote control of the vehicle 100 to the vehicle 100 via the server communication unit 390. When the vehicle 100 receives the remote control request, the ECU 180 implements driving control, and as a result, the vehicle 100 automatically travels.

[0033] During self-propelled transportation, the server control unit 312 obtains vehicle information from a vehicle detector as an external sensor arranged on the driving road in the factory. "Vehicle information" means information including at least one of the image of the vehicle 100 and the position information of the vehicle 100. As a vehicle detector, for example, a camera can be used. The camera is communicatively connected to the server 300 through wireless communication or wired communication. The camera is fixed at a position where it can shoot the vehicle 100 traveling on the driving road in the factory, and obtains the image of the vehicle 100 as vehicle information. In addition, the vehicle detector can also replace the image of the vehicle 100 or obtain the position of the vehicle 100 in addition. In the case of obtaining the position of the vehicle 100, various detectors such as LiDAR, infrared sensor, laser sensor, ultrasonic sensor, millimeter wave radar, etc. that can detect the position of the vehicle 100 are used as the vehicle detector. In addition, the "vehicle information" may also include the driving direction of the vehicle 100 or the orientation of the vehicle 100. The driving direction of the vehicle 100 and the orientation of the vehicle 100 can be obtained by detecting the shape of the vehicle 100 or the parts of the vehicle 100, for example. However, the traveling direction and orientation of the vehicle 100 may be estimated by acquiring only the position of the vehicle 100 by a vehicle detector and using the changes over time of the vehicle 100 .

[0034] The server control unit 312 generates control values ​​for each actuator while analyzing the acquired vehicle information, and uses the generated control values ​​to cause the ECU 180 to perform driving control of the vehicle 100. For example, the server control unit 312 adjusts the relative position of the vehicle 100 with respect to a target route pre-set on the travel road by analyzing the vehicle information, thereby causing the vehicle 100 to travel along the target route.

[0035] The inspection device 200 uses the travel speed detected by a device outside the vehicle 100, such as the inspection device 200, to inspect whether the vehicle 100 can travel normally by remote control. The travel speed of the vehicle 100 detected by the inspection device 200 is also referred to as "inspection-side speed" or simply as "measured value". A device provided in the inspection device 200 and detecting output related to the travel of the vehicle 100 is also referred to as an "inspection detection unit". In addition, when the inspection device 200 determines that there is an abnormality in the inspection result, it determines which of the vehicle 100, the server 300, and the inspection device 200 is abnormal.

[0036] The inspection device 200 includes a roller device 250, an inspection control device 210, and an inspection communication unit 290. The inspection communication unit 290 communicates with the server 300, the vehicle 100, and the like via the network 72.

[0037] The roller device 250 obtains the travel speed of the vehicle 100 as one form of the “output value related to the travel of the vehicle 100”. The roller device 250 includes a roller 256, a motor 252, and a speed sensor 254. Figure 1 As shown, when vehicle 100 is arranged at a position that can be inspected by inspection device 200, roller 256 is in contact with the peripheral surface of wheel 160 of vehicle 100. In this state, roller 256 rotates following the rotation of wheel 160.

[0038] The motor 252 can rotate the roller 256 at a predetermined torque and rotation speed. When the rotation direction of the wheel 160 when the vehicle 100 is moving forward is set to the forward direction, and the rotation direction when the vehicle 100 is moving backward is set to the reverse direction, the motor 252 can rotate the wheel 160 in either the forward direction or the reverse direction by switching the rotation direction of the roller 256.

[0039] The speed sensor 254 is a sensor that detects the rotation speed of the roller 256. As the speed sensor 254, for example, a rotary encoder or the like can be used. The speed sensor 254 calculates the running speed of the vehicle 100 using the detected rotation speed of the roller 256. The running speed of the vehicle 100 can also be calculated by the inspection control device 210 that obtains the rotation speed of the roller 256 from the speed sensor 254. The speed sensor 254 is one form of the "inspection detection unit".

[0040] Figure 3 2 is a block diagram showing the internal functional configuration of the inspection control device 210. The inspection control device 210 includes a CPU 212 as a central processing unit and a storage device 220. These are connected to each other via an internal bus or an interface circuit.

[0041] The storage device 220 is, for example, a RAM, a ROM, a HDD (hard disk drive), an SSD (solid state drive), etc. By executing a computer program stored in the storage device 220 by the CPU 212, the CPU 212 functions as the inspection unit 214 and the abnormality determination unit 216. However, some or all of these functions may be constituted by hardware circuits.

[0042] The maintenance information acquisition unit 218 acquires maintenance information 224 related to the maintenance performed on the inspection device 200. The maintenance information acquisition unit 218 acquires information related to maintenance manually input by an operator who has performed maintenance on the inspection device 200 as the maintenance information 224. The maintenance information acquisition unit 218 may acquire the maintenance information 224 from a management device that centrally manages the inspection device 200, the maintenance information of the inspection device 200, and the like. The acquired maintenance information 224 is stored in the storage device 220.

[0043] The inspection unit 214 uses the inspection side speed obtained by the roller device 250 to inspect whether the vehicle 100 to be inspected can travel normally by unmanned driving. When the inspection result of the inspection unit 214 shows an abnormality, the abnormality determination unit 216 executes an abnormality determination process as a processing routine for determining the cause of the abnormality. In the abnormality determination process, the abnormality determination unit 216 uses the maintenance information 224 of the inspection device 200 and the maintenance information 324 of the server 300 to determine which of the server 300, the inspection device 200, and the inspection object has an abnormality. The inspection result based on the inspection unit 214 and the determination result of the cause of the abnormality based on the abnormality determination unit 216 are stored in the storage device 220 as the inspection result 222.

[0044] Figure 4A: is a flowchart showing the processing order of the driving control of the vehicle 100 in the first embodiment. In step S1, the server 300 uses the detection result output from the sensor located outside the vehicle 100, that is, the external sensor, to obtain the vehicle position information. The vehicle position information is the position information that becomes the basis for generating the driving control signal. In the present embodiment, the vehicle position information includes the position and orientation of the vehicle 100 in the reference coordinate system of the factory. In the present embodiment, the reference coordinate system of the factory is the global coordinate system, and any position in the factory can be represented by the X, Y, and Z coordinates in the global coordinate system. In the present embodiment, the external sensor is a camera installed in the factory, and the captured image is output from the external sensor as the detection result. That is, in step S1, the server 300 uses the captured image obtained from the camera as the external sensor to obtain the vehicle position information.

[0045] In detail, in step S1, the server 300 detects the shape of the vehicle 100 from the captured image, calculates the coordinates of the positioning point of the vehicle 100 in the coordinate system of the captured image, that is, the local coordinate system, and transforms the calculated coordinates into coordinates in the global coordinate system, thereby obtaining the position of the vehicle 100. The shape of the vehicle 100 contained in the captured image can be detected by, for example, inputting the captured image into a detection model using artificial intelligence. The detection model is prepared, for example, in the system 50 or outside the system 50, and is pre-stored in the memory of the server 300. As the detection model, for example, a machine learning model that has been learned in a manner to achieve either semantic segmentation or instance segmentation can be cited. As the machine learning model, for example, a convolutional neural network (hereinafter CNN) that has been learned by supervised learning using a learning data set can be used. The learning data set, for example, has a plurality of training images containing the vehicle 100, and labels indicating whether each region in the training image is a region representing the vehicle 100 or a region other than the vehicle 100. When learning CNN, it is preferred to update the parameters of CNN by back propagation (error back propagation method) to reduce the error between the output result of the detection model and the label. In addition, the server 300 estimates the direction of the moving vector of the vehicle 100 calculated from the position change of the feature point of the vehicle 100 between the frames of the captured image, for example, using the optical flow method, so that the orientation of the vehicle 100 can be obtained.

[0046] In step S2, the server 300 determines the target position to which the vehicle 100 should go next. In the present embodiment, the target position is represented by the coordinates of X, Y, and Z in the global coordinate system. In the memory of the server 300, a reference path is pre-stored as the path that the vehicle 100 should travel. The path is represented by a node showing a departure point, a node showing a passing point, a node showing a destination, and a link connecting each node. The server 300 uses the vehicle position information and the reference path to determine the target position to which the vehicle 100 should go next. The server 300 determines the target position on the reference path that is further ahead than the current position of the vehicle 100.

[0047] In step S3, the server 300 generates a driving control signal for driving the vehicle 100 toward the determined target position. In the present embodiment, the driving control signal includes the acceleration and steering angle of the vehicle 100 as parameters. The server 300 calculates the driving speed of the vehicle 100 according to the change of the position of the vehicle 100, and compares the calculated driving speed with the target speed. In general, the server 300 determines the acceleration in a manner to accelerate the vehicle 100 when the driving speed is lower than the target speed, and determines the acceleration in a manner to decelerate the vehicle 100 when the driving speed is higher than the target speed. In addition, when the vehicle 100 is located on the reference path, the server 300 determines the steering angle and acceleration in a manner to prevent the vehicle 100 from deviating from the reference path, and when the vehicle 100 is not located on the reference path, in other words, when the vehicle 100 deviates from the reference path, determines the steering angle and acceleration in a manner to return the vehicle 100 to the reference path. In other embodiments, the driving control signal may also include the speed of the vehicle 100 as a parameter instead of or in addition to the acceleration of the vehicle 100.

[0048] In step S4, the server 300 transmits the generated travel control signal to the vehicle 100. The server 300 repeatedly acquires vehicle position information, determines a target position, generates a travel control signal, transmits the travel control signal, and the like in a predetermined cycle.

[0049] In step S5, the vehicle 100 receives the travel control signal transmitted from the server 300. In step S6, the vehicle 100 controls the actuator of the vehicle 100 using the received travel control signal, thereby causing the vehicle 100 to travel at the acceleration and steering angle indicated by the travel control signal. The vehicle 100 repeatedly receives the travel control signal and controls the actuator of the vehicle 100 at a predetermined cycle. According to the system 50 in this embodiment, the vehicle 100 can be driven by remote control, and the vehicle 100 can be moved without using a transport device such as a crane or a conveyor.

[0050] Figure 4B 1 is a flowchart showing a processing routine of the inspection method according to the first embodiment. This process starts with the inspection unit 214 detecting that the vehicle 100 to be inspected has arrived at the inspection process, or detecting that the vehicle 100 to be inspected has started self-propelled transportation to the inspection process. The arrival of the vehicle 100 at the inspection process can be obtained, for example, from the detection result of the vehicle 100 provided in the inspection process, such as a sensor or camera.

[0051] In step S10, the server control unit 312 drives the vehicle 100 automatically by unmanned driving, and places the vehicle 100 at a position where it can be inspected by the inspection device 200. That is, the server control unit 312 drives the vehicle 100 by remote control, such as Figure 1 As shown, the vehicle 100 is arranged on a roller device 250 .

[0052] In step S20, the server control unit 312 sends a command signal for starting the inspection to the inspection device 200. The inspection unit 214 that receives the command signal starts the inspection. The inspection unit 214 may also obtain vehicle identification information from the vehicle 100 to be inspected before the inspection starts, and compare the obtained vehicle identification information with the vehicle identification information of the inspection object predetermined in production management.

[0053] In step S30, the inspection unit 214 instructs the vehicle 100 to be inspected to be driven in such a manner as to achieve a driving speed predetermined as a target value. More specifically, the inspection unit 214 outputs a command signal for causing the vehicle 100 to travel at a predetermined driving speed to the server 300. The server control unit 312 that has received the command signal drives the actuator of the vehicle 100 to be inspected by remote control using unmanned driving so that the vehicle 100 automatically travels at a predetermined driving speed. Hereinafter, the "driving speed predetermined as a target value" is also referred to as the "inspection speed". The inspection speed can be set to any speed, such as 40 km / hr, 60 km / hr, etc. Step S30 is also referred to as the "first process".

[0054] In step S40, the vehicle speed acquisition unit 316 acquires the vehicle speed from the wheel speed sensor 170. If the acquired travel speed reaches the inspection speed, the server control unit 312 drives the vehicle 100 to maintain the inspection speed. In step S50, the vehicle speed acquisition unit 316 outputs to the inspection device 200 that the acquired vehicle speed has reached the inspection speed.

[0055] In step S70, the inspection unit 214 obtains the inspection side speed as a measured value from the roller device 250. Step S70 is also referred to as the "second process". In step S80, the inspection unit 214 confirms whether the difference between the inspection side speed obtained and the target value given as an instruction is within the first range. The first range can be set to any range such as plus or minus 5 km / hr, plus or minus 10 km / hr, minus 10 km / hr or more and plus or minus 5 km / hr or less. The first range can also be set in accordance with legally required conditions, etc. The first range is also referred to as the "reference range". If the difference between the inspection side speed and the target value is within the first range (S80: Yes), the inspection unit 214 moves the processing to step S84 and outputs that there is no abnormality in the inspection object.

[0056] When the difference between the inspection-side speed and the target value is outside the first range (S80: No), the inspection unit 214 moves the process to step S82. In step S82, the inspection unit 214 determines that an abnormality exists and moves the process to step S100. In step S100, the abnormality specifying unit 216 executes an abnormality specifying step.

[0057] When the inspection unit 214 determines that an abnormality exists, it is estimated that the determined abnormality is caused by any of an abnormality of the inspection device 200, an abnormality of the vehicle 100, or an abnormality of the server 300. Examples of the abnormality of the inspection device 200 include an abnormality of the roller device 250 such as the roller 256 and the speed sensor 254 not operating normally, and an abnormality of the software or hardware of the inspection control device 210. Examples of the abnormality of the vehicle 100 include a failure of the wheel speed sensor 170 and an abnormality of the ECU 180. Examples of the abnormality of the ECU 180 include an abnormality of the program stored in the storage device 186 and an abnormality of the indicated value. Examples of the abnormality of the server 300 include an abnormality of the program stored in the storage device 220, an abnormality of the control value, and an abnormality of the communication of the server communication unit 390.

[0058] Figure 5 2 is a flowchart showing a processing routine of an abnormality determination process. In step S110, the abnormality determination unit 216 obtains the maintenance information 224 of the inspection device 200 as one of the target devices and the maintenance information 324 of the server 300 as another target device. In addition, the maintenance information 224 of the inspection device 200 may also be obtained before step S170 described later. In the present embodiment, the abnormality determination unit 216 confirms the information related to the execution timing of the maintenance performed on the inspection device 200 and the server 300 in the obtained maintenance information 224 and maintenance information 324. Step S110 is also called a "maintenance information acquisition process".

[0059] In step S120, the abnormality determination unit 216 confirms whether the maintenance of the server 300 is performed within a predetermined period from the timing at which the inspection side speed is obtained by the inspection unit 214, that is, the timing at which the second process is performed. The abnormality determination unit 216 may also confirm whether the timing at which the second process is performed or the current time point is within a predetermined period from the execution timing of the maintenance of the server 300. The "predetermined period" in this case is a period during which the effect of the maintenance of the server 300 can be fully obtained. In other words, the predetermined period is a period during which it can be fully inferred that the server 300 after maintenance can operate normally. If the timing at which the second process is performed is outside the predetermined period from the execution timing of the maintenance (S120: No), the abnormality determination unit 216 moves the processing to step S130.

[0060] In step S130, the abnormality determination unit 216 performs an auxiliary check. "Auxiliary check" means that in the abnormality determination process, the normal vehicle 100 prepared in advance is used to implement the above-mentioned steps S10 to S80 to check whether there is an abnormality. However, in the "auxiliary check", at least the same steps as the first step and the second step mentioned above are included. The auxiliary check is a method of determining whether the server 300 has an abnormality.

[0061] The "normal vehicle 100" means a vehicle 100 in which the output value related to the driving of the vehicle 100 is normal. The normal vehicle 100 is, for example, a vehicle 100 that is driven manually without passing through the server 300 and is determined to have no abnormality by the inspection of the inspection device 200, a vehicle 100 that has just been repaired, a vehicle 100 that has just been determined to have no abnormality by the inspection device 200 that has just been repaired, or a vehicle 100 that has been determined to have no abnormality by an inspection device other than the inspection device 200 instead of the inspection device 200 or in addition to the inspection device 200, and other vehicles 100 in which it can be sufficiently estimated that the output value related to the driving of the vehicle 100 has no abnormality. The normal vehicle 100 may be any one of these vehicles 100, or may be a plurality of vehicles 100 that are arbitrarily combined among these vehicles 100. In the present embodiment, in the auxiliary inspection, the inspection device 200 is used to perform steps S10 to S80 shown in FIG. 4 to inspect whether there is any abnormality for the normal vehicle 100. The normal vehicle 100 may be a vehicle 100 as a product or a vehicle other than a product and used exclusively for inspection.

[0062] If the timing of executing the second process is within a predetermined period from the execution timing of the maintenance of the server 300 (S120: Yes), the abnormality determination unit 216 moves the processing to step S124 to determine that the server 300 does not have an abnormality. In this case, the abnormality determination unit 216 omits steps S130 and S140 and moves the processing to step S170. That is, if the second process is executed within a predetermined period from the execution timing of the maintenance, the determination that the server 300 does not have an abnormality is made on the basis of omitting the determination process, i.e., the auxiliary inspection, for determining whether the server 300 has an abnormality. In addition, the normal output process of outputting the meaning that the server 300 does not have an abnormality can also be replaced by or performed together with the omission of the auxiliary inspection. By configuring in this way, the process of determining whether the server 300 has an abnormality based on the confirmation result of the maintenance information can be simplified, so that the productivity of the inspection method involved in this embodiment is improved.

[0063] In step S140, the abnormality determination unit 216 confirms the result of the auxiliary inspection. That is, the inspection unit 214 confirms whether the difference between the inspection side speed obtained using the normal vehicle 100 and the target value is within the second range. The second range can be set to any range such as plus or minus 5 km / hr, plus or minus 10 km / hr, minus 10 km / hr or more and plus or minus 5 km / hr or less. In the present embodiment, the second range is set to the same range as the first range. However, the second range and the first range can also be set to be different from each other. For example, the inspection conditions of the auxiliary inspection can also be made stricter by setting the second range to a narrower range than the first range.

[0064] When the difference between the inspection-side speed and the target value is outside the second range and it is determined that an abnormality exists in the auxiliary inspection (S140: No), the abnormality determination unit 216 moves the process to step S150 and outputs information indicating that an abnormality exists in the server 300. Step S150 is also referred to as a "third process". In step S160, the abnormality determination unit 216 notifies the administrator of the server 300 of information indicating that an abnormality exists in the server 300 or information for urging the repair of the server 300, and ends this process.

[0065] When the difference between the inspection-side speed and the target value is within the second range and it is determined that there is no abnormality in the auxiliary inspection (S140: Yes), the abnormality determination unit 216 moves the processing to step S170. In step S170, the abnormality determination unit 216 confirms whether the maintenance of the inspection device 200 is performed within a predetermined period from the timing of the execution of the second process. The "predetermined period" in this case is a period during which the effect of the maintenance of the inspection device 200 can be fully obtained. In other words, the predetermined period is a period during which it can be fully inferred that the inspection device 200 after maintenance can operate normally. If the timing of the execution of the second process is outside the predetermined period from the timing of the execution of the maintenance (S170: No), the abnormality determination unit 216 moves the processing to step S180.

[0066] In step S180, the abnormality specifying unit 216 performs a subsequent inspection using a plurality of vehicles 100 different from the inspection target vehicle 100. The "subsequent inspection" means that a plurality of vehicles 100 different from the inspection target vehicle 100 and normal vehicles 100 are used to perform the subsequent inspection. Figure 4B The following steps S10 to S80 are used to check whether there is an abnormality. The subsequent inspection is a method of determining whether there is an abnormality in the inspection device 200. The subsequent inspection process only needs to include at least the first step and the second step.

[0067] The plurality of vehicles 100 used in the subsequent inspection process are preferably the plurality of vehicles 100 that are scheduled to be inspected successively after the vehicle 100 to be inspected. By making the subsequent inspection of the plurality of vehicles 100 also serve as the normal inspection of the plurality of vehicles 100, it is possible to suppress the reduction in productivity of the inspection process caused by the subsequent inspection. In addition, the number of the plurality of vehicles 100 used in the subsequent inspection can be predetermined to be any number greater than 2. From the perspective of improving the inspection accuracy, the number of vehicles 100 is preferably large.

[0068] If the timing of executing the second process is within a predetermined period from the execution timing of the maintenance of the inspection device 200 (S170: Yes), the abnormality determination unit 216 moves the processing to step S174 to determine that the inspection device 200 does not have an abnormality. In this case, the abnormality determination unit 216 omits steps S180 and S190 and moves the processing to step S220. That is, if the second process is executed within a predetermined period from the execution timing of the maintenance, the determination that the inspection device 200 does not have an abnormality is made on the basis of omitting the determination process for determining whether the inspection device 200 has an abnormality, that is, the subsequent inspection. In addition, a normal output process that outputs that the inspection device 200 does not have an abnormality may be performed instead of or together with the omission of the subsequent inspection. By configuring in this way, the process of determining whether the inspection device 200 has an abnormality based on the confirmation result of the maintenance information can be simplified, and the productivity of the inspection method involved in this embodiment can be improved.

[0069] In step S190, the results of the inspection based on the plurality of vehicles 100 are confirmed. In the subsequent inspection, if the difference between the obtained inspection side speed and the indicated target value in at least one of the plurality of vehicles 100 is outside the third range (S190: No), the abnormality determination unit 216 moves the processing to step S200, and outputs that the inspection device 200 has an abnormality. The third range can be set to any range such as plus or minus 5 km / hr, plus or minus 10 km / hr, minus 10 km / hr or more and plus or minus 5 km / hr or less. In the present embodiment, the third range is set to the same range as the first range. However, the third range and the first range may also be set to be different from each other. For example, the inspection conditions of the subsequent inspection may be made stricter by setting the third range to a narrower range than the first range. In step S210, the abnormality determination unit 216 notifies the manager of the inspection device 200, etc., of information indicating that the inspection device 200 has an abnormality, or information urging the inspection device 200 to be repaired.

[0070] In step S190, in the subsequent inspection, when the difference between the obtained inspection-side speed and the target value given as an instruction is within the third range in all vehicles 100 of the plurality of vehicles 100 (S190: Yes), the abnormality determination unit 216 moves the process to step S220, and outputs information indicating that the inspection target vehicle 100 has an abnormality. Step S220 is also referred to as a "fourth process". In step S230, the server control unit 312 causes the inspection target vehicle 100 to travel from the inspection process to the repair process where the vehicle 100 can be repaired, by remote control, and ends this process.

[0071] As described above, the inspection method according to the present embodiment includes: a maintenance information acquisition step of acquiring maintenance information 224 and maintenance information 324 related to the history of maintenance performed on the server 300 and the inspection device 200; and an abnormality determination step of determining which of the server 300, the inspection device 200, and the inspection target vehicle 100 has an abnormality using the acquired maintenance information 224 and 324 when the difference between the inspection-side speed and the target value is not within a predetermined reference range. Therefore, in the inspection of the vehicle 100 that can be driven by remote control using the server 300 and the inspection device 200, it is possible to determine with high reliability which of the inspection target vehicle 100, the inspection device 200, and the server 300 has an abnormality as the cause of the abnormality.

[0072] According to the inspection method of this embodiment, the abnormality identification unit 216 confirms information related to the execution timing of the maintenance performed on the server 300 and the inspection device 200 as maintenance information. The cause of the abnormality can be determined by a simple method of confirming the execution timing of the maintenance. In addition, by using the effect of the maintenance on the device to determine the cause of the abnormality, the determination of the cause of the abnormality can be simplified.

[0073] According to the inspection method of this embodiment, in the abnormality determination step, when the timing of executing the second step is within a predetermined period from the execution timing of the maintenance of the server 300 and the inspection device 200, it is determined that there is no abnormality in the server 300 and the inspection device 200 on which maintenance is executed. Therefore, auxiliary inspections and subsequent inspections can be omitted based on maintenance information, and the abnormality determination step can be simplified while the effect of maintenance on the device is obtained.

[0074] B. Second Implementation Method: Figure 6 1 is a block diagram showing the internal functional structure of the inspection control device 210b that executes the inspection method according to the second embodiment. The inspection control device 210b is different from the inspection control device 210 shown in the first embodiment in that it includes a storage device 220b storing a learned model 226 instead of the storage device 220, and the other structures are the same as the inspection control device 210.

[0075] The learned model 226 is a machine learning model for abnormality detection. The learned model 226 outputs the abnormality probability of the inspection device 200, server 300, and inspection object by inputting the inspection input / output data and maintenance information of the inspection device 200, server 300, and inspection object into the learned model 226.

[0076] The learned model 226 is, for example, a machine learning model that utilizes a neural network (NN). For a machine learning model, for example, a model having a structure such as a recursive neural network (RNN), a convolutional neural network (CNN), a generalized regression neural network (General Regression Neural Network), or a random forest (Random Forest) is suitable. In the present embodiment, a learning model of an RNN having a recursive structure such as a long short-term memory (LSTM) capable of long-term time series analysis is adopted. For a machine learning model, it can also be a machine learning model that utilizes algorithms such as the k-nearest neighbor method, Hotelling theory, LOF method (local deviation factor method), and naive Bayes method instead of a neural network. In addition, for the prediction of abnormal probability, it is not limited to machine learning, and various techniques such as regression analysis such as multivariate regression analysis and multivariate analysis can also be used.

[0077] The learning model 226 is learned using the past data of the input and output data of the inspection device 200, the server 300, and the inspection object, the past data of the inspection results 222 of the inspection system 500 corresponding to them, the past data related to the maintenance information, and the past data related to the normality or abnormality of the server 300, the inspection device 200, and the inspection object. As the learning method of the neural network, it is preferable to use a support vector machine (SVM) and an error back propagation method (Backpropagation). In addition, it is not limited to both the input data and the output data of each device, and only one of the input data and the output data can be input to the machine learning model. By inputting the input and output data and maintenance information of the inspection device 200, the server 300, and the inspection object during the inspection into the learning model 226, the abnormality probability of each of the inspection device 200, the server 300, and the inspection object is output. At this time, for example, if it is within a predetermined period from the execution timing of the maintenance, the probability that the device on which the maintenance is performed does not have an abnormality is higher than the probability in the period when the maintenance is not performed.

[0078] Figure 7is a flowchart showing a processing routine of the abnormality determination process involved in the second embodiment. In step S300, the machine learning model is trained using the past data of the input and output data of the inspection device 200, the server 300, and the inspection object, the past data of the inspection result 222 of the inspection system 500 corresponding to them, the past data related to the maintenance information, and the past data related to the normality or abnormality of the server 300, the inspection device 200, and the inspection object. Step S300 is also called a "learning process". The learning process can also be implemented in advance independently of the abnormality determination process.

[0079] In step S302, the abnormality specifying unit 216 inputs the input and output data of the inspection object into the learned model 226. The input and output data of the inspection object are, for example, the number of revolutions of the motor 140 of the vehicle 100 during the inspection, the vehicle speed data 322 obtained from the wheel speed sensor 170, the control value of each actuator of the vehicle 100 by the driving control unit 184, the output value of each actuator, etc. Figure 4B Various input and output data obtained from the vehicle 100 during the inspection shown. Alternatively, only factors significant to the inspection result may be extracted from the various input and output data obtained from the vehicle 100.

[0080] In step S310, the abnormality identification unit 216 inputs the input and output data of the server 300 into the learned model 226. The input and output data of the server 300 are control values, inspection time, vehicle speed data 322, etc. sent from the server 300 to the vehicle 100 during remote control during inspection. Figure 4B Various input and output data obtained from the server 300 in the inspection shown. In addition, only factors meaningful to the inspection result may be extracted from the various input and output data obtained from the server 300.

[0081] In step S320, the abnormality identification unit 216 inputs the input and output data of the inspection device 200 to the learned model 226. The input and output data of the inspection device 200 are the inspection side speed obtained from the roller device 250, the torque, rotation speed, and speed of the motor 252 and roller 256 during the inspection, the inspection time, and the inspection result 222. Figure 4B Various input and output data obtained from the inspection device 200 in the inspection shown. In addition, only factors meaningful to the inspection result may be extracted from the various input and output data obtained from the inspection device 200.

[0082] In step S330, the abnormality specifying unit 216 acquires the maintenance information 224 and 324 and inputs the acquired information into the learned model 226. Only factors of the maintenance information 224 and 324 that are significant to the inspection result may be extracted and input into the learned model 226.

[0083] In step S340, the learned model 226 outputs the abnormality probability of each of the inspection device 200, the server 300, and the inspection target vehicle 100 based on the data input in the above steps S302 to S330. In step S350, the abnormality determination unit 216 compares each abnormality probability with a predetermined threshold value to determine the cause of the abnormality. For example, the abnormality determination unit 216 determines the device or inspection target whose abnormality probability is greater than the predetermined threshold value as the cause of the abnormality.

[0084] As described above, the inspection method according to the present embodiment further includes a learning step of learning the machine learning model using past data related to the input and output of the server 300, past data related to the input and output of the inspection device 200, past data related to the maintenance information 324, and past data related to the normality or abnormality of the server 300, the inspection device 200, and the vehicle 100 to be inspected. In the abnormality identification step, the learned model 226 is used to identify which of the server 300, the inspection device 200, and the vehicle 100 to be inspected has an abnormality. Therefore, by using the learned model 226, the productivity of the abnormality identification step and the accuracy of identifying the cause of the abnormality can be improved.

[0085] C. Third Implementation Method: Figure 8 1 is a flowchart showing a processing routine of an abnormality determination process of the inspection method according to the third embodiment. In this embodiment, the abnormality determination process is different from the abnormality determination process of the inspection method according to the first embodiment in that steps S120 and S170 are replaced with steps S120c and S170c, and steps S122 and S172 are also included. In the first embodiment described above, an example is shown in which the execution timing of maintenance performed in the maintenance information is used to determine the cause of the abnormality. In contrast, in this embodiment, information related to whether an abnormality of the server 300 and the inspection device 200 is detected during maintenance in the maintenance information is used to determine the cause of the abnormality.

[0086] In step S120c, the abnormality determination unit 216 checks the maintenance information to determine whether the maintenance information includes information indicating that an abnormality was detected in the server 300 during maintenance. In this case, the "abnormality" may not include a minor abnormality to the extent that the function of the server 300 is not impaired. In addition, the maintenance for which the abnormality is detected is not limited to all maintenance performed in the past, but may be only maintenance within a specified period, the latest maintenance, or maintenance performed a specified number of times in the past.

[0087] If the maintenance information does not include information indicating that an abnormality of server 300 is detected during maintenance (S120c: No), abnormality specifying unit 216 moves the process to step S130. If the maintenance information includes information indicating that an abnormality of server 300 is detected during maintenance (S120c: Yes), abnormality specifying unit 216 moves the process to step S122.

[0088] In step S122, the abnormality determination unit 216 further checks the maintenance information 324 to determine whether the cause of the abnormality detected in step S120c has been eliminated. "The cause of the abnormality has been eliminated" means that the cause of the abnormality has been determined, and the determined cause has been eliminated, and it has become a state that can be fully inferred that the target device can operate normally. For example, when an abnormality caused by a failure of a component is detected during maintenance, when the failed component is replaced with a new one, etc., it is consistent with the state that the component that caused the abnormality has been eliminated.

[0089] When the maintenance information does not include information indicating that the cause of the abnormality of the server 300 has been eliminated (S122: No), the abnormality specifying unit 216 moves the process to step S150 and outputs information indicating that there is an abnormality in the server 300. That is, the abnormality outputting step of outputting information indicating that there is an abnormality in the server 300 is performed without omitting the auxiliary inspection, which is a determining step for determining whether there is an abnormality in the server 300.

[0090] When the maintenance information includes information indicating that the cause of the abnormality of the server 300 has been removed (S122: Yes), the abnormality determination unit 216 moves the process to step S130 to perform an auxiliary check. In other words, although the maintenance was performed on the server 300, an abnormality was detected during the maintenance, so the auxiliary check is performed to confirm whether the server 300 has an abnormality. However, this is not limited to this. In the case where the abnormality of the server 300 has been removed and it can be fully inferred that the server 300 is operating normally, the abnormality determination unit 216 can also determine that there is no abnormality in the server 300, and move the process to step S170c on the basis of omitting the auxiliary check.

[0091] In step S170c, the abnormality specifying unit 216 checks the maintenance information to confirm whether the maintenance information includes information indicating that an abnormality is detected in the inspection device 200 during maintenance. In this case, the "abnormality" may not include a minor abnormality to the extent that the function of the inspection device 200 is not impaired. If the maintenance information does not include information indicating that an abnormality of the inspection device 200 is detected during maintenance (S170c: No), the abnormality specifying unit 216 moves the process to step S180. If the maintenance information includes information indicating that an abnormality of the inspection device 200 is detected during maintenance (S170c: Yes), the abnormality specifying unit 216 moves the process to step S172.

[0092] In step S172, the abnormality determination unit 216 further checks the maintenance information 224 to check whether the cause of the abnormality detected in step S170c has been eliminated. If the cause of the abnormality of the inspection device 200 has not been eliminated (S172: No), the abnormality determination unit 216 moves the process to step S200 and outputs that the inspection device 200 has an abnormality. That is, the abnormality output process of outputting information indicating that the inspection device 200 has an abnormality is executed on the basis of omitting the determination process for determining whether the inspection device 200 has an abnormality, that is, the subsequent inspection process.

[0093] When the maintenance information includes information that the cause of the abnormality of the inspection device 200 has been eliminated (S172: Yes), the abnormality determination unit 216 moves the process to step S180 to perform a subsequent inspection process. In other words, although the inspection device 200 has been maintained, an abnormality is detected during the maintenance, so the presence or absence of the abnormality of the inspection device 200 is confirmed through the subsequent inspection process. However, this is not limited to this. In the case where the abnormality of the inspection device 200 has been eliminated and it can be sufficiently inferred that the inspection device 200 is operating normally, the abnormality determination unit 216 may also determine that there is no abnormality in the inspection device 200, and move the process to step S220 on the basis of omitting the subsequent inspection process.

[0094] As described above, according to the inspection method of this embodiment, the abnormality specifying unit 216 confirms, as maintenance information, information related to whether an abnormality is detected in at least one of the devices during maintenance of the server 300 and the inspection device 200. By using this simple method of confirming whether an abnormality is detected during maintenance, the cause of the abnormality can be specified with high reliability.

[0095] According to the inspection method of this embodiment, in the abnormality determination step, when the maintenance information includes information indicating that an abnormality of any target device in the server 300 and the inspection device 200 is detected during maintenance, and also includes information that a component that is the cause of the abnormality of any target device in which the abnormality is detected has been replaced, a determination step of determining a device in which the component that is the cause of the abnormality has been replaced is performed. Even if an abnormality is detected during maintenance, if the cause of the abnormality has been removed, the device may not be abnormal. Therefore, it is possible to perform appropriate determination of the cause of the abnormality in consideration of the fact that the abnormality during maintenance has been repaired.

[0096] D. Fourth Implementation Method: Fig. 91 is a flowchart showing a processing routine of an abnormality determination process of the inspection method according to the fourth embodiment. In this embodiment, the abnormality determination process is different from the abnormality determination process of the inspection method according to the first embodiment in that steps S120 and S170 are replaced with steps S120d and S170d. In the first embodiment, an example of using the execution timing of the maintenance performed in the maintenance information is shown. In contrast, in this embodiment, information related to whether the abnormality of the server 300 and the inspection device 200 is continuously or intermittently detected during maintenance is used in the maintenance information.

[0097] In step S120d, the abnormality determination unit 216 confirms the maintenance information to confirm whether the maintenance information includes information indicating that an abnormality is continuously or intermittently detected in the server 300 during maintenance. "Continuously detecting an abnormality" means that an abnormality is continuously detected in maintenance times greater than or equal to a predetermined first threshold value of 2 or more. The first threshold value can be set using any number of times that the probability that the device being the object has an abnormality is sufficiently high. "Intermittently detecting an abnormality" means that an abnormality is detected more than or equal to a predetermined second threshold value of 2 or more during a predetermined period or a predetermined number of maintenance times. The predetermined period, number of times and the second threshold value can be set using any period, number of times that the probability that the device being the object has an abnormality is sufficiently high. In addition, the "continuously or intermittently detected abnormality" in this case may not include an abnormality that is so minor that the function of the server 300 is not impaired. The continuously or intermittently detected abnormality may include both the case where the same abnormality is detected continuously or intermittently and the case where different abnormalities are detected continuously or intermittently.

[0098] If the maintenance information does not include information indicating that a continuous or intermittent abnormality of the server 300 was detected during maintenance (S120d: No), the abnormality determination unit 216 moves the processing to step S130. In the case where the maintenance information includes information indicating that a continuous or intermittent abnormality was detected (S120d: Yes), the abnormality determination unit 216 moves the processing to step S150 and executes output of information indicating that an abnormality exists in the server 300. In other words, with respect to a device in which a continuous or intermittent abnormality is detected, it is presumed that there is a high possibility that the abnormality of the device has occurred again, and an auxiliary inspection or subsequent inspection as a determination process is omitted, and an abnormality output process of outputting information indicating that an abnormality exists in the device is executed. In addition, in the present embodiment, it is preferably not applied as follows. Figure 8 The abnormality has been eliminated as shown in step S122.

[0099] In step S170d, similarly to step S120d, the abnormality determination unit 216 checks the maintenance information to determine whether the maintenance information includes information indicating that an abnormality is continuously or intermittently detected in the inspection device 200 during maintenance. The "abnormality detected continuously or intermittently" in this case may not include abnormalities that are so minor that the function of the inspection device 200 is not impaired. In addition, the abnormality detected continuously or intermittently may include both the case where the same abnormality is detected continuously or intermittently and the case where different abnormalities are detected continuously or intermittently.

[0100] If the maintenance information does not include information indicating that a continuous or intermittent abnormality of the inspection device 200 is detected during maintenance (S170d: No), the abnormality determination unit 216 moves the process to step S180. If the maintenance information includes information indicating that a continuous or intermittent abnormality is detected (S170d: Yes), the abnormality determination unit 216 moves the process to step S200 and outputs that the inspection device 200 has an abnormality. In addition, in the present embodiment, it is preferable not to apply the following Figure 8 The abnormality has been eliminated as shown in step S172.

[0101] As described above, according to the inspection method of this embodiment, the abnormality specifying unit 216 confirms, as maintenance information, information related to whether an abnormality of at least one of the target devices is detected continuously or intermittently during maintenance of the server 300 and the inspection device 200. By using a simple method of confirming whether there is a continuous or intermittent abnormality during maintenance, the cause of the abnormality can be specified with high reliability.

[0102] According to the inspection method of this embodiment, in the abnormality determination step, when the maintenance information includes information that an abnormality is detected continuously or intermittently in any target device of the server 300 and the inspection device 200 during maintenance, an output is performed indicating that an abnormality exists in the device in which the abnormality is detected. Therefore, by using a simple method of confirming whether there is a continuous or intermittent abnormality during maintenance, the determination step can be omitted, and the abnormality determination step can be simplified.

[0103] E. Fifth Implementation Method: Fig.10 1 is a flowchart showing a processing routine of the inspection method according to the fifth embodiment. In the inspection method of the first embodiment, an example of inspecting an abnormality related to the running speed of the vehicle 100 is shown, but in the inspection method of this embodiment, it is inspected whether the brake 162 of the vehicle 100 is operating properly. Fig.10 As shown, this process is similar to Figure 4BThe inspection method of the first embodiment shown in the figure is different in that steps S30, S50, S70, S80 are replaced with steps S30e, S50e, S70e, S80e, step S72 is further included, and step S40 is not included. In addition, this process can also be continuously executed after the inspection in the first embodiment is completed, while the vehicle 100 is placed in the inspection device 200. In this case, steps S10 and S20 of this process can be omitted.

[0104] In step S30e, the inspection unit 214 gives an instruction to the vehicle 100 to be inspected to operate the brake 162 as a stop unit to stop the rotation of the wheel 160, that is, to stop the running action of the vehicle 100. More specifically, the inspection unit 214 outputs a command signal for operating the brake 162 to achieve a braking force that is a predetermined target value to the server 300. The server control unit 312 that has received the command signal operates the brake 162 of the vehicle 100 to be inspected to achieve a predetermined braking force through remote control to stop the running action of the vehicle 100. Step S30e is also referred to as a "stop instruction process".

[0105] In step S50e, the server control unit 312 outputs information indicating that the brake 162 is actuated according to the target value to the inspection device 200. In step S70e, the inspection unit 214 drives the motor 252 of the roller device 250 to rotate the roller 256. Specifically, the inspection unit 214 rotates the roller 256 in contact with the wheel 160, and applies an external force to the wheel 160 for rotating the wheel 160 in the forward direction. The "external force for rotating the wheel 160 in the forward direction" refers to, for example, a force applied to the outer periphery of the roller 256 by the motor 252, or a torque of the roller 256 corresponding to the force. The inspection unit 214 increases the torque of the roller 256 in stages until the rotation of the wheel 160 is detected by the speed sensor 254 or the like.

[0106] In step S72, when roller 256 rotates, inspection unit 214 detects the rotation of roller 256, that is, the rotation of wheel 160, through speed sensor 254. Inspection unit 214 acquires the torque applied to roller 256 at the timing of detecting the rotation of wheel 160. Steps S70e and S72 are also referred to as "external force acquisition process".

[0107] In step S80e, it is checked whether the difference between the torque applied to the roller 256 at the timing of detecting the rotation of the wheel 160 and the torque corresponding to the braking force as the target value is within a predetermined target external force range. If it is torque, the target external force range can be set to plus or minus 5 Nm (Newton meter), etc., and if it is external force, the target external force range can be set to an arbitrary range such as plus or minus 5 N (Newton). In step S80e, it can be checked whether the brake 162 applies the braking force according to the target value to the wheel 160. It is also possible to check the defect that the wheel 160 does not rotate when the brake 162 is in operation but a predetermined external force is applied.

[0108] If the difference between the torque applied to the roller 256 and the torque corresponding to the braking force as the target value is within the target external force range (S80e: Yes), the inspection unit 214 moves the process to step S84 and outputs that there is no abnormality. If the difference between the torque applied to the roller 256 and the torque corresponding to the braking force as the target value is outside the target external force range (S80e: No), the inspection unit 214 moves the process to step S82, determines that there is an abnormality, and moves the process to step S100e to execute the abnormality determination step according to the second embodiment.

[0109] Fig.11 1 is a flowchart showing a processing routine of the abnormality determination step in the inspection method according to the fifth embodiment. In this embodiment, the abnormality determination step shown in the first embodiment is different in that step S140 is replaced by step S140e and step S190 is replaced by step S190e, but is otherwise the same as that shown in the first embodiment.

[0110] In step S140e, the result of the inspection based on the normal vehicle 100 is confirmed. More specifically, using the normal vehicle 100, the Fig.10 Steps S10 to S80e are shown. It is checked for a plurality of vehicles 100 whether the difference between the torque applied to the roller 256 and the torque corresponding to the braking force as the target value is within the auxiliary target external force range. The auxiliary target external force range can be set in the same manner as the target external force range. In the present embodiment, the auxiliary target external force range is the same range as the target external force range. If the difference between the torque of the roller 256 and the torque of the target value in a normal vehicle 100 is outside the auxiliary target external force range (S140e: No), the process moves to step S170, and information indicating that an abnormality exists in the server 300 is output.

[0111] In step S190e, the results of the inspection based on the plurality of vehicles 100 are confirmed. More specifically, the plurality of vehicles 100 are used to perform Fig.10If the difference between the torque of the roller 256 and the target value is within the predetermined subsequent target external force range in all the vehicles 100 (S190e: Yes), the process proceeds to step S220 to output information indicating that the inspection object has an abnormality.

[0112] If the difference between the torque of the roller 256 and the torque of the target value is outside the predetermined subsequent target external force range in at least one of the plurality of vehicles 100 (S190e: No), the process proceeds to step S200 to output information indicating that an abnormality exists in the inspection device 200. In the present embodiment, the subsequent target external force range is set to the same range as the target external force range.

[0113] As described above, according to the inspection method of this embodiment, in the inspection of the brake 162 of the vehicle 100 traveling by remote control, as in the first embodiment, it is possible to identify the cause of the abnormality as the vehicle 100 to be inspected, the inspection device 200, and the server 300. In addition, in the inspection of the brake 162, as in the first embodiment, the abnormality identification process can be simplified by using maintenance information, so that productivity can be improved.

[0114] F. Other implementation methods: (F1) In the above-mentioned embodiments, an example is shown in which maintenance information related to the results of maintenance performed on both the server 300 and the inspection device 200 and the history of the maintenance is used. On the other hand, maintenance information related to the results of maintenance performed on either the server 300 or the inspection device 200 and the history of the maintenance may be used.

[0115] (F2) In the third embodiment described above, an example of an inspection method including steps S122 and S172 is shown. In contrast, either step S122 or step S172 may be omitted, or both step S122 and step S172 may be omitted. When step S122 is omitted, if the maintenance information includes information indicating that an abnormality of the server 300 is detected during maintenance (S120c: Yes), the abnormality determination unit 216 determines that an abnormality exists in the server 300, and the process proceeds to step S150. When step S172 is omitted, if the maintenance information includes information indicating that an abnormality of the inspection device 200 is detected during maintenance (S170c: Yes), the abnormality determination unit 216 determines that an abnormality exists in the inspection device 200, and the process proceeds to step S150.

[0116] According to the inspection method configured in this way, in the abnormality determination step, when the maintenance information includes information indicating that an abnormality is detected in any of the server 300 and the inspection device 200 during maintenance, the determination step for determining whether an abnormality exists in the device in which the abnormality is detected is omitted, and a determination is made that the device in which the abnormality is detected has an abnormality. Therefore, the abnormality determination step can be simplified by a simple method of confirming whether an abnormality exists during maintenance.

[0117] (F3) In the above-mentioned embodiments, the inspection method for inspecting whether the running speed of the vehicle 100 and the brake 162 of the vehicle 100 are appropriate is described as an example. In contrast, the present disclosure can also be applied to an inspection method for inspecting the appropriateness of detection values ​​of various detectors provided on the vehicle 100, such as an acceleration sensor, a sensor for detecting the state of charge of the battery 120, and a sensor for detecting the distance between the vehicle 100 and an external target object.

[0118] (F4) In the above embodiment, an example is shown in which, in step S180, as a plurality of vehicles 100 different from the inspection target, a plurality of vehicles 100 scheduled to be inspected successively after the inspection target vehicle 100 is used. On the other hand, a plurality of vehicles 100 arbitrarily extracted and not related to the inspection schedule may be used.

[0119] (F5) In the above-mentioned embodiments, the CPU 310 of the server 300 is shown as an example in which the server control unit 312, the maintenance information acquisition unit 314, the vehicle speed acquisition unit 316, and the vehicle information acquisition unit 318 function. On the other hand, all or part of the functions of the server control unit 312, the maintenance information acquisition unit 314, the vehicle speed acquisition unit 316, and the vehicle information acquisition unit 318 may be realized by the CPU 212 of the inspection control device 210.

[0120] (F6) In the first embodiment, an example is shown in which the subsequent inspection process is performed when the difference between the inspection-side speed obtained in the normal vehicle 100 and the target value is outside the second range in the auxiliary inspection. In contrast, the subsequent inspection process may be omitted. In this case, a process may be provided for outputting that an abnormality exists in either the inspection object or the inspection device 200 or that an abnormality does not exist in the server 300 when the difference between the inspection-side speed obtained in the normal vehicle 100 and the target value is within the second range in step S140.

[0121] (F7) In the first embodiment, when the inspection object is abnormal, the inspection object is moved to a place where the inspection object can be repaired by remote control. In contrast, when the inspection object is abnormal, other processing such as notification to the manager may be performed instead of or in addition to the movement of the inspection object by remote control.

[0122] (F8) In the above-mentioned embodiments, examples are shown in which the vehicle 100 is a passenger car, a truck, a bus, and an engineering vehicle. However, the vehicle 100 is not limited thereto, and may also include various automobiles such as a two-wheeled vehicle and a four-wheeled vehicle, a tram, and the like. In addition, various mobile bodies other than the vehicle 100 may also be used. "Mobile body" means an object that can move. Mobile bodies include, for example, electric vertical take-off and landing aircraft (so-called flying cars), ships, airplanes, robots, linear motor vehicles, and the like. In this case, the expressions "vehicle" and "car" in the present disclosure may be appropriately replaced with "mobile body", and the expression "driving" may be appropriately replaced with "moving". In addition, the inspection device 200 detects the moving action of the moving part that moves the mobile body instead of the rotation of the wheels 160, and obtains the inspection side speed of the moving mobile body.

[0123] (F9) In each of the above-mentioned embodiments, the vehicle 100 only needs to have a structure capable of moving by unmanned driving, for example, it may also be in the form of a platform having the structure described below. Specifically, in order for the vehicle 100 to perform the three functions of "driving", "turning" and "stopping" by unmanned driving, it is sufficient to have at least a control device (server) for controlling the driving of the vehicle 100 and actuators such as a drive device, a steering device and a braking device. In the case where the vehicle 100 obtains information from the outside for unmanned driving, the vehicle 100 may also have a communication device. That is, the vehicle 100 that can move by unmanned driving may not be equipped with at least a part of the internal parts such as the driver's seat and the instrument panel, may not be equipped with at least a part of the external parts such as the bumper and the fender, and may not be equipped with a body shell. In this case, the remaining parts such as the body shell may be assembled to the vehicle 100 before the vehicle 100 is shipped from the factory, or the remaining parts such as the body shell may be assembled to the vehicle 100 after the vehicle 100 is shipped from the factory in a state where the remaining parts such as the body shell are not assembled to the vehicle 100. Each part may be assembled from any direction such as the upper side, the lower side, the front side, the rear side, the right side, or the left side of the vehicle 100, and may be assembled from the same direction or from different directions. In addition, the position of the stand may be determined in the same manner as the vehicle 100 in the first embodiment.

[0124] (F10) In the inspection method of each embodiment described above, an example of omitting the auxiliary inspection and the subsequent inspection and an example of executing the normal output process in the case of a predetermined period from the acquired maintenance execution timing in the abnormality determination process are shown. On the other hand, the auxiliary inspection and the subsequent inspection may be omitted regardless of the maintenance execution timing, and the normal output process may be executed based on the execution of maintenance.

[0125] (F11) In the inspection method of the third embodiment, the abnormality determination step includes an example of an abnormality output step of outputting that the device in which the abnormality is detected has an abnormality, after omitting the auxiliary inspection and the subsequent inspection, when an abnormality is detected in any of the server 300 and the inspection device 200 during maintenance. On the other hand, if the inspection method uses the learned model 226 as in the second embodiment, the omission of the determination step and the abnormality output step may not be performed.

[0126] (F12) In the inspection method of the fourth embodiment, the abnormality determination step includes an example of an abnormality output step of outputting that the device in which the abnormality is detected is abnormal, after omitting auxiliary inspection and subsequent inspection, when an abnormality of any device in the server 300 and the inspection device 200 is continuously or intermittently detected during maintenance. On the other hand, if the inspection method uses the learned model 226 as in the second embodiment, the omission of the determination step and the abnormality output step may not be performed.

[0127] (F13) In the above-mentioned embodiments, the external sensor is not limited to a camera, and may be, for example, a distance measuring device. The distance measuring device is, for example, LiDAR (Light Detection And Ranging). In this case, the detection result output by the external sensor may also be three-dimensional point cloud data representing the vehicle 100. In this case, the server 300 and the vehicle 100 may also obtain the vehicle position information by template matching using the three-dimensional point cloud data as the detection result and the reference point cloud data prepared in advance.

[0128] (F14) In the first embodiment described above, the server 300 automatically generates a travel control signal to be sent to the vehicle 100. Alternatively, the server 300 may generate a travel control signal to be sent to the vehicle 100 in accordance with an operation of an external operator located outside the vehicle 100. For example, the external operator may operate an operating device including a display for displaying a captured image output from an external sensor, a steering wheel for remotely operating the vehicle 100, an accelerator pedal, a brake pedal, and a communication device for communicating with the server 300 via wired communication or wireless communication, and the server 300 may generate a travel control signal in accordance with the operation applied to the operating device.

[0129] (F15) The vehicle 100 can be manufactured by combining a plurality of modules. A module means a unit composed of one or more parts that are assembled according to the structure and function of the vehicle 100. For example, the rack of the vehicle 100 can be manufactured by combining a front module that constitutes the front part of the rack, a central module that constitutes the central part of the rack, and a rear module that constitutes the rear part of the rack. In addition, the number of modules that constitute the rack is not limited to 3, and may be less than 2 or more than 4. In addition, in addition to the rack, a part of the vehicle 100 that is different from the rack may also be modularized, or a part of the vehicle 100 that is different from the rack may be modularized instead of the rack. In addition, various modules may also include any exterior parts such as bumpers and grilles, and any interior parts such as seats and consoles. In addition, not limited to the vehicle 100, any type of mobile body may be manufactured by combining a plurality of modules. Such a module may be manufactured, for example, by joining a plurality of parts by welding or fixings, or may be manufactured by integrally molding at least a portion of the module into one part by casting. The molding method of integrally molding at least a part of a module as a single part is also called Giga-casting or Mega-casting. By using Giga-casting, various parts of a moving body that were previously formed by joining multiple parts can be formed into a single part. For example, the front module, the center module, and the rear module mentioned above can also be manufactured using Giga-casting.

[0130] (F16) Transporting the vehicle 100 by driving the unmanned vehicle 100 is also referred to as "self-propelled transport". In addition, the structure for realizing self-propelled transport is also referred to as "vehicle remote control autonomous driving transport system". In addition, the production method of producing the vehicle 100 by self-propelled transport is also referred to as "self-propelled production". In self-propelled production, for example, in a factory that manufactures the vehicle 100, at least a part of the transportation of the vehicle 100 is realized by self-propelled transport.

[0131] The control unit and method thereof described in the present disclosure may be implemented by a special-purpose computer provided by constituting a processor and a memory, the processor being programmed in a manner to execute one or more functions embodied by a computer program. Alternatively, the control unit and method thereof described in the present disclosure may be implemented by a special-purpose computer provided by constituting a processor by one or more special-purpose hardware logic circuits. Alternatively, the control unit and method thereof described in the present disclosure may also be implemented by one or more special-purpose computers, the one or more special-purpose computers being composed of a combination of a processor and a memory programmed in a manner to execute one or more functions, and a processor constituted by one or more hardware logic circuits. In addition, the computer program may also be stored in a computer-readable non-temporary tangible recording medium as instructions executed by a computer.

[0132] The present disclosure is not limited to the above-mentioned embodiments, and can be implemented in various configurations within the scope of the main purpose. For example, the technical features in the embodiments corresponding to the technical features in each method recorded in the "Contents of the Invention" column can be appropriately replaced or combined in order to solve part or all of the above-mentioned problems, or to achieve part or all of the above-mentioned effects. In addition, as long as the technical feature is not described as a necessary part in this specification, it can be appropriately deleted. Description of Reference Numerals

[0133] 70 ... access point, 72 ... network, 100 ... vehicle, 120 ... battery, 140 ... motor, 150 ... power receiving device, 160 ... wheel, 162 ... brake, 170 ... wheel speed sensor, 180 ... ECU, 182 ... CPU, 184 ... driving control unit, 186 ... storage device, 188 ... vehicle speed data, 190 ... vehicle communication unit, 200 ... inspection device, 210, 210b ... inspection control device, 212 ... CPU, 214 ... inspection unit, 216 ... abnormality determination unit, 218 ... maintenance information acquisition unit, 220 , 220b…storage device, 222…inspection result, 224…maintenance information, 226…learning completed model, 250…roller device, 252…motor, 254…speed sensor, 256…roller, 290…inspection communication unit, 300…server, 310…CPU, 312…server control unit, 314…maintenance information acquisition unit, 316…vehicle speed acquisition unit, 318…vehicle information acquisition unit, 320…storage device, 322…vehicle speed data, 324…maintenance information, 390…server communication unit, 500…inspection system.

Claims

1. An inspection method is a method for inspecting a mobile object that can be moved by unmanned driving, comprising: In a first step, a server is provided to instruct a moving body to be inspected to be driven so that an output value related to movement of the moving body becomes a predetermined target value; The second step is to measure the output value using an inspection device for inspecting the movable body to obtain a measured value; a maintenance information acquisition step of acquiring maintenance information related to a history of maintenance performed on at least one of the server and the inspection device; as well as The abnormality specifying step specifies, when the difference between the target value and the measured value is not within a predetermined reference range, which of the server, the inspection device, and the moving object to be inspected has an abnormality using the maintenance information.

2. The inspection method according to claim 1, wherein: The maintenance information is information related to execution timing of performing the maintenance on the target device.

3. The inspection method according to claim 2, wherein: In the abnormality specifying step, when the timing at which the second step is executed is within a predetermined period from the execution timing included in the maintenance information, it is determined that there is no abnormality in the target device on which the maintenance is executed.

4. The inspection method according to claim 1, further comprising: a learning step of causing a machine learning model to learn using past data related to input and output of the server, past data related to input and output of the inspection device, past data related to the maintenance information, and past data related to normality or abnormality of the server, the inspection device, and the moving body of the inspection object, In the abnormality determination step, the machine learning model learned in the learning step is used to determine which of the server, the inspection device, and the moving object of the inspection object has an abnormality.

5. The inspection method according to claim 4, wherein: In the abnormality determination step, when the second step is executed within a predetermined period from the execution timing of the maintenance performed on the object device, information indicating that the probability that there is no abnormality in the object device on which the maintenance is performed is higher than when the maintenance is not performed is output.

6. The inspection method according to claim 1, wherein: The maintenance information is information regarding whether an abnormality of the target device is detected during the maintenance.

7. The inspection method according to claim 6, wherein: In the abnormality specifying step, when the maintenance information includes information indicating that an abnormality of the target device is detected during the maintenance, a determination is made that the target device in which the abnormality is detected has an abnormality.

8. The inspection method according to claim 6, wherein: In the abnormality determination process, when the maintenance information includes information indicating that an abnormality of the object device was detected during the maintenance and also includes information that a component that caused the abnormality of the object device in which the abnormality was detected has been replaced, a determination is made that there is no abnormality in the object device in which the abnormality was detected, or a determination process is performed to determine whether there is an abnormality in the object device in which the abnormality was detected.

9. The inspection method according to claim 1, wherein: The maintenance information is information related to whether an abnormality of the target device is detected continuously or intermittently during the maintenance.

10. The inspection method according to claim 9, wherein: In the abnormality specifying step, when the maintenance information includes information indicating that an abnormality of the target device is detected continuously or intermittently during the maintenance, information indicating that an abnormality exists in the target device in which the continuous or intermittent abnormality is detected is output.