Inspection system and method of inspection

Abstract

The inspection system includes an image acquisition unit that acquires an image captured by an imaging device, the image including projected light projected from a headlamp provided in a moving body onto a projection target, and an inspection unit that inspects a light distribution characteristic of the headlamp using the acquired image.

Description

Technical Field

[0001] This disclosure relates to inspection systems and inspection methods. Background Technology

[0002] Japanese Patent Publication No. 2017-538619 discloses a technology that enables vehicles to drive autonomously during the vehicle manufacturing process.

[0003] A new inspection technique is desired for examining the light distribution characteristics of headlights on moving objects such as vehicles. This issue is common to any moving object equipped with headlights, regardless of the type of moving object or whether it can move autonomously. Summary of the Invention

[0004] Technical means for solving the problem

[0005] This disclosure can be implemented in the following ways.

[0006] (1) According to one aspect of the present disclosure, an inspection system is provided. The inspection system includes: an image acquisition unit that acquires an image captured by an imaging device, which includes projected light from a headlight mounted on a moving body projected onto a projection object; and an inspection unit that uses the acquired image to inspect the light distribution characteristics of the headlight.

[0007] According to this method, the light distribution characteristics of a headlight can be checked using a new approach that incorporates an image containing the projected light from the headlight.

[0008] (2) In the above-described manner, an adjustment unit may be provided to adjust the optical system of the headlight, and the adjustment unit adjusts the optical system according to the inspection results of the inspection unit on the light distribution characteristics. According to this method, not only can the light distribution characteristics be inspected, but the light distribution characteristics can also be effectively improved based on the inspection results.

[0009] (3) In the above method, the inspection unit may also inspect the light distribution characteristics by comparing the light distribution pattern of the projected light in the image with a reference light distribution pattern corresponding to the type of moving object. According to this method, the light distribution characteristics of various types of moving objects can be inspected in a simpler way.

[0010] (4) In the above method, a control unit may be provided to move the mobile body by autonomous driving. The control unit performs: an entry process to move the mobile body to a preset reference position; a standby process to keep the mobile body at the reference position after the entry process; and a disengagement process to move the mobile body from the reference position after the standby process. During the execution of the standby process, the image acquisition unit acquires the image captured during the execution of the standby process, and the inspection unit inspects the light distribution characteristics during the execution of the standby process. According to this method, it is possible to move the mobile body to the reference position by autonomous driving, inspect the light distribution characteristics while the mobile body is at the reference position, and leave the reference position after the inspection is completed. As a result, it is possible to inspect the light distribution characteristics more smoothly by autonomous driving.

[0011] (5) In the above-described manner, an adjustment unit may be included to adjust the optical system of the headlight. The light distribution characteristics include optical axis characteristics related to the optical axis of the headlight. After checking the optical axis characteristics, if the checking result of the checking unit on the optical axis characteristics does not meet the preset optical axis conditions, the adjustment unit performs an adjustment process to adjust the optical system according to the checking result during the execution of the standby process. After the adjustment process is executed, the checking unit re-checks the optical axis characteristics during the execution of the standby process. According to this method, when the checking result of the optical axis characteristics does not meet the optical axis conditions, the adjustment of the optical system and the re-checking of the optical axis characteristics can be performed efficiently while the moving body is stationary at a reference position.

[0012] (6) In the above method, the control unit may not perform the disengagement process until the inspection result meets the optical axis condition. According to this method, the process from checking the optical axis characteristics to adjusting the optical system can be performed in one go while the moving body is stationary in the reference position.

[0013] (7) Alternatively, in the above-described manner, the control unit may be configured to control the headlights to switch them from off to on after the entry process begins and before the image is captured. According to this method, the light distribution characteristics can be checked more smoothly while suppressing energy consumption caused by the headlights.

[0014] (8) Alternatively, in the above-described manner, the control unit may be configured to control the headlights to switch them from on to off after the image is captured and before the separation process begins. This method can further suppress energy consumption caused by the headlights.

[0015] (9) In the above method, the projection object may also be a wall surface located outside the moving body. According to this method, the light distribution characteristics can be checked using the wall.

[0016] (10) In the above-described manner, the projection object may also be the road surface of a travel road on which the vehicle, as the moving body, can travel. According to this method, the light distribution characteristics can be checked using the travel road.

[0017] (11) In the above method, the headlight includes a first headlight and a second headlight, the projected light includes a first light projected by the first headlight and a second light projected by the second headlight, and the inspection unit uses the acquired image to inspect the light distribution characteristics of the first headlight and the second headlight. According to this method, the light distribution characteristics of the first headlight and the second headlight can be inspected at once using an inspection image of the projected light.

[0018] (12) In the above-described manner, the imaging device may also be located outside the mobile body and used to obtain the position information of the mobile body for autonomous driving. According to this method, the light distribution characteristics can be checked using the imaging device used in autonomous driving.

[0019] In addition to the aforementioned method as an inspection system, this disclosure can also be implemented as, for example, a control device, an inspection method, a program for implementing the inspection method, a non-transitory recording medium containing the program, or a program product. Furthermore, the program product can be provided, for example, as a recording medium containing the program, or as a program product that can be distributed via a network. Attached Figure Description

[0020] Figure 1 This is a conceptual diagram showing the configuration of the inspection system in the first embodiment.

[0021] Figure 2 This is a block diagram showing the configuration of the inspection system in the first embodiment.

[0022] Figure 3 This is the first diagram illustrating the headlight inspection in the first embodiment.

[0023] Figure 4 This is the second figure illustrating the headlight inspection in the first embodiment.

[0024] Figure 5 This is a flowchart illustrating the processing flow of vehicle driving control in the first embodiment.

[0025] Figure 6This is a flowchart illustrating the inspection process in the first embodiment.

[0026] Figure 7 This is a diagram illustrating the headlight inspection in the second embodiment.

[0027] Figure 8 This is an explanatory diagram showing the general configuration of the inspection system in the third embodiment.

[0028] Figure 9 This is a flowchart illustrating the vehicle driving control process in the third embodiment. Detailed Implementation

[0029] A. First implementation method:

[0030] Figure 1 This is a conceptual diagram showing the configuration of the inspection system 50 in the first embodiment. The inspection system 50 includes one or more vehicles 100, a server 200, one or more external sensors 300, and a terminal device 450.

[0031] In this disclosure, "mobile body" means an object capable of movement, such as a vehicle or an electric vertical takeoff and landing aircraft (so-called flying car). A vehicle can be a wheeled vehicle or a tracked vehicle, such as a passenger car, truck, bus, two-wheeled vehicle, four-wheeled vehicle, or engineering vehicle. Vehicles include battery electric vehicles (BEVs), gasoline vehicles, hybrid electric vehicles, and fuel cell vehicles. When the mobile body is not a vehicle, the terms "vehicle" or "car" in this disclosure may be appropriately replaced with "mobile body," and the term "driving" may be appropriately replaced with "moving."

[0032] Vehicle 100 is configured to operate autonomously. "Autonomous operation" means driving without relying on the driving actions of passengers. Driving actions refer to actions related to at least one of "driving," "steering," or "stopping" of vehicle 100. Autonomous driving is achieved through automatic or manual remote control using devices located outside vehicle 100, or through autonomous control of vehicle 100. In vehicle 100 operating autonomously, passengers who do not perform driving actions may also be present. Passengers who do not perform driving actions include, for example, people simply sitting in the seats of vehicle 100, or people performing tasks different from driving actions while riding in vehicle 100. Furthermore, driving based on passenger driving actions is sometimes referred to as "manned driving."

[0033] In this specification, "remote control" includes "fully remote control," in which all actions of vehicle 100 are determined entirely from outside the vehicle 100, and "partially remote control," in which some actions of vehicle 100 are determined from outside the vehicle 100. Additionally, "autonomous control" includes "fully autonomous control," in which vehicle 100 autonomously controls its own actions without receiving any information from external devices, and "partially autonomous control," in which vehicle 100 autonomously controls its own actions using information received from external devices.

[0034] Vehicle 100 only needs to have a configuration capable of moving autonomously, and for example, it can be in the form of a platform with the configuration described below. Specifically, in order for vehicle 100 to perform the three functions of "driving," "steering," and "stopping" autonomously, it only needs to have at least the vehicle control device and actuator assembly described later. When vehicle 100 obtains information from the outside for autonomous driving, it also needs to have a communication device. That is, vehicle 100 capable of moving autonomously may not be equipped with at least some of the interior components such as the driver's seat and dashboard, nor with at least some of the exterior components such as bumpers and mudguards, nor with a body shell. In this case, the remaining components such as the body shell can be assembled onto vehicle 100 before it is shipped from factory FC, or the remaining components such as the body shell can be assembled onto vehicle 100 after it has been shipped from factory FC without them. Each component can be assembled from any direction, such as the upper, lower, front, rear, right, or left side of the vehicle 100, and can be assembled from the same direction or from different directions. Furthermore, the shape of the test stand can be determined in the same way as the vehicle 100 in the first embodiment.

[0035] In this embodiment, the inspection system 50 is used in the factory FC that manufactures the vehicle 100. The reference coordinate system of the factory FC is the global coordinate system GC, and any position within the factory FC can be represented by the X, Y, and Z coordinates in the global coordinate system GC. The factory FC includes a first location PL1, a second location PL2, and an inspection location DP. The first location PL1 and the inspection location DP, as well as the inspection location DP and the second location PL2, are connected by a travel road TR that the vehicle 100 can travel on. The vehicle 100 moves autonomously from the first location PL1 to the second location PL2, passing through the inspection location DP and traveling along the travel road TR. At the first location PL1 and the second location PL2, manufacturing processes related to the vehicle 100, such as assembly and inspection, are performed. At the first location PL1, a first process related to the vehicle 100 is performed. At the second location PL2, a second process following the first process is performed.

[0036] Furthermore, the term "driving road" in this disclosure is not limited to driving road TR, but means the floor on which vehicle 100 can drive. In this embodiment, the first location PL1, the second location PL2, and the inspection location DP include driving roads.

[0037] At the inspection site DP, a headlight inspection is performed. During the headlight inspection, the headlights 150 equipped on the vehicle 100 are inspected. The headlights 150 are mounted on a moving body and used to illuminate the front of the moving body. In this embodiment, the vehicle 100 is equipped with a first headlight 150A and a second headlight 150B as headlights 150. That is, the headlights 150 include a first headlight 150A and a second headlight 150B. In this embodiment, the first headlight 150A and the second headlight 150B are a pair of headlights arranged on the left and right sides of the vehicle 100. The first headlight 150A corresponds to the right headlight, and the second headlight 150B corresponds to the left headlight. In this embodiment, the first headlight 150A and the second headlight 150B correspond to the headlights being inspected during the headlight inspection. In other embodiments, for example, one of the first headlight 150A and the second headlight 150B may be the object of inspection. Hereinafter, without making a special distinction between the first headlight 150A and the second headlight 150B, both may be simply referred to as headlight 150.

[0038] In other embodiments, vehicle 100 may also include fog lights as headlights 150. In this case, the headlights of the object being inspected need to include at least one of one or more headlights and one or more fog lights.

[0039] External sensor 300 is a sensor located outside vehicle 100. In this embodiment, external sensor 300 is composed of a camera. The camera, serving as external sensor 300, captures images of vehicle 100 and outputs the captured images as detection results. External sensor 300 is equipped with a communication device (not shown) and can communicate with other devices such as server 200 via wired or wireless communication. In the factory FC, multiple external sensors 300 are installed along the driving road TR. The positions of each external sensor 300 in the factory FC are pre-adjusted. As will be described later, in this embodiment, external sensor 300 is used as an "image capture device" in headlight inspection.

[0040] Figure 2 This is a block diagram showing the configuration of the inspection system 50. The vehicle 100 includes a vehicle control unit 110 for controlling various parts of the vehicle 100, an actuator assembly 120 containing one or more actuators driven under the control of the vehicle control unit 110, a communication device 130 for communicating with external devices such as a server 200 via wireless communication, and the aforementioned headlight 150. The actuator assembly 120 includes actuators for a drive mechanism to accelerate the vehicle 100, actuators for a steering mechanism to change the direction of travel of the vehicle 100, and actuators for a braking mechanism to decelerate the vehicle 100. Furthermore, the actuator assembly 120 includes a headlight actuator for operating the headlight 150. The headlight actuator includes, for example, an actuator for switching the headlight 150 on and off, and an actuator for switching the operating mode of the headlight 150 between low beam and high beam modes.

[0041] The headlight 150 includes an optical system 151, an adjustment mechanism 155, and a light source 159. The optical system 151 converges the light emitted from the light source 159 and emits the converged light to the outside of the headlight 150. The optical system 151 includes lenses, reflectors, and shaders for focusing and emitting light. Furthermore, this optical system 151 functions to form a cut-off line for the headlight 150. The light source 159 is, for example, a halogen lamp, an LED lamp, or a HID lamp. The adjustment mechanism 155 is used to adjust the optical system 151. More specifically, in this embodiment, the adjustment mechanism 155 adjusts the optical axis of the headlight 150 by adjusting the position and angle of the reflectors or lenses included in the optical system 151. The adjustment mechanism 155 is configured, for example, as an electrically operated adjustment mechanism, including a motor that generates a driving force for changing the position and angle of the optical system 151, and a transmission mechanism for transmitting the driving force of the motor to the optical system 151. As will be described later, in this embodiment, the adjustment mechanism 155 is configured to be controllable by the adjustment unit 230 of the server 200.

[0042] The vehicle control unit 110 comprises a computer having a processor 111, a memory 112, an input / output interface 113, and an internal bus 114. The processor 111, memory 112, and input / output interface 113 are bidirectionally connected via the internal bus 114. An actuator assembly 120, a communication device 130, and a headlight 150 are connected to the input / output interface 113. The processor 111 executes various functions, including those of the vehicle control unit 115, by executing the program PG1 stored in the memory 112.

[0043] The vehicle control unit 115 drives the vehicle 100 by controlling the actuator assembly 120. The vehicle control unit 115 controls the actuator assembly 120 using a driving control signal received from the server 200, thereby enabling the vehicle 100 to drive. The driving control signal is a control signal used to drive the vehicle 100. In this embodiment, the driving control signal includes the acceleration and steering angle of the vehicle 100 as parameters. In other embodiments, the driving control signal may include the speed of the vehicle 100 as a parameter instead of its acceleration, or it may include the speed of the vehicle 100 as a parameter in addition to its acceleration.

[0044] In addition, in this embodiment, the vehicle control unit 115 activates the headlight by using a control signal received from the server 200 to activate the headlight actuator included in the actuator group 120.

[0045] Server 200 is a computer comprising a processor 201, a memory 202, an input / output interface 203, and an internal bus 204. The processor 201, memory 202, and input / output interface 203 are bidirectionally connected via the internal bus 204. A communication device 205 for communicating with various external devices is connected to the input / output interface 203. The communication device 205 can communicate with vehicle 100 wirelessly and with various external sensors 300 via wired or wireless communication. The memory 202 stores various information such as program PG2, detection model DM, reference path RR, pattern data PD, pattern detection model PM1, and condition data CD. The processor 201 executes the program PG2 stored in the memory 202 to perform various functions, including those of a remote control unit 210, an image acquisition unit 215, an inspection unit 220, a judgment unit 225, and an adjustment unit 230. The remote control unit 210 in the first embodiment corresponds to the "control unit" in this disclosure.

[0046] The remote control unit 210 acquires detection results based on sensors, uses the detection results to generate a driving control signal for controlling the actuator assembly 120 of the vehicle 100, and sends the driving control signal to the vehicle 100, thereby enabling the vehicle 100 to drive remotely. Furthermore, in this embodiment, the remote control unit 210 generates a control signal for activating the headlight 150 and sends it to the vehicle 100, thereby enabling remote control of the headlight.

[0047] Figure 3 This is the first diagram illustrating the headlight inspection in this embodiment. In the headlight inspection, the light distribution characteristics of the headlight 150 are checked. As the light distribution characteristics of the headlight, it is preferable to check at least one of the optical axis characteristics, luminous quantity characteristics, and color temperature characteristics of the headlight 150. That is, the inspection items in the headlight inspection preferably include at least one of the optical axis characteristics, luminous quantity characteristics, and color temperature characteristics. The optical axis characteristics are characteristics related to the optical axis of the headlight 150. The luminous quantity characteristics are characteristics related to the luminous quantity of the headlight 150. The color temperature characteristics are characteristics related to the color temperature of the headlight 150. In checking the optical axis characteristics, the suitability of the cut-off line position of the headlight 150 is checked. In the case where the headlight 150 is a headlamp as in this embodiment, "suitable cut-off line position" includes "suitable inflection point position." An inflection point means the point where the cut-off line bends.

[0048] like Figure 3 As shown, the image acquisition unit 215 acquires the inspection image KG captured by the imaging device CM. The inspection image KG includes a projection light LT. The projection light LT is light projected from the headlight 150 onto the projection object. In this embodiment, the projection object is the wall surface WP of the wall WL provided on the exterior of the vehicle 100. The wall WL is provided at the inspection location DP. More specifically, in this embodiment, the wall WL is formed by a gate GT provided at the factory FC. The gate GT is configured to be openable and closable. And, by closing the gate GT, the wall WL is formed. The vehicle 100 can pass through the gate GT by traveling between the open gate GTs. That is, the gate GT is configured to switch between a permitted state that allows the vehicle 100 to pass and a prohibited state that prohibits the vehicle 100 from passing. The gate GT may also be configured to be controllable by a control unit, for example. In this way, the wall WL can be appropriately formed by the gate GT in accordance with the progress of the headlight inspection, and the vehicle 100 can be appropriately allowed to pass. Alternatively, for example, the gate GT can also be configured as an automatic door that allows vehicle 100 to pass when it is in a position forward of the reference position P1 described later, and prevents vehicle 100 from passing when it is in the reference position P1 or when it is in a position backward of the reference position P1, thus forming a wall WL. Furthermore, in Figure 3And as will be discussed later Figure 4 In the diagram, the gate GT in the permitted state is indicated by a dashed line.

[0049] In this embodiment, the projected light LT includes a first light LT1 projected by the first headlight 150A and a second light LT2 projected by the second headlight 150B. More specifically, in this embodiment, the projected light LT is formed by simultaneously projecting light from the first headlight 150A and light from the second headlight 150B onto the projected object. In the inspection image KG containing such a projected light LT, the first light LT1 and the second light LT2 can be located in mutually separated positions, or in positions that partially or completely overlap each other. In this embodiment, the inspection unit 220 uses the inspection image KG containing such a projected light LT to inspect the light distribution characteristics of the first headlight 150A and the second headlight 150B in one operation.

[0050] More specifically, the imaging device CM captures an image (KG) of an object being projected onto by a projected light (LT), thereby obtaining an inspection image (KG). As described later, the inspection image (KG) is used for headlight inspection. Furthermore, in headlight inspection, the inspection image (KG) may also be used, for example, after undergoing various preprocessing steps. In this embodiment, the imaging device CM functions as a camera within the external sensor 300. Consequently, as described later, in this embodiment, the imaging device CM is also used to obtain vehicle position information for autonomous driving.

[0051] The inspection unit 220 uses the inspection image KG acquired by the image acquisition unit 215 to inspect the light distribution characteristics of the headlight 150. In this embodiment, the inspection unit 220 inspects the light distribution characteristics by performing a comparison process. The comparison process is a process of comparing an object pattern with a reference light distribution pattern. The object pattern represents the light distribution pattern of the projected light LT in the inspection image KG. The reference light distribution pattern is a reference light distribution pattern corresponding to the type of vehicle 100, i.e., the vehicle model. The reference light distribution pattern may also be a light distribution pattern corresponding to, for example, the specifications of the headlight 150 or the delivery location of the vehicle 100, in addition to the vehicle model. The specifications of the headlight 150 are, for example, the type of light source 159. "Delivery location" refers to the country or region where the vehicle 100, as a product, is delivered. The reference light distribution pattern corresponds to the light distribution pattern of the projected light projected from a headlight with ideal light distribution characteristics onto the projection object.

[0052] In the comparison process, firstly, the inspection unit 220 obtains object pattern information TI representing the object pattern and reference pattern information SI representing the reference light distribution pattern. In this embodiment, the inspection unit 220 uses a pattern detection model PM1 to obtain the object pattern information TI. In this embodiment, the pattern detection model PM1 is a machine learning model that has been learned by taking an image as input and outputting pattern information representing the light distribution pattern in the input image. As the pattern detection model PM1, a convolutional neural network (CNN) that has been learned through supervised learning can be used, for example. In such supervised learning, a learning dataset containing the inspection image KG as an explanatory variable and the pattern information as a target variable, i.e., a label, is used. In this embodiment, the pattern information, corresponding to the inspection items of the headlight inspection, includes light cut-off line information indicating the position of the light cut-off line, light quantity information indicating the light quantity, and light color information indicating the light color. The light cut-off line information may also include inflection point information indicating the position of the inflection point. The light cut-off line information is used, for example, for checking the optical axis characteristics. The light quantity information is used, for example, for checking the light quantity characteristics. The light color information is used, for example, for checking the light color characteristics. The inspection unit 220 obtains object pattern information TI containing various information by inputting the inspection image KG into the pattern detection model PM1.

[0053] In this embodiment, the inspection unit 220 acquires pre-prepared reference pattern information SI. The reference pattern information SI is prepared in advance, for example, by inputting an image containing a reference light distribution pattern into the pattern detection model PM1. Furthermore, in other embodiments, the inspection unit 220 may, for example, acquire a reference image containing a reference light distribution pattern during comparison processing, and input the acquired reference image into the pattern detection model PM1 to obtain the reference pattern information SI. In this case, the inspection unit 220 acquires the reference image, for example, from memory 202, memory 112, an external computer, recording medium, or the like.

[0054] In this embodiment, the reference pattern information SI is included in the pattern data PD pre-stored in the memory 202. In the pattern data PD, the vehicle model and the reference pattern information SI corresponding to the vehicle model are mutually associated. As described above, when the reference beam pattern is a beam pattern corresponding to the specifications of the headlight 150 and the delivery location of the vehicle 100, the reference pattern information SI in the pattern data PD is also associated with the specifications of the headlight 150 and the delivery location of the vehicle 100. The inspection unit 220 can obtain the type information IM1 indicating the vehicle model of the vehicle 100, and use the obtained type information and refer to the pattern data PD to obtain the reference pattern information SI corresponding to the vehicle model. Alternatively, the inspection unit 220 can also use, for example, specification information IM2 indicating the specifications of the headlight 150 and delivery location information IM3 indicating the delivery location of the vehicle 100, and refer to the pattern data PD to obtain the reference pattern information SI corresponding to the specifications and delivery location of the headlight 150.

[0055] Furthermore, the type information IM1, specification information IM2, and delivery location information IM3 can be obtained, for example, by reading the QR code attached to the vehicle 100, or by the user inputting it into the server 200 via an input device, or from a process management device (not shown) that manages the manufacturing process of the vehicle 100. In this context, "user" refers to a user of the factory FC or inspection system 50, such as a manager or operator within the factory FC. Additionally, the input device can be, for example, a terminal device 450 held by the user. The terminal device 450 can be, for example, a tablet computer, a smartphone, etc.

[0056] In the comparison processing, the inspection unit 220 next compares the acquired object pattern information TI with the reference pattern information SI to obtain light distribution characteristic information DI representing the light distribution characteristics of the headlight 150. Then, the inspection unit 220 outputs the light distribution characteristic information DI as the inspection result related to each inspection item, according to each headlight 150 under inspection and each inspection item. In this embodiment, the light distribution characteristic information DI includes, corresponding to the inspection items of the headlight inspection, light axis characteristic information representing light axis characteristics, light quantity characteristic information representing light quantity characteristics, and light color characteristic information representing light color characteristics. In addition, in this embodiment, the light distribution characteristic information DI represents the difference between the object pattern information TI and the reference pattern information SI. For example, the light axis characteristic information includes information representing the difference in the position coordinates of the cut-off lines between the object pattern information TI and the reference pattern information SI, the distance between the cut-off lines, the difference in the position coordinates of the inflection points, and the distance between the inflection points. In addition, the light quantity characteristic information includes, for example, information representing the difference in light quantity between the object pattern information TI and the reference pattern information SI. In addition, the light color characteristic information includes, for example, the difference in light color between the object pattern information TI and the reference pattern information SI.

[0057] The determination unit 225 determines whether the inspection results of the light distribution characteristics by the inspection unit 220 meet the preset characteristic condition CC. In this embodiment, the determination unit 225 determines whether the characteristic condition CC is met based on the inspection results obtained for each headlamp 150 of the inspection object and each inspection item. Then, the determination unit 225 outputs a determination result Jr for each headlamp 150 of the inspection object and each inspection item. In this embodiment, the characteristic condition CC is the condition that the difference represented by the light distribution characteristic information DI is below a preset reference level. Therefore, the characteristic condition CC in this embodiment includes the optical axis condition related to the optical axis characteristics, the light quantity condition related to the light quantity characteristics, and the light color condition related to the light color characteristics. In addition, the characteristic condition CC is included in the condition data CD, which is defined in the condition data CD according to each inspection item.

[0058] The adjustment unit 230 adjusts the optical system 151 based on the inspection results of the light distribution characteristics by the inspection unit 220. In this embodiment, the adjustment unit 230 controls the adjustment mechanism 155 based on the inspection results, thereby adjusting the optical system 151 of the headlight 150 corresponding to the inspection results. For example, the adjustment unit 230 adjusts the optical system 151 of the first headlight 150A based on the inspection results of the optical axis of the first headlight 150A. Furthermore, the adjustment unit 230 adjusts the optical system 151 of the second headlight 150B based on the inspection results of the optical axis of the second headlight 150B. More specifically, when adjusting the optical system 151, the adjustment unit 230 generates an optical system control signal OS for controlling the adjustment mechanism 155 and sends the generated optical system control signal OS to the vehicle 100. As a result, the adjustment mechanism 155 is operated remotely, and the optical system 151 is adjusted. In this embodiment, the adjustment unit 230 sends an optical system control signal OS to the vehicle 100 to reduce the optical axis difference based on the optical axis difference related to the optical axis as indicated by the optical axis characteristic information, thereby adjusting the optical system 151 in a manner that reduces the optical axis difference.

[0059] The reporting unit 235 reports inspection result information related to the inspection results of the headlight inspection to the user. The inspection result information FI may, for example, show at least one of the information indicating the inspection result of the inspection unit 220 and the judgment result JR of the judgment unit 225. In this embodiment, the reporting unit 235 reports the inspection result information FI via the terminal device 450. In other embodiments, the reporting unit 235 may also report the inspection results via, for example, a display device that outputs visual information, a speaker that outputs audio information, a printing device, etc. Furthermore, in this embodiment, the reporting unit 235 reports the inspection result information FI according to each inspection item of the headlight inspection.

[0060] Figure 4 This is the second diagram illustrating the headlight inspection in this embodiment. (See diagram below.) Figure 4 As shown, in the headlight check in this embodiment, the remote control unit 210 performs the entry process EP, the standby process SP, and the exit process LP.

[0061] The entry process EP is a process that moves the vehicle 100 to a preset reference position P1. In the entry process EP of this embodiment, the remote control unit 210 generates a driving control signal RS1 for moving the vehicle 100 to the reference position P1, and sends the generated driving control signal RS1 to the vehicle 100.

[0062] The standby processing SP is a process that keeps the vehicle 100 stationary at the reference position P1 after entering the processing EP. In the standby processing SP, the remote control unit 210 generates a driving control signal RS2 to keep the vehicle 100 stationary at the reference position P1 and sends the generated driving control signal RS2 to the vehicle 100. Furthermore, for example, if the vehicle 100 is configured to stop when no driving control signal is received, the remote control unit 210 may also stop sending the driving control signal in the standby processing SP, keeping the vehicle 100 stationary at the reference position P1. Additionally, in the standby processing SP of this embodiment, the vehicle 100 is controlled to move towards a predetermined reference direction DS at the reference position P1. In this embodiment, the reference direction DS is an orthogonal direction to the wall WP in the relative directions opposite to the wall WP. More specifically, the reference direction DS is the -Y direction.

[0063] Furthermore, in other embodiments, the remote control unit 210 may, for example, determine whether the vehicle 100 located at the reference position P1 is facing the reference direction DS before acquiring the inspection image KG. In such orientation determination, an external sensor 300 may be used, for example. Additionally, if the vehicle 100 located at the reference position P1 is not facing the reference direction DS, the remote control unit 210 may also remotely control the vehicle 100 so that the vehicle 100 is located at the reference position P1 and facing the reference direction DS.

[0064] The disengagement process LP is the process that moves vehicle 100 from reference position P1 after standby process SP. In the disengagement process LP of this embodiment, the remote control unit 210 generates a driving control signal RS3 to move vehicle 100 from reference position P1 to the next position and sends the generated driving control signal RS3 to vehicle 100. In this embodiment, by executing the disengagement process LP, vehicle 100 proceeds to the second location PL2 by passing the gate GT in the permitted state.

[0065] In this embodiment, the inspection image KG described above is captured during the execution of the standby processing SP. More specifically, light is shone from the headlight 150 of a vehicle 100, which is stopped at a reference position P1 and moving towards a reference direction DS, onto the wall WP, thereby displaying a projected light LT on the wall WP. Then, the inspection image KG is captured by the imaging device CM, which captures the projected light LT displayed on the wall WP as described above. In addition, the image acquisition unit 215 acquires the inspection image KG captured in this way during the execution of the standby processing SP. Furthermore, the inspection unit 220 uses the inspection image KG acquired as described above to inspect the light distribution characteristics during the execution of the standby processing SP.

[0066] In addition, such as Figure 4 As shown, in this embodiment, the remote control unit 210 switches the headlight 150 of the object to be inspected from off to on after entering the processing EP and before taking the inspection image KG. Additionally, the remote control unit 210 switches the headlight 150 of the object to be inspected from on to off after taking the inspection image KG and before leaving the processing LP.

[0067] Figure 5 This is a flowchart illustrating the processing flow of the vehicle 100's driving control in the first embodiment. Figure 5 In the processing flow, the processor 201 of the server 200 functions as the remote control unit 210, and the processor 111 of the vehicle 100 functions as the vehicle control unit 115.

[0068] In step S1, the processor 201 of the server 200 uses the detection results output from the external sensor 300 to obtain vehicle position information. This vehicle position information is the basis for generating driving control signals. In this embodiment, the vehicle position information includes the position and orientation of the vehicle 100 in the global coordinate system GC of the factory FC. Specifically, in step S1, the processor 201 uses images captured from a camera, which is the external sensor 300, to obtain the vehicle position information.

[0069] Specifically, in step S1, the processor 201 detects the shape of the vehicle 100 from the captured image, calculates the coordinates of the vehicle 100's location points in the local coordinate system of the captured image, and converts the calculated coordinates into coordinates in the global coordinate system GC, thereby obtaining the position of the vehicle 100. The shape of the vehicle 100 contained in the captured image can be detected, for example, by inputting the captured image into a detection model DM employing artificial intelligence. The detection model DM can be, for example, a learned machine learning model trained to perform either semantic segmentation or instance segmentation. This machine learning model can be, for example, a convolutional neural network (hereinafter CNN) trained using a training dataset under supervised learning. The training dataset, for example, contains multiple training images of the vehicle 100, and labels indicating which region in the training images represents the vehicle 100 and which region outside the vehicle 100 it represents. During CNN learning, it is preferable to update the CNN parameters by back-propagation (error backpropagation method) to reduce the error between the output of the detection model DM and the labels. In addition, the processor 201 can estimate the orientation of the vehicle 100 by using optical flow, for example, based on the direction of the vehicle 100's movement vector calculated from the position changes of feature points of the vehicle 100 between frames of the captured image.

[0070] In step S2, the processor 201 of the server 200 determines the target location that the vehicle 100 should go to next. In this embodiment, the target location is represented by the X, Y, and Z coordinates in the global coordinate system GC. The memory 202 of the server 200 pre-stores a reference path RR, which serves as the path that the vehicle 100 should travel. The path is represented by nodes indicating the starting point, nodes indicating the waypoints, nodes indicating the destination, and links connecting the nodes. The processor 201 uses the vehicle location information and the reference path RR to determine the target location that the vehicle 100 should go to next. The processor 201 determines the target location on the reference path RR, which is further ahead of the vehicle 100's current location.

[0071] In step S3, the processor 201 of the server 200 generates a driving control signal to move the vehicle 100 toward the determined target position. The processor 201 calculates the vehicle 100's speed based on the vehicle 100's position shift and compares the calculated speed with the target speed. Generally, when the speed is lower than the target speed, the processor 201 determines acceleration to make the vehicle 100 accelerate; when the speed is higher than the target speed, it determines acceleration to make the vehicle 100 decelerate. Furthermore, when the vehicle 100 is on the reference path RR, the processor 201 determines the steering angle and acceleration to prevent the vehicle 100 from leaving the reference path RR; when the vehicle 100 is not on the reference path RR—in other words, when the vehicle 100 has left the reference path RR—it determines the steering angle and acceleration to return the vehicle 100 to the reference path RR.

[0072] In step S4, the processor 201 of the server 200 sends the generated driving control signal to the vehicle 100. The processor 201 repeatedly performs tasks such as acquiring vehicle position information, determining target position, generating driving control signals, and sending driving control signals at predetermined intervals.

[0073] In step S5, the processor 111 of vehicle 100 receives a driving control signal sent from server 200. In step S6, the processor 111 of vehicle 100 uses the received driving control signal to control the actuator assembly 120, thereby causing vehicle 100 to travel at the acceleration and steering angle represented by the driving control signal. The processor 111 repeatedly receives the driving control signal and controls the actuator assembly 120 at a predetermined cycle. According to the inspection system 50 in this embodiment, vehicle 100 can be driven remotely, and vehicle 100 can be moved without the use of conveying equipment such as cranes or conveyors.

[0074] Figure 6 This is a flowchart illustrating the processing flow of the inspection process used to implement the inspection method in this embodiment. The inspection process is the process used to perform a headlight inspection. The inspection process is initiated, for example, by the processor 201 of the server 200 when the vehicle 100 is located at a predetermined position within the factory FC.

[0075] exist Figure 6 In step S105, such as Figure 4 As shown, the remote control unit 210 begins processing EP, thereby initiating the movement of vehicle 100 towards reference position P1. Figure 6 In step S110, such as Figure 4As shown, the remote control unit 210 switches the headlight 150 of the object under inspection from off to on, more specifically, from off to low beam mode. Step S110 is executed during the execution of the process EP.

[0076] exist Figure 6 In step S115, such as Figure 4 As shown, the remote control unit 210 terminates the entry process EP and begins the standby process SP, thereby bringing the vehicle 100 to a reference position P1. Step S115 is executed when the movement of the vehicle 100 to the reference position P1 is completed. Then, during the execution of the standby process SP, an inspection image KG is captured by an external sensor 300, which is an imaging device CM.

[0077] exist Figure 6 In step S120, the image acquisition unit 215 acquires the captured inspection image KG. In step S125, the inspection unit 220 uses the inspection image KG acquired in step S120 to acquire object pattern information TI. In step S130, the inspection unit 220 acquires reference pattern information SI corresponding to the vehicle model of the vehicle 100. In step S135, the inspection unit 220 compares the object pattern information TI acquired in step S125 with the reference pattern information SI acquired in step S130, thereby inspecting the light distribution characteristics of the headlight 150.

[0078] In steps S140, S141, and S142, the determination unit 225 determines whether the inspection result in step S135 satisfies the characteristic condition CC. More specifically, in step S140, the determination unit 225 determines whether the inspection result of the light color characteristic, i.e., the light color characteristic information, satisfies the light color condition. If the light color characteristic information satisfies the light color condition in step S140, in step S141, the determination unit 225 determines whether the inspection result of the light quantity characteristic, i.e., the light quantity characteristic information, satisfies the light quantity condition. If the characteristic condition CC is not satisfied in step S140 or step S141, the determination unit 225 advances the process to step S150. If the light quantity characteristic information satisfies the light quantity condition in step S141, in step S142, the determination unit 225 determines whether the inspection result of the optical axis characteristic, i.e., the optical axis characteristic information, satisfies the optical axis condition.

[0079] If the optical axis condition is not met in step S142, the adjustment unit 230 performs an adjustment process in step S145. This adjustment process is the adjustment of the optical system 151 during the standby process SP. In step S145 of this embodiment, the adjustment unit 230 adjusts the optical system 151 to minimize the optical axis difference based on the optical axis characteristic information. Afterwards, the external sensor 300, which serves as the imaging device CM, captures the inspection image KG again.

[0080] Afterwards, the inspection unit 220 returns the process to step S120. Furthermore, in the next step S120, the inspection image KG, captured after the adjustment process in step S145, is obtained. Additionally, the next step S135 is equivalent to a re-inspection process. This re-inspection process re-inspects the optical axis characteristics of the headlamp 150 during the execution of the standby process SP. Furthermore, in the next steps S140, S141, and S142, the determination unit 225 determines whether the inspection result of the light distribution characteristics re-inspected in the next step S135 meets the characteristic condition CC. Moreover, after step S135 executed for the second time or more, the processes in steps S140 and S141 can be omitted.

[0081] If the light color condition or light quantity condition is not met in step S140 or S141, or if the optical axis condition is met in step S142, in step S150, the remote control unit 210 switches the headlight 150 of the object under inspection from on to off, more specifically, from low beam mode to off. Furthermore, as... Figure 4 As shown, the processes of steps S115 to S150 are executed during the execution of the standby process SP.

[0082] In step S155, the standby process SP ends, and the disengagement process LP is executed, thereby moving the vehicle 100 from the reference position P1 to the next location. That is, in this embodiment, the inspection unit 220 executes the disengagement process LP only when the inspection result of the optical axis characteristics meets the optical axis conditions, and does not execute the disengagement process LP until the inspection result of the optical axis characteristics meets the optical axis conditions. As a result, in this embodiment, while the vehicle 100 is stopped at the reference position P1, the inspection of the optical axis characteristics and the adjustment of the optical system 151 can be repeatedly performed until the optical axis characteristics of the headlight 150 meet the optical axis conditions. Then, when the optical axis conditions are met, the vehicle 100 is quickly moved from the reference position P1 by the disengagement process LP.

[0083] In step S160, the reporting unit 235 reports inspection result information FI related to vehicle 100. In step S160, the latest inspection result information FI related to vehicle 100 is reported. For example, if the above-mentioned re-inspection process has been performed more than once, in step S160, regarding the optical axis characteristics, the inspection result of the optical axis characteristics of the last performed re-inspection process and the judgment result JR related to that inspection result are reported. That is, in step S160 of this embodiment, inspection result information FI indicating that the optical axis characteristics are normal is reported. Furthermore, for example, if the light color condition or light quantity condition is not met in step S140 or step S141, inspection result information FI indicating that the light color characteristic or light quantity characteristic is abnormal is reported. In such cases of abnormal light color characteristic or light quantity characteristic, for example, repair or replacement of the light source 159 or repair or replacement of the optical system 151 can be performed on the headlight 150. Alternatively, after such repair of the headlight 150, a headlight inspection can be performed again on the same vehicle 100.

[0084] According to the inspection system 50 of this embodiment described above, the light distribution characteristics of the headlight 150 are inspected using an inspection image KG containing the projected light LT projected from the headlight 150 onto the projection object. Therefore, the light distribution characteristics of the headlight 150 can be inspected using this novel method of the inspection image KG. Furthermore, in this embodiment, the dedicated equipment, i.e., a headlight tester, previously used in the inspection of the headlight 150 is unnecessary; a more general-purpose imaging device such as a CM can be used to construct an inspection system 50 capable of automatically inspecting the headlight 150.

[0085] Furthermore, in this embodiment, the optical system 151 is adjusted by the adjustment unit 230 based on the inspection results of the inspection unit 220. Therefore, not only can the light distribution characteristics be inspected, but the light distribution characteristics can also be effectively improved based on the inspection results.

[0086] Furthermore, in this embodiment, the light distribution characteristics are checked by comparing the light distribution pattern of the projected light LT in the inspection image KG, i.e., the object pattern, with a reference light distribution pattern corresponding to the type of vehicle 100. Therefore, the light distribution characteristics of various types of vehicles 100 can be checked in a simpler way.

[0087] Furthermore, in this embodiment, an entry process (EP), a standby process (SP), and a departure process (LP) are executed. During the execution of the standby process (SP), the imaging device (CM) captures the inspection image (KG), the image acquisition unit (215) acquires the inspection image (KG), and the inspection unit (220) inspects the light distribution characteristics. Therefore, it is possible to use autonomous driving to move the vehicle 100 to a reference position (P1), inspect the light distribution characteristics while the vehicle 100 remains at the reference position (P1), and vacate the reference position (P1) after the inspection is completed. As a result, it is possible to perform light distribution characteristic inspections more smoothly using autonomous driving. In particular, it is possible to continuously and smoothly perform headlight inspections on multiple vehicles 100.

[0088] Furthermore, in this embodiment, after checking the optical axis characteristics, if the check result of the optical axis characteristics does not meet the optical axis conditions, an adjustment process is performed, and after the adjustment process is performed, a re-check process is performed. Therefore, even if the check result of the optical axis characteristics does not meet the optical axis conditions, the adjustment of the optical system 151 and the re-check of the optical axis characteristics can be performed efficiently while the vehicle 100 is stationary at the reference position P1.

[0089] Furthermore, in this embodiment, the disengagement process LP is not performed if the optical axis characteristics check result does not meet the optical axis conditions. Therefore, the process from checking the optical axis characteristics to adjusting the optical system 151 can be performed in one go while the vehicle 100 is stationary at the reference position P1.

[0090] Furthermore, in this embodiment, the headlight 150 is switched from off to on after entering the processing EP and before capturing the inspection image KG. Therefore, the light distribution characteristics can be checked more smoothly while suppressing the energy consumption caused by the headlight 150.

[0091] Furthermore, in this embodiment, the headlight 150 is switched from on to off after the inspection image KG is captured and before the disengagement process LP begins. Therefore, energy consumption caused by the headlight 150 can be further suppressed.

[0092] Furthermore, in this embodiment, the projection target is the wall surface WP of the wall WL located on the exterior of the vehicle 100. Therefore, the light distribution characteristics can be inspected using the wall WL. As a result, light from the headlight 150 can be captured from the front by using the wall WL as the projection target. Therefore, compared to the case where the projection target is the floor surface, the possibility of obtaining an inspection image KG containing a clearer projection pattern is increased, and the possibility of performing headlight inspections more appropriately is improved. Additionally, in this embodiment, the wall WL is composed of a gate GT that allows and prohibits the passage of the vehicle 100. Therefore, by allowing the vehicle 100 to pass through the gate GT after the inspection, the vehicle 100 can exit the inspection area DP more smoothly after the inspection.

[0093] Furthermore, in this embodiment, the light distribution characteristics of the first headlight 150A and the second headlight 150B can be inspected at once using an inspection image KG that captures the projection light LT including the first light LT1 projected by the first headlight 150A and the second light LT2 projected by the second headlight 150B.

[0094] Furthermore, in this embodiment, the light distribution characteristics can be checked using a camera 300, which is used as an external sensor to obtain vehicle location information for autonomous driving.

[0095] B. Second implementation method:

[0096] Figure 7 This is a diagram illustrating the headlight inspection in the second embodiment. (See diagram below.) Figure 7 As shown, in the headlight inspection of the second embodiment, unlike the first embodiment, the projected light LT is projected onto the road surface RP of the travel path TR1 of the inspection location DP. That is, the projection target is the road surface RP. In this embodiment, the projected light LT is displayed on the road surface RP by illuminating light from the headlight 150 of the vehicle 100 parked at the reference position P1. Then, the inspection image KG is captured by the imaging device CM, which captures the projected light LT displayed on the road surface RP in this way. Furthermore, the points of the inspection system 50 in the second embodiment that are not specifically described are the same as those in the first embodiment. According to the inspection system 50 in the second embodiment, the light distribution characteristics can be inspected using the travel path TR1. As a result, for example, the light distribution characteristics can be inspected even if a wall WL for headlight inspection is not provided in the inspection location DP. In addition, since the vehicle 100 can travel on the road surface RP used as the projection target, the movement of the vehicle 100 accompanying the headlight inspection can be carried out more smoothly compared to the method of using a wall WL.

[0097] C. Third implementation method:

[0098] Figure 8 This is an explanatory diagram showing the schematic configuration of the inspection system 50v in the third embodiment. The difference between this embodiment and the first embodiment is that the inspection system 50v does not include a server 200. Furthermore, the vehicle 100 in this embodiment can be driven autonomously. Other configurations are the same as in the first embodiment unless otherwise specified.

[0099] In this embodiment, the communication device 130 of the vehicle 100 can communicate with the external sensor 300 and the terminal device 450. The processor 111 of the vehicle control device 110 functions as the vehicle control unit 115v, image acquisition unit 215, inspection unit 220, determination unit 225, and adjustment unit 230 by executing the program PG1 stored in the memory 112. The vehicle control unit 115v acquires the output results obtained from the sensors, generates a driving control signal using the output results, and outputs the generated driving control signal to actuate the actuator assembly 120, thereby enabling the vehicle 100 to drive autonomously. In this embodiment, in addition to the program PG1, the memory 112 also stores the detection model DM, reference path RR, pattern data PD, pattern detection model PM1, and condition data CD in advance. The vehicle control unit 115v in the third embodiment is equivalent to the "control unit" in this disclosure.

[0100] Figure 9 This is a flowchart illustrating the processing flow of the vehicle 100's driving control in the third embodiment. Figure 9 In the processing flow, the processor 111 of the vehicle 100 functions as the vehicle control unit 115v by executing program PG1.

[0101] In step S901, the processor 111 of the vehicle control device 110 obtains vehicle position information using the detection results output from the camera, which is an external sensor 300. In step S902, the processor 111 determines the target location that the vehicle 100 should go to next. In step S903, the processor 111 generates a driving control signal to make the vehicle 100 move toward the determined target location. In step S904, the processor 111 controls the actuator assembly 120 using the generated driving control signal, thereby making the vehicle 100 move according to the parameters represented by the driving control signal. The processor 111 repeatedly performs the acquisition of vehicle position information, determination of target location, generation of driving control signal, and control of actuators at a predetermined cycle. According to the inspection system 50v in this embodiment, even without remote control of the vehicle 100 through the server 200, the vehicle 100 can be driven autonomously.

[0102] In this embodiment, the processor 111 of the vehicle control device 110 executes the... Figure 6 The same inspection and processing are performed. However, in this embodiment, in Figure 6 In steps S105 and S155, the vehicle 100 is moved by autonomous control. In addition, in steps S110 to S150, the vehicle 100 is put into standby mode by autonomous control.

[0103] According to the inspection system 50v in the third embodiment described above, the light distribution characteristics of the headlight 150 can also be inspected by using the new method of inspection image KG.

[0104] D. Other implementation methods:

[0105] (D1) In the above embodiments, the inspection system 50 may also not have the adjustment unit 230.

[0106] (D2) In the above embodiments, during the comparison process, object pattern information TI and reference pattern information SI are prepared using a pattern detection model PM1 as a machine learning model, but are not limited thereto. For example, the object pattern information TI and reference pattern information SI can also be obtained using a predetermined algorithm for extracting predetermined features from an image and describing the extracted predetermined features. Such predetermined features correspond to the inspection items of the headlight inspection, and for example include lightness features related to lightness, chroma features related to chroma, hue features related to hue, and luminance features related to brightness. The lightness features, chroma features, hue features, and luminance features may each include edge features related to edges. More specifically, for example, when the inspection item includes the optical axis, the predetermined features preferably include at least one of the lightness features and the luminance features. In addition, when the inspection item includes light quantity, the predetermined features preferably include at least one of the lightness features and the luminance features. In addition, when the inspection item includes light color, the predetermined features preferably include the hue features. Alternatively, the pattern detection model PM1 can also be configured as a rule-based model capable of outputting object pattern information TI and reference pattern information SI using a specified algorithm.

[0107] (D3) In the above embodiments, the light distribution characteristics are checked by comparing the object pattern with a reference light distribution pattern, but this is not a limitation. For example, the inspection unit 220 may also check the light distribution characteristics by inputting the inspection image KG into the inspection model. The inspection model is, for example, configured as a machine learning model that has been learned by taking the inspection image KG as input and outputting the inspection result of the light distribution characteristics. As such an inspection model, a convolutional neural network (CNN) that has been learned through supervised learning can be used, for example. Alternatively, the inspection model may be, for example, a rule-based model that is constructed to check the light distribution characteristics based on the inspection image KG.

[0108] (D4) In the above embodiments, the entry process EP, standby process SP, and disengagement process LP are performed during the headlight check, but some or all of the entry process EP, standby process SP, and disengagement process LP may not be performed. For example, at least part of the movement of vehicle 100 to reference position P1, the stopping of vehicle 100 at reference position P1, and the movement of vehicle 100 from reference position P1 can also be achieved by a manned driver or by transporting vehicle 100 by a transport device.

[0109] (D5) In the above embodiments, the inspection image KG is captured when the vehicle 100 is stationary, but this is not a limitation. For example, the inspection image KG may also be captured when the vehicle 100 is traveling at a speed below a predetermined speed. The predetermined speed mentioned here is a speed low enough to properly perform headlight inspection, and is determined, for example, based on experiments or simulations. More specifically, the predetermined speed is, for example, a speed low enough to properly perform the detection of object pattern information TI using the pattern detection model PM1 and the extraction of predetermined feature quantities using a predetermined algorithm. In this way, vehicle inspection can be performed more efficiently without stopping the vehicle 100. Furthermore, in the method of capturing the inspection image KG while the vehicle 100 is traveling, it is preferable to capture the inspection image KG when the vehicle 100 is at the reference position P1 and the vehicle 100 is facing the reference direction DS. In this way, the positional and angular relationships between the vehicle 100, the projection object, and the capturing device CM can be fixed at the time of capturing the inspection image KG, so the headlight inspection can be performed more effectively using the inspection image KG. Furthermore, regardless of whether the inspection image KG is captured while the vehicle 100 is stationary or while the vehicle 100 is moving, the inspection image KG can be captured even when the vehicle 100 is not at the reference position P1 or when the vehicle 100 is not facing the reference direction DS. In this case, at least one of the inspection image KG and the information obtained based on the inspection image KG can be corrected according to the position or orientation of the vehicle 100 at the time the inspection image KG was captured. The information obtained based on the inspection image KG is, for example, object pattern information TI.

[0110] (D6) Adjustment processing is performed in each of the above embodiments, but it may also be omitted. For example, after checking the light distribution characteristics of the headlight 150 once, the removal process LP may be performed without adjustment processing to end the inspection process. Alternatively, re-inspection processing is performed in each of the above embodiments, but it may also be omitted. For example, after adjustment processing is performed, the removal process LP may be performed without re-inspection processing to end the inspection process.

[0111] (D7) In the above embodiments, the headlight 150 is switched from off to on after the start of the processing EP and before the inspection image KG is captured, but this is not limited to this. For example, the headlight 150 may be switched on before the start of the processing EP and the headlight 150 may remain on until the inspection image KG is captured. Alternatively, the headlight 150 may be switched on after the start of the standby processing SP.

[0112] (D8) In the above embodiments, the headlight 150 is switched from on to off after the inspection image KG is captured and before the disengagement process LP begins, but this is not limited to this. For example, the headlight 150 may remain on after the inspection image KG is captured, instead of being switched off. Alternatively, the headlight 150 may be switched off after the disengagement process LP begins, for example.

[0113] (D9) In the above embodiments, the projection target is not limited to the wall surface WP or the road surface RP. For example, the projection target may also be the floor surface of a floor where the vehicle 100 cannot drive.

[0114] (D10) In the above embodiments, the projected light LT includes a first light LT1 based on the first headlight 150A and a second light LT2 based on the second headlight 150B. Conversely, the projected light LT may also include only the projected light based on one headlight 150, or only the projected light based on three or more headlights 150. For example, if the headlight of the object under inspection is a single headlight 150, the projected light LT may include only the projected light based on that single headlight 150. Furthermore, if the headlight of the object under inspection is two or more headlights 150, the projected light LT may also include only the projected light based on one headlight 150. In this case, the light distribution characteristics of each headlight of the object under inspection can be inspected using separately different inspection images containing only the projected light based on each headlight.

[0115] (D11) In the above embodiments, a camera, which is an external sensor 300, is used as the imaging device CM for headlight inspection, but it is not limited to this. For example, a camera that is not used for autonomous driving and is installed in a camera at the factory FC can also be used as an external imaging device CM for the vehicle 100. In addition, a camera installed on a vehicle 100 other than the vehicle 100 to be inspected for headlight inspection can also be used as an external imaging device CM for the vehicle 100. Furthermore, the imaging device CM is not limited to an external imaging device for the vehicle 100; an imaging device mounted on the vehicle 100 can also be used.

[0116] (D12) In the above embodiments, various functional units such as the image acquisition unit 215, inspection unit 220, determination unit 225, and adjustment unit 230 in the inspection system 50 can also be installed in the vehicle 100. In this case, either all of the image acquisition unit 215, inspection unit 220, determination unit 225, and adjustment unit 230 can be installed in the vehicle 100, as described in the third embodiment, or only some of these functional units can be installed in the vehicle 100. In addition, in the inspection system 50, some or all of these functional units can also be installed in devices outside the server 200 and the vehicle 100, for example. Furthermore, various information such as the detection model DM, reference path RR, pattern data PD, pattern detection model PM1, and condition data CD can be stored in the memory 112, the memory 202, or devices and recording media outside the server 200 and the vehicle 100.

[0117] (D13) In the above embodiments, the external sensor 300 is not limited to a camera, but may also be a ranging device, for example. The ranging device may be a LiDAR (Light Detection and Ranging) system. In this case, the detection result output by the external sensor 300 may also be three-dimensional point cloud data representing the vehicle 100.

[0118] (D14) In the first embodiment described above, the server 200 performs the process from obtaining the vehicle location information to generating the driving control signal. In contrast, the vehicle 100 may also perform at least a portion of the process from obtaining the vehicle location information to generating the driving control signal. For example, it may be performed in the manner described in (1) to (3) below.

[0119] (1) The server 200 may obtain vehicle location information, determine the target location that vehicle 100 should go to next, and generate a path from the current location of vehicle 100 as indicated by the obtained vehicle location information to the target location. The server 200 may generate a path from the current location to the target location, or a path to the destination. The server 200 may send the generated path to vehicle 100. Vehicle 100 may generate a driving control signal in such a way that vehicle 100 travels on the path received from server 200, and use the generated driving control signal to control actuator group 120.

[0120] (2) The server 200 can obtain vehicle location information and send the obtained vehicle location information to the vehicle 100. The vehicle 100 can decide the target location that the vehicle 100 should go to next, generate a path from the current position of the vehicle 100 represented by the received vehicle location information to the target location, generate a driving control signal in the manner that the vehicle 100 travels on the generated path, and use the generated driving control signal to control the actuator group 120.

[0121] (3) In the methods described in (1) and (2) above, the vehicle 100 may be equipped with an internal sensor, and the detection results output from the internal sensor may be used in at least one of the path generation and driving control signal generation. For example, in the method described in (1) above, the server 200 may obtain the detection results of the internal sensor and reflect the detection results of the internal sensor in the path when generating the path. In the method described in (1) above, the vehicle 100 may obtain the detection results of the internal sensor and reflect the detection results of the internal sensor in the driving control signal when generating the driving control signal. In the method described in (2) above, the vehicle 100 may obtain the detection results of the internal sensor and reflect the detection results of the internal sensor in the path when generating the path. In the method described in (2) above, the vehicle 100 may obtain the detection results of the internal sensor and reflect the detection results of the internal sensor in the driving control signal when generating the driving control signal.

[0122] (D15) In the third embodiment described above, the vehicle 100 may be equipped with an internal sensor, and the detection results output from the internal sensor may be used in at least one of the processes of path generation and driving control signal generation. For example, the vehicle 100 may acquire the detection results from the internal sensor and reflect these results in the path generation. Alternatively, the vehicle 100 may acquire the detection results from the internal sensor and reflect these results in the driving control signal when generating the driving control signal.

[0123] (D16) In the third embodiment described above, the vehicle 100 obtains vehicle position information using the detection results of the external sensor 300. In contrast, the vehicle 100 may be equipped with internal sensors. The vehicle 100 uses the detection results of the internal sensors to obtain vehicle position information, determines the target location the vehicle 100 should go to next, generates a path from the current position of the vehicle 100 as indicated by the obtained vehicle position information to the target location, generates a driving control signal for traveling on the generated path, and uses the generated driving control signal to control the actuator assembly 120. In this case, the vehicle 100 can travel without using the detection results of any external sensor 300. Furthermore, the vehicle 100 may obtain the target arrival time and / or congestion information from outside the vehicle 100, reflecting the target arrival time and / or congestion information in at least one of the path and the driving control signal. Additionally, the entire functionality of the inspection system 50v may be provided within the vehicle 100. That is, the processing implemented by the inspection system 50v in this disclosure can be implemented solely by the vehicle 100.

[0124] (D17) In the first embodiment described above, the server 200 automatically generates a driving control signal to be sent to the vehicle 100. Alternatively, the server 200 may also generate a driving control signal to be sent to the vehicle 100 according to the operation of an external operator located outside the vehicle 100. For example, the server 200 may generate a driving control signal corresponding to the operation applied to the driving control device, which is equipped with a display showing images captured from external sensors 300, a steering wheel for remotely operating the vehicle 100, an accelerator pedal, a brake pedal, and a communication device for communicating with the server 200 via wired or wireless communication, operated by an external operator.

[0125] (D18) Vehicle 100 can also be manufactured by combining multiple modules. A module means a unit composed of one or more parts according to the structure and function of vehicle 100. For example, the chassis of vehicle 100 can be manufactured by combining a front module constituting the front part of the chassis, a central module constituting the central part of the chassis, and a rear module constituting the rear part of the chassis. In addition, the number of modules constituting the chassis is not limited to three, and may be two or less or four or more. In addition, parts of vehicle 100 that are different from the chassis can be modularized, or parts of vehicle 100 that are different from the chassis can be modularized instead of the chassis. In addition, various modules may include any exterior parts such as bumpers and grilles, and any interior parts such as seats and consoles. In addition, not limited to vehicle 100, any kind of moving body can be manufactured by combining multiple modules. Such modules can be manufactured, for example, by joining multiple parts using welding or fasteners, or by integrally molding at least a part of the module into a single part using casting. A molding method that integrally molds at least a portion of a module into a single component is also known as Giga-casting or Mega-casting. By using Giga-casting, it is possible to form the various parts of a vehicle 100, which were previously formed by joining multiple components, into a single component. For example, the aforementioned front module, central module, and rear module can also be manufactured using Giga-casting.

[0126] (D19) Transporting vehicle 100 using the driving of driverless vehicle 100 is also called "autonomous transport". Furthermore, the configuration used to achieve autonomous transport is also called a "vehicle remote control autonomous driving transport system". Additionally, the production method that uses autonomous transport to produce vehicle 100 is also called "autonomous production". In autonomous production, for example in a factory FC that manufactures vehicle 100, at least a portion of the transport of vehicle 100 is achieved through autonomous transport.

[0127] This disclosure is not limited to the embodiments described above, and can be implemented in various configurations without departing from its spirit. For example, technical features in the embodiments that correspond to the technical features in the various embodiments described in the "Summary of the Invention" section can be appropriately replaced or combined to solve some or all of the above-described problems, or to achieve some or all of the above-described effects. In addition, such technical features can be appropriately deleted as long as they are not described as essential parts in this specification.

Claims

1. An inspection system, comprising: The image acquisition unit acquires an image captured by the imaging device, including the projected light from the headlight of the moving body projected onto the projection object; and The inspection department uses the acquired images to inspect the light distribution characteristics of the headlights.

2. The inspection system according to claim 1, wherein, It also includes an adjustment unit for adjusting the optical system of the headlight. The adjustment unit adjusts the optical system based on the inspection results of the inspection unit on the light distribution characteristics.

3. The inspection system according to claim 1, wherein, The inspection unit inspects the light distribution characteristics by comparing the light distribution pattern of the projected light in the image with a reference light distribution pattern corresponding to the type of the moving body.

4. The inspection system according to claim 1, wherein, It also has a control unit that enables the mobile body to move autonomously. The control unit performs: The process begins, causing the moving body to move towards a pre-set reference position. Standby processing: After the entry process, the moving body is brought to a stop at the reference position. as well as After the standby process, the moving body is moved from the reference position. The image acquisition unit acquires the image captured during the standby processing execution period. The inspection unit checks the light distribution characteristics during the standby processing.

5. The inspection system according to claim 4, wherein, It also includes an adjustment unit for adjusting the optical system of the headlight. The light distribution characteristics include optical axis characteristics related to the optical axis of the headlamp. After checking the optical axis characteristics, if the checking result of the checking unit does not meet the preset optical axis conditions, the adjustment unit performs an adjustment process to adjust the optical system based on the checking result during the standby process. The inspection unit re-inspects the optical axis characteristics after the adjustment process is executed and during the standby process.

6. The inspection system according to claim 5, wherein, The control unit does not perform the disengagement process until the inspection result meets the optical axis condition.

7. The inspection system according to claim 4, wherein, The control unit is configured to control the headlights. After the entry process begins but before the image is captured, the control unit switches the headlights from off to on.

8. The inspection system according to claim 4, wherein, The control unit is configured to control the headlights. After the image is captured and before the detachment process begins, the control unit switches the headlights from on to off.

9. The inspection system according to claim 1, wherein, The projection target is the wall surface of a wall located outside the moving body.

10. The inspection system according to claim 1, wherein, The projection target is the road surface of the road on which the vehicle, as the moving body, can travel.

11. The inspection system according to claim 1, wherein, The headlights include a first headlight and a second headlight. The projected light includes a first light projected by the first headlight and a second light projected by the second headlight. The inspection unit uses the acquired images to inspect the light distribution characteristics of the first headlight and the second headlight.

12. The inspection system according to any one of claims 1 to 11, wherein, The camera is located outside the mobile body and is used to obtain the location information of the mobile body for unmanned driving.

13. An inspection method, To acquire an image captured by a shooting device, containing the projected light from the headlights of a moving object projected onto the object. The acquired images are used to examine the light distribution characteristics of the headlights.

Images