Vehicle manufacturing system and vehicle manufacturing method

Abstract

The present invention provides a vehicle manufacturing system and a vehicle manufacturing method that enable the rapid stopping of a vehicle. [Solution] The vehicle manufacturing system 50 according to this embodiment is a vehicle manufacturing system that controls multiple vehicles 100 to travel in a convoy during the manufacturing process or transport process, and comprises a camera that takes images of the travel area and its surroundings in which the multiple vehicles travel, a worker detection unit 252 that detects workers based on the images captured by the camera, and a stop control unit 255 that performs image analysis of multiple frames of the captured images and stops the vehicle 100 if a worker detected in the previous frame is not detected in the subsequent frame.

Description

Technical Field

[0001] The present disclosure relates to a vehicle manufacturing system and a vehicle manufacturing method.

Background Art

[0002] Patent Document 1 discloses a vehicle manufacturing system. The vehicle travels within a system for manufacturing a vehicle by autonomous control or remote control.

Prior Art Document

Patent Document

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a vehicle manufacturing factory, a plurality of vehicles travel autonomously along a conveyance path and are sequentially manufactured. Therefore, productivity can be improved. On the other hand, it is also desirable to control the vehicle from the outside. For example, in an emergency, an operator may want to stop or decelerate the vehicle. In such a case, operating devices such as switches and buttons are installed near the manufacturing line so that the operator can easily operate. However, installing devices in the conveyance path hinders the running of the vehicle and the work of the operator. Due to the limitation of the installation location of the devices, there is a problem that the vehicle cannot be stopped promptly.

[0005] Therefore, an object of the present disclosure is to provide a vehicle manufacturing system and a vehicle manufacturing method capable of promptly stopping a vehicle.

Means for Solving the Problems

[0006] ' The vehicle manufacturing system according to this disclosure is a vehicle manufacturing system that controls multiple vehicles to travel in a convoy during a manufacturing process or a transport process, and comprises: a camera that takes images of a travel area and its surroundings in which the multiple vehicles travel; a worker detection unit that detects workers in the vicinity of the vehicles by performing image processing on the images captured by the camera; and a stop control unit that performs image analysis on multiple frames of the captured images and stops the vehicles if the workers detected in the previous frame are not detected in the subsequent frames.

[0007] The vehicle manufacturing method according to this disclosure is a vehicle manufacturing method that controls multiple vehicles to travel in a convoy during a manufacturing process or a transport process, comprising the steps of: capturing images of a travel area and its surroundings on which the multiple vehicles are traveling using a camera; detecting workers in the vicinity of the vehicles by performing image processing on the images captured by the camera; and stopping the vehicles by performing image analysis on multiple frames of the captured images and determining if the workers detected in the previous frame are not detected. [Effects of the Invention]

[0008] This disclosure provides a vehicle manufacturing system and a vehicle manufacturing method that can quickly stop a vehicle. [Brief explanation of the drawing]

[0009] [Figure 1] This is a schematic diagram showing the overall configuration of the vehicle manufacturing system. [Figure 2] This is a schematic diagram showing a part of the vehicle manufacturing system. [Figure 3] This is a schematic plan view showing a portion of the track layout of the vehicle manufacturing system. [Figure 4] This is a schematic side view showing a portion of the track layout of a vehicle manufacturing system. [Figure 5] This is a block diagram of the control system for a vehicle manufacturing system. [Figure 6] This is a diagram illustrating the state of a worker who has fallen. [Figure 7] This is a flowchart showing the vehicle manufacturing process. [Figure 8] This is a diagram illustrating the vehicle's driving control. [Figure 9] This is a control block diagram illustrating example 1 of the driving control system. [Figure 10] This is a flowchart to explain example 1 of the driving control system. [Figure 11] This is a control block diagram illustrating example 2 of the driving control system. [Figure 12] This is a flowchart to explain example 2 of the driving control system. [Modes for carrying out the invention]

[0010] Embodiments of the present invention will be described below with reference to the drawings. However, the invention claimed is not limited to the following embodiments. Furthermore, not all of the configurations described in the embodiments are necessarily essential for solving the problem. For clarity of explanation, the following descriptions and drawings have been omitted and simplified as appropriate. In each drawing, the same elements are denoted by the same reference numerals, and redundant explanations have been omitted where necessary.

[0011] Embodiment 1 Vehicle manufacturing system The vehicle manufacturing system 50 according to this embodiment will be described with reference to Figures 1 and 2. Figure 1 is a schematic diagram showing the configuration of the vehicle manufacturing system 50. Figure 2 is a schematic diagram showing two vehicles 100 in motion. Note that in Figure 1, an XY Cartesian coordinate system is shown for illustrative purposes.

[0012] The vehicle manufacturing system (simply referred to as the system) 50 is used in a vehicle manufacturing factory that manufactures vehicles 100. Alternatively, the vehicle manufacturing system 50 is also used at a transportation location where transportation processes such as transportation to the yard and shipping are carried out. As shown in FIG. 1, the vehicle manufacturing system 50 includes a server 200, a sensor 300, and a robot 600. The plurality of vehicles 100 are self-propelled vehicles that can move on their own during the manufacturing process. The vehicle manufacturing system 50 controls the plurality of vehicles 100 to travel in a queue.

[0013] The sensor 300 includes a communication device 330 that transmits and receives data to and from the server 200. The server 200 includes a communication device 230 that transmits and receives data to and from the sensor 300. Further, as shown in FIG. 2, the communication device 230 has a function of transmitting and receiving data to and from the vehicle 100. Also, the vehicle 100 includes a communication device 130 that receives data from the server 200. Each vehicle 100 includes the communication device 130.

[0014] The communication device 130, the communication device 230, and the communication device 330 may each be general-purpose devices such as a network hub or a router device. The communication device 130, the communication device 230, and the communication device 330 use, for example, general-purpose wireless communication such as WiFi (registered trademark). An address for specifying a communication partner is set for each of the communication device 130, the communication device 230, and the communication device 330. The communication address is, for example, an IP (Internet Protocol) address.

[0015] Each vehicle 100 is a vehicle before completion. As shown in FIG. 1, the vehicle 100 travels along a preset path TR. As the vehicle 100 travels along the path TR, the vehicle 100 is being manufactured. Specifically, while the vehicle 100 is traveling on the path, an operator W or a robot 600 or the like performs operations such as part assembly, switch operation, welding, and inspection. Thereby, the operations of each manufacturing process are executed. And the vehicle 100 is manufactured by performing the operations of each manufacturing process in a predetermined order.

[0016] A plurality of vehicles 100 travel in a formation. Specifically, the vehicles 100 travel at a constant speed such that the vehicle distance remains constant at a predetermined distance. Furthermore, the speeds of the plurality of vehicles 100 are the same. Also, the road TR has a straight-ahead region TR1 where the vehicle 100 travels straight and a turning region TR2 where the vehicle turns. In the straight-ahead region TR1, the road TR is straight.

[0017] The turning region TR2 is a location where the vehicle 100 changes direction. In the turning region TR2, the vehicle 100 makes a U-turn. In the turning region TR2, for example, the road TR is in the shape of an arc having a predetermined radius of curvature. In the turning region TR2, the road TR is a semi-circle. The turning regions TR2 are provided at both ends of the straight-ahead region TR1. For example, when the vehicle 100 advances in the +X direction in the straight-ahead region TR1, it reaches the turning region TR2. When the vehicle 100 makes a 180-degree turn in the turning region TR2, it advances in the -X direction in the straight-ahead region TR1. Conversely, when advancing in the -X direction in the straight-ahead region TR1, it reaches the turning region TR2. When the vehicle 100 makes a 180-degree turn in the turning region TR2, it advances in the +X direction in the straight-ahead region TR1. Thus, the vehicles 100 are sequentially manufactured by alternately passing through the straight-ahead region TR1 and the turning region TR2.

[0018] The sensor 300 is a camera that images the vehicle 100 while it is moving or stopped. The sensor 300 images one or a plurality of vehicles 100. The sensor 300 is provided to detect the inter-vehicle distance. Based on the image captured by the sensor 300, the server 200 can detect the position of the vehicle 100 in the factory. For example, it is installed on the wall surface, columns, ceiling, etc. of the factory and images the vehicle 100 from an oblique upper direction. The sensor 300 captures an image with an angle of view that includes two or more vehicles 100 forming a formation. The sensor 300 is set at the same height as the vehicle 100 and may image two or more vehicles 100 from the side.

[0019] The communication device 330 transmits the image captured by the sensor 300 to the server 200. The communication device 330 may transmit not only the captured image but also information obtained from the captured image to the server 200. In other words, the communication device 330 transmits the detection results detected by the sensor 300. The communication device 330 may be built into the sensor 300 or it may be a separate unit. Also, the communication device 330 may be shared by multiple sensors 300. In other words, if multiple sensors 300 are installed, one communication device 330 may transmit data to the server 200.

[0020] In this manner, when the sensor 300 captures an image of the vehicle 100, the communication device 330 transmits the captured image and other data to the server 200. The communication device 230 receives the captured image data from the sensor 300. The server 200 can estimate the distance between vehicles by performing predetermined image processing on the image captured by the sensor 300. For example, the server 200 calculates the distance between vehicles in a convoy of multiple vehicles 100. The number of vehicles in the convoy is not particularly limited; it must be three or more.

[0021] Furthermore, the sensor 300 for detecting the distance between vehicles is not limited to a camera. The sensor for detecting the distance between vehicles may be various types of sensors such as an RGB camera, a far-infrared camera, or LiDAR. The sensor 300 is not limited to an optical sensor; it may also be radar. Of course, two or more sensors 300 may be installed, or two or more types of sensors 300 may be used in combination. For example, the sensor 300 may include both LiDAR and a camera.

[0022] The communication device 330 transmits the detection result to the server 200. As described above, the detection result transmitted by the sensor 300 may be an captured image or information extracted from the image. For example, if the sensor 300 has an image processing function, the sensor 300 transmits information extracted by image processing to the server 200.

[0023] Furthermore, the sensor 300 may be mounted on the vehicle 100, as shown in Figure 2. For example, an on-board camera, LiDAR, or radar can be the sensor 300. If the sensor 300 is an on-board camera, the sensor 300 will capture an image of the vehicle 100 in front. If the sensor 300 is an on-board LiDAR, the sensor 300 will measure the distance to the vehicle 100 in front. The communication device 130 will transmit the image and measurement results to the server 200.

[0024] The server 200 controls the vehicle 100 so that it moves along the track TR. Furthermore, the server 200 controls multiple vehicles 100 so that they travel in a convoy. For example, the vehicles 100 travel in a single file along the track TR. The server 200 transmits control signals to each vehicle 100 via the communication device 230.

[0025] Furthermore, the detailed configuration of the track TR and its surrounding equipment will be explained using Figures 3 and 4. Figure 3 is a schematic plan view showing a vehicle traveling on the track TR and workers W in its vicinity. Figures 3 and 4 show three vehicles 100 autonomously traveling along the track TR.

[0026] Here, the area in which vehicle 100 travels is defined as the travel area A. The travel area A includes the track TR. In this XY plan view, since the track TR is a straight line along the X direction, the travel area A is a strip-shaped area along the X direction. The travel area A is a strip-shaped area with a width approximately the same as the width of vehicle 100.

[0027] A worker W is present around vehicle 100. Worker W is performing tasks on vehicle 100. While vehicle 100 is traveling in travel area A, worker W performs tasks such as assembling parts, operating switches, welding, and inspection. This completes the tasks for each manufacturing process. Then, by performing the tasks for each manufacturing process in a predetermined order, vehicle 100 is manufactured. Worker W is also walking at a distance from vehicle 100. Alternatively, worker W is walking towards vehicle 100 carrying parts or other items.

[0028] Here, the area corresponding to the driving area A is defined as detection area DA1. The area other than detection area DA1 is defined as non-detection area DA2. In this example, non-detection area DA2 is located on both sides of detection area DA1. Of course, detection area DA1 and non-detection area DA2 are not limited to the shapes and arrangements shown in the diagram. Non-detection area DA2 is the area outside detection area DA1, that is, the area other than detection area DA1.

[0029] As will be described later, the server 200 determines whether worker W is hidden in the blind spot of vehicle 100 in detection area DA1. On the other hand, the server 200 does not determine whether worker W is hidden in the blind spot of vehicle 100 in non-detection area DA2. The determination process in detection area DA1 will be described later. Worker W is in either detection area DA1 or non-detection area DA2.

[0030] Furthermore, control equipment 30 is provided around the travel area A. The control equipment 30 transmits a control signal to the server 200 to stop the vehicle 100. The control equipment 30 is installed, for example, on the ceiling or walls of the factory building. The installation location of the control equipment 30 may be movable. In this case, control equipment 30 is provided on both sides of the travel area A. That is, control equipment 30 is provided on both the +Y side and the -Y side of the travel area A. Of course, the installation location and number of control equipment 30 are not particularly limited.

[0031] A string 31 is connected to the control device 30. The control device 30 and the string 31 are installed at a height that does not interfere with the worker W or the vehicle 100. Furthermore, a suspension string 32 is attached to the string 31. The suspension string 32 is suspended at a height that can be reached by the worker W. When the worker W pulls the suspension string 32, the control device 30 turns on and transmits a control signal. As a result, the vehicle 100 stops.

[0032] When worker W detects an anomaly or trouble, they can pull the suspension cord 32 to bring the vehicle 100 to an emergency stop. The suspension cord 32 functions as a stop switch to stop the vehicle 100. In other words, when worker W pulls the suspension cord 32, which is the stop switch, the control device 30 turns on and sends a control signal to the server 200. As a result, the vehicle 100 stops. The control device 30, the cord 31, and the suspension cord 32 function as emergency stop devices.

[0033] Here, the suspension cords 32 are positioned outside the travel area A so as not to interfere with the vehicle 100. If the suspension cords 32, which are operated by the worker W, are installed in the travel area A, they may come into contact with the moving vehicle 100. There may be cases where the worker W, who is near the vehicle 100, wants to stop the vehicle 100 immediately. Therefore, the suspension cords 32 are installed on both sides of the travel area A. In other words, the suspension cords 32 are located in the non-detection area DA2 described above. Also, if there are too many suspension cords 32, they may obstruct the work or passage of the worker W. Therefore, the suspension cords 32 are scattered throughout the non-detection area DA2.

[0034] Furthermore, if worker W, who is in the driving area A, i.e., the detection area DA1, wants to stop the vehicle 100 using the suspension cord 32, worker W will have to move to the suspension cord 32 and pull it. Therefore, if the distance from worker W to the suspension cord 32 is far, it will be difficult to quickly pull the suspension cord 32. For this reason, in the detection area DA1, the vehicle 100 can be controlled based on the image captured by the sensor 300.

[0035] The control for stopping the vehicle 100 during the manufacturing or transport process will be explained below with reference to Figure 5. Figure 5 is a block diagram showing the configuration of the control system of the vehicle manufacturing system 50. As shown in Figure 5, the server 200 includes a worker detection unit 252, an area determination unit 253, and a stop control unit 255. Although Figure 5 shows one vehicle 100 and one sensor 300, multiple vehicles 100 and sensors 300 are provided, as shown in Figure 1.

[0036] Vehicle 100 includes a vehicle control unit 115, an actuator group 120, and a communication device 130. Sensor 300 is equipped with the communication device 130. Note that the server 200 is not limited to a single physical device, but may be distributed. For example, the database may be a separate storage device or cloud server located independently of the processor.

[0037] The communication device 230 includes a receiver 231 and a transmitter 232. The receiver 231 receives various signals and data from the sensor 300 and the vehicle 100. For example, the receiver 231 receives data indicating the detection result from the sensor 300. The data received from the sensor 300 may be image data or data extracted from image data.

[0038] The transmitter 232 transmits various signals and data to the sensor 300 and the vehicle 100. For example, the transmitter 232 transmits control instruction values ​​to the vehicle 100. Of course, the server 200 may also send and receive data other than those mentioned above. For communication between the receiver 231 and the transmitter 232, it is possible to use processing in accordance with general-purpose communication standards such as WiFi (registered trademark).

[0039] The communication device 130 of vehicle 100 is a wireless terminal device for wireless communication with server 200. The communication device 130 is configured with an IP (Internet Protocol) address, etc. When the communication device 130 of vehicle 100 receives a control instruction value, vehicle 100 moves according to the control instruction value. The actuator group 120 includes wheel motors for driving the wheels, steering motors for controlling the steering angle, brakes for stopping the vehicle, etc. The vehicle control unit 115 generates control signals to control the actuator group 120 according to the control instruction. The vehicle control unit 115 may be composed of an ECU (Electronic Control Unit). This allows vehicle 100 to move along the track TR.

[0040] In the following explanation, it is assumed that the server 200 performs image processing on the captured images acquired from the sensor 300, but the processing may be performed by a device other than the server 200. For example, the sensor 300 may perform part of the processing. Specifically, the sensor 300 may extract the features necessary for image processing and send those features to the server 200. Alternatively, a processor such as a GPU (Graphics Processing Unit) installed in the sensor 300 may detect the worker W and send the detection result.

[0041] As described above, the sensor 300 transmits the captured image to the server 200. The captured image may be a moving image or a still image. When the communication device 230 of the server 200 receives the captured image, the worker detection unit 252 detects the workers W contained in the captured image by performing image processing on the image. For example, the worker detection unit 252 detects each worker W by performing image processing on the captured image. An AI model built using machine learning or an image processing program can be used for the process of detecting the workers W.

[0042] Since known methods can be used for the processing of the worker detection unit 252, a detailed explanation will be omitted. As described above, the sensor 300 may transmit data such as feature quantities extracted from the captured image, rather than the captured image itself. Alternatively, the processing of the worker detection unit 252 may be performed by the sensor 300.

[0043] For example, the worker detection unit 252 can detect worker W by inputting a captured image into a detection model that utilizes artificial intelligence. Examples of detection models include pre-trained machine learning models that have been trained to implement either semantic segmentation or instance segmentation. As for this machine learning model, for example, a convolutional neural network (CNN) trained by supervised learning using a training dataset can be used. The training dataset includes, for example, multiple training images containing workers and ground truth labels indicating whether the area where the worker is located is a detection area or a non-detection area. When training the CNN, it is preferable to update the CNN parameters by backpropagation to reduce the error between the output result of the detection model and the ground truth label.

[0044] The stop control unit 255 performs image analysis on multiple frames of the captured image and stops the vehicle 100 if the worker W detected in the previous frame is not detected in the subsequent frame. For example, as shown in Figures 3 and 4, suppose the sensor 300 is capturing an image from the front with a field of view V that includes the vehicle 100 and the worker W behind it. Here, the sensor 300 is installed facing diagonally downwards. The worker W is directly behind the vehicle 100. In the frame, the lower body of the worker W will be hidden by the vehicle 100. In other words, the frame includes the head and upper body of the worker W. Suppose the worker W is performing assembly work on the vehicle 100 from behind.

[0045] At this point, if worker W falls, the situation will be as shown in Figure 6. In Figure 6, the fallen worker W is hidden in the blind spot of vehicle 100. In other words, sensor 300 is unable to image worker W, who is hidden in the blind spot. Therefore, the stop control unit 255 analyzes multiple frames to detect that worker W, who was in the previous frame, has disappeared from the frame. In other words, the stop control unit 255 detects that worker W has been hidden in the blind spot of vehicle 100 or the like.

[0046] If worker W falls, their entire body or most of their body will be in the blind spot of vehicle 100, etc. Therefore, worker W, who was included in the previous frame, will no longer be included in the next frame. The stop control unit 255 can detect the fall of worker W, etc., by comparing multiple frames. If worker W enters the blind spot of vehicle 100 relative to sensor 300, worker W will disappear from the frame. Therefore, if worker W, who was detected by worker detection unit 252 in a given frame, cannot be detected in the next frame, the stop control unit 255 generates a stop signal to stop vehicle 100.

[0047] Then, the transmitter 232 transmits a stop signal to the vehicle 100. When the communication device 130 of the vehicle 100 receives the stop signal, the vehicle control unit 115 stops the vehicle 100. For example, the vehicle control unit 115 applies the brakes. This brings the vehicle 100 to a stop. In this way, if the worker W falls near the vehicle 100, the stop control unit 255 can quickly stop the vehicle 100. This prevents the vehicle 100 from coming into contact with the fallen worker W.

[0048] For example, the worker detection unit 252 detects workers W in each frame and stores the number and location of workers W in memory or elsewhere. The stop control unit 255 compares the number of workers W between two consecutive frames. If the number of workers W has decreased compared to the previous frame, the stop control unit 255 detects that workers W are hidden in a blind spot. Of course, if workers W move into the field of view from outside the field of view V, the stop control unit 255 takes that increase in workers into account and processes accordingly. Furthermore, the worker detection unit 252 is not limited to detecting workers in each frame; it may also detect workers every multiple frames. In other words, the stop control unit 255 only needs to compare a given frame with the frame before it.

[0049] Since the vehicle 100 is in motion, it is difficult to ensure that there are no blind spots around the vehicle 100. In other words, in order to image the entire front, rear, left, and right sides of the moving vehicle 100, it would be necessary to install sensors 300 at various positions and angles. In this embodiment, even if a blind spot occurs in the sensor 300, if a worker W falls in that blind spot, the stop control unit 255 will stop the vehicle 100. This prevents the fallen worker W from coming into contact with the vehicle W100. Safety can be improved without increasing the number of sensors 300. Furthermore, since the number of sensors 300 can be reduced, the image processing load can be reduced.

[0050] The stop control unit 255 may stop the vehicle 100 if it is estimated that the worker W is in a blind spot of the camera caused by the vehicle 100. For example, the stop control unit 255 may estimate that the worker W is hidden in the blind spot of the vehicle 100 by referring to the front-to-back relationship between the worker W and the vehicle 100 with respect to the sensor 300. As shown in Figure 4, suppose the vehicle 100 is between the worker W and the sensor 300. In this case, part of the worker W, who is behind the vehicle 100, will be hidden by the vehicle 100. Specifically, in Figure 4, the lower half of the worker W is hidden by the vehicle 100, so only the upper half is captured in the image.

[0051] Therefore, the stop control unit 255 may detect the relative positions of the vehicle 100 and the worker W by image analysis. For example, the boundary line between the vehicle 100 and the worker W can be determined, and the relative positions can be detected based on the shape of the boundary line. The stop control unit 255 may also estimate the relative positions of the worker W and the vehicle 100 using a machine learning model. The stop control unit 255 may stop the vehicle 100 when the worker W, who is behind the vehicle 100, disappears from the frame.

[0052] The stop control unit 255 may determine whether worker W has moved outside the field of view V, or whether it has become a blind spot for vehicle 100 and is no longer visible in the frame. For example, if worker W, who is located near the periphery of the frame, walks towards the outside of the field of view V, worker W may move out of the frame. In such a case, even if the number of workers has decreased compared to the previous frame, the stop control unit 255 will not stop vehicle 100. In this way, the server 200 can appropriately control vehicle 100.

[0053] For example, the worker detection unit 252 detects the position of each worker W. Here, the position of worker W may be a pixel address in the frame, or it may be a position within the factory. The stop control unit 255 compares the positions of worker W in each frame and estimates the direction and speed of movement of worker W. The stop control unit 255 may use a machine learning model to estimate the speed and direction of movement of worker W.

[0054] The stop control unit 255 determines, based on the direction of movement, whether the worker W is moving outside the field of view V. If the worker W, who was moving from near the edge of the frame towards the outside of the field of view V, disappears from the frame, the stop control unit 255 determines that the worker W has disappeared from the frame due to movement. In this case, since the worker W moved outside the field of view V by walking or other means, the stop control unit 255 does not determine that the worker W has fallen. The stop control unit 255 does not generate a stop signal.

[0055] On the other hand, if worker W, who was in the center of the captured image, disappears from the frame, the stop control unit 255 determines that worker W has fallen. Alternatively, if worker W, who was moving toward the center of the field of view V, disappears from the frame, the stop control unit 255 determines that worker W has fallen. Therefore, the stop control unit 255 generates a stop signal and stops the vehicle 100. This allows the server 200 to control the vehicle 100 appropriately.

[0056] The stop control unit 255 can estimate whether or not the worker W is hidden in the blind spot of the vehicle 100 by performing image analysis on multiple frames. Furthermore, estimation may be performed using a machine learning model. The machine learning model may be an RNN (Recurrent Neural Network) model or an LSTM (Long Short Term Memory) model that takes multiple frame images as input.

[0057] Furthermore, the stop control unit 255 may also detect the posture of the worker W. If the stop control unit 255 detects that the worker W has fallen based on their posture, it may generate a stop signal and stop the vehicle 100. This allows the vehicle 100 to be stopped quickly. The stop control unit 255 may also use a machine learning model to detect posture and a machine learning model to detect falls.

[0058] Furthermore, the server 200 may also have an area determination unit 253. The processing performed by the area determination unit 253 will be described below.

[0059] The area determination unit 253 determines whether the detected worker W is in the detection area DA1 or the non-detection area DA2. For example, the location of the sensor 300 in the building is fixed. A field of view is set for each sensor 300. The locations of the driving area A, the track TR, the detection area DA1, and the non-detection area DA2 within the field of view of the sensor 300 are known. In the captured image, it is possible to determine whether the worker W is in the detection area DA1 or the non-detection area DA2 based on the location where the worker W is detected, i.e., the XY address. Of course, it is also possible to determine that the worker W is in the detection area DA1 based on the size of the worker W in the captured image and its position relative to the vehicle 100 and other objects.

[0060] The area determination unit 253 can use an AI model built using machine learning or an image processing program for its processing. A single machine learning model can also be used for the worker detection unit 252 and the area determination unit 253. In this case, the machine learning model takes the captured image or features extracted from the captured image as input data and outputs people in the detection area DA1. That is, the machine learning model may be configured to detect and output only workers W in the detection area DA1.

[0061] Then, the area determination unit 253 determines that if worker W, who was detected in detection area DA1, is no longer detected, the stop control unit 255 will stop the vehicle. As described above, detection area DA1 corresponds to the driving area A on which vehicle 100 travels. Therefore, if worker W in detection area DA1 falls, they may come into contact with vehicle 100. Thus, if worker W in detection area DA1 disappears from the frame, the stop control unit 255 determines that worker W has fallen. Therefore, the stop control unit 255 generates and transmits a stop signal. In this way, the server 200 can quickly stop vehicle 100.

[0062] On the other hand, the non-detection area DA2 is outside the driving area A. Therefore, even if worker W falls in the non-detection area DA2, the possibility of contact with vehicle 100 is low. In other words, even if worker W enters a blind spot of vehicle 100 or other objects in the non-detection area DA2, there is no risk of contact with vehicle 100. Therefore, even if worker W, who was in the non-detection area DA2, disappears from the frame, the stop control unit 255 will not stop vehicle 100. In this way, vehicle 100 can be controlled appropriately.

[0063] Furthermore, if worker W, who was in detection area DA1, moves to non-detection area DA2, the stop control unit 255 determines that worker W has not fallen. Similarly, if worker W, who was in detection area DA1, moves outside the field of view V, the stop control unit 255 determines that worker W has not fallen. Therefore, in these cases, the stop control unit 255 does not generate a stop signal. In this way, the server 200 can appropriately control the vehicle 100.

[0064] In the event of an abnormality, such as worker W falling, the server 200 can quickly stop the vehicle 100. Furthermore, worker W, being in detection area DA1, is likely to be far from the suspension rope 32. Therefore, if worker W in detection area DA1 detects an abnormality, worker W can quickly control the vehicle 100.

[0065] Furthermore, within the factory, the detection area DA1 and the non-detection area DA2 may be separated according to the installation location of the sensor 300 or the work process. For example, suppose the order of work processes and the work locations in which worker W performs work are predetermined within the travel area A. In such a case, depending on the work process, locations where worker W is in a blind spot and will not be captured in the image can be identified in advance.

[0066] For example, suppose there is a work process in which worker W assembles parts onto vehicle 100 while sitting or crouching. In such a work process, there is a high probability that worker W will be hidden in the blind spot of vehicle 100. Alternatively, suppose there is a work process in which two or more workers W perform the work. In this case, one worker may be hidden in the blind spot of the other worker. Therefore, even if worker W does not fall, worker W may not be visible in the frame. Thus, in the driving area A, the location where a specific work process is performed can be set as a non-detection area DA2. In this way, detection area DA1 and non-detection area DA2 may be set based on the work process and the camera installation within the facility. Detection area DA1 and non-detection area DA2 can be set according to the map of the factory, etc.

[0067] Furthermore, the stop signal may include information indicating the vehicle 100 to be stopped. For example, the stop signal may include the ID of the vehicle 100 to be stopped. In this case, the stop control unit 255 generates a stop signal that includes the ID of the vehicle to be stopped. The vehicle 100 to be stopped may be determined by the position of the worker W. The stop control unit 255 stops the vehicles 100 before and after the worker W has disappeared from the frame. The stop control unit 255 stops only two vehicles 100. The stop control unit 255 can identify the vehicle 100 to be stopped from the position where the worker W was. Of course, the number of vehicles 100 that the stop control unit 255 stops is not limited to two. The number of vehicles 100 that the stop control unit 255 stops may be just one immediately after the worker W, or it may be three or more.

[0068] Furthermore, when worker W pulls the suspension cord 32 (see Figures 3 and 4), the control device 30 sends a signal to the server 200 to stop the vehicle 100. The server 200 then sends a stop signal to the vehicle 100 to stop it, as described above. This allows worker W, who is in the non-detection area DA2, to stop the vehicle quickly. Alternatively, the control device 30 may directly send a stop signal to the vehicle 100.

[0069] Furthermore, in order to improve the accuracy of worker W detection or posture detection, worker W may wear clothing with distinctive colors or patterns. Alternatively, worker W may wear wristbands or the like to improve the accuracy of arm detection. Also, to improve the accuracy of head detection, marks may be placed on helmets or hats. In image processing, worker detection and posture detection are performed by referring to the colors, patterns, wristbands, marks, etc. Furthermore, in machine learning, images of workers wearing distinctive uniforms, wristbands, hats, or helmets may be used as training data. Then, a machine learning model is created using supervised learning, with frames where worker W is in a blind spot as the ground truth data.

[0070] The vehicle manufacturing method will be explained with reference to Figure 7. Figure 7 is a flowchart of the vehicle manufacturing method according to this embodiment. Specifically, Figure 7 shows the processing flow for one frame. Therefore, the processing shown in Figure 6 is executed for each frame of the sensor 300.

[0071] First, the server 200 acquires a frame of the captured image from the sensor 300 (S11). The worker detection unit 252 detects the worker W included in the captured image (S12). The stop control unit 255 compares the detected worker W with the worker W in the previous frame (S13). The stop control unit 255 determines whether all workers who were in the previous frame have been detected (S14).

[0072] If all workers who were present in the previous frame were detected (YES in S14), the process ends. In other words, the server 200 repeats the same process for the next frame. If all workers who were present in the previous frame were not detected (NO in S14), the stop control unit 255 determines whether or not a worker was in the detection area DA1 (S15). In other words, it determines whether or not a worker who is no longer detected in a later frame was in the detection area DA1 in the previous frame. If that worker was not in the detection area DA1 in the previous frame (NO in S15), the process ends. In other words, the server 200 repeats the same process for the next frame.

[0073] If the operator was in the detection area DA1 in the previous frame (YES in S15), the stop control unit 255 generates a stop signal (S16). Here, the transmitter 232 transmits the stop signal to the vehicle 100 (S17). Thereby, the vehicle 100 can be quickly stopped.

[0074] The server 200 repeats the above process for each frame image of the sensor 300. Of course, the server 200 may perform the above process not for all frame images of the sensor 300 but only for some frame images. Further, the server 200 may perform the above process for some of the sensors 300 without performing the above process for all the sensors 300.

[0075] Hereinafter, in the system, a driving control example for controlling the driving of the vehicle 100 will be described.

[0076] <A. Driving control example 1> FIG. 8 is a conceptual diagram showing the configuration of the system 50 in the driving control example 1. The system 50 includes a plurality of vehicles 100 as moving bodies, a server 200, and one or more sensors 300.

[0077] When the moving body is other than a vehicle, the expressions "vehicle" and "car" in the present disclosure can be appropriately replaced with "moving body", and the expression "driving" can be appropriately replaced with "moving".

[0078] Vehicle 100 is configured to operate autonomously. "Autonomous operation" means operation without the operation of a passenger. Operation refers to operations related to at least one of the following: "going," "turning," or "stopping" of vehicle 100. Autonomous operation is achieved by automatic or manual remote control using a device located outside vehicle 100, or by autonomous control of vehicle 100. Vehicle 100 operating autonomously may have passengers on board who do not perform operation. Passengers who do not perform operation include, for example, people simply sitting in the seats of vehicle 100, or people performing tasks other than operation, such as assembly, inspection, or operating switches, while on board vehicle 100. Operation by a passenger is sometimes called "manned operation."

[0079] In this specification, "remote control" includes "fully remote control," in which all operations of the vehicle 100 are completely determined from outside the vehicle 100, and "partial remote control," in which some operations of the vehicle 100 are determined from outside the vehicle 100. Furthermore, "autonomous control" includes "fully autonomous control," in which the vehicle 100 autonomously controls its own operations without receiving any information from external devices, and "partial autonomous control," in which the vehicle 100 autonomously controls its own operations using information received from external devices.

[0080] In this embodiment, system 50 is used in a factory FC where vehicle 100 is manufactured. The reference coordinate system of the factory FC is the global coordinate system GC. That is, any position within the factory FC is represented by X, Y, Z coordinates in the global coordinate system GC. The factory FC comprises a first location PL1 and a second location PL2. The first location PL1 and the second location PL2 are connected by a track TR on which vehicle 100 can travel. Multiple sensors 300 are installed in the factory FC along the track TR. The position of each sensor 300 in the factory FC is pre-adjusted. Vehicle 100 moves from the first location PL1 to the second location PL2 via the track TR by unmanned operation.

[0081] Figure 9 is a block diagram showing the configuration of system 50. The vehicle 100 includes a vehicle control device 110 for controlling various parts of the vehicle 100, an actuator group 120 including one or more actuators driven under the control of the vehicle control device 110, and a communication device 130 for communicating wirelessly with external devices such as a server 200. The actuator group 120 includes actuators for a drive system to accelerate the vehicle 100, actuators for a steering system to change the direction of travel of the vehicle 100, and actuators for a braking system to decelerate the vehicle 100.

[0082] The vehicle control device 110 is composed of a computer comprising a processor 111, a memory 112, an input / output interface 113, and an internal bus 114. The processor 111, the memory 112, and the input / output interface 113 are connected via the internal bus 114 to enable bidirectional communication. The input / output interface 113 is connected to an actuator group 120 and a communication device 130. The processor 111 implements various functions, including those of a vehicle control unit 115, by executing PG1 stored in the memory 112.

[0083] The vehicle control unit 115 drives the vehicle 100 by controlling the actuator group 120. The vehicle control unit 115 can drive the vehicle 100 by controlling the actuator group 120 using the driving control signal received from the server 200. The driving control signal is a control signal for driving 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, or in addition to, the acceleration of the vehicle 100.

[0084] The server 200 is composed of a computer comprising a processor 201, memory 202, an input / output interface 203, and an internal bus 204. The processor 201, memory 202, and input / output interface 203 are connected via the internal bus 204 to enable bidirectional communication. A communication device 205 for communicating with various devices outside the server 200 is connected to the input / output interface 203. The communication device 205 can communicate with the vehicle 100 via wireless communication and can communicate with each sensor 300 via wired or wireless communication. The processor 201 implements various functions, including those of a remote control unit 210, by executing PG2 stored in memory 202.

[0085] The remote control unit 210 acquires detection results from sensors, generates a driving control signal to control the actuator group 120 of the vehicle 100 using the detection results, and transmits the driving control signal to the vehicle 100, thereby driving the vehicle 100 by remote control. In addition to the driving control signal, the remote control unit 210 may also generate and output control signals to control various auxiliary equipment and actuators that operate various devices such as wipers, power windows, and lamps, which are provided on the vehicle 100. In other words, the remote control unit 210 may operate these various devices and auxiliary equipment by remote control.

[0086] Sensor 300 is a sensor located outside of vehicle 100. In this embodiment, sensor 300 is a sensor that detects vehicle 100 from outside of vehicle 100. 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.

[0087] Specifically, the sensor 300 is comprised of a camera. The camera, as part of the sensor 300, captures an image including the vehicle 100 and outputs the captured image as the detection result.

[0088] Figure 10 is a flowchart showing the processing procedure for vehicle 100's driving control in an example of driving control. In the processing procedure shown in Figure 10, the processor 201 of the server 200 functions as a remote control unit 210 by executing program PG2. The processor 111 of the vehicle 100 functions as a vehicle control unit 115 by executing program PG1.

[0089] In step S110, the processor 201 of the server 200 acquires vehicle position information of the vehicle 100 using the detection result output from the sensor 300. The vehicle position information is the position information that forms the basis for generating the driving control signal. 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 S110, the processor 201 acquires vehicle position information using the captured image acquired from the camera, which is the sensor 300.

[0090] In detail, in step S110, the processor 201 detects the outline of the vehicle 100 from the captured image, calculates the coordinates of the vehicle 100's positioning point in the coordinate system of the captured image, i.e., the local coordinate system, and obtains the position of the vehicle 100 by converting the calculated coordinates to coordinates in the global coordinate system GC. The outline of the vehicle 100 included in the captured image can be detected, for example, by inputting the captured image into a detection model DM that utilizes artificial intelligence. The detection model DM is prepared, for example, within or outside the system 50 and pre-stored in the memory 202 of the server 200. Examples of the detection model DM include a pre-trained machine learning model that has been trained to implement either semantic segmentation or instance segmentation. As this machine learning model, for example, a convolutional neural network (CNN) trained by supervised learning using a training dataset can be used. The training dataset includes, for example, multiple training images containing vehicle 100, and labels indicating whether each region in the training images represents vehicle 100 or something other than vehicle 100. During CNN training, it is preferable to update the CNN parameters using backpropagation to reduce the error between the output result of the detection model DM and the labels. Furthermore, the processor 201 can obtain the orientation of vehicle 100 by, for example, using the optical flow method, estimating it based on the direction of the vehicle 100's movement vector calculated from the positional changes of the vehicle 100's feature points between frames of the captured images.

[0091] In step S120, the processor 201 of the server 200 determines the next target location that the vehicle 100 should head to. In this embodiment, the target location is represented by X, Y, Z coordinates in the global coordinate system GC. The memory 202 of the server 200 pre-stores a reference route RR, which is the path that the vehicle 100 should travel. The route is represented by a node indicating the starting point, nodes indicating waypoints, a node indicating the destination, and links connecting each node. The processor 201 uses the vehicle position information and the reference route RR to determine the next target location that the vehicle 100 should head to. The processor 201 determines the target location on the reference route RR beyond the vehicle 100's current location.

[0092] In step S130, the processor 201 of the server 200 generates a driving control signal to drive the vehicle 100 toward the determined target position. The processor 201 calculates the vehicle's speed from the change in the vehicle's position and compares the calculated speed with the target speed. Overall, the processor 201 determines the acceleration so that the vehicle 100 accelerates if the speed is lower than the target speed, and determines the acceleration so that the vehicle 100 decelerates if the speed is higher than the target speed. Furthermore, if the vehicle 100 is located on the reference path RR, the processor 201 determines the steering angle and acceleration so that the vehicle 100 does not deviate from the reference path RR, and if the vehicle 100 is not located on the reference path RR, in other words, if the vehicle 100 has deviated from the reference path RR, the processor 201 determines the steering angle and acceleration so that the vehicle 100 returns to the reference path RR.

[0093] In step S140, the processor 201 of the server 200 transmits the generated driving control signal to the vehicle 100. The processor 201 repeats the process of acquiring the position of the vehicle 100, determining the target position, generating the driving control signal, and transmitting the driving control signal at predetermined intervals.

[0094] In step S150, the processor 111 of the vehicle 100 receives a driving control signal transmitted from the server 200. In step S160, the processor 111 of the vehicle 100 controls the actuator group 120 using the received driving control signal, thereby driving the vehicle 100 at the acceleration and steering angle represented by the driving control signal. The processor 111 repeats the reception of the driving control signal and the control of the actuator group 120 at a predetermined cycle. According to the system 50 in this example, the vehicle 100 can be driven by remote control, and the vehicle 100 can be moved without using conveying equipment such as a crane or a conveyor.

[0095] <B:Driving Control Example 2> FIG. 11 is an explanatory diagram showing a schematic configuration of the system 50v in Driving Control Example 2. In this example, the system 50v is different from Driving Control Example 1 in that it does not include the server 200. Also, the vehicle 100v in the configuration can travel by autonomous control of the vehicle 100v. For other configurations, unless otherwise specified, they are the same as those described above.

[0096] In this example, the processor 111v of the vehicle control device 110v functions as the vehicle control unit 115v by executing the program PG1 stored in the memory 112v. The vehicle control unit 115v acquires the output result from the sensor, generates a driving control signal using the output result, and outputs the generated driving control signal to operate the actuator group 120, thereby enabling the vehicle 100v to travel by autonomous control. In this example, in addition to the program PG1, the detection model DM and the reference route RR are stored in the memory 112v in advance.

[0097] FIG. 12 is a flowchart showing the processing procedure of the driving control of the vehicle 100v in Example 2. In the processing procedure of FIG. 12, the processor 111v of the vehicle 100v functions as the vehicle control unit 115v by executing the program PG1.

[0098] In step S210, the processor 111v of the vehicle control device 110v acquires vehicle position information using the detection result output from the camera, which is the sensor 300. In step S220, the processor 111v determines the target position to which the vehicle 100v should next go. In step S230, the processor 111v generates a driving control signal to drive the vehicle 100v toward the determined target position. In step S240, the processor 111v controls the actuator group 120 using the generated driving control signal to drive the vehicle 100v according to the parameters expressed in the driving control signal. The processor 111v repeats the acquisition of vehicle position information, determination of the target position, generation of the driving control signal, and control of the actuators at a predetermined cycle. According to the system 50v in this example, the vehicle 100v can be driven by autonomous control of the vehicle 100v without remote control of the vehicle 100v by the server 200.

[0099] YY: Other examples of driving control (YY1) In the above example, sensor 300 is a camera. However, sensor 300 does not have to be a camera; for example, it could be LiDAR (Light Detection And Ranging). In this case, the detection result output by sensor 300 may be 3D point cloud data representing vehicle 100. In this case, the server 200 and vehicle 100 may acquire vehicle position information by template matching using the 3D point cloud data as the detection result and pre-prepared reference point cloud data.

[0100] In (YY2) Driving control example 1, the server 200 performs the processing from acquiring vehicle position information to generating driving control signals. In contrast, the vehicle 100 may perform at least a part of the processing from acquiring vehicle position information to generating driving control signals. For example, the following forms (1) to (3) may be used.

[0101] (1) The server 200 may acquire vehicle location information, determine the next target location that vehicle 100 should head to, and generate a route from the vehicle 100's current location, as shown in the acquired vehicle location information, to the target location. The server 200 may generate a route to the target location between the current location and the destination, or it may generate a route to the destination. The server 200 may transmit the generated route to vehicle 100. Vehicle 100 may generate a driving control signal so that vehicle 100 travels along the route received from the server 200, and may use the generated driving control signal to control the actuator group 120.

[0102] (2) The server 200 may acquire vehicle location information and transmit the acquired vehicle location information to the vehicle 100. The vehicle 100 may determine the next target location to which the vehicle 100 should go, generate a route from the vehicle 100's current location shown in the received vehicle location information to the target location, generate a driving control signal so that the vehicle 100 travels along the generated route, and control the actuator group 120 using the generated driving control signal.

[0103] (3) In the embodiments of (1) and (2) above, the vehicle 100 is equipped with internal sensors, and the detection results output from the internal sensors may be used in at least one of the generation of a route and the generation of a driving control signal. The internal sensors are sensors mounted on the vehicle 100. The internal sensors may include, for example, sensors that detect the motion state of the vehicle 100, sensors that detect the operating state of each part of the vehicle 100, and sensors that detect the environment around the vehicle 100. Specifically, the internal sensors may include, for example, cameras, LiDAR, millimeter-wave radar, ultrasonic sensors, GPS sensors, acceleration sensors, gyroscopes, etc. For example, in the embodiment of (1) above, the server 200 may acquire the detection results of the internal sensors and reflect the detection results of the internal sensors in the route when generating a route. In the embodiment of (1) above, the vehicle 100 may acquire the detection results of the internal sensors and reflect the detection results of the internal sensors in the driving control signal when generating a driving control signal. In the embodiment of (2) above, the vehicle 100 may acquire the detection results of the internal sensors and reflect the detection results of the internal sensors in the route when generating a route. In the embodiment described in (2) above, the vehicle 100 may acquire the detection results of the internal sensors and reflect the detection results of the internal sensors in the driving control signal when generating the driving control signal.

[0104] (YY3) In the driving control example 2, the vehicle 100v is equipped with an internal sensor, and the detection result output from the internal sensor may be used in at least one of the generation of the route and the generation of the driving control signal. For example, the vehicle 100v may acquire the detection result from the internal sensor and reflect the detection result from the internal sensor in the route when generating the route. The vehicle 100v may acquire the detection result from the internal sensor and reflect the detection result from the internal sensor in the driving control signal when generating the driving control signal.

[0105] (YY4) In driving control example 2, vehicle 100v acquires vehicle position information using the detection results of sensor 300. Alternatively, vehicle 100v may be equipped with an internal sensor, which may acquire vehicle position information using the detection results of the internal sensor, determine the next target location to which vehicle 100v should go, generate a route from vehicle 100v's current location to the target location as shown in the acquired vehicle position information, generate a driving control signal for driving along the generated route, and control the actuator group 120 using the generated driving control signal. In this case, vehicle 100v can drive without using the detection results of sensor 300 at all. Vehicle 100v may also acquire target arrival time and congestion information from outside vehicle 100v and reflect the target arrival time and congestion information in at least one of the route and the driving control signal. Furthermore, all the functional configurations of system 50v may be provided in vehicle 100v. That is, the processing realized by system 50v in this disclosure may be realized by vehicle 100v alone. For example, the leading vehicle 100V may transmit a control instruction value to the following vehicle 100.

[0106] (YY5) In the driving control example 1, the server 200 automatically generates a driving control signal to be transmitted to the vehicle 100. Alternatively, the server 200 may generate a driving control signal to be transmitted to the vehicle 100 in accordance with the operation of an external operator located outside the vehicle 100. For example, the external operator may operate a control device that includes a display for displaying captured images output from the sensor 300, a steering wheel for remotely controlling the vehicle 100, an accelerator pedal, a brake pedal, and a communication device for communicating with the server 200 via wired or wireless communication, and the server 200 may generate a driving control signal in accordance with the operation applied to the control device.

[0107] (YY6) In each of the above driving control examples, the vehicle 100 only needs to have a configuration that allows it to move by unmanned operation, and may be in the form of a platform having the configuration described below. Specifically, in order for the vehicle 100 to perform the three functions of "driving," "turning," and "stopping" by unmanned operation, it only needs to be equipped with at least a vehicle control device 110 and an actuator group 120. When the vehicle 100 acquires information from the outside for unmanned operation, the vehicle 100 may further be equipped with a communication device 130. That is, the vehicle 100 that can move by unmanned operation does not need to have at least some of the interior parts such as the driver's seat and dashboard installed, at least some of the exterior parts such as the bumper and fender installed, and does not need to have a body shell installed. In this case, the remaining parts such as the body shell may be attached to the vehicle 100 before it is shipped from the factory FC, or the remaining parts such as the body shell may be attached to the vehicle 100 after it has been shipped from the factory FC, while the remaining parts such as the body shell are not attached to the vehicle 100. Each part may be attached from any direction, such as the top, bottom, front, rear, right, or left side of the vehicle 100, and each part may be attached from the same direction or from different directions. The positioning of the platform can also be determined in the same way as the vehicle 100 in the first embodiment.

[0108] (YY7) Vehicle 100 may be manufactured by combining multiple modules. A module means a unit composed of multiple parts grouped together according to the part or function of the vehicle 100. For example, the platform of vehicle 100 may be manufactured by combining a front module that constitutes the front part of the platform, a central module that constitutes the central part of the platform, and a rear module that constitutes the rear part of the platform. The number of modules that constitute the platform is not limited to three, but may be two or fewer, or four or more. In addition to, or instead of, the parts that constitute the platform may be modularized, as well as parts that constitute parts of the vehicle 100 that are different from the platform. Various modules may also include any exterior parts such as bumpers and grilles, or any interior parts such as seats and consoles. Furthermore, not limited to vehicle 100, any type of mobile body may be manufactured by combining multiple modules. Such modules may be manufactured, for example, by joining multiple parts by welding or fasteners, or by integrally molding at least a part of the parts that constitute the module as a single part by casting. A molding technique for integrally molding a single component, especially a relatively large component, is also called gigacast or megacast. For example, the front module, central module, and rear module mentioned above may be manufactured using gigacast.

[0109] (YY8) Transporting vehicle 100 using the unmanned operation of the vehicle 100 is also called "autonomous transport." The configuration for realizing autonomous transport is also called a "vehicle remote control autonomous driving transport system." Furthermore, a production method that uses autonomous transport to produce vehicle 100 is also called "autonomous production." In autonomous production, for example, at a factory fuel cell (FC) that manufactures vehicle 100, at least a portion of the transport of vehicle 100 is realized by autonomous transport.

[0110] (YY9) In each of the above driving control examples, some or all of the functions and processes implemented in software may be implemented in hardware. Also, some or all of the functions and processes implemented in hardware may be implemented in software. As hardware for implementing the various functions in each of the above embodiments, various circuits such as integrated circuits and discrete circuits may be used.

[0111] In the above driving control examples 1 and 2, the stop control shown in Figures 3 to 7 can also be applied. For example, the remote control unit 210 shown in Figure 9 performs stop control using image processing. In addition, in Figures 8 to 12, stop control using the suspension string 32 and control equipment 30 shown in Figures 3 and 4 may also be applied.

[0112] Furthermore, some or all of the processing in the aforementioned sensor 300, vehicle 100, server 200, sensor 300, robot 600, etc., can be implemented as computer programs. Such programs can be stored using various types of non-temporary computer-readable media and supplied to a computer. Non-temporary computer-readable media include various types of tangible recording media. Examples of non-temporary computer-readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, RAMs (Random Access Memory)). Programs may also be supplied to a computer using various types of temporary computer-readable media. Examples of temporary computer-readable media include electrical signals, optical signals, and electromagnetic waves. Temporary computer-readable media can be supplied to a computer via wired communication channels such as electric wires and optical fibers, or via wireless communication channels.

[0113] It should be noted that the present invention is not limited to the embodiments described above, and can be modified as appropriate without departing from the spirit of the invention. [Explanation of symbols]

[0114] 30 Control equipment 31 string 32 Hanging string 50 Vehicle Manufacturing Systems 100 vehicles 115 Vehicle Control Unit 120 Actuator Group 130 Communication equipment 200 servers 230 Communication equipment 231 Receiver 232 Transmitter 252 Worker detection unit 253 Area determination unit 255 Stop Control Unit 300 sensors 330 Communication equipment A Driving area DA1 detection area DA2 Non-detection area

Claims

1. A vehicle manufacturing system that controls multiple vehicles to travel in a convoy during the manufacturing or transport process, A camera that captures images of the driving area and its surroundings where multiple vehicles are traveling, A worker detection unit detects workers in the vicinity of the vehicle by performing image processing on the image captured by the aforementioned camera, A vehicle manufacturing system comprising: an image analysis unit that analyzes multiple frames of the captured image and stops the vehicle if the worker detected in the previous frame is not detected in the subsequent frame.

2. An area determination unit that determines whether the operator is in a detection area corresponding to the travel area or in non-detection areas on both the left and right sides of the travel area, The vehicle manufacturing system according to claim 1, wherein the vehicle is stopped when a worker who was detected in the detection area in the previous frame is no longer detected in the subsequent frame.

3. The vehicle manufacturing system according to claim 1 or 2, wherein the vehicle is stopped when it is estimated that the worker is in a blind spot of the camera caused by the vehicle.

4. The vehicle manufacturing system according to claim 2, wherein a stop switch for stopping the vehicle is provided in the non-detection area.

5. A vehicle manufacturing method that controls multiple vehicles to travel in a convoy during the manufacturing process or the transport process, The steps include: using a camera to capture images of the driving area and its surroundings where multiple vehicles are traveling; The steps include: detecting workers in the vicinity of the vehicle by performing image processing on the image captured by the camera; A vehicle manufacturing method comprising the step of performing image analysis on multiple frames of the captured image and stopping the vehicle if the worker detected in the previous frame is not detected.

Images