Vehicle control system and vehicle control method

Abstract

This invention relates to a vehicle control system and a vehicle control method. The vehicle control system according to this disclosure includes: a plurality of cameras arranged side-by-side along the longitudinal direction of a work line, the cameras being configured to capture images of a vehicle traveling on the work line from above; and a controller configured to control the movement of the vehicle based on the images captured by the plurality of cameras. In the vehicle control system, a worker performs work while the vehicle is self-propelled in a predetermined direction, and the plurality of cameras includes pairs of cameras arranged side-by-side along the longitudinal direction of the work line, each pair of cameras being configured to capture images of the vehicle from a left-side upper and a right-side upper, respectively.

Description

Technical Field

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

[0002] For example, as disclosed in Patent Document 1, when manufacturing a vehicle, there is a known technology in which, for example, the vehicle is not transported by a conveyor, but is transported by self-propulsion using autonomous control or remote control (self-propulsion conveying technology).

[0003] [Patent Document 1] Japanese Patent No. 7424535 Summary of the Invention

[0004] When vehicles are self-propelled along a production line without the use of a belt conveyor, multiple cameras that capture images of the vehicles from above are placed along the longitudinal direction of the production line. In this case, if the multiple cameras are placed directly above the vehicles, there is a problem: the external shape of the vehicles in the images captured by the cameras has few feature points, and therefore the controller (i.e., the computer) has difficulty identifying the vehicles in the captured images, and the position of the vehicles cannot be accurately estimated.

[0005] In view of the above, this disclosure has been made and a vehicle control system is provided that can more easily identify vehicles traveling on a work line and more accurately estimate the position of the vehicles.

[0006] A vehicle control system according to the present disclosure includes: Multiple cameras, arranged side-by-side along the longitudinal direction of the work line, are configured to capture images of vehicles traveling on the work line from above; and A controller configured to control the vehicle's movement based on images captured by multiple cameras, wherein... While the vehicle propels itself in a predetermined direction, the worker performs tasks while moving. The multiple cameras include pairs of cameras arranged side by side along the longitudinal direction of the work line, each pair of cameras being configured to capture images of the vehicle from the upper left and upper right, respectively.

[0007] In the vehicle control system according to this disclosure, each pair of cameras that capture images of the vehicle from the upper left and the upper right, respectively, are arranged side by side along the longitudinal direction of the work line. Therefore, it is easier to identify vehicles traveling on the work line and to estimate the position of the vehicles more accurately.

[0008] The controller can select the image from the pairs of images captured by the cameras where the vehicle is easily identifiable, and control the vehicle's movement based on the selected image. With this configuration, even if the vehicle is difficult to identify in one of the images captured by the pairs of cameras, it can select the other image where the vehicle is easily identifiable, and the vehicle's position can be estimated more accurately.

[0009] When one of the vehicle's left and right doors is open, the controller can select the image of the vehicle from the side whose door is closed as the image that makes the vehicle easier to identify. With this configuration, even when one of the vehicle's right and left doors is open, it is possible to select the image of the vehicle from the side whose door is closed, and the vehicle's position can be estimated more accurately.

[0010] When one of the vehicle's left and right doors is open, the controller can select an image of the vehicle from images captured by a pair of cameras, based on the door opening signal transmitted from the vehicle, showing the side whose door is not open, and control the vehicle's movement based on the selected image. With this configuration, even when one of the vehicle's right and left doors is open, it is possible to select an image of the vehicle from the side whose door is not open, and to estimate the vehicle's position more accurately.

[0011] The work line can be covered by a lighting canopy, which is arched to span the width of the work line and extend along it, and multiple cameras are mounted within the canopy. A vehicle control system is applicable to the aforementioned work line.

[0012] The vehicle control method according to this disclosure includes: Images of vehicles traveling on the work line are captured from above by multiple cameras arranged side-by-side along the longitudinal direction of the work line; and The controller controls the vehicle's movement based on images captured by multiple cameras, where... While the vehicle propels itself in a predetermined direction, the worker performs tasks while moving. The multiple cameras include pairs of cameras arranged side by side along the longitudinal direction of the work line, each pair of cameras being configured to capture images of the vehicle from the upper left and upper right, respectively.

[0013] In the vehicle control method according to this disclosure, each pair of cameras that capture images of the vehicle from the upper left and the upper right, respectively, are arranged side by side along the longitudinal direction of the work line. Therefore, it is easier to identify vehicles traveling on the work line and to estimate the position of the vehicles more accurately.

[0014] The controller can select the image from the pairs of images captured by the cameras where the vehicle is easily identifiable, and control the vehicle's movement based on the selected image. With this configuration, even if the vehicle is difficult to identify in one of the images captured by the pairs of cameras, it can select the other image where the vehicle is easily identifiable, and the vehicle's position can be estimated more accurately.

[0015] When one of the vehicle's left and right doors is open, the controller can select the image of the vehicle from the side whose door is closed as the image that makes the vehicle easier to identify. With this configuration, even when one of the vehicle's right and left doors is open, it is possible to select the image of the vehicle from the side whose door is closed, and the vehicle's position can be estimated more accurately.

[0016] When one of the vehicle's left and right doors is open, the controller can select an image of the vehicle from images captured by a pair of cameras, based on the door opening signal transmitted from the vehicle, showing the side whose door is not open, and control the vehicle's movement based on the selected image. With this configuration, even when one of the vehicle's right and left doors is open, it is possible to select an image of the vehicle from the side whose door is not open, and to estimate the vehicle's position more accurately.

[0017] The work line can be covered by a lighting canopy, which is arched to span the work line in its width direction and extend along it, and multiple cameras are mounted within the lighting canopy. A vehicle control method is applicable to the aforementioned work line.

[0018] According to this disclosure, a vehicle control system can be provided that can more easily identify vehicles traveling on a work line and more accurately estimate the position of the vehicles.

[0019] The above and other objects, features and advantages of this disclosure will be more fully understood from the detailed description and accompanying drawings given below. Attached Figure Description

[0020] Figure 1 This is a block diagram illustrating the control system of the vehicle control system according to the first embodiment; Figure 2 It is a schematic front view showing a self-propelled work line; Figure 3 It is a schematic side view of a work line where vehicles are self-propelled; Figure 4 It is a diagram used to illustrate the driving control of a vehicle; Figure 5 This is a control block diagram used to illustrate driving control example 1; Figure 6 This is a flowchart used to illustrate Example 1 of driving control; Figure 7 This is a control block diagram used to illustrate Example 2 of driving control; and Figure 8 This is a flowchart used to illustrate driving control example 2. Detailed Implementation

[0021] The specific embodiments to which this disclosure applies will now be described in detail with reference to the accompanying drawings. However, this disclosure is not limited to the following embodiments. Furthermore, for clarity, the following description and drawings have been appropriately simplified.

[0022] (First embodiment)

[0023] Overview of Vehicle Control Systems

[0024] First, refer to Figure 1 An overview of the vehicle control system according to the first embodiment is described. Figure 1 This is a block diagram illustrating the control system of the vehicle control system according to the first embodiment. Figure 1 As shown, the vehicle control system (also referred to as the system) 50 includes a server 200 and a camera 310, and controls the movement of the vehicle 100.

[0025] The vehicle control system 50 is applied, for example, to the control of self-propulsion of vehicle 100 on a production line in a vehicle manufacturing plant. Therefore, the vehicle 100 to be controlled is a self-propelled vehicle capable of self-propulsion during the manufacturing process. In other words, vehicle 100 is a vehicle capable of moving autonomously during the manufacturing process.

[0026] like Figure 1 As shown, server 200 includes memory 202, communication device 205, position estimation unit 207, and driving control unit 208. Vehicle 100 includes vehicle control device 110, actuator 120, and communication device 130.

[0027] Note that server 200 can consist not only of a single physical device, but also of multiple distributed devices.

[0028] Server 200 has the function of estimating the position of vehicle 100 based on images captured from vehicle 100 received from camera 310 and controlling the driving of vehicle 100 to be controlled.

[0029] In server 200, communication device 205 communicates with camera 310 and vehicle 100 via network 500. Communication device 205 receives data such as captured images from camera 310, and transmits information (vehicle control information) generated based on the images for controlling the driving of vehicle 100 to vehicle 100.

[0030] The position estimation unit 207 identifies the vehicle 100 and estimates its position based on images of the vehicle 100 captured by the camera 310. Specifically, the communication device 205 receives data such as captured images from the camera 310, and the position estimation unit 207 estimates the position of the vehicle 100 by analyzing the received captured images (i.e., image analysis).

[0031] The driving control unit 208 generates information (vehicle control information) for controlling the driving of the vehicle 100 based on the position of the vehicle 100 estimated by the position estimation unit 207.

[0032] Vehicle control information generated by the driving control unit 208 is transmitted to the vehicle 100 via the communication device 205. In the vehicle 100, the communication device 130 receives the vehicle control information transmitted from the server 200, and the vehicle control device 110 operates the actuator 120 based on the received vehicle control information, thereby driving the vehicle 100.

[0033] Camera 310 is a form of external sensor 300, described later, and captures images of vehicle 100 traveling on the work line from above. Camera 310 has communication capabilities, and data such as images captured by camera 310 are transmitted to server 200 via network 500.

[0034] <Details of the application of vehicle control systems on production lines>

[0035] Next, we will refer to Figure 2 and Figure 3 The details of the vehicle control system according to this embodiment being applied to a work line are described. Figure 2 It is a schematic front view showing a self-propelled work line. Figure 3 It is a schematic side view of a self-propelled work line.

[0036] Notice, Figure 2 and Figure 3 The right-handed XYZ orthogonal coordinates shown are only for ease of explanation of the positional relationships within the components. Figure 2 In the figures, for example, the positive direction of the Z-axis is vertically upward, and the XY plane is a horizontal plane, and this direction and plane are the same throughout all the figures.

[0037] like Figure 2 and Figure 3 As shown, the work line extends in the X-axis direction, and a vehicle 100, controlled by a vehicle control system, self-propels along the work line in the positive X-axis direction. In the work line, workers (not shown) perform tasks while moving with the self-propelled vehicle 100. These tasks include, for example, inspection and assembly. Note that... Figure 2 and Figure 3Each of the work lines shown in the diagram is covered by a lighting shed 400, which is formed in an arch shape to span the work line in the width direction (Y-axis direction) and extend along the work line in the X-axis direction.

[0038] like Figure 2 As shown, the lighting shed 400 includes rod-shaped lighting fixtures 410a, 410b, and 410c. The lighting fixtures 410a, 410b, and 410c are, for example, light-emitting diodes (LEDs) or fluorescent lamps. However, they are not limited to specific fixtures.

[0039] Note that a 400mm lighting enclosure is not required.

[0040] exist Figure 2 In the example shown, a pair of lighting fixtures 410a extending along the Z-axis are positioned facing each other on their respective sides in the width direction of the work line across the vehicle 100. Furthermore, a lighting fixture 410c extending along the Y-axis is positioned above the work line—i.e., the vehicle 100. Additionally, a pair of lighting fixtures 410b are configured to extend obliquely between the respective upper ends of the lighting fixtures 410a and the respective ends of the lighting fixtures 410c.

[0041] In other words, a pair of lighting fixtures 410a, a pair of lighting fixtures 410b and lighting fixtures 410c are set in an arch shape so that they span the work line in the width direction (Y-axis direction) of the work line as a whole.

[0042] In addition, such as Figure 3 As shown, the lighting fixtures 410a, 410b and 410c, which are arranged in an arched shape, are arranged side by side along the work line in the X-axis direction.

[0043] In addition, such as Figure 2 and Figure 3 As shown, the lighting shed 400 includes beams 420a, 420b, and 420c extending in the X-axis direction and beam 430 extending in the Y-axis direction. Beam 420a connects to and supports lighting fixtures 410a arranged side-by-side along the work line in the X-axis direction. Beam 420b connects to and supports lighting fixtures 410b arranged side-by-side along the work line in the X-axis direction. Beam 420c connects to and supports lighting fixtures 410c arranged side-by-side along the work line in the X-axis direction.

[0044] Note that, although Figure 2 and Figure 3 The number of each of beams 420a, 420b, and 420c shown is two, but not limited to this. Furthermore, beams 420a, 420b, and 420c are not required.

[0045] like Figure 2As shown, beam 430 extending in the Y-axis direction supports the pair of cameras 310a and 310b. Furthermore, as... Figure 3 As shown, beam 430 is supported by beam 420b between lighting fixtures 410b arranged side by side in the X-axis direction.

[0046] Notice, Figure 2 and Figure 3 The lighting shed 400 shown is merely an example, and many other variations of it may exist.

[0047] like Figure 2 As shown, the paired cameras 310a and 310b capture images of vehicle 100 from the upper left and the upper right, respectively. Furthermore, as... Figure 3 As shown, the pair of cameras 310a and 310b are arranged side by side along the longitudinal direction (X-axis direction) of the work line. Figure 1 The camera 310 shown includes Figure 2 and Figure 3 The pair of cameras shown are 310a and 310b.

[0048] Note that the pair of cameras 310a and 310b do not require special support from beam 420b, as long as they are mounted in the lighting shed 400 and are capable of capturing images of vehicle 100 from both the upper left and upper right. That is to say, many other variations in how the pair of cameras 310a and 310b are mounted are possible.

[0049] Note that if the camera is positioned directly above vehicle 100 on the work line, the external shape of vehicle 100 in the image captured by the camera will have very few feature points, and therefore... Figure 1 The position estimation unit 207 shown has difficulty identifying vehicle 100 in the captured image as a vehicle. Specifically, as... Figure 2 and Figure 3 As shown, when the work line is covered by the lighting canopy 400, the entire image of vehicle 100 cannot be captured by the camera because the camera is mounted close to vehicle 100. Therefore, the position estimation unit 207 has a greater difficulty in identifying vehicle 100 in the captured image.

[0050] Meanwhile, in the vehicle control system according to this embodiment, a pair of cameras 310a and 310b capture images of the vehicle 100 from the upper left and the upper right, respectively. Therefore, the external shape of the vehicle 100 in the images captured by cameras 310a and 310b has many feature points, and thus the position estimation unit 207 can easily identify the vehicle 100 in the captured images as a vehicle. As a result, the position estimation unit 207 can estimate the position of the vehicle 100 more accurately.

[0051] Furthermore, on the production line, a worker can open one of the left and right doors of vehicle 100. In this case, among the images of vehicle 100 captured by the pair of cameras 310a and 310b, it is more difficult for the position estimation unit 207 to identify vehicle 100 as a vehicle in the image captured on the side with the door open than in the image captured on the side with the door closed.

[0052] Therefore, the position estimation unit 207 can select images from those captured by the paired cameras 310a and 310b in which the vehicle 100 is easily identifiable, and control the driving of the vehicle 100 based on the selected images. As a result, the position estimation unit 207 is able to estimate the position of the vehicle 100 more accurately.

[0053] Similarly, in some cases, workers are working next to vehicle 100 on the work line. In this case, among the images of vehicle 100 captured by the pair of cameras 310a and 310b, it may be more difficult for the position estimation unit 207 to identify vehicle 100 as a vehicle in the image captured on the side where the worker is working than in the image captured on the side where the worker is not working.

[0054] In this scenario, the position estimation unit 207 can select images from those captured by the paired cameras 310a and 310b in which the vehicle 100 is easily identifiable, and control the movement of the vehicle 100 based on the selected images. As a result, the position estimation unit 207 is able to estimate the position of the vehicle 100 more accurately.

[0055] As described above, the position estimation unit 207 can select images from those captured by the pair of cameras 310a and 310b in which the vehicle 100 is easily identifiable, and control the driving of the vehicle 100 based on the selected images.

[0056] Note that when one of the left and right doors of vehicle 100 is open, position estimation unit 207 can select an image of the side of vehicle 100 whose door is not open from the images captured by the paired cameras 310a and 310b based on the door opening signal transmitted from vehicle 100. With this configuration, even when it is uncertain which images captured by the paired cameras 310a and 310b include the easily identifiable vehicle 100, position estimation unit 207 can select an image of the side of vehicle 100 whose door is not open. Furthermore, since the door opening can be detected by sensors that are standard equipment in the vehicle, additional sensors are not required.

[0057] As described above, in the vehicle control system 50 according to this embodiment, the paired cameras 310a and 310b are arranged side by side in the longitudinal direction of the work line, and each pair of the paired cameras 310a and 310b captures an image of the vehicle 100 from the upper left obliquely and from the upper right obliquely, respectively. Therefore, in the vehicle control system 50 according to this embodiment, it is possible to more easily identify the vehicle 100 traveling on the work line and to more accurately estimate the position of the vehicle 100.

[0058] In addition, in the vehicle control system 50 according to this embodiment, the controller (for example, the server 200) can select an image in which the vehicle 100 is easily identifiable from the images captured by the paired cameras 310a and 310b, and control the travel of the vehicle 100 based on the selected image. For example, when one of the left and right doors of the vehicle 100 is opened, an image of the vehicle 100 on the side where the door is not opened is selected. With this configuration, even if it is difficult to identify the vehicle 100 in one of the images captured by the paired cameras 310a and 310b, it is possible to select another image in which the vehicle 100 is easily identifiable, and to more accurately estimate the position of the vehicle 100.

[0059] A travel control example for controlling the travel of the vehicle 100 in the system 50 will be described below.

[0060] <A. Travel control example 1>

[0061] Figure 4 is a conceptual diagram showing the configuration of the system 50 according to Travel Control Example 1. The system 50 includes one or more of the vehicles 100 as mobile bodies, the server 200, and one or more of the external sensors 300.

[0062] Note that when the mobile body is not a vehicle, the terms "vehicle" or "automobile" in the present disclosure may be replaced by "mobile body" as appropriate, and the term "travel" may be replaced by "move" as appropriate. <s

[0063] The vehicle 100 is configured to be capable of traveling autonomously. "Autonomous driving" means driving that does not depend on the driving operation of the driver. The driving operation means an operation regarding at least one of "traveling", "turning", and "stopping" of the vehicle 100. Autonomous driving is achieved by automatic or manual remote control of a device located outside the vehicle 100, or by autonomous control of the vehicle 100.

[0064] Any passenger not performing driving operations may ride in the driverless vehicle 100. Examples of passengers not performing driving operations include those merely sitting in a seat in the vehicle 100 and those performing tasks different from driving operations while riding in the vehicle 100, such as assembly, inspection, or switching. Note that driving by passenger driving operations can be referred to as "manned driving".

[0065] In this specification, "remote control" includes "full remote control" in which all operations of vehicle 100 are completely determined from outside vehicle 100, and "partial remote control" in which some operations of vehicle 100 are determined from outside vehicle 100. Furthermore, "autonomous control" includes "full autonomous control" in which vehicle 100 autonomously controls its own operations without receiving any information from devices located outside vehicle 100, and "partial autonomous control" in which vehicle 100 autonomously controls its own operations using information received from devices located outside vehicle 100.

[0066] In this embodiment, system 50 is used in a factory FC for manufacturing vehicle 100. The reference coordinate system of the factory FC is the global coordinate system GC. That is, the desired position in the factory FC is represented by the X, Y, and Z coordinates in the global coordinate system GC. The factory FC includes a first location PL1 and a second location PL2. The first location PL1 and the second location PL2 are connected to each other by a travel path TR along which vehicle 100 can travel. Multiple external sensors 300 are installed along the travel path TR in the factory FC. The positions of the corresponding external sensors 300 in the factory FC are pre-adjusted. Vehicle 100 moves from the first location PL1 to the second location PL2 along the travel path TR by autonomous driving.

[0067] Figure 5 This is a block diagram illustrating the configuration of system 50. Vehicle 100 includes a vehicle control unit 110 for controlling each part of vehicle 100, an actuator 120 including one or more actuators driven under the control of vehicle control unit 110, and a communication unit 130 for communicating wirelessly with an external device such as server 200. Actuator 120 includes actuators for a drive mechanism for accelerating vehicle 100, actuators for a steering mechanism for changing the direction of travel of vehicle 100, and actuators for a control mechanism for decelerating vehicle 100.

[0068] The vehicle control unit 110 comprises a computer including 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 interconnected via the internal bus 114, enabling them to communicate with each other. An actuator 120 and a communication device 130 are connected to the input / output interface 113. The processor 111 executes a program PG1 stored in the memory 112, thereby implementing various functions, including those of the vehicle control unit 115.

[0069] The vehicle control unit 115 drives the vehicle 100 by controlling the actuator 120. The vehicle control unit 115 can drive the vehicle 100 by controlling the actuator 120 using a driving control signal received from the server 200. 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 another embodiment, instead of or additionally including the acceleration of the vehicle 100, the driving control signal may include the speed of the vehicle 100 as a parameter.

[0070] Server 200 comprises a computer including processor 201, memory 202, input / output interface 203, and internal bus 204. Processor 201, memory 202, and input / output interface 203 are interconnected via internal bus 204, enabling them to communicate with each other. Communication device 205, for communicating with various types of devices located outside server 200, is connected to input / output interface 203. Communication device 205 is capable of communicating wirelessly with vehicle 100 and with each of the external sensors 300 via wired or wireless communication. Processor 201 executes program PG2 stored in memory 202, thereby implementing various functions, including those of a remote control unit 210.

[0071] The remote control unit 210 acquires the detection results from the sensors, uses the detection results to generate a driving control signal for controlling the actuator 120 of the vehicle 100, and transmits the generated driving control signal to the vehicle 100, thereby enabling the vehicle 100 to move remotely. In other words, the remote control unit 210 includes... Figure 1 The functions of the position estimation unit 207 and the driving control unit 208 shown are illustrated.

[0072] Furthermore, the remote control unit 210 can generate not only driving control signals, but also control signals for controlling actuators and operating various types of auxiliary equipment or devices installed in the vehicle 100, such as windshield wipers, power windows, or lights. In other words, the remote control unit 210 can operate these various types of equipment or auxiliary devices remotely.

[0073] The external sensor 300 is a sensor located outside the vehicle 100. According to this embodiment, the external sensor 300 is a sensor that captures information about the vehicle 100 from the outside. The external sensor 300 includes a communication device (not shown) and is capable of communicating with other devices, such as the server 200, via wired or wireless communication.

[0074] Specifically, the external sensor 300 consists of a camera. The camera, acting as the external sensor 300, captures images including those of the vehicle 100 and outputs the captured images as detection results.

[0075] Figure 6 This is a flowchart illustrating the processing procedure of driving control for a vehicle 100 according to a driving control example. Figure 6 In the processing shown, the processor 201 of server 200 is used as a remote control unit 210 by executing program PG2. Furthermore, the processor 111 of vehicle 100 is used as a vehicle control unit 115 by executing program PG1.

[0076] In step S110, the processor 201 of the server 200 uses the detection results output from the external sensor 300 to acquire the vehicle position information of the vehicle 100. The vehicle position information is the position information based on which the driving control signal is generated. 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 uses captured images obtained from a camera, which is the external sensor 300, to acquire the vehicle position information.

[0077] Specifically, in step S110, processor 201 ( Figure 1 The position estimation unit 207 shown (as a functional block) detects, for example, the external shape of vehicle 100 from the captured image, calculates the coordinate system of the captured image, i.e. the coordinates of the positioning point of vehicle 100 in the local coordinate system, and converts the calculated coordinates into coordinates in the global coordinate system GC, thereby obtaining the position of vehicle 100.

[0078] The external shape of vehicle 100 included in the captured image can be detected, for example, by inputting the captured image into a detection model DM using artificial intelligence. The detection model DM is prepared, for example, either within or outside system 50, and is pre-stored in memory 202 of server 200. Examples of detection models DM include trained machine learning models that have been trained to perform either semantic segmentation or instance segmentation. For example, a convolutional neural network (hereinafter referred to as a CNN) trained using supervised learning on a learning dataset can be used as this machine learning model.

[0079] The training dataset includes, for example, multiple training images of vehicle 100, and labels indicating whether each region in the training images refers to a region of vehicle 100 or a region of something other than vehicle 100. When performing CNN learning, the parameters of the CNN are preferably updated such that the error between the output of the detection model DM and the labels is reduced through backpropagation. Furthermore, the processor 201 can obtain the orientation of vehicle 100 by estimating the orientation of vehicle 100 using an optical flow method based on the direction of the movement vector of vehicle 100 calculated from the changes in the positions of feature points of vehicle 100 between frames of the captured images.

[0080] In step S120, 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 route RR, which is the route that the vehicle 100 should travel. The route is represented by nodes indicating the departure point, nodes indicating the waypoint, nodes indicating the destination, and links connecting the corresponding nodes. The processor 201 uses the vehicle position information and the reference route RR to determine the target location that the vehicle 100 should go to next. The processor 201 determines the position before the current position of the vehicle 100 on the reference route RR as the target location.

[0081] In step S130, the processor 201 of the server 200 generates a driving control signal for causing the vehicle 100 to travel toward the determined target position. The processor 201 calculates the traveling speed of the vehicle 100 based on the change in the position of the vehicle 100, and compares the calculated traveling speed with the target speed. Generally, when the traveling speed is lower than the target speed, the processor 201 determines an acceleration to accelerate the vehicle 100, and when the traveling speed is higher than the target speed, the processor 201 determines an acceleration to decelerate the vehicle 100. In addition, when the vehicle 100 is positioned on the reference route RR, the processor 201 determines a steering angle and an acceleration to prevent the vehicle 100 from deviating from the reference route RR, and when the vehicle 100 is not positioned on the reference route RR, that is, when the vehicle 100 deviates from the reference route RR, the processor 201 determines a steering angle and an acceleration to cause the vehicle 100 to return to the reference route RR.

[0082] 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 acquisition of the position of the vehicle 100, the determination of the target position, the generation of the driving control signal, the transmission of the driving control signal, etc. in a predetermined cycle.

[0083] In step S150, the processor 111 of the vehicle 100 receives the driving control signal transmitted from the server 200. In step S160, the processor 111 of the vehicle 100 uses the received driving control signal to control the actuator 120, so that the vehicle 100 travels at the acceleration and steering angle indicated in the driving control signal. The processor 111 repeats the reception of the driving control signal and the control of the actuator 120 in a predetermined cycle. With the system 50 according to this example, the vehicle 100 can travel by remote control, and thus the vehicle 100 can be moved without using conveying equipment such as a crane or a conveyor.

[0084] <B: Driving Control Example 2>

[0085] Figure 7 FIG. is an explanatory diagram showing a schematic configuration of a system 50v according to Driving Control Example 2. In this example, the system 50v is different from the system 50 according to Driving Control Example 1 in that the system 50v does not include the server 200. In addition, the vehicle 100v has a configuration that enables it to travel under its own autonomous control. Unless otherwise specified, other configurations are the same as the above configurations.

[0086] In this example, the processor 111v of the vehicle control unit 110v acts as the vehicle control unit 115v by executing the program PG1 stored in the memory 112v. The vehicle control unit 115v acquires the results output by the sensors, uses the output results to generate a driving control signal, and outputs the generated driving control signal to operate the actuator 120, thereby enabling the vehicle 100v to drive autonomously. In this example, in addition to pre-stored program PG1, the memory 112v also pre-stores the detection model DM and the reference route RR.

[0087] Figure 8 This is a flowchart illustrating the processing procedure for driving control of a vehicle 100V according to Driving Control Example 2. Figure 8 In the process shown, the processor 111v of vehicle 100v is used as vehicle control unit 115v by executing program PG1.

[0088] In step S210, the processor 111v of the vehicle control device 110v uses the detection results output from the camera, which is an external sensor 300, to obtain vehicle position information.

[0089] In step S220, processor 111v determines the target location that vehicle 100v should go to next.

[0090] In step S230, the processor 111v generates a driving control signal for causing the vehicle 100v to move toward the determined target position.

[0091] In step S240, the processor 111v uses the generated driving control signal to control the actuator 120, thereby causing the vehicle 100v to drive according to the parameters indicated in the driving control signal.

[0092] The processor 111v repeatedly acquires vehicle position information, determines the target position, generates driving control signals, and controls the actuators within a predetermined cycle. Using the system 50v according to this example, the vehicle 100v can be driven autonomously without remote control by the server 200.

[0093] YY: Other driving control examples

[0094] (YY1) In the example above, the external sensor 300 is a camera. However, the external sensor 300 may not be a camera, and may instead be, for example, light detection and ranging (LiDAR). In this case, the detection result output from the external sensor 300 may be three-dimensional point cloud data indicating the vehicle 100. In this case, the server 200 and the vehicle 100 can obtain vehicle position information by template matching using the three-dimensional point cloud data obtained as the detection result and pre-prepared reference point cloud data.

[0095] (YY2) In driving control example 1, server 200 performs the process from acquiring vehicle location information to generating driving control signals. However, vehicle 100 may perform at least some of the processes from acquiring vehicle location information to generating driving control signals. For example, it may take the form (1) to (3).

[0096] (1) Server 200 can acquire vehicle location information, determine the target location that vehicle 100 should go to next, and generate a route from the current location of vehicle 100 to the target location as indicated in the acquired vehicle location information. Server 200 can generate a route to the target location between the current location and the destination, or it can generate a route to the destination. Server 200 can transmit the generated route to vehicle 100. Vehicle 100 can generate a driving control signal for driving vehicle 100 along the route received from server 200, and use the generated driving control signal to control actuator 120.

[0097] (2) Server 200 can acquire vehicle location information and transmit the acquired vehicle location information to vehicle 100. Vehicle 100 can determine the target location that vehicle 100 should go to next, generate a route from the current location of vehicle 100 indicated in the received vehicle location information to the target location, generate a driving control signal for making vehicle 100 travel along the generated route, and use the generated driving control signal to control actuator 120.

[0098] (3) In forms (1) and (2) above, the internal sensor may be mounted on the vehicle 100, and the detection results output from the internal sensor may be used for at least one of route generation or driving control signal generation. The internal sensor is a sensor mounted on the vehicle 100. Examples of internal sensors may include sensors that detect the motion state of the vehicle 100, sensors that detect the operational state of each part of the vehicle 100, and sensors that detect the environment near the vehicle 100. Specifically, examples of internal sensors may include cameras, LiDAR, millimeter-wave radar, ultrasonic sensors, GPS sensors, accelerometers, and gyroscopes.

[0099] For example, in form (1) above, server 200 can acquire the detection results of internal sensors and reflect the detection results of internal sensors in the route when generating the route. In form (1) above, vehicle 100 can acquire the detection results of internal sensors and reflect the detection results of internal sensors in the driving control signal when generating the driving control signal. In form (2) above, vehicle 100 can acquire the detection results of internal sensors and reflect the detection results of internal sensors in the route when generating the route. In form (2) above, vehicle 100 can acquire the detection results of internal sensors and reflect the detection results of internal sensors in the driving control signal when generating the driving control signal.

[0100] (YY3) In driving control example 2, internal sensors can be installed on vehicle 100v, and the detection results output from the internal sensors can be used for at least one of route generation and driving control signal generation. For example, vehicle 100v can acquire the detection results of the internal sensors and reflect the detection results of the internal sensors in the route when generating the route. Vehicle 100v can 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.

[0101] (YY4) In driving control example 2, vehicle 100v uses the detection results of external sensor 300 to acquire vehicle position information. However, internal sensors can be mounted on vehicle 100v, and vehicle 100v can use the detection results of internal sensors to acquire vehicle position information. In this case, vehicle 100v determines the target location where vehicle 100v should go next and generates a route from vehicle 100v's current position to the target location indicated in the acquired vehicle position information. Then, vehicle 100v generates a driving control signal for vehicle 100v to travel along the generated route and uses the generated driving control signal to control actuator 120. With this configuration, vehicle 100v can drive without using any detection results from external sensor 300.

[0102] Note that vehicle 100v can acquire target arrival time and congestion information from outside the vehicle 100v, and reflect the target arrival time and congestion information in at least one of the route and driving control signals. Furthermore, all functional configurations of system 50v can be set within vehicle 100v. That is, the processes implemented by system 50v in this disclosure can be implemented independently by vehicle 100v.

[0103] (YY5) In driving control example 1, server 200 automatically generates driving control signals to be transmitted to vehicle 100. However, server 200 can generate driving control signals to be transmitted to vehicle 100 based on operations performed by an external operator located outside vehicle 100. For example, the external operator can operate a control device including a display for showing captured images output from external sensors 300, a steering device for remotely controlling vehicle 100, an accelerator pedal and a brake pedal, and a communication device for communicating with server 200 via wired or wireless communication, and server 200 can generate driving control signals corresponding to the operations performed by the control device.

[0104] (YY6) In each of the above driving control examples, vehicle 100 only needs to have a configuration in which it can move by autonomous driving, and the platform form of vehicle 100 can have a configuration as described below. Specifically, vehicle 100 only needs to include at least vehicle control device 110 and actuator 120 in order to perform the three functions of "moving", "turning" and "stopping" by autonomous driving.

[0105] When vehicle 100 obtains autonomous driving information from the outside, vehicle 100 may further include a communication device 130. That is, vehicle 100 capable of autonomous driving may not have at least some of the internal components such as driver's seat and dashboard, at least some of the external components such as bumpers and fenders, and a main body shell.

[0106] In this configuration, unattached components such as the main housing can be installed on the vehicle 100 before it is shipped from the factory FC, or unattached components such as the main housing can be installed on the vehicle 100 after it is shipped from the factory FC, provided that unattached components such as the main housing are not installed on the vehicle 100. Components can be installed on the vehicle 100 from their desired orientation, such as from their top, bottom, front, rear, right, or left side. They can also be installed on the vehicle 100 from the same or different directions. Note that the platform configuration can be determined as in the case of the vehicle 100 according to the first embodiment.

[0107] (YY7) Vehicle 100 can be manufactured by combining multiple modules with each other. A module means a unit formed by multiple parts grouped according to the parts or functions of vehicle 100. For example, the platform of vehicle 100 can be manufactured by combining a front module forming the front part of the platform, a central module forming the central part of the platform, and a rear module forming the rear part of the platform with each other.

[0108] Note that the number of modules forming the platform is not limited to three, but may instead be two or fewer, or four or more. Furthermore, as additions to or replacements to the components forming the platform, components forming the parts of the vehicle 100 other than the platform may be formed in the form of modules. Moreover, the various modules described above may include any external components such as bumpers or grilles, or any internal components such as seats and consoles.

[0109] Furthermore, not only vehicle 100, but any form of mobile body can be manufactured by combining multiple modules together. Each of these modules can be manufactured, for example, by connecting multiple parts through welding, jigs, etc., or by casting at least some of the parts forming the module integrally molded into a single part. The molding method used to integrally mold parts into a single part, especially relatively large parts, is also known as giga-casting or mega-casting. For example, the aforementioned front module, central module, and rear module can be manufactured using giga-casting.

[0110] (YY8) The transportation of vehicle 100 using driverless operation is also referred to as "self-propelled transportation". Furthermore, the configuration used to achieve self-propelled transportation is called a "vehicle remote-controlled autonomous driving transportation system". Additionally, the production method for producing vehicle 100 using self-propelled transportation is also called "self-propelled production". In self-propelled production, for example, in factory FC where vehicle 100 is manufactured, a portion of the transportation of vehicle 100 is achieved through self-propelled transportation.

[0111] (YY9) In each of the above driving control examples, some or all of the functions and processes implemented in software can be implemented in hardware. Furthermore, some or all of the functions and processes implemented in hardware can be implemented in software. For example, various types of circuits, such as integrated circuits or discrete circuits, can be used as hardware to implement the various types of functions in each of the above embodiments.

[0112] Note that in this disclosure, some or all of the processes performed in the aforementioned external sensor 300, vehicle 100, server 200, etc., can be implemented by having the central processing unit (CPU) execute a computer program.

[0113] The program described above includes instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more of the functions described in the embodiments. The program may be stored on a non-transitory computer-readable medium or a tangible storage medium. By way of example, and not limitation, a non-transitory computer-readable medium or tangible storage medium may include random access memory (RAM), read-only memory (ROM), flash memory, solid-state drives (SSDs) or other types of memory technologies, CD-ROMs, digital versatile discs (DVDs), Blu-ray discs or other types of optical disc storage, magnetic tape cassettes, magnetic tapes, and disk storage or other types of magnetic storage devices. The program may be transmitted on a transient computer-readable medium or a communication medium. By way of example, and not limitation, a transient computer-readable medium or communication medium may include electrical, optical, acoustic, or other forms of propagated signals.

[0114] As will be apparent from the present disclosure as described herein, embodiments of the present disclosure can be varied in many ways. Such variations should not be considered as departing from the spirit and scope of the present disclosure, and all such modifications that will be apparent to those skilled in the art are intended to be included within the scope of the appended claims.

Claims

1. A vehicle control system, comprising: Multiple cameras are arranged side-by-side along the longitudinal direction of the work line and are configured to capture images of vehicles traveling on the work line from above. as well as A controller configured to control the vehicle's movement based on images captured by the plurality of cameras. in, While the vehicle is self-propelled in a predetermined direction along the work line, the worker performs tasks while moving. The plurality of cameras includes pairs of cameras arranged side by side along the longitudinal direction of the work line, each pair of cameras being configured to capture images of the vehicle from the upper left and upper right, respectively.

2. The vehicle control system according to claim 1, wherein The controller: From the images captured by the pair of cameras, select an image in which the vehicle is easily identifiable; as well as The vehicle's movement is controlled based on the selected image.

3. The vehicle control system according to claim 2, wherein, When one of the vehicle's left and right doors is opened, the controller selects an image of the vehicle from the side where the door is not open as the image from which the vehicle is most easily identifiable.

4. The vehicle control system according to claim 1, wherein The controller: When one of the left and right doors of the vehicle is opened, an image of the vehicle on the side with the closed door is selected from the images captured by the paired cameras based on the door opening signal transmitted from the vehicle. as well as The vehicle's movement is controlled based on the selected image.

5. The vehicle control system according to any one of claims 1 to 4, wherein, The work line is covered by a lighting canopy, which is arched to span the work line in its width direction and extend along it. The multiple cameras are installed in the lighting shed.

6. A vehicle control method, comprising: Multiple cameras arranged side-by-side along the longitudinal direction of the work line capture images of vehicles traveling on the work line from above. as well as Based on the images captured by the multiple cameras, the controller controls the vehicle's movement. in, While the vehicle is self-propelled in a predetermined direction along the work line, the worker performs tasks while moving. The plurality of cameras includes pairs of cameras arranged side by side along the longitudinal direction of the work line, each pair of cameras being configured to capture images of the vehicle from the upper left and upper right, respectively.

7. The vehicle control method according to claim 6, wherein The controller: From the images captured by the pair of cameras, select an image in which the vehicle is easily identifiable; as well as The vehicle's movement is controlled based on the selected image.

8. The vehicle control method according to claim 7, wherein, When one of the vehicle's left and right doors is opened, the controller selects an image of the vehicle from the side where the door is not open as the image from which the vehicle is most easily identifiable.

9. The vehicle control method according to claim 6, wherein The controller: When one of the left and right doors of the vehicle is opened, an image of the vehicle on the side with the closed door is selected from the images captured by the paired cameras based on the door opening signal transmitted from the vehicle. as well as The vehicle's movement is controlled based on the selected image.

10. The vehicle control method according to any one of claims 6 to 9, wherein, The work line is covered by a lighting canopy, which is arched to span the work line in its width direction and extend along it. The multiple cameras are installed in the lighting shed.

Images