Unmanned driving system and unmanned driving method

Abstract

This unmanned driving system comprises: an internal sensor that is mounted on a vehicle capable of traveling by unmanned driving and detects a traveling environment around the vehicle; an external sensor that is located outside the vehicle and detects the vehicle and the traveling environment; and a first control device that, when it is determined that a possibility of contact between an obstacle in the traveling environment and the vehicle is low, causes the vehicle to travel in a first mode using a detection result of the internal sensor, and when it is determined that the possibility of contact is high, causes the vehicle to travel in a second mode using at least a detection result of the external sensor.

Description

Unmanned driving system and unmanned driving method Cross-reference to related applications

[0001] This application is based on Japanese Application No. 2025-026708 filed on February 21, 2025, the content of which is incorporated herein by reference.

[0002] The present disclosure relates to an unmanned driving system and an unmanned driving method.

[0003] Techniques are known for detecting obstacles existing around a vehicle using a camera mounted on the vehicle and driving the vehicle in an unmanned manner so that the vehicle does not come into contact with the obstacles (for example, Patent Document 1).

[0004] Japanese Unexamined Patent Application Publication No. 2018-018389

[0005] In places with many blind spots from the vehicle, such as curves and intersections, or places with many moving obstacles such as people and other vehicles, the possibility of the vehicle coming into contact with the obstacles is high. Therefore, it is difficult to suppress contact between the vehicle and the obstacles only with the sensors mounted on the vehicle. For this reason, further improvements are required to suppress contact between a vehicle driving in an unmanned manner and obstacles.

[0006] The present disclosure can be realized in the following forms.

[0007] (1) According to a first embodiment of the present disclosure, an unmanned driving system is provided. This unmanned driving system is mounted on a vehicle capable of driving by unmanned operation and includes an internal sensor that detects the driving environment around the vehicle, an external sensor located outside the vehicle that detects the vehicle and the driving environment, and a first control device that, when it is determined that the possibility of contact between the vehicle and an obstacle in the driving environment is low, drives the vehicle in a first mode using the detection results of the internal sensor, and when it is determined that the possibility of contact is high, drives the vehicle in a second mode using at least the detection results of the external sensor. According to this embodiment of the unmanned driving system, when it is determined that the possibility of contact between the vehicle and an obstacle is high, the vehicle can be driven using the detection results of the external sensor located outside the vehicle. Therefore, contact between the vehicle and an obstacle can be suppressed compared to an embodiment in which the vehicle is driven using only the detection results of the internal sensor. (2) In the above embodiment of the unmanned driving system, the first control device may determine the likelihood of contact using a map that shows the likelihood of contact for each location where the vehicle is driving. According to this embodiment of the unmanned driving system, the likelihood of contact can be determined with a simple configuration. (3) In the above-described unmanned driving system, the first control device may determine the likelihood of contact using the detection results of the internal sensor. With this configuration of the unmanned driving system, even if the likelihood of contact at each location changes over time, the likelihood of contact can be appropriately determined. (4) In the above-described unmanned driving system, in the second mode, the first control device may compare the number of obstacles detected by the external sensor with the number of obstacles detected by the internal sensor, and use the detection results of the sensor that has detected more obstacles than the external sensor to cause the vehicle to avoid the obstacles. With this configuration of the unmanned driving system, contact between the vehicle and obstacles can be more effectively suppressed compared to the configuration in which only the detection results of the external sensor are used in the second mode. (5) The above-described unmanned driving system further comprises a second control device mounted on the vehicle.The first control device is located outside the vehicle, and the second control device may, in the first mode, drive the vehicle using parameters determined by the second control device using the detection results of the internal sensors, and in the second mode, drive the vehicle using parameters determined by the first control device at least using the detection results of the external sensors. In this form of unmanned driving system, in the second mode, the first control device determines the parameters, and in the first mode, the second control device determines the parameters. This reduces the processing load on the first control device in the first mode. (6) The unmanned driving system of the above form further comprises a second control device mounted on the vehicle. In the second mode, the second control device determines parameters related to the acceleration of the vehicle using the detection results of the internal sensors, and the first control device is located outside the vehicle, and in the second mode, it may determine parameters related to the steering and deceleration of the vehicle using the detection results of the external sensors. In this form of unmanned driving system, in the second mode, the first control device and the second control device share the task of determining the parameters. Therefore, the processing load on the first control device in the second mode can be reduced. (7) According to a second embodiment of the present disclosure, an unmanned driving method is provided. This unmanned driving method determines the likelihood of contact between a vehicle capable of driving unmanned and an obstacle in the driving environment surrounding the vehicle. If it is determined that the likelihood of contact is low, the vehicle is driven in a first mode using the detection results of an internal sensor mounted on the vehicle that detects the driving environment. If it is determined that the likelihood of contact is high, the vehicle is driven in a second mode using the detection results of an external sensor located outside the vehicle that detects the vehicle and the driving environment. According to this embodiment of the unmanned driving method, if it is determined that there is a high likelihood of contact between the vehicle and an obstacle, the vehicle can be driven using the detection results of an external sensor located outside the vehicle. Therefore, contact between the vehicle and an obstacle can be suppressed compared to an embodiment in which the vehicle is driven using only the detection results of an internal sensor. The present disclosure can also be implemented in various forms other than unmanned driving systems and unmanned driving methods.For example, it can be implemented in the form of vehicles, servers, computer programs, program products, and recording media on which computer programs are stored.

[0008] An explanatory diagram showing the configuration of the unmanned driving system of the first embodiment. An explanatory diagram showing the configuration of the vehicle of the first embodiment. An explanatory diagram showing the configuration of the server of the first embodiment. An explanatory diagram showing the functional configuration of the unmanned driving system of the first embodiment. A flowchart showing the procedure for mode switching processing of the first embodiment. A flowchart showing the procedure for vehicle driving control in remote control mode. A flowchart showing the procedure for vehicle driving control in autonomous control mode. An explanatory diagram showing how the vehicle travels on dedicated and non-dedicated tracks. A flowchart showing the procedure for mode switching processing of the second embodiment. A flowchart showing the procedure for obstacle avoidance control of the third embodiment. An explanatory diagram showing the configuration of the unmanned driving system of the fourth embodiment. An explanatory diagram showing the configuration of the vehicle of the fourth embodiment. A flowchart showing the procedure for mode switching processing of the fourth embodiment.

[0009] A. First Embodiment: Figure 1 is an explanatory diagram showing the configuration of the unmanned driving system 10 in the first embodiment. The unmanned driving system 10 comprises a vehicle 100, a server 200, and at least one external sensor 300. In this embodiment, the unmanned driving system 10 is used to drive the vehicle 100 at a factory fuel cell (FC) where the vehicle 100 is manufactured. In this embodiment, the server 200 corresponds to the first control device in this disclosure, and the vehicle control device 110 mounted on the vehicle 100 corresponds to the second control device in this disclosure. The method executed by the unmanned driving system 10 is sometimes called the unmanned driving method.

[0010] 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."

[0011] 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.

[0012] 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 a vehicle 100 can travel. The track TR includes two dedicated tracks TRA1 and TRA2, on which entry by vehicles other than the vehicle 100 is prohibited, and a non-dedicated track TRB, on which entry by vehicles other than the vehicle 100 is not prohibited. In the following description, when the two dedicated tracks TRA1 and TRA2 are not specifically distinguished, they will simply be referred to as dedicated track TRA. Workers of the factory FC may walk on the non-dedicated track TRB, and other vehicles other than the vehicle 100 may travel on it, either with or without a driver. In this embodiment, the first location PL1 and the non-dedicated track TRB are connected by dedicated track TRA1, and the non-dedicated track TRB and the second location PL2 are connected by dedicated track TRA2.

[0013] In this embodiment, the first location PL1 is where the vehicle 100 is assembled. Upon assembly at the first location PL1, the vehicle 100 is ready for unmanned operation. The vehicle 100 assembled at the first location PL1 travels unmanned from the first location PL1 to the second location PL2, passing through the dedicated track TRA1, the non-dedicated track TRB, and the dedicated track TRA2 in that order. The second location PL2 is where the vehicle 100 is inspected. After passing the inspection at the second location PL2, the vehicle 100 is shipped from the factory FC.

[0014] Multiple external sensors 300 are installed in the factory FC. In this embodiment, multiple external sensors 300 are installed along the non-dedicated track TRB. The external sensors 300 are sensors located outside the vehicle 100. The external sensors 300 detect the vehicle 100 and the driving environment around the vehicle 100. In this disclosure, the driving environment means the environment in which the vehicle 100 travels. The driving environment includes the environment of the track TR. In this embodiment, the external sensors 300 are cameras. However, the external sensors 300 may be LiDAR, for example, instead of cameras. The external sensors 300 are equipped with a communication device (not shown) and communicate with the server 200 by wired or wireless communication. The position and orientation of the external sensors 300 in the factory FC are pre-adjusted. The external sensors 300 are installed so as to overlook the non-dedicated track TRB. The reference coordinate system for Factory FC is the global coordinate system GC, and any location within Factory FC can be represented by X, Y, and Z coordinates in the global coordinate system GC.

[0015] Figure 2 is an explanatory diagram showing the configuration of the vehicle 100. The vehicle 100 comprises a vehicle control device 110, an actuator group 120, an internal sensor group 130, and a communication device 140. The actuator group 120 includes at least one actuator. In this embodiment, the actuator group 120 includes an actuator for a drive system that generates the propulsion force of the vehicle 100, an actuator for a steering system that changes the direction of travel of the vehicle 100, and an actuator for a braking system that generates the braking force of the vehicle 100. Each actuator included in the actuator group 120 is driven under the control of the vehicle control device 110.

[0016] The internal sensor group 130 includes at least one internal sensor. An internal sensor is a sensor mounted on the vehicle 100. The internal sensor group 130 includes an ambient sensor 131 that detects the driving environment around the vehicle 100. In this embodiment, the ambient sensor 131 is a camera that captures images of the driving environment in front of the vehicle 100. However, the ambient sensor 131 is not limited to a camera and may be, for example, a LiDAR. In this embodiment, in addition to the ambient sensor 131, the internal sensor group 130 includes a vehicle speed sensor 132 that detects the speed of the vehicle 100 and a steering angle sensor 133 that detects the steering angle of the vehicle 100. The detection results of each sensor included in the internal sensor group 130 are transmitted to the vehicle control device 110.

[0017] The communication device 140 communicates with the outside of the vehicle 100 via wireless communication. In this embodiment, the communication device 140 communicates with the server 200 via wireless communication. In this embodiment, the communication device 140 is detachably mounted on the vehicle 100. The communication device 140 may be removed from the vehicle 100 before the vehicle 100 is shipped from the factory fuel cell (FC).

[0018] The vehicle control device 110 controls various parts of the vehicle 100. 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 so as to be able to communicate bidirectionally. The input / output interface 113 is connected to an actuator group 120, an internal sensor group 130, and a communication device 140.

[0019] Figure 3 is an explanatory diagram showing the configuration of the server 200. The server 200 is located outside the vehicle 100. The server 200 is composed of a computer comprising a processor 201, a memory 202, an input / output interface 203, and an internal bus 204. The processor 201, the memory 202, and the input / output interface 203 are connected via the internal bus 204 to enable bidirectional communication. The server 200 further comprises a communication device 205 for communicating with the outside. The communication device 205 is connected to the input / output interface 203. In this embodiment, the communication device 205 communicates with the vehicle 100 via wireless communication and with the external sensor 300 via wired or wireless communication. In this embodiment, the memory 202 has a detection model DM and a reference path RR pre-stored in it. The memory 202 also has a map MP pre-stored in it that shows the range of the dedicated track TRA and the range of the non-dedicated track TRB.

[0020] Vehicle 100 has two operating modes. The two operating modes include a first mode in which vehicle 100 drives based on the detection results of the ambient sensor 131, and a second mode in which vehicle 100 drives based on the detection results of the external sensor 300, or the detection results of the external sensor 300 and the ambient sensor 131. In this embodiment, in the first mode, vehicle 100 drives by autonomous control, and in the second mode, vehicle 100 drives by remote control by the server 200. In the following description, the first mode in this embodiment will be referred to as the autonomous control mode, and the second mode in this embodiment will be referred to as the remote control mode.

[0021] In autonomous control mode, the vehicle control device 110 generates a driving control signal using the detection results of the internal sensor group 130, and drives the vehicle 100 by controlling the actuator group 120 using the vehicle control signal it has generated. The driving control signal is a control signal for driving the vehicle 100 in an unmanned manner. 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 the acceleration of the vehicle 100, or in addition to the acceleration of the vehicle 100.

[0022] In remote control mode, the server 200 generates a driving control signal using at least the detection results of the external sensor 300 and transmits the driving control signal to the vehicle 100. In remote control mode, the vehicle control device 110 drives the vehicle 100 by controlling the actuator group 120 using the driving control signal received from the server 200. However, in remote control mode, the server 200 may generate a driving control signal using the detection results of the external sensor 300 and the detection results of the internal sensor group 130.

[0023] Figure 4 is an explanatory diagram showing the functional configuration of the unmanned driving system 10. The processor 201 of the server 200 functions as a remote control unit 291 and a driving permission issuing unit 295 by executing a computer program PG2 that is pre-stored in the memory 202. The communication device 140 of the vehicle 100 includes a processor, memory, and input / output interface that are connected bidirectionally by an internal bus. The processor of the communication device 140 functions as a first abnormality detection unit 195 by executing a computer program that is pre-stored in the memory. The processor 111 of the vehicle control device 110 functions as a vehicle control unit 191 and a second abnormality detection unit 196 by executing a computer program PG1 that is pre-stored in the memory 112.

[0024] In remote control mode, the remote control unit 291 acquires vehicle position information, including the position and orientation of the vehicle 100, using the detection results of the external sensor 300, and generates a driving control signal using the vehicle position information. If the external sensor 300 detects an obstacle around the vehicle 100, the remote control unit 291 generates a driving control signal to avoid contact between the vehicle 100 and the obstacle. Specifically, if an obstacle is detected around the vehicle 100, the remote control unit 291 generates a driving control signal to either stop the vehicle 100 before the obstacle or to have the vehicle 100 bypass the obstacle. The remote control unit 291 transmits the driving control signal to the vehicle control unit 191 via wireless communication.

[0025] In remote control mode, the vehicle control unit 191 drives the vehicle 100 by controlling the actuator group 120 using the driving control signal received from the remote control unit 291. In autonomous control mode, the vehicle control unit 191 acquires vehicle position information using the detection results of the surrounding sensor 131, generates a driving control signal using the vehicle position information, and drives the vehicle 100 by controlling the actuator group 120 using the driving control signal it has generated. If the surrounding sensor 131 detects an obstacle around the vehicle 100, the vehicle control unit 191 generates a driving control signal to avoid contact between the vehicle 100 and the obstacle. Specifically, if the vehicle control unit 191 detects an obstacle around the vehicle 100, it generates a driving control signal to either have the vehicle 100 stop before the obstacle or have the vehicle 100 bypass the obstacle.

[0026] In remote control mode and autonomous control mode, the vehicle control unit 191 transmits the current state of the vehicle 100 to the remote control unit 291, the first abnormality detection unit 195, and the second abnormality detection unit 196. The state of the vehicle 100 includes the time elapsed since the last driving control signal was received from the remote control unit 291, the vehicle speed of the vehicle 100, the steering angle of the vehicle 100, the position of the vehicle 100, and the direction of travel of the vehicle 100.

[0027] The driving permit issuing unit 295 determines a first permit condition for allowing the vehicle 100 to operate unmanned, and transmits the determined first permit condition to the first abnormality determination unit 195. In this embodiment, the first permit condition includes parameters such as grace period, maximum steering angle, direction of travel, and maximum vehicle speed. The grace period is the upper limit of the time from when the vehicle control unit 191 last receives a driving control signal from the remote control unit 291 until when it receives the next driving control signal. If all parameters are within the range of the first permit condition, the vehicle 100 is permitted to operate unmanned; if at least one parameter is outside the range of the first permit condition, the vehicle 100 is prohibited from operating unmanned.

[0028] In this embodiment, the driving permit issuing unit 295 sets different first permit conditions depending on the position of the vehicle 100. Specifically, the driving permit issuing unit 295 sets different first permit conditions depending on whether the vehicle 100 is located on the dedicated track TRA or on the non-dedicated track TRB. The memory 202 of the server 200 stores in advance the first permit conditions for the dedicated track TRA and the first permit conditions for the non-dedicated track TRB. The first permit conditions for the non-dedicated track TRB are stricter than the first permit conditions for the dedicated track TRA. Stricter first permit conditions mean that the permissible range for the state of the vehicle 100 during unmanned operation is narrower. In this embodiment, strict first permit conditions include a short grace period, a small maximum steering angle, a narrow permissible range for deviation in the direction of travel, and a small maximum vehicle speed. The server 200's memory 202 has a map MP pre-stored in it that shows the range of the dedicated track TRA and the range of the non-dedicated track TRB. The driving permit issuing unit 295 uses the map MP and the vehicle position information of the vehicle 100 to determine whether the vehicle 100 is located on the dedicated track TRA or on the non-dedicated track TRB.

[0029] The first abnormality detection unit 195 compares the first permission conditions received from the driving permission issuing unit 295 with the current state of the vehicle 100. If the current state of the vehicle 100 is within the range of the first permission conditions, the first abnormality detection unit 195 compares the latest state of the vehicle 100 with the latest first permission conditions after a predetermined time has elapsed. Conversely, if the current state of the vehicle 100 is outside the range of the first permission conditions, the first abnormality detection unit 195 transmits an emergency stop signal to the vehicle control unit 191 to bring the vehicle 100 to an emergency stop. The emergency stop signal is a control signal for bringing the vehicle 100 to an emergency stop. When the vehicle control unit 191 receives the emergency stop signal from the first abnormality detection unit 195, it controls the actuator group 120 according to the emergency stop signal to bring the vehicle 100 to a stop.

[0030] The second abnormality detection unit 196 compares the current state of the vehicle 100 with a second permission condition pre-stored in the memory 112 of the vehicle control device 110. At least a part of the second permission condition is different from the first permission condition. In this embodiment, the second permission condition is fixed. That is, the second permission condition does not change according to the position of the vehicle 100. By fixing the second permission condition, it is possible to use a common second permission condition for multiple vehicles 100. By using a common second permission condition for multiple vehicles 100, the manufacturing cost of the vehicle 100 can be reduced. If the current state of the vehicle 100 is within the range of the second permission condition, the second abnormality detection unit 196 compares the latest state of the vehicle 100 with the second permission condition after a predetermined time has elapsed. On the other hand, if the current state of the vehicle 100 is outside the range of the second permission condition, the second abnormality detection unit 196 transmits an emergency stop signal to the vehicle control unit 191 to emergency stop the vehicle 100. When the vehicle control unit 191 receives an emergency stop signal from the second abnormality detection unit 196, it controls the actuator group 120 in accordance with the emergency stop signal to bring the vehicle 100 to a stop.

[0031] Vehicle 100 travels on the dedicated track TRA in autonomous control mode. When vehicle 100 is traveling in autonomous control mode, the driving permission issuing unit 295 makes the first permission condition more lenient than the second permission condition. Therefore, vehicle 100 makes an emergency stop mainly based on the judgment result using the second permission condition of the second abnormality judgment unit 196. In autonomous control mode, the vehicle control unit 191 does not receive driving control signals from the remote control unit 291, so the grace period is unlimited. In autonomous control mode, the maximum steering angle is increased, the allowable range of deviation in the direction of travel is widened, and the maximum vehicle speed is increased compared to when it is in remote control mode. As a result, the frequency of emergency stops by vehicle 100 on the dedicated track TRA, where workers and other vehicles do not enter, can be reduced. However, if an external sensor 300 is installed around the dedicated track TRA, and the external sensor 300 detects an abnormality in the vehicle 100 that cannot be detected by the internal sensor group 130, for example, if a broken window is detected or if one of the four wheels is not mounted, an emergency stop signal may be transmitted from the remote control unit 291 to the vehicle control unit 191.

[0032] Vehicle 100 travels on the non-dedicated track TRB in remote control mode. When vehicle 100 is traveling in remote control mode, the driving permission issuing unit 295 makes the first permission conditions stricter than the second permission conditions. Therefore, vehicle 100 makes an emergency stop mainly based on the judgment result using the first permission conditions of the first abnormality determination unit 195. For example, if communication is lost between vehicle 100 and server 200 while in remote control mode, vehicle control unit 191 will not be able to receive a new driving control signal from the remote control unit 291. In this case, an emergency stop signal is sent from the first abnormality determination unit 195 to vehicle control unit 191 when the grace period included in the first permission conditions is exceeded. While in remote control mode, vehicle control unit 191 drives vehicle 100 according to the last driving control signal received from the remote control unit 291 until a new driving control signal is received from the remote control unit 291. However, if vehicle control unit 191 receives an emergency stop signal from the first abnormality determination unit 195, it stops vehicle 100. Therefore, the vehicle 100's driving state can be stabilized within the grace period, and if the grace period is exceeded, the vehicle 100's continued driving can be suppressed. This prevents the vehicle 100 from coming into contact with workers or other vehicles on a non-dedicated track (TRB) where workers or other vehicles may enter, by preventing the vehicle 100 from continuing to drive after a communication interruption.

[0033] In this embodiment, the cycle for which the remote control unit 291 decides whether or not to stop the vehicle 100 is longer than the cycle for which the first abnormality detection unit 195 decides whether or not to stop the vehicle 100. Therefore, the decision to stop the vehicle 100 can be made more quickly compared to the case where only the remote control unit 291 decides whether or not to stop the vehicle 100. Furthermore, in this embodiment, since the remote control unit 291 also decides whether or not to stop the vehicle 100 in addition to the first abnormality detection unit 195, even if the first abnormality detection unit 195 misses the possibility of the vehicle 100 coming into contact with an obstacle, the vehicle 100 can be stopped by the decision of the remote control unit 291.

[0034] In this embodiment, the driving permission issuing unit 295 transmits the braking force during an emergency stop along with the first permission conditions to the first abnormality detection unit 195. Therefore, the braking force of the vehicle 100 can be varied depending on the emergency stop signal from the first abnormality detection unit 195. In contrast, the braking force of the vehicle 100 is fixed when the emergency stop signal from the second abnormality detection unit 196 is received. Consequently, the first abnormality detection unit 195 can stop the vehicle 100 more flexibly depending on the location and situation compared to the second abnormality detection unit 196. Furthermore, in this embodiment, the communication device 140 equipped with the first abnormality detection unit 195 is configured to be detachable from the vehicle 100. The communication device 140 is removed from the vehicle 100 after the unmanned operation of the vehicle 100 at the factory fuel cell (FC) is completed. Therefore, the communication device 140 can be reused in multiple vehicles 100, thereby suppressing an increase in the manufacturing cost of the vehicle 100. Furthermore, in this embodiment, the communication device 140 is provided with a first abnormality detection unit 195, and the vehicle control device 110 is provided with a second abnormality detection unit 196. Therefore, even if the communication device 140 becomes detached or malfunctions, the second abnormality detection unit 196 can cause the vehicle 100 to make an emergency stop.

[0035] Figure 5 is a flowchart of the mode switching process for switching between the autonomous control mode and the remote control mode of the vehicle 100. In this embodiment, the mode switching process is repeatedly executed by the server 200 at a predetermined interval. In step S110, the server 200 acquires vehicle position information indicating the position of the vehicle 100. When the operating mode of the vehicle 100 is the remote control mode, the server 200 acquires vehicle position information using the external sensor 300. When the operating mode of the vehicle 100 is the autonomous control mode, the vehicle 100 generates vehicle position information using the internal sensor group 130, and the server 200 acquires vehicle position information from the vehicle 100. When the operating mode of the vehicle 100 is the autonomous control mode, the server 200 acquires vehicle position information from the vehicle 100.

[0036] In step S120, the server 200 determines whether the vehicle 100 is located on the dedicated track TRA. In this embodiment, the server 200 uses the vehicle location information and the map MP to determine whether the vehicle 100 is located on the dedicated track TRA. Here, entry of workers and other vehicles is prohibited on the dedicated track TRA, while entry of workers and other vehicles is not prohibited on the non-dedicated track TRB. Therefore, when the vehicle 100 is located on the dedicated track TRA, the possibility of the vehicle 100 coming into contact with an obstacle is lower than when the vehicle 100 is located on the non-dedicated track TRB. Obstacles here include workers and other vehicles. In the following description, the possibility of the vehicle 100 coming into contact with an obstacle will be referred to as the possibility of contact. Determining that vehicle 100 is located on the dedicated track TRA corresponds to determining that there is a high probability of contact between vehicle 100 and an obstacle, while determining that vehicle 100 is not located on the dedicated track TRA corresponds to determining that there is a low probability of contact between vehicle 100 and an obstacle. Map MP shows the range of the dedicated track TRA and the non-dedicated track TRB, in other words, the probability of contact at each location where vehicle 100 is traveling.

[0037] If it is determined in step S120 that the vehicle 100 is located on the dedicated track TRA, the server 200 switches the operating mode of the vehicle 100 to autonomous control mode in step S130. Conversely, if it is determined in step S120 that the vehicle 100 is not located on the dedicated track TRA, the server 200 switches the operating mode of the vehicle 100 to remote control mode in step S140. After that, the server 200 terminates the mode switching process.

[0038] Figure 6 is a flowchart showing the processing procedure for controlling the driving of vehicle 100 in remote control mode. In step S11, the server 200 acquires vehicle position information using the detection result output from the external sensor 300, which is a sensor located outside the vehicle 100. 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 vehicle 100 in the reference coordinate system of the factory FC. In this embodiment, the reference coordinate system of the factory FC is the global coordinate system GC, and any position within the factory FC can be represented by the X, Y, Z coordinates in the global coordinate system GC. In this embodiment, the external sensor 300 is a camera installed in the factory FC, and the external sensor 300 outputs an captured image as a detection result. That is, in step S11, the server 200 acquires vehicle position information using the captured image acquired from the camera, which is the external sensor 300.

[0039] In detail, in step S11, the server 200, for example, 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 unmanned driving system 10 and stored in the memory 202 of the server 200. Examples of the detection model DM include a 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 (hereinafter referred to as CNN) trained by supervised learning using a training dataset can be used. The training dataset includes, for example, multiple training images containing the vehicle 100, and labels indicating whether each region in the training images represents the vehicle 100 or a region other than the vehicle 100. During CNN training, it is preferable that the CNN parameters are updated using backpropagation to reduce the error between the output result of the detection model DM and the labels. Furthermore, the server 200 can obtain the orientation of the 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.

[0040] In step S12, 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, and Z coordinates in the global coordinate system GC. The server 200's memory 202 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 server 200 uses the vehicle position information and the reference route RR to determine the next target location that the vehicle 100 should head to. The server 200 determines the target location on the reference route RR beyond the vehicle 100's current location.

[0041] In step S13, the server 200 generates a driving control signal to drive the vehicle 100 toward the determined target position. However, if an obstacle is detected around the vehicle 100 by the external sensor 300, the server 200 generates a driving control signal to avoid contact between the vehicle 100 and the obstacle. In this embodiment, the driving control signal includes the acceleration and steering angle of the vehicle 100 as parameters. The server 200 calculates the driving speed of the vehicle 100 from the change in the position of the vehicle 100 and compares the calculated driving speed with the target speed. Overall, if the driving speed is lower than the target speed, the server 200 determines the acceleration so that the vehicle 100 accelerates, and if the driving speed is higher than the target speed, it determines the acceleration so that the vehicle 100 decelerates. Furthermore, if the vehicle 100 is located on the reference path RR, the server 200 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 server 200 determines the steering angle and acceleration so that the vehicle 100 returns to the reference path RR. 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.

[0042] In step S14, the server 200 transmits the generated driving control signal to the vehicle 100. The server 200 repeats the process of acquiring vehicle position information, determining the target position, generating the driving control signal, and transmitting the driving control signal at predetermined intervals.

[0043] In step S15, the vehicle 100 receives a driving control signal transmitted from the server 200. In step S16, the vehicle 100 uses the received driving control signal to control the actuator group 120 of the vehicle 100, thereby driving the vehicle 100 at the acceleration and steering angle indicated in the driving control signal. The vehicle 100 repeats the reception of the driving control signal and the control of the actuator group 120 of the vehicle 100 at predetermined intervals. In remote control mode, the vehicle 100 can be driven by remote control, and the vehicle 100 can be moved without using transport equipment such as cranes or conveyors.

[0044] FIG. 7 is a flowchart showing the processing procedure of the driving control of the vehicle 100 in the autonomous control mode. In step S21, the vehicle 100 acquires vehicle position information using the detection result output from the surrounding sensor 131. The vehicle 100 can acquire vehicle position information by, for example, SLAM (Simultaneous Localization and Mapping) technology. In step S22, the vehicle 100 determines the target position that the vehicle 100 should head to next. In step S23, the vehicle 100 generates a driving control signal for driving the vehicle 100 toward the determined target position. However, when an obstacle is detected around the vehicle 100 by the surrounding sensor 131, the vehicle 100 generates a driving control signal so as to avoid contact between the vehicle 100 and the obstacle. In step S24, the vehicle 100 controls the actuator group 120 of the vehicle 100 using the generated driving control signal, and drives the vehicle 100 according to the parameters represented in the driving control signal. The vehicle 100 repeats the acquisition of vehicle position information, determination of the target position, generation of the driving control signal, and control of the actuator group 120 at a predetermined cycle. According to the autonomous control mode, the vehicle 100 can be driven by the autonomous control of the vehicle 100 without remotely controlling the vehicle 100 by the server 200.

[0045] FIG. 8 is an explanatory diagram showing how the vehicle 100 travels on the dedicated lane TRA and the non-dedicated lane TRB. As shown in the upper part of FIG. 8, when the vehicle 100 is located on the dedicated lane TRA, the vehicle 100 travels in the autonomous control mode. In the autonomous control mode, the vehicle 100 travels by autonomous control using the detection result of the surrounding sensor 131 mounted on itself. In the dedicated lane TRA, entry of workers and other vehicles is prohibited. However, for example, an object flying due to wind may exist on the dedicated lane TRA as an obstacle OB. When the vehicle 100 detects the obstacle OB by the surrounding sensor 131, the vehicle 100 avoids the obstacle OB by decelerating or steering. When the vehicle 100 enters from the dedicated lane TRA to the non-dedicated lane TRB, the operation mode of the vehicle 100 is switched from the autonomous control mode to the remote control mode by the mode switching process.

[0046] As shown in the lower part of FIG. 8, when the vehicle 100 is located on the non-exclusive road TRB, the vehicle 100 travels in the remote control mode. In the remote control mode, the server 200 uses the detection results of the external sensor 300 provided along the non-exclusive road TRB to drive the vehicle 100 by remote control. In the non-exclusive road TRB, the entry of workers and other vehicles is not prohibited. Therefore, there is a possibility that workers and other vehicles may exist on the non-exclusive road TRB as obstacles OB. When the server 200 detects an obstacle OB by the external sensor 300, the server 200 causes the vehicle 100 to avoid the obstacle OB by decelerating or steering. When the vehicle 100 enters from the non-exclusive road TRB to the exclusive road TRA, the operation mode of the vehicle 100 is switched from the remote control mode to the autonomous control mode by mode switching processing.

[0047] According to the driverless system 10 in the present embodiment described above, on the exclusive road TRA where the possibility of contact between the vehicle 100 and the obstacle OB is relatively low, the vehicle 100 is driven based on the detection results of the surrounding sensor 131. For this reason, since it is not necessary to provide the external sensor 300 around the exclusive road TRA, the number of external sensors 300 in the driverless system 10 can be reduced. In addition, in the present embodiment, on the non-exclusive road TRB where the possibility of contact between the vehicle 100 and the obstacle OB is relatively high, the vehicle 100 is driven based on the detection results of the external sensor 300. In the present embodiment, the surrounding sensor 131 can detect an obstacle in front of the vehicle 100. On the other hand, the external sensor 300 can detect not only an obstacle in front of the vehicle 100 but also obstacles on the side and rear of the vehicle 100. For this reason, the external sensor 300 has fewer blind spots than the surrounding sensor 131. Therefore, in the present embodiment, compared with the form in which the vehicle 100 travels on the non-exclusive road TRB based on the detection results of the surrounding sensor 131, the contact between the vehicle 100 and the obstacle OB can be suppressed.

[0048] Furthermore, in this embodiment, the server 200 uses vehicle location information and map MP to determine whether the vehicle 100 is located on the dedicated track TRA or on the non-dedicated track TRB. Therefore, it is possible to determine whether the vehicle 100 is located on the dedicated track TRA or on the non-dedicated track TRB with a simple configuration.

[0049] In this embodiment, the vehicle 100 travels on the dedicated track TRA in autonomous control mode and on the non-dedicated track TRB in remote control mode. In autonomous control mode, the vehicle control device 110 generates a driving control signal using the detection results of the surrounding sensor 131 and drives the vehicle 100 by controlling the actuator group 120 using the driving control signal. In contrast, in remote control mode, the server 200 generates a driving control signal using the detection results of the external sensor 300 and transmits the driving control signal to the vehicle control device 110. The vehicle control device 110 drives the vehicle 100 by controlling the actuator group 120 using the driving control signal received from the server 200. Therefore, the processing load on the vehicle control device 110 when traveling on the non-dedicated track TRB can be reduced.

[0050] B. Second Embodiment: Figure 9 is a flowchart showing the procedure for mode switching processing performed in the unmanned driving system 10 in the second embodiment. In the second embodiment, the server 200 determines the likelihood of contact based on the number of obstacles detected by the surrounding sensor 131, which is an internal sensor, rather than the map MP, which is different from the first embodiment. In the second embodiment, external sensors 300 are installed around the dedicated track TRA in addition to the non-dedicated track TRB. The other configurations are the same as in the first embodiment unless otherwise specified.

[0051] In this embodiment, the server 200 repeatedly executes a mode switching process at a predetermined interval. In step S210, the server 200 obtains the number of obstacles detected by the surrounding sensor 131. In step S220, the server 200 determines whether the number of obstacles detected by the surrounding sensor 131 is below a predetermined threshold. The more obstacles detected by the surrounding sensor 131, the higher the probability of the vehicle 100 coming into contact with an obstacle. Therefore, determining whether the number of obstacles detected by the surrounding sensor 131 is below a threshold is equivalent to determining the likelihood of the vehicle 100 coming into contact with an obstacle. The threshold is stored in advance in the server 200's memory 202. If it is determined in step S220 that the number of obstacles detected by the surrounding sensor 131 is below a predetermined threshold, the server 200 drives the vehicle 100 in an autonomous control mode using the detection results of the surrounding sensor 131 in step S230. In contrast, if in step S220 the number of obstacles detected by the surrounding sensor 131 exceeds a predetermined threshold, the server 200 drives the vehicle 100 in step S240 using a remote control mode that utilizes the detection results of the external sensor 300. After that, the server 200 terminates the mode switching process.

[0052] In the unmanned driving system 10 of this embodiment described above, when there are many obstacles around the vehicle 100, the server 200 remotely controls the vehicle 100 to move using the detection results of the external sensor 300, which has fewer blind spots than the surrounding sensor 131. Therefore, contact between the vehicle 100 and obstacles can be suppressed. Furthermore, in this embodiment, even when the probability of contact changes over time depending on the location, the likelihood of contact can be appropriately determined.

[0053] C. Third Embodiment: Figure 10 is a flowchart showing the obstacle avoidance control process performed in the unmanned driving system 10 in the third embodiment. In the third embodiment, the server 200 uses the detection result of the external sensor 300, whichever has a larger number of obstacles detected around the vehicle 100, to cause the vehicle 100 to avoid obstacles, unlike in the first embodiment. The other configurations are the same as in the first embodiment unless otherwise specified.

[0054] The obstacle avoidance control shown in Figure 10 is performed by the server 200 during remote control mode. In step S310, the server 200 obtains the number of obstacles detected by the internal ambient sensor 131 and the number of obstacles detected around the vehicle 100 by the external sensor 300. In step S320, the server 200 determines whether the number of obstacles detected by the ambient sensor 131 is greater than the number of obstacles detected around the vehicle 100 by the external sensor 300. If in step S320 the server determines that the number of obstacles detected by the ambient sensor 131 is greater than the number of obstacles detected around the vehicle 100 by the external sensor 300, the server 200 uses the detection results of the ambient sensor 131 to cause the vehicle 100 to avoid the obstacles in step S330. In contrast, if in step S320 the number of obstacles detected by the surrounding sensor 131 is determined to be less than or equal to the number of obstacles detected around the vehicle 100 by the external sensor 300, the server 200, in step S340, uses the detection results of the external sensor 300 to cause the vehicle 100 to avoid the obstacles.

[0055] According to the unmanned driving system 10 of this embodiment described above, in remote control mode, the vehicle 100 travels using the detection result of the ambient sensor 131 and the detection result of the external sensor 300, whichever has a larger number of obstacles detected around the vehicle 100. Therefore, compared to the configuration in which the vehicle 100 travels using only the detection result of the external sensor 300 in remote control mode, contact between the vehicle 100 and obstacles can be suppressed.

[0056] D. Fourth Embodiment: Figure 11 is an explanatory diagram showing the configuration of the unmanned driving system 10 in the fourth embodiment. Figure 12 is an explanatory diagram showing the configuration of the vehicle 100 in the fourth embodiment. Figure 13 is a flowchart showing the procedure for mode switching processing performed in the unmanned driving system 10 in the fourth embodiment. In the fourth embodiment, the unmanned driving system 10 does not have a server 200, and the vehicle 100 is driven by autonomous control, which is different from the first embodiment. The other configurations are the same as in the first embodiment unless otherwise specified. In this embodiment, the vehicle control device 110 corresponds to the first control device in this disclosure.

[0057] As shown in Figure 11, in this embodiment, the unmanned driving system 10 comprises a vehicle 100 and at least one external sensor 300. The vehicle 100 communicates with the external sensor 300 via wireless communication through a communication device 140. As shown in Figure 12, the memory 112 of the vehicle control device 110 has the detection model DM, the reference path RR, and the map MP stored in advance. In this embodiment, the vehicle 100 has two operating modes: a first autonomous control mode and a second autonomous control mode. In the first autonomous control mode, the vehicle 100 drives autonomously using the detection results of the surrounding sensor 131. In the first autonomous control mode, the vehicle 100 uses the surrounding sensor 131 to detect obstacles present around the vehicle 100. In the second autonomous control mode, the vehicle 100 drives autonomously using the detection results of the external sensor 300. In the first autonomous control mode, the vehicle 100 travels on a dedicated track TRA, and in the second autonomous control mode, it travels on a non-dedicated track TRB. In the second autonomous control mode, the vehicle 100 uses an external sensor 300 to detect obstacles present around the vehicle 100. In this embodiment, the first autonomous control mode corresponds to the first mode in this disclosure, and the second autonomous control mode corresponds to the second mode in this disclosure.

[0058] The mode switching process shown in Figure 13 is repeatedly executed by the vehicle control device 110 at a predetermined interval. In step S410, the vehicle control device 110 acquires vehicle position information indicating the position of the vehicle 100. If the operating mode of the vehicle 100 is the first autonomous control mode, the vehicle control device 110 acquires vehicle position information using the external sensor 300. If the operating mode of the vehicle 100 is the second autonomous control mode, the vehicle control device 110 acquires vehicle position information using the internal sensor group 130. In step S420, the vehicle control device 110 determines whether the vehicle 100 is located on the dedicated track TRA. In this embodiment, the vehicle control device 110 uses the vehicle position information and the map MP to determine whether the vehicle 100 is located on the dedicated track TRA. If it is determined in step S420 that the vehicle 100 is located on the dedicated track TRA, the vehicle control device 110 switches the operating mode of the vehicle 100 to the first autonomous control mode in step S430. In response to this, if it is determined in step S420 that the vehicle 100 is not located on the dedicated track TRA, the vehicle control device 110 switches the operating mode of the vehicle 100 to the second autonomous control mode in step S440. After that, the vehicle control device 110 terminates the mode switching process.

[0059] With the unmanned driving system 10 of this embodiment described above, the vehicle 100 can be driven autonomously without remote control from the server 200. Furthermore, in this embodiment, contact between the vehicle 100 and obstacles OB can be suppressed compared to the configuration in which the vehicle 100 is driven on a non-dedicated track TRB based on the detection results of the surrounding sensor 131.

[0060] E. Other Embodiments: (E1) In the unmanned driving system 10 of the first embodiment described above, when the vehicle 100 is traveling on the dedicated track TRA, the vehicle control device 110 autonomously controls the vehicle 100 using the detection results of the surrounding sensor 131, and when the vehicle 100 is traveling on the non-dedicated track TRB, the server 200 remotely controls the vehicle 100 using the detection results of the external sensor 300. In contrast, in the unmanned driving system 10 of the other embodiment, when the vehicle 100 is traveling on the dedicated track TRA, the server 200 remotely controls the vehicle 100 using the detection results of the surrounding sensor 131, and when the vehicle 100 is traveling on the non-dedicated track TRB, the server 200 remotely controls the vehicle 100 using the detection results of the external sensor 300. Alternatively, when the vehicle 100 is traveling on the dedicated track TRA, the server 200 may remotely control the vehicle 100 using the detection results of the surrounding sensor 131, and when the vehicle 100 is traveling on the non-dedicated track TRB, the vehicle control device 110 may autonomously control the vehicle 100 using the detection results of the external sensor 300.

[0061] (E2) In the unmanned driving system 10 of the first and fourth embodiments described above, when the vehicle 100 is located on the dedicated track TRA, the vehicle 100 drives based on the detection results of the surrounding sensor 131, and when the vehicle 100 is located on the non-dedicated track TRB, the vehicle 100 drives based on the detection results of the external sensor 300. In contrast, in the unmanned driving system 10 of the other embodiments, the external sensor 300 is installed in areas including curves and areas including intersections, and when the vehicle 100 is not located in an area including curves or an intersection, the vehicle 100 drives based on the detection results of the surrounding sensor 131, and when the vehicle 100 is located in an area including curves or an intersection, the vehicle 100 may drive based on the detection results of the external sensor 300. In this case, the surrounding sensor 131 mounted on the vehicle 100 can cause the vehicle 100 to drive based on the detection results of the external sensor 300 in curves and intersections where blind spots are likely to occur.

[0062] (E3) In the unmanned driving system 10 in each of the above embodiments, in remote control mode, the server 200 generates a driving control signal that includes parameters related to the acceleration, steering, and deceleration of the vehicle 100, and the vehicle 100 drives according to the driving control signal generated by the server 200. In contrast, in other embodiments, in remote control mode, the server 200 generates a driving control signal that includes parameters related to the steering and deceleration of the vehicle 100, and the vehicle control device 110 generates a driving control signal that includes parameters related to the acceleration of the vehicle 100, and the vehicle 100 drives according to the driving control signal generated by the vehicle control device 110 and the driving control signal generated by the server 200. In this case, since the server 200 and the vehicle control device 110 share the responsibility of generating the driving control signal in remote control mode, the processing load on the server 200 can be reduced. Furthermore, steering and avoidance, which are responsible for avoiding obstacles, are performed based on the detection results of the external sensor 300, which has fewer blind spots than the surrounding sensor 131. Therefore, the possibility of the vehicle 100 coming into contact with an obstacle can be reduced.

[0063] (E4) In the unmanned driving system 10 of the fourth embodiment described above, in the mode switching process, the likelihood of contact is determined according to the position of the vehicle 100, similar to the first embodiment. Alternatively, in the unmanned driving system 10 of the fourth embodiment, the likelihood of contact may be determined according to the number of obstacles detected by the surrounding sensor 131, similar to the second embodiment.

[0064] (E5) In the unmanned driving system 10 of the fourth embodiment described above, the vehicle control device 110 may, in the second autonomous control mode, similar to the server 200 of the third embodiment, use the detection result of the ambient sensor 131 and the detection result of the external sensor 300, whichever has a larger number of obstacles detected around the vehicle 100, to cause the vehicle 100 to avoid obstacles.

[0065] (E6) In the unmanned driving system 10 in each of the above embodiments, when there is a high probability of contact between the vehicle 100 and an obstacle, the vehicle 100 is driven based on the detection result of the external sensor 300, and when there is a low probability of contact between the vehicle 100 and an obstacle, the vehicle 100 is driven based on the detection result of the internal sensor, the ambient sensor 131. In contrast, for example, if the ambient sensor 131 can detect obstacles in all directions, the ambient sensor 131 has fewer blind spots than the external sensor 300. In this case, driving the vehicle 100 based on the detection result of the ambient sensor 131 reduces the probability of contact between the vehicle 100 and an obstacle more than driving the vehicle 100 based on the detection result of the external sensor 300. The unmanned driving system 10 may also drive the vehicle 100 based on the detection result of the ambient sensor 131 when there is a high probability of contact between the vehicle 100 and an obstacle, and drive the vehicle 100 based on the detection result of the external sensor 300 when there is a low probability of contact between the vehicle 100 and an obstacle.

[0066] (E7) In the first to third embodiments described above, the server 200 automatically generates a driving control signal to be transmitted to the vehicle 100 in remote control mode. 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, an external operator may operate a control device that includes a display for displaying captured images output from an external 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.

[0067] (E8) In each of the above embodiments, the vehicle 100 only needs to have a configuration that allows it to move by unmanned operation, and may take 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, an actuator group 120, and an internal sensor group 130. When the vehicle 100 acquires information from the outside for unmanned operation, the vehicle 100 may further be equipped with a communication device 140. 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 a driver's seat and dashboard attached, at least some of the exterior parts such as bumpers and fenders attached, and does not need to have a body shell attached. 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 they 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.

[0068] (E9) The vehicle 100 may be manufactured by combining multiple modules. A module means a unit composed of one or more parts grouped together according to the configuration and function of the vehicle 100. For example, the platform of the 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 the platform, or in place of the platform, parts of the vehicle 100 that are different from the platform may be modularized. 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 the 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 module as a single part by casting. The molding method of integrally molding at least a part of the module as a single part is also called gigacast or megacast. By using Gigacast, parts of a mobile body that were conventionally formed by joining multiple components can be formed as single components. For example, the front module, central module, and rear module mentioned above may be manufactured using Gigacast.

[0069] (E10) Transporting the 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 the vehicle 100 is also called "autonomous production." In autonomous production, for example, at a factory fuel cell (FC) that manufactures the vehicle 100, at least a portion of the transport of the vehicle 100 is realized by autonomous transport.

[0070] (E11) In each of the above embodiments, 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.

[0071] This disclosure is not limited to the embodiments described above, and can be implemented in various configurations without departing from its spirit. For example, the technical features in the embodiments corresponding to the technical features in each form described in the summary of the invention can be replaced or combined as appropriate in order to solve some or all of the above-described problems, or to achieve some or all of the above-described effects. Furthermore, if a technical feature is not described as essential in this specification, it can be deleted as appropriate.

[0072] 10...Unmanned driving system, 100...Vehicle, 110...Vehicle control device, 111...Processor, 112...Memory, 113...Input / output interface, 114...Internal bus, 120...Actuator group, 130...Internal sensor group, 131...Ambient sensor, 132...Vehicle speed sensor, 133...Steering angle sensor, 140...Communication device, 191...Vehicle control unit, 195...First anomaly detection unit, 196...Second anomaly detection unit, 200...Server, 201...Processor, 202...Memory, 203...Input / output interface, 204...Internal bus, 205...Communication device, 291...Remote control unit, 295...Driving permission issuing unit, 300...External sensor

Claims

1. An unmanned driving system comprising: an internal sensor mounted on a vehicle capable of driving by unmanned operation, which detects the driving environment around the vehicle; an external sensor located outside the vehicle, which detects the vehicle and the driving environment; and a first control device that, when it is determined that the possibility of contact between the vehicle and an obstacle in the driving environment is low, drives the vehicle in a first mode using the detection results of the internal sensor, and when it is determined that the possibility of contact is high, drives the vehicle in a second mode using at least the detection results of the external sensor.

2. An unmanned driving system according to claim 1, wherein the first control device determines the likelihood of collision using a map showing the likelihood of collision for each location where the vehicle is traveling.

3. An unmanned driving system according to claim 1, wherein the first control device determines the likelihood of contact using the detection results of the internal sensor.

4. An unmanned driving system according to claim 1, wherein in the second mode, the first control device compares the number of obstacles detected by the external sensor with the number of obstacles detected by the internal sensor, and causes the vehicle to avoid obstacles using the detection result of the sensor that has detected more obstacles than the external sensor or the internal sensor.

5. An unmanned driving system according to claim 1, further comprising a second control device mounted on the vehicle, wherein the first control device is located outside the vehicle, and the second control device, in the first mode, drives the vehicle using parameters determined by the second control device using the detection results of the internal sensors, and in the second mode, drives the vehicle using parameters determined by the first control device using at least the detection results of the external sensors.

6. An unmanned driving system according to claim 1, further comprising a second control device mounted on the vehicle, wherein the second control device determines parameters relating to the acceleration of the vehicle using the detection results of the internal sensors in the second mode, and the first control device is located outside the vehicle and determines parameters relating to the steering and deceleration of the vehicle using the detection results of the external sensors in the second mode.

7. An unmanned driving method, comprising: determining the likelihood of contact between a vehicle capable of driving by unmanned operation and an obstacle in the driving environment surrounding the vehicle; if it is determined that the likelihood of contact is low, driving the vehicle in a first mode using the detection results of an internal sensor mounted on the vehicle that detects the driving environment; and if it is determined that the likelihood of contact is high, driving the vehicle in a second mode using the detection results of an external sensor located outside the vehicle that detects the vehicle and the driving environment.

Images