Control system and control method

Abstract

A control system for controlling a mobile body capable of moving autonomously includes: a first generation unit that generates a first candidate for a driving-permissible range that allows the mobile body to move without contacting other objects, using the position and orientation of the mobile body obtained by a predetermined first acquisition method based on the detection results of a first sensor; a second generation unit that generates a second candidate for a driving-permissible range using the position and orientation of the mobile body obtained by a predetermined second acquisition method based on the detection results of a second sensor; and a determination unit that determines the overlapping range of the first candidate and the second candidate as the driving-permissible range and sends the determined driving-permissible range to a control unit of the mobile body, wherein the first generation unit and the second generation unit satisfy at least one of a first condition that the first sensor and the second sensor are different sensors and a second condition that the first acquisition method and the second acquisition method are different acquisition methods.

Description

Technical Field

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

[0002] Previously, there was a known technique for determining the reliability of sensors by generating vehicle postures separately for each detection result from multiple sensors and comparing the generated results (Japanese Patent Application Publication No. 2018-44880). In this technique, the vehicle posture generated using images captured by a camera is compared with the vehicle posture generated using measurement results from a gyroscope sensor. If there is no significant difference in the generated results, the gyroscope sensor is judged to be functioning normally.

[0003] When a moving object, such as a vehicle, is continuously moving towards other objects, it may come into contact with those objects. Therefore, by pre-determining a permissible driving range for the moving object to move without contact, and stopping the moving object if it deviates from this range, the delay caused by the movement can be minimized, and contact with other objects can be avoided. When using multiple sensors to obtain the position and orientation of the moving object to determine the permissible driving range, a technique that can easily determine a highly reliable driving range is desired. This challenge is not limited to multiple sensors; it is common when determining the permissible driving range by obtaining the position and orientation of the moving object through multiple different methods. Summary of the Invention

[0004] This disclosure can be implemented in the following ways.

[0005] (1) According to one aspect of this disclosure, a control system is provided. The control system for controlling a mobile body capable of moving autonomously includes: a first generation unit that generates a first candidate for a driving-permissible range that allows the mobile body to move in a manner that does not contact other objects, using the position and orientation of the mobile body obtained by a predetermined first acquisition method based on the detection results of a first sensor; a second generation unit that generates a second candidate for the driving-permissible range using the position and orientation of the mobile body obtained by a predetermined second acquisition method based on the detection results of a second sensor; and a determination unit that determines the overlapping range of the first candidate and the second candidate as the driving-permissible range and sends the determined driving-permissible range to a control unit of the mobile body, wherein the first generation unit and the second generation unit satisfy at least one of a first condition and a second condition, the first condition being that the first sensor and the second sensor are different sensors, and the second condition being that the first acquisition method and the second acquisition method are different acquisition methods. According to this method, by determining the overlapping range of the first and second candidates as the permissible driving range, the narrowest range that can be determined using the position and orientation of the moving body obtained by each sensor or acquisition method can be defined as the permissible driving range. Furthermore, the permissible driving range can be determined without comparing the position and orientation of the moving body obtained by each sensor or acquisition method, or by setting a threshold for judging the reliability of each sensor or acquisition method. Therefore, a highly reliable permissible driving range can be easily determined.

[0006] (2) In the above method, the first generation unit and the second generation unit may satisfy both the first condition and the second condition. According to this method, the more different the conditions for obtaining the position and orientation of the moving body are, the more likely the obtained position and orientation of the moving body will differ, and the more likely the difference between the first candidate and the second candidate will become larger. Since the driving allowable range is determined as the overlapping range of the first candidate and the second candidate, the greater the difference between the first candidate and the second candidate, the narrower the range can be determined as the driving allowable range. Therefore, it is possible to easily determine a driving allowable range with higher reliability.

[0007] (3) In the above method, the permissible driving range may also be defined by at least one of the following parameters: the steering angle of the mobile body that is allowed to move, the speed of the mobile body that is allowed to move, and the grace period for the continuation of the movement of the mobile body. The first generation unit and the second generation unit generate candidates for each parameter, and the decision unit determines the overlapping range for each parameter, and determines the determined overlapping range as the permissible driving range. According to this method, the permissible driving range can be defined by at least one of the steering angle of the mobile body, the speed of the mobile body, and the grace period involved in the movement of the mobile body. Furthermore, according to this method, even if the maximum value of the allowed movement in the first candidate and the second candidate is different for each parameter, the narrowest range can be used to determine the permissible driving range for each parameter. Therefore, a more reliable permissible driving range can be determined simply.

[0008] (4) In the above-described manner, the permitted driving range may also be defined by the travel zone of the moving body, indicating either forward or backward movement. According to this method, the permitted driving range corresponding to the travel zone of the moving body can be determined.

[0009] (5) In the above method, it may also include: a detection unit that detects when another moving object, which is the other object, approaches the moving body; and a memory that stores a map representing the movable area of ​​the moving body determined based on the stationary object, which is the other object. The first generation unit and the second generation unit generate the candidate for the turning angle based on the relative position and distance between the moving body and the stationary object calculated using the map, respectively, when the detection unit does not detect the other moving object approaching the moving body. The first generation unit and the second generation unit also generate the candidate for the turning angle based on the relative position and distance between the moving body and the stationary object calculated using the map and the relative position and distance between the moving body and the other moving object calculated using the detection result of the sensor, respectively, when the detection unit detects the other moving object approaching the moving body. According to this method, the relative position and distance between the moving body and the stationary object can be calculated without detecting the stationary object with the sensor each time. Therefore, candidate turning angles for the moving body can be easily generated. Furthermore, when other moving objects approach the moving vehicle, candidate steering angles for the moving vehicle can be generated by considering not only stationary objects but also the presence of other moving objects. This allows for flexible determination of a highly reliable driving range that adapts to changes in the moving vehicle's surrounding environment.

[0010] (6) In the above method, it may also include: a detection unit that detects when another moving object, which is the other object, approaches the moving body; and a memory that stores a map representing preset values ​​of the moving speed in each region of the moving body's movable area determined based on the stationary object, which is the other object; the first generation unit and the second generation unit respectively generate a candidate for the moving speed with the preset value obtained using the map set to the maximum value when the detection unit does not detect that the other moving object is approaching the moving body, and generate a candidate for the grace time corresponding to the preset value; the first generation unit and the second generation unit respectively generate a candidate for the moving speed with a variable value set to the maximum value when the detection unit detects that the other moving object is approaching the moving body, and generate a candidate for the grace time corresponding to the variable value, wherein the variable value is a value corresponding to the distance between the moving body and the other moving object calculated using the detection result of the sensor. According to this method, without needing to detect stationary objects with sensors every time, candidates for the moving object's speed and the allowable time for its movement can be easily generated using a preset value of the moving object's speed corresponding to its position. Furthermore, when other moving objects approach the moving object, the candidates for both the moving object's speed and the allowable time for its movement can be generated considering not only stationary objects but also the presence of other moving objects. This allows for flexible determination of a highly reliable driving allowable range in response to changes in the moving object's surrounding environment. Moreover, when other moving objects approach the moving object, candidates for both the moving object's speed and the allowable time for its movement can be generated using variable values ​​corresponding to the distance between the moving object and other moving objects. This ensures the safety of the moving object when moving near other moving objects and reduces the possibility of the moving object stalling.

[0011] (7) In the above-described manner, the first generation unit and the second generation unit may also generate candidates for at least one of the steering angle, the travel speed, and the grace time based on the size of the moving body. According to this method, more accurate candidates for the steering angle, travel speed, and grace time corresponding to the size of the moving body can be generated. Therefore, more accurate candidates can be used to determine the permissible driving range, thus making it easier to determine a more reliable permissible driving range.

[0012] (8) In the above method, the first generation unit and the second generation unit may also generate the candidates for the travel distinction based on the gear position of the moving body. According to this method, by obtaining the gear position of the moving body, the candidates for the travel distinction of the moving body can be easily generated.

[0013] (9) In the above-described manner, a confirmation unit may also be included, which confirms whether the driving permission range sent by the decision unit matches the driving permission range received by the control unit. According to this method, it can be confirmed that the driving permission range is correctly transmitted and received from the decision unit to the control unit of the moving body. Therefore, the reliability of the driving permission range can be ensured.

[0014] (10) According to other aspects of this disclosure, a control method is provided. The control method for a mobile body capable of moving autonomously includes: a first generation step, generating a first candidate driving permissible range for the mobile body to move in a manner that allows it to move without contact with other objects, using the position and orientation of the mobile body obtained by a predetermined first acquisition method based on the detection results of a first sensor; a second generation step, generating a second candidate driving permissible range for the mobile body to move in a manner that allows it to move without contact with other objects, using the position and orientation of the mobile body obtained by a predetermined second acquisition method based on the detection results of a second sensor; and a determination step, determining the overlapping range of the first candidate and the second candidate as the driving permissible range, and sending the determined driving permissible range to a control unit of the mobile body, wherein at least one of a first condition and a second condition is satisfied in the first generation step and the second generation step, the first condition being that the first sensor and the second sensor are different sensors, and the second condition being that the first acquisition method and the second acquisition method are different acquisition methods. According to this method, by determining the overlapping range of the first and second candidates as the permissible driving range, the narrowest range that can be determined using the position and orientation of the moving body obtained by each sensor or acquisition method can be defined as the permissible driving range. Furthermore, the permissible driving range can be determined without comparing the position and orientation of the moving body obtained by each sensor or acquisition method, or by setting a threshold for judging the reliability of each sensor or acquisition method. Therefore, a highly reliable permissible driving range can be easily determined.

[0015] This disclosure can be implemented in various ways other than the control system and control method described above. For example, it can be implemented as a server, a mobile body that can perform at least a portion of the functions of the control system described above, a method for manufacturing the control system described above, a computer program that implements the control method described above, a non-transitory recording medium on which the computer program is recorded, etc. Attached Figure Description

[0016] Figure 1 This is a conceptual diagram showing the structure of the control system in the first embodiment.

[0017] Figure 2This is a block diagram showing the structure of the control system in the first embodiment.

[0018] Figure 3 This is a conceptual diagram illustrating the vehicle control method in the first embodiment.

[0019] Figure 4 This is a flowchart illustrating the processing sequence of vehicle driving control in the first embodiment.

[0020] Figure 5 This is a flowchart illustrating the processing sequence for determining the driving permission range in the first embodiment.

[0021] Figure 6 This is a diagram showing one example of the candidates for each parameter and the corresponding driving allowance ranges for these candidates.

[0022] Figure 7 This is a first concept diagram representing candidate generation methods for various parameters corresponding to the vehicle's surrounding environment.

[0023] Figure 8 This is a second concept diagram representing candidate generation methods for various parameters corresponding to the vehicle's surrounding environment.

[0024] Figure 9 This is a third concept diagram representing candidate generation methods for various parameters corresponding to the vehicle's surrounding environment.

[0025] Figure 10 This is the fourth concept diagram representing the candidate generation methods for various parameters corresponding to the vehicle's surrounding environment.

[0026] Figure 11 This is the fifth concept diagram representing the candidate generation methods for various parameters corresponding to the vehicle's surrounding environment.

[0027] Figure 12 This is a flowchart illustrating the processing sequence of vehicle stop control in the first embodiment.

[0028] Figure 13 This is an explanatory diagram showing the general structure of the control system in the second embodiment.

[0029] Figure 14 This is a flowchart illustrating the processing sequence of vehicle driving control in the second embodiment. Detailed Implementation

[0030] A. First implementation method: Figure 1 This is a conceptual diagram showing the structure of the control system 50 in the first embodiment. The control system 50 includes one or more vehicles 100 as moving bodies, a server 200, and one or more external sensors 300 as sensors.

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

[0032] Vehicle 100 is configured to operate autonomously. "Autonomous driving" refers to driving without relying on passenger-operated actions. Driving actions refer to actions related to at least one of "driving," "turning," or "stopping" of vehicle 100. Autonomous driving is achieved through automatic or manual remote control of a device located outside vehicle 100, or through autonomous control of vehicle 100. Passengers who do not perform driving operations may also ride in the autonomously operating vehicle 100. Passengers who do not perform driving operations include, for example, people who simply sit in the seats of vehicle 100, or people who perform tasks different from driving operations such as assembly, inspection, or switching operations while riding in vehicle 100. It should be noted that driving based on passenger-operated actions is sometimes referred to as "manned driving."

[0033] In this specification, "remote control" includes "full remote control," which completely determines all actions of vehicle 100 from outside the vehicle 100, and "partial remote control," which determines a portion of the actions of vehicle 100 from outside the vehicle 100. Additionally, "autonomous control" includes: "full autonomous control," where vehicle 100 autonomously controls its own actions without receiving any information from external devices; and "partial autonomous control," where vehicle 100 autonomously controls its own actions using information received from external devices.

[0034] In this embodiment, the control system 50 is used in the factory FC that manufactures the vehicle 100. The reference coordinate system of the factory FC is the global coordinate system GC, and any position within the factory FC can be represented by the X, Y, and Z coordinates in the global coordinate system GC. The factory FC has a first location PL1 and a second location PL2. The first location PL1 and the second location PL2 are connected by a travel path TR that the vehicle 100 can travel on. The vehicle 100 moves from the first location PL1 to the second location PL2 via the travel path TR in an unmanned manner.

[0035] In the factory FC, multiple external sensors 300 are installed along the driving path TR. The positions of each external sensor 300 in the factory FC are pre-adjusted. The external sensors 300 are sensors located outside the vehicle 100. In this embodiment, the external sensors 300 are sensors that capture images of the vehicle 100 from the outside. The external sensors 300 are equipped with a communication device (not shown) and can communicate with other devices such as the server 200 via wired or wireless communication. Specifically, the external sensors 300 are composed of cameras. The camera, which is the external sensor 300, captures images of the vehicle 100 and outputs the captured images as detection results.

[0036] Figure 2 This is a block diagram illustrating the structure of the control system 50 in the first embodiment. The server 200 is a computer comprising a processor 201, a memory 202, an input / output interface 203, and an internal bus 204. The processor 201, memory 202, and input / output interface 203 are connected via the internal bus 204 in a bidirectional communication manner. A communication device 205 for communicating with various external devices is connected to the input / output interface 203. The communication device 205 can communicate wirelessly with the vehicle 100 and can communicate with various external sensors 300 via wired or wireless communication. The processor 201 executes the program PG2 stored in the memory 202, thereby implementing various functions, including those of a remote control unit 210, a first generation unit 211, a second generation unit 212, and a detection unit 213.

[0037] 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 assembly 120 of the vehicle 100, and sends the driving control signal to the vehicle 100, thereby enabling the vehicle 100 to move remotely. The remote control unit 210 can also generate and output control signals, for example, for controlling actuators that operate various auxiliary devices, wipers, power windows, lights, and other equipment on the vehicle 100. That is, the remote control unit 210 can also remotely control the operation of such various equipment and auxiliary devices.

[0038] The first generation unit 211 and the second generation unit 212 respectively perform preprocessing for determining the driving permissible range DP. The driving permissible range DP is the range of driving states of the vehicle 100 that are allowed to travel in a manner that does not contact other objects. The driving permissible range DP is defined by parameters representing the driving state of the vehicle 100. The relative position and distance of the vehicle 100 to other objects vary depending on the position and orientation of the vehicle 100. Therefore, the driving permissible range DP varies depending on the position and orientation of the vehicle 100. Therefore, the first generation unit 211 and the second generation unit 212 respectively generate candidate parameters corresponding to the position and orientation of the vehicle 100. Specifically, the first generation unit 211 uses the position and orientation of the vehicle 100 obtained by a predetermined first acquisition method using the detection results of the first sensor to generate candidate parameters defining the driving permissible range DP. The second generation unit 212 uses the position and orientation of the vehicle 100 obtained by a predetermined second acquisition method using the detection results of the second sensor to generate second candidate parameters defining the driving permissible range DP. In this embodiment, the locations of the sensors used by the first generation unit 211 and the second generation unit 212 to obtain the detection results when acquiring the position and orientation of the vehicle 100 are different. That is, in both the first generation unit 211 and the second generation unit 212, the type of sensor used as the source of the detection results is the same—a camera serving as an external sensor 300. Furthermore, the methods for acquiring the position and orientation of the vehicle 100 are the same in both the first generation unit 211 and the second generation unit 212—using the detection model DM described later to detect the shape of the vehicle 100 from the captured image. The first generation unit 211 and the second generation unit 212 each send candidate parameters generated to the decision unit 131.

[0039] The detection unit 213 detects when another moving object MO, which is capable of moving, approaches the vehicle 100. For example, the detection unit 213 detects other moving objects MO that exist around the vehicle 100 by using the detection results of the external sensor 300, thereby detecting that other moving objects MO have approached the vehicle 100.

[0040] The vehicle 100 includes a vehicle control device 110 for controlling various parts of the vehicle 100, an actuator assembly 120 including one or more actuators driven under the control of the vehicle control device 110, and a communication device 130 for communicating with external devices such as a server 200 via wireless communication. The actuator assembly 120 includes actuators for a drive device for accelerating the vehicle 100, actuators for a steering device for changing the direction of travel of the vehicle 100, and actuators for a braking device for decelerating the vehicle 100.

[0041] The communication device 130 can communicate wirelessly with external devices such as the server 200, and can communicate with the vehicle control device 110 via wired communication. Furthermore, in this embodiment, the communication device 130 also functions as a decision unit 131 and a stop control unit 132.

[0042] The decision unit 131 determines the driving permissible range DP as the overlap range between the candidate parameters received from the first generation unit 211 (i.e., the first candidate) and the candidate parameters received from the second generation unit 212 (i.e., the second candidate). Then, the decision unit 131 sends the determined driving permissible range DP to the stop control unit 132.

[0043] When the driving state of the vehicle 100 deviates from the driving permission range DP received from the decision unit 131, the stop control unit 132 determines that continued driving of the vehicle 100 would cause the vehicle 100 to come into contact with other objects, and stops the vehicle 100. In the case of stopping the vehicle 100, the stop control unit 132 generates a stop signal for stopping the vehicle 100 and sends the stop signal to the vehicle control device 110, thereby stopping the vehicle 100.

[0044] The vehicle control unit 110 comprises a computer equipped with 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 connected via the internal bus 114 in a bidirectional communication manner. An actuator assembly 120 and a communication device 130 are connected to the input / output interface 113. The processor 111 executes the program PG1 stored in the memory 112 to perform various functions, including those of the vehicle control unit 115.

[0045] The vehicle control unit 115 drives the vehicle 100 by controlling the actuator assembly 120. The vehicle control unit 115 controls the actuator assembly 120 using a driving control signal received from the server 200, thereby enabling the vehicle 100 to drive. The driving control signal is a control signal used to drive the vehicle 100. In this embodiment, the driving control signal includes the acceleration and steering angle of the vehicle 100 as parameters. In other embodiments, the driving control signal may replace the acceleration of the vehicle 100 or include the speed of the vehicle 100 as a parameter. Furthermore, when the vehicle control unit 115 receives a stop signal from the stop control unit 132, it uses the stop signal to control the actuator assembly 120, thereby stopping the vehicle 100.

[0046] Figure 3This is a conceptual diagram illustrating the control method of the vehicle 100 in the first embodiment. Driving control of the vehicle 100 using driving control signals and stopping control of the vehicle 100 using the driving permission range DP are performed via different communication paths CP1 and CP2. The first communication path CP1 can transmit and receive more information compared to the second communication path CP2. On the other hand, the second communication path CP2 functions as a communication path with higher reliability by limiting the amount of information that can be transmitted and received compared to the first communication path CP1. It should be noted that... Figure 3 In the diagram, the wireless communication sections in communication paths CP1 and CP2 are represented by dashed lines, while the wired communication sections are represented by solid lines.

[0047] Figure 4 This is a flowchart illustrating the processing sequence of the driving control of the vehicle 100 in the first embodiment. The driving control of the vehicle 100 is achieved via... Figure 3 The first communication path CP1 shown is used. Figure 4 In the processing sequence, the processor 201 of the server 200 functions as a remote control unit 210 by executing program PG2. Additionally, the processor 111 of the vehicle 100 functions as a vehicle control unit 115 by executing program PG1.

[0048] In step S1, the processor 201 of the server 200 uses the detection results output from the external sensor 300 to obtain vehicle position information. This vehicle position information is the basis for generating driving control signals. In this embodiment, the vehicle position information includes the position and orientation of the vehicle 100 in the global coordinate system GC of the factory FC. Specifically, in step S1, the processor 201 uses images captured from a camera, which is the external sensor 300, to obtain the vehicle position information.

[0049] Specifically, in step S1, the processor 201 detects the shape of the vehicle 100 from the captured image, calculates the coordinates of the measurement points of the vehicle 100 in the coordinate system of the captured image, i.e., the local coordinate system, and transforms the calculated coordinates into coordinates in the global coordinate system GC, thereby obtaining the position of the vehicle 100. The shape of the vehicle 100 contained in the captured image can be detected, for example, by inputting the captured image into a detection model DM that utilizes artificial intelligence. The detection model DM is prepared, for example, within the control system 50, outside the control system 50, and pre-stored in the memory 202 of the server 200. As the detection model DM, for example, a learned machine learning model that has been trained in a manner that achieves either semantic segmentation or instance segmentation can be used. As this machine learning model, for example, a convolutional neural network (hereinafter referred to as CNN) learned by supervised learning using a learning dataset can be used. The learning dataset, for example, has multiple training images containing the vehicle 100 and labels indicating which region in the training images represents the vehicle 100 and which region outside the vehicle 100 it represents. During CNN learning, it is preferable to update the CNN parameters through backpropagation (error backpropagation method) to reduce the error between the output of the detection model DM and the label. In addition, the processor 201 can, for example, estimate the orientation of the vehicle 100 by using optical flow method based on the orientation of the movement vector of the vehicle 100 calculated from the position changes of the feature points of the vehicle 100 between frames of the captured image.

[0050] In step S2, the processor 201 of the server 200 determines the next target location that the vehicle 100 should go to. In this embodiment, the target location is represented by the X, Y, and Z coordinates in the global coordinate system GC. The path that the vehicle 100 should travel, i.e., the reference path RR, is pre-stored in the memory 202 of the server 200. The path is represented by nodes indicating the origin, nodes indicating the transit points, nodes indicating the destination, and links connecting the nodes. The processor 201 uses the vehicle location information and the reference path RR to determine the next target location that the vehicle 100 should go to. The processor 201 determines the target location on the reference path RR that is earlier than the current location of the vehicle 100.

[0051] In step S3, the processor 201 of the server 200 generates a driving control signal to cause the vehicle 100 to move toward the determined target position. The processor 201 calculates the vehicle 100's speed based on the vehicle 100's position shift and compares the calculated speed with the target speed. For the processor 201 as a whole, when the speed is lower than the target speed, the acceleration is determined to make the vehicle 100 accelerate; when the speed is higher than the target speed, the acceleration is determined to make the vehicle 100 decelerate. Furthermore, when the vehicle 100 is on the reference path RR, the processor 201 determines the steering angle and acceleration to prevent the vehicle 100 from leaving the reference path RR; when the vehicle 100 is not on the reference path RR—in other words, when the vehicle 100 has left the reference path RR—the processor determines the steering angle and acceleration to ensure the vehicle 100 returns to the reference path RR.

[0052] In step S4, the processor 201 of the server 200 sends the generated driving control signal to the vehicle 100. The processor 201 repeatedly performs tasks such as acquiring vehicle position information, determining target position, generating driving control signals, and sending driving control signals at a predetermined cycle.

[0053] In step S5, the processor 111 of vehicle 100 receives a driving control signal sent from server 200. In step S6, the processor 111 of vehicle 100 uses the received driving control signal to control actuator assembly 120, thereby causing vehicle 100 to travel at the acceleration and steering angle represented by the driving control signal. The processor 111 repeats the receiving of driving control signals and the control of actuator assembly 120 at a predetermined cycle. According to the control system 50 of this embodiment, vehicle 100 can be driven remotely, and vehicle 100 can be moved without the use of handling equipment such as cranes or conveyors.

[0054] Figure 5 This is a flowchart illustrating the processing sequence for determining the driving permissible range (DP) in the first embodiment. The determination of the driving permissible range (DP) is achieved via... Figure 3 The second communication path CP2 is shown. As mentioned above, the driving permissible range DP varies depending on the position and orientation of vehicle 100. The position and orientation of vehicle 100 change from the point in time when autonomous driving begins. Therefore, Figure 5 The process shown is repeated at a predetermined interval, for example, each time the position and orientation of vehicle 100 are obtained, or from the time when autonomous driving begins.

[0055] The permissible driving range DP can be defined, for example, by the steering angle of vehicle 100, the speed of vehicle 100, and the grace time for the vehicle 100 to travel. In this case, the relative position and distance of vehicle 100 to other objects differ on the front and rear sides of vehicle 100. Therefore, the range of permissible steering angle, the range of permissible speed, and the range of permissible continued driving grace time vary depending on whether vehicle 100 is moving forward or backward. Therefore, the following explanation will use the case where the permissible driving range DP is defined by these four parameters: the steering angle of vehicle 100, the speed of vehicle 100, the grace time for the vehicle 100 to travel, and the driving range of vehicle 100.

[0056] In step S101, the first generation unit 211 of server 200 obtains Figure 1 The first position PO1 and first orientation DI1 of the vehicle 100 are shown. The first position PO1 and first orientation DI1 of the vehicle 100 are obtained by inputting a first captured image PI1 output by a first camera CM1 that captures the vehicle 100 from a viewpoint into a detection model DM, and detecting the shape of the vehicle 100. The first position PO1 of the vehicle 100 can be represented, for example, by the X and Y coordinates when looking down at the vehicle 100 from the Z direction perpendicular to the road surface. Similarly, the first orientation DI1 of the vehicle 100 can be represented, for example, by the angle θ when looking down at the vehicle 100 from the Z direction perpendicular to the road surface.

[0057] like Figure 5 As shown, in step S102, the first generation unit 211 uses the first position PO1 and the first orientation DI1 of the vehicle 100 to generate a first candidate for each parameter. That is, the first generation unit 211 uses the first position PO1 and the first orientation DI1 of the vehicle 100 to generate a first candidate for the steering angle of the vehicle 100, a first candidate for the driving speed of the vehicle 100, a first candidate for the grace time involved in the driving of the vehicle 100, and a first candidate for the driving distinction of the vehicle 100.

[0058] In step S103, the first generation unit 211 sends the first candidate of each generated parameter to the vehicle 100.

[0059] In step S104, the second generation unit 212 of the server 200 obtains Figure 1The second position PO2 and second orientation DI2 of the vehicle 100 are shown. The second position PO2 and second orientation DI2 of the vehicle 100 are obtained by inputting a second captured image PI2, output from a second camera CM2 that captures the vehicle 100 from another viewpoint, into a detection model DM, and detecting the shape of the vehicle 100. Similar to the first position PO1 of the vehicle 100, the second position PO2 of the vehicle 100 can be represented, for example, by the X and Y coordinates when viewing the vehicle 100 from a Z-direction perpendicular to the road surface. Similarly, the second orientation DI2 of the vehicle 100 can be represented, for example, by the angle θ when viewing the vehicle 100 from a Z-direction perpendicular to the road surface.

[0060] like Figure 5 As shown, in step S105, the second generation unit 212 uses the second position PO2 and the second orientation DI2 of the vehicle 100 to generate a second candidate for each parameter. That is, the second generation unit 212 uses the second position PO2 and the second orientation DI2 of the vehicle 100 to generate a second candidate for the steering angle of the vehicle 100, a second candidate for the driving speed of the vehicle 100, a second candidate for the grace time involved in the driving of the vehicle 100, and a second candidate for the driving distinction of the vehicle 100.

[0061] In step S106, the second generation unit 212 sends the second candidates of each generated parameter to the decision unit 131 of the communication device 130 mounted on the vehicle 100.

[0062] It should be noted that for each step from S101 to S103 and each step from S104 to S106, one of them can be executed first, or they can be executed simultaneously.

[0063] In step S107, the decision unit 131 determines the overlap range between the first candidate of each parameter received from the first generation unit 211 and the second candidate of each parameter received from the second generation unit 212 for each parameter. Then, the decision unit 131 determines the overlap range determined for each parameter as the driving allowable range DP.

[0064] Figure 6 This is a diagram showing an example of candidates for the parameters defining the permissible driving range (DP) and the corresponding permissible driving range (DP) for these candidates. Figure 6The diagram illustrates the maximum steering angle, maximum speed, maximum grace time, and travel distinction of vehicle 100 in both the first and second candidate vehicles. The maximum steering angle is the maximum value within the range of permissible steering angles for vehicle 100. The maximum speed is the maximum value within the range of permissible speeds for vehicle 100. The maximum grace time is the maximum value within the range of permissible continued travel grace time for vehicle 100. Travel distinction indicates whether vehicle 100 travels forward or backward. It should be noted that the minimum steering angle of vehicle 100 is 0 degrees, the minimum speed is 0 km / h, and the minimum grace time for vehicle 100 is 0 seconds. The minimum steering angle is the minimum value within the range of permissible steering angles for vehicle 100. The minimum speed is the minimum value within the range of permissible speeds for vehicle 100. The minimum grace time is the minimum value within the range of permissible continued travel grace time for vehicle 100.

[0065] The maximum steering angle, for example, when the steering angle for traveling without turning the vehicle 100 degrees to either the left or right is set to 0 degrees as the central value, can be represented by the angle difference relative to 0 degrees as the central value. Figure 6 In this context, the maximum steering angle when vehicle 100 turns left is expressed as a negative value relative to the center value, and the maximum steering angle when vehicle 100 turns right is expressed as a positive value relative to the center value. Figure 6In the example shown, the first candidate maximum steering angle, i.e., the maximum steering angle generated using the first position PO1 and the first orientation DI1 of vehicle 100, is 15 degrees when vehicle 100 turns left and 5 degrees when vehicle 100 turns right. That is, based on the calculation using the first captured image PI1 output from the first camera CM1, when vehicle 100 turns left, the steering angle can be changed within a range of 0 degrees to 15 degrees. When vehicle 100 turns right, the steering angle can be changed within a range of 0 degrees to 5 degrees. On the other hand, the second candidate maximum steering angle, i.e., the maximum steering angle generated using the second position PO2 and the second orientation DI2 of vehicle 100, is 10 degrees when vehicle 100 turns left and 7 degrees when vehicle 100 turns right. In other words, based on the calculation using the second captured image PI2 output from the second camera CM2, when vehicle 100 turns left, the steering angle can be changed within a range of 0 degrees to 10 degrees. When turning right, vehicle 100 is permitted to change its steering angle within a range of 0 degrees to 7 degrees. The overlap between the first and second candidates for these steering angles is 0 degrees to 10 degrees when turning left and 0 degrees to 5 degrees when turning right. Therefore, within the permissible driving range DP, the steering angle for turning left is determined to be 0 degrees to 10 degrees, and the steering angle for turning right is determined to be 0 degrees to 5 degrees.

[0066] exist Figure 6 In the example shown, the first candidate maximum speed, i.e., the maximum speed generated using the first position PO1 and first orientation DI1 of vehicle 100, is 5 km / h. That is, based on the calculation using the first captured image PI1 output from the first camera CM1, the vehicle 100's speed is allowed to change within a range of 0 km / h to 5 km / h. On the other hand, the second candidate maximum speed, i.e., the maximum speed generated using the second position PO2 and second orientation DI2 of vehicle 100, is 7.5 km / h. That is, based on the calculation using the second captured image PI2 output from the second camera CM2, the vehicle 100's speed is allowed to change within a range of 0 km / h to 7.5 km / h. The overlap between these first and second candidates for vehicle 100's speed is 0 km / h to 5 km / h. Therefore, within the driving allowable range DP, the vehicle 100's speed is determined to be 0 km / h to 5 km / h.

[0067] exist Figure 6In the example shown, the maximum grace time for the first candidate, i.e., the maximum grace time generated using the first position PO1 and first orientation DI1 of vehicle 100, is 1.5 seconds. That is, based on the calculation using the first captured image PI1 output from the first camera CM1, it is allowed for vehicle 100 to continue traveling at a speed of 5 km / h from 0 seconds as the current time point to 1.5 seconds later. On the other hand, the maximum grace time for the second candidate, i.e., the maximum grace time generated using the second position PO2 and second orientation DI2 of vehicle 100, is 1 second. That is, based on the calculation using the second captured image PI2 output from the second camera CM2, it is allowed for vehicle 100 to continue traveling at a speed of 7.5 km / h from 0 seconds as the current time point to 1 second later. The overlap range between the first and second candidates for these grace times is more than 0 seconds and less than 1 second. Therefore, within the driving allowable range DP, the grace time involved in the travel of vehicle 100 is determined to be more than 0 seconds and less than 1 second.

[0068] exist Figure 6 In the example shown, the travel zone of vehicle 100 is forward in both the first and second candidates. Therefore, within the permissible driving range DP, the travel zone of vehicle 100 is determined to be forward. Thus, the permissible driving range DP for the case where vehicle 100 is forward is defined by four parameters: the steering angle of vehicle 100, the travel speed of vehicle 100, the grace time involved in the travel of vehicle 100, and the travel zone of vehicle 100.

[0069] Figures 7 to 11 The figures are conceptual diagrams representing candidate generation methods for each parameter corresponding to the surrounding environment of vehicle 100. Specific examples of candidate generation methods for each parameter are shown below.

[0070] The first generation unit 211 and the second generation unit 212 generate, respectively, a range of steering angles that can be changed in a manner that will not come into contact with other objects, based on the relative position and distance of the vehicle 100 and other objects.

[0071] If the detection unit 213 does not detect any other moving object MO approaching the vehicle 100, the first generation unit 211 and the second generation unit 212 respectively use the map MP stored in the memory 202 of the server 200 to generate candidate steering angles for the vehicle 100. The map MP represents... Figure 1The drivable area DA is shown. The drivable area DA is determined based on stationary objects SO that are other objects located around the drivable road TR. Stationary objects SO are, for example, fences, manufacturing equipment, or structures such as walls and pillars dividing the factory FC. The first generation unit 211 and the second generation unit 212 respectively reflect the position and orientation of the vehicle 100 onto the map MP, determine the position and orientation of the vehicle 100 relative to the drivable area DA, and calculate the relative position and distance between the vehicle 100 and the stationary objects SO. Then, the first generation unit 211 and the second generation unit 212 respectively calculate the maximum steering angles CL and CR of the vehicle 100 corresponding to the calculated relative position and distance between the vehicle 100 and the stationary objects SO. Then, the first generation unit 211 and the second generation unit 212 respectively generate a range from the minimum steering angle to the maximum steering angles CL and CR as candidates for the steering angle of the vehicle 100. For example, in Figure 1 In the example shown, vehicle 100 is positioned to the right of the drivable area DA in the direction of travel, parallel to the drivable area DA. In this case, the first generation unit 211 and the second generation unit 212 generate candidate steering angles for vehicle 100 in such a way that the maximum steering angle CR when vehicle 100 turns right is less than the maximum steering angle CL when vehicle 100 turns left.

[0072] When the detection unit 213 detects that another moving object MO is approaching the vehicle 100, the first generation unit 211 and the second generation unit 212 generate candidate steering angles for the vehicle 100 using the map MP and the detection results from the sensors, respectively. Specifically, the first generation unit 211 and the second generation unit 212 use the map MP to calculate the relative position and distance between the vehicle 100 and the stationary object SO, and use the detection results from the sensors to calculate the relative position and distance between the vehicle 100 and other moving objects MO. Then, the first generation unit 211 and the second generation unit 212 calculate the maximum steering angles CL and CR of the vehicle 100 corresponding to the calculated relative position and distance between the vehicle 100 and the stationary object SO, and the maximum steering angles CL and CR of the vehicle 100 corresponding to the calculated relative position and distance between the vehicle 100 and other moving objects MO, respectively. Then, the first generation unit 211 and the second generation unit 212 generate a range from the minimum steering angle to the maximum steering angles CL and CR as candidate steering angles for the vehicle 100. For example, as Figure 7 and Figure 8 As shown, when other moving objects MO approach vehicle 100, the first generation unit 211 and the second generation unit 212 respectively generate candidates with maximum steering angles CL and CR that can avoid contact with other moving objects MO.

[0073] The first generation unit 211 and the second generation unit 212 generate candidates for driving speed based on the distance between the vehicle 100 and other objects, and generate candidates for a grace period for the time during which the vehicle can travel without contacting other objects while continuing to travel at the generated driving speed candidates.

[0074] If the detection unit 213 does not detect any other moving object MO approaching the vehicle 100, the first generation unit 211 and the second generation unit 212 respectively use the map MP stored in the memory 202 of the server 200 to generate candidate speeds for the vehicle 100. The map MP also indicates... Figure 1 The preset values ​​DV for the driving speeds in each region DA1-DA5 within the drivable area DA are shown. The preset values ​​DV for the driving speeds are set, for example, based on the target production time of vehicle 100, the number and arrangement of stationary objects SO, and the frequency of movement of other moving objects MO such as operators. The first generation unit 211 and the second generation unit 212 respectively reflect the position of vehicle 100 onto the map MP, determine the position of vehicle 100 relative to the drivable area DA, and thus obtain a preset value DV corresponding to the position of vehicle 100. Then, the first generation unit 211 and the second generation unit 212 respectively use the obtained preset value DV as the maximum speed CV. Then, the first generation unit 211 and the second generation unit 212 respectively generate a range from the minimum speed to the maximum speed CV as candidates for the driving speed of vehicle 100. That is, the first generation unit 211 and the second generation unit 212 respectively generate candidates for the driving speed of vehicle 100 with the preset value DV obtained using the map MP as the maximum value.

[0075] If the detection unit 213 does not detect any other moving object MO approaching the vehicle 100, the first generation unit 211 and the second generation unit 212 each generate a time corresponding to a preset value DV used as the maximum speed CV among the candidates for the vehicle 100's travel speed, as a candidate for a grace period. Specifically, the first generation unit 211 and the second generation unit 212 each calculate the braking distance of the vehicle 100 when the brakes are engaged while traveling at the travel speed indicated by the preset value DV used as the maximum speed CV among the candidates for the vehicle 100's travel speed. Thus, the first generation unit 211 and the second generation unit 212 each determine a braking start position that allows the vehicle to stop without contacting a stationary object SO. Then, the first generation unit 211 and the second generation unit 212 each calculate the time from reaching the braking start position while traveling at the travel speed indicated by the preset value DV used as the maximum speed CV among the candidates for the vehicle 100's travel speed, as the maximum grace period CT. Then, the first generation unit 211 and the second generation unit 212 respectively generate a range from the minimum grace time to the maximum grace time CT as candidates for the grace time involved in the driving of the vehicle 100.

[0076] When the detection unit 213 detects that another moving object MO is approaching the vehicle 100, the first generation unit 211 and the second generation unit 212 respectively use the detection results of the sensors to generate candidate speeds for the vehicle 100 and candidate grace periods for the vehicle 100's travel. Specifically, the first generation unit 211 and the second generation unit 212 respectively use the detection results of the sensors to calculate the distance between the vehicle 100 and other moving objects MO. Then, the first generation unit 211 and the second generation unit 212 respectively calculate the maximum speed CV of the vehicle 100 corresponding to the calculated distance between the vehicle 100 and other moving objects MO. Then, the first generation unit 211 and the second generation unit 212 respectively generate a range from the minimum speed to the maximum speed CV as candidate speeds for the vehicle 100. That is, the first generation unit 211 and the second generation unit 212 respectively generate candidate speeds for the vehicle 100 with the variable value VV corresponding to the distance between the vehicle 100 and other moving objects MO calculated using the sensor detection results set to the maximum value. For example, as Figure 7 As shown, when other moving objects MO approach vehicle 100 but can avoid contact by turning vehicle 100, the first generation unit 211 and the second generation unit 212 respectively generate candidates that set a variable value VV smaller than the preset value DV of the driving speed as the maximum speed CV. Similarly, as Figure 8 As shown, when multiple other moving objects MO approach the vehicle 100 but the vehicle 100 is able to pass between them, the first generation unit 211 and the second generation unit 212 each generate a candidate variable value VV smaller than the preset speed DV, setting it as the maximum speed CV. Thus, the vehicle 100 decelerates when traveling near other moving objects MO. On the other hand, as... Figure 9 and Figure 10 As shown, when other moving objects MO approach vehicle 100 and cannot avoid contact even if vehicle 100 turns, the first generation unit 211 and the second generation unit 212 generate candidate speeds for vehicle 100 respectively, in a manner that makes the maximum speed CV zero. Additionally, as... Figure 11 As shown, when multiple other moving objects MO approach the vehicle 100 but it is impossible to pass between them, the first generation unit 211 and the second generation unit 212 also generate candidate speeds for the vehicle 100 in a manner that makes the maximum speed CV zero. This stops the vehicle 100 and prevents it from contacting other moving objects MO. Specifically, the first generation unit 211 and the second generation unit 212 set the variable value VV, which is smaller the closer the vehicle 100 is to other moving objects MO in the direction of travel, as the maximum speed CV.

[0077] When the detection unit 213 detects that another moving object MO is approaching the vehicle 100, the first generation unit 211 and the second generation unit 212 each generate a time corresponding to a variable value VV used as the maximum speed CV among the candidates for the vehicle 100's travel speed, as a candidate for a grace period. Specifically, the first generation unit 211 and the second generation unit 212 each calculate the braking distance of the vehicle 100 when the brakes are engaged while traveling at the travel speed indicated by the variable value VV used as the maximum speed CV among the candidates for the vehicle 100's travel speed. Thus, the first generation unit 211 and the second generation unit 212 each determine a braking start position that allows the vehicle to stop without contacting other moving objects MO. Then, the first generation unit 211 and the second generation unit 212 each calculate the time from reaching the braking start position while traveling at the travel speed indicated by the variable value VV used as the maximum speed CV among the candidates for the vehicle 100's travel speed, as the maximum grace period CT. Then, the first generation unit 211 and the second generation unit 212 respectively generate a range from the minimum grace time to the maximum grace time CT as candidates for the grace time involved in the driving of the vehicle 100.

[0078] It should be noted that, as Figures 9 to 11 As shown, when other moving objects MO approach vehicle 100 and prevent vehicle 100 from continuing to move, the first generation unit 211 and the second generation unit 212 can also generate candidates for the grace time in such a way that the maximum grace time CT becomes zero. That is, in these cases, the first generation unit 211 and the second generation unit 212 can generate candidates in such a way that at least one of the maximum speed CV and the maximum grace time CT in the driving allowable range DP becomes zero.

[0079] The first generation unit 211 and the second generation unit 212 generate candidates for the driving distinction PD of the vehicle 100 based on the gear position of the vehicle 100. For example, when the gear position of the vehicle 100 is set to forward, the first generation unit 211 and the second generation unit 212 respectively generate candidates indicating a forward driving situation. When the gear position of the vehicle 100 is set to reverse, the first generation unit 211 and the second generation unit 212 respectively generate candidates indicating a reverse driving situation.

[0080] Figure 12 This is a flowchart illustrating the processing sequence of the vehicle 100's stop control in the first embodiment. The vehicle 100's stop control is achieved via... Figure 3 The second communication path CP2 is shown. As mentioned above, the driving permission range DP is updated each time based on the position and orientation of vehicle 100. Therefore, Figure 12 The process shown is repeated at predetermined intervals, for example, whenever the driving permission range (DP) is updated, or from the point in time when autonomous driving begins.

[0081] In step S201, the decision unit 131 of the communication device 130 mounted on the vehicle 100 sends the determined driving allowable range DP to the stop control unit 132 of the communication device 130 mounted on the vehicle 100.

[0082] In step S202, the stop control unit 132 acquires the driving state of the vehicle 100. For example, the stop control unit 132 acquires the measured value corresponding to the parameter of the specified driving allowable range DP as the driving state of the vehicle 100.

[0083] In step S203, the stop control unit 132 determines whether the driving state of the vehicle 100 has deviated from the driving permission range DP received from the decision unit 131, and determines whether the vehicle 100 will come into contact with other objects while the vehicle 100 continues to drive based on the determination result.

[0084] If the driving state of vehicle 100 does not deviate from the driving permission range DP received from decision unit 131 (step S203: No), stop control unit 132 determines that even if vehicle 100 continues to drive, vehicle 100 will not come into contact with other objects, and ends the process. Thus, the driving of vehicle 100 continues.

[0085] If the driving state of vehicle 100 deviates from the driving permission range DP received from decision unit 131 (step S203: Yes), stop control unit 132 determines that continued driving of vehicle 100 would cause vehicle 100 to come into contact with other objects, and executes step S204. In step S204, stop control unit 132 generates a stop signal. In step S205, stop control unit 132 sends the generated stop signal to vehicle control device 110 mounted on vehicle 100. In step S206, vehicle control unit 115 of vehicle control device 110 uses the received stop signal to control actuator assembly 120, thereby stopping vehicle 100. Thus, the driving of vehicle 100 is interrupted.

[0086] The following is a specific example of the method for determining the departure of the driving permissible range DP when the driving permissible range DP is defined by the four parameters mentioned above.

[0087] For example, even if the driving allowable range DP for reversing is applied to a vehicle 100 moving forward, the steering angle, speed, and grace time specified by the driving allowable range DP are unreliable and meaningless because the relative positions and distances of the vehicle 100 to other objects are different on the front and rear sides of the vehicle 100. Similarly, even if the driving allowable range DP for moving forward is applied to a vehicle 100 moving backward, the steering angle, speed, and grace time specified by the driving allowable range DP are unreliable and meaningless because the relative positions and distances of the vehicle 100 to other objects are different on the front and rear sides of the vehicle 100. Therefore, it is preferable to stop the vehicle 100 when the vehicle 100's travel interval PD determined based on the actual gear position of the vehicle 100 is inconsistent with the vehicle 100's travel interval PD specified by the driving allowable range DP received from the determination unit 131. Therefore, the stop control unit 132 obtains the actual gear position of the vehicle 100 from the vehicle control unit 115. Furthermore, if the driving range PD of the vehicle 100 determined based on the gear position obtained from the vehicle control unit 115 is inconsistent with the driving range PD of the vehicle 100 as defined by the driving allowable range DP, the stop control unit 132 determines that the vehicle has deviated from the driving allowable range DP.

[0088] Furthermore, for example, the longer the time elapsed since the point in time when the candidates for the parameters defining the permissible driving range DP were generated, the higher the likelihood of changes in the position and orientation of the vehicle 100, thus reducing the reliability of the permissible driving range DP. Therefore, it is preferable that the vehicle 100 be stopped even if the decision unit 131 is unable to receive candidates for each parameter from the first generation unit 211 and the second generation unit 212 after the maximum grace time CT defined in the permissible driving range DP has elapsed. Therefore, the stop control unit 132 obtains from the decision unit 131 the elapsed time since the decision unit 131 last received candidates for each parameter from the first generation unit 211 and the second generation unit 212, respectively. Then, if the elapsed time received from the decision unit 131 exceeds the maximum grace time CT defined in the permissible driving range DP, the stop control unit 132 determines that the vehicle has deviated from the permissible driving range DP.

[0089] Originally, the permissible driving range DP is the range of driving states of the vehicle 100 that allows it to travel without contacting other objects. Therefore, even if there are no problems with the vehicle 100's travel distinction PD or the acceptance of candidates for each parameter, it is preferable to stop the vehicle 100 if its steering angle, speed, or elapsed time deviates from the permissible driving range DP. Therefore, the stop control unit 132 obtains the actual steering angle CN and the actual speed of the vehicle 100 from the vehicle control unit 115. Furthermore, if the actual steering angle CN of the vehicle 100 obtained from the vehicle control unit 115 exceeds the maximum steering angle CL or CR specified by the permissible driving range DP, the stop control unit 132 determines that it has deviated from the permissible driving range DP. If the actual speed obtained from the vehicle control unit 115 exceeds the maximum speed CV specified by the permissible driving range DP, the stop control unit 132 determines that it has deviated from the permissible driving range DP. When the elapsed time from the current point in time exceeds the maximum grace time CT specified by the driving permissible range DP, the stop control unit 132 determines that the vehicle has left the driving permissible range DP.

[0090] That is, in the stop control unit 132, preferably, for at least one of the multiple parameters that define the driving allowable range DP, the vehicle 100 is stopped when it leaves the driving allowable range DP.

[0091] It should be noted that when the driving status of the vehicle 100 cannot be obtained from the vehicle control unit 115, the stop control unit 132 cannot grasp the driving status of the vehicle 100, and cannot compare the driving status of the vehicle 100 with the driving allowable range DP. Therefore, in such cases, it is preferable to stop the vehicle 100. Thus, when the driving status of the vehicle 100 cannot be obtained, the stop control unit 132 also generates a stop signal and sends the generated stop signal to the vehicle control device 110, thereby stopping the vehicle 100.

[0092] As explained above, the relative position and distance of vehicle 100 to other objects vary depending on the position and orientation of vehicle 100. Therefore, the permissible driving range DP varies depending on the position and orientation of vehicle 100. Here, the position and orientation of vehicle 100 can be obtained, for example, by detecting vehicle 100 or its surrounding environment using sensors and inputting the detection results into a learned machine learning model. However, the output values ​​of a typical machine learning model have errors, and even if the same detection results are used to obtain the position and orientation of vehicle 100 using the same method, the obtained position and orientation may sometimes differ. Furthermore, differences in the obtained position and orientation can also occur depending on various factors such as the type of sensor and the installation environment. Therefore, when detecting the same vehicle 100 using multiple sensors and obtaining the position and orientation of vehicle 100 for each detection result, it is difficult to distinguish whether the difference in the obtained position and orientation is caused solely by errors in the output values ​​or by factors other than these. In such situations, it is difficult to definitively determine the degree to which a sensor's reliability is negated due to a difference in the obtained position and orientation. Setting the threshold for judging sensor reliability requires considerable labor, thus making the determination of the permissible driving range (DP) cumbersome. Furthermore, when the position and orientation obtained from the detection results of multiple sensors differ by more than the threshold, and it is impossible to determine which sensor is defective, it is sometimes impossible to determine a highly reliable permissible driving range (DP), necessitating a complete vehicle stop.

[0093] Regarding this, according to the first embodiment described above, when the control system 50 determines the driving permissible range DP using the position and orientation of the vehicle 100 obtained by multiple sensors of the same type located at different locations using the same acquisition method, it can do so as follows: The control system 50 can generate a first candidate and a second candidate for parameters defining the driving permissible range DP using the position and orientation of the vehicle 100 obtained by the detection results of each sensor. Furthermore, the control system 50 can determine the driving permissible range DP as the overlapping range of the first candidate and the second candidate. In other words, the control system 50 can determine the driving permissible range DP by executing a first generation step, a second generation step, and a determination step. The first generation step is the step of generating the first candidate for parameters defining the driving permissible range DP. The first generation step is equivalent to... Figure 5 Steps S101 to S103. The second generation process is the process of generating a second candidate parameter for the specified driving permissible range DP. The second generation process is equivalent to... Figure 5Steps S104 to S106. The decision process is the process of determining the overlapping range of the first candidate and the second candidate as the driving permissible range DP, and sending the determined driving permissible range DP to the control unit of the vehicle 100. The decision process is equivalent to Figure 5 Step S107 and Figure 12 Step S201. According to this method, the control system 50 determines the driving allowable range DP by defining the overlap range between the first candidate and the second candidate as the driving allowable range DP, and can determine the narrowest range that can be determined using the position and orientation of the vehicle 100 obtained from each sensor as the driving allowable range DP. That is, the control system 50 can determine the driving allowable range DP with more stringent conditions applied based on the driving state of the vehicle 100. Therefore, the control system 50 can determine a driving allowable range DP with high reliability. Furthermore, in this manner, the control system 50 can determine the driving allowable range DP without comparing the position and orientation of the vehicle 100 obtained from each sensor, and without setting a threshold for judging the reliability of each sensor. Therefore, the control system 50 can simply determine a driving allowable range DP with high reliability.

[0094] Furthermore, in the first embodiment described above, the driving permissible range DP is defined by four parameters: the steering angle of the permitted vehicle 100, the driving speed of the permitted vehicle 100, the grace time for the vehicle 100 to continue driving, and the driving differentiation PD of the vehicle 100. In this manner, the control system 50, by limiting the types and number of parameters defining the driving permissible range DP, can control the driving range DP of vehicles traveling within the permitted range. Figure 3 The amount of information transmitted and received through the second communication path CP2 is minimized. Therefore, the control system 50 can easily confirm that the driving allowable range DP sent by the decision unit 131 matches the driving allowable range DP received by the stop control unit 132.

[0095] It should be noted that the permissible driving range DP can also be specified by a combination of more than one parameter other than those mentioned above. For example, the permissible driving range DP can also be specified by the curvature of the vehicle 100's driving trajectory instead of the vehicle 100's steering angle.

[0096] Furthermore, according to the first embodiment described above, the control system 50 generates candidates for each of the multiple parameters defining the permissible driving range DP, and determines the overlap range of the candidates for each parameter, thereby determining the permissible driving range DP. In this manner, as... Figure 6As shown, even when the maximum permissible driving range differs for each parameter in the first and second candidates, the control system 50 is able to determine the permissible driving range DP using the narrowest possible range for each parameter. Thus, the control system 50 can easily determine the more reliable permissible driving range DP.

[0097] Furthermore, according to the first embodiment described above, the control system 50 is capable of detecting the approach of other moving objects MO to the vehicle 100. In this way, the control system 50 can generate candidates for parameters specifying the driving permissible range DP using different generation methods based on whether or not other moving objects MO are approaching the vehicle 100.

[0098] Furthermore, according to the first embodiment described above, when other moving objects MO are not approaching the vehicle 100, the control system 50 can operate as follows: In this case, the control system 50 can use a map MP representing the drivable area DA of the vehicle 100 determined based on the stationary object SO to calculate the relative position and distance between the vehicle 100 and the stationary object SO. Then, the control system 50 can generate a candidate steering angle for the vehicle 100 based on the relative position and distance between the vehicle 100 and the stationary object SO calculated using the map MP. In this way, the control system 50 can calculate the relative position and distance between the vehicle 100 and the stationary object SO without detecting the stationary object SO with sensors every time. As a result, the control system 50 can easily generate a candidate steering angle for the vehicle 100.

[0099] Furthermore, according to the first embodiment described above, when another moving object MO approaches the vehicle 100, the control system 50 can be configured as follows: In this case, the control system 50 can use the map MP to calculate the relative position and distance between the vehicle 100 and the stationary object SO, as described above. Further, the control system 50 can use the sensor detection results to calculate the relative position and distance between the vehicle 100 and other moving objects MO by detecting other moving objects MO using sensors. Then, the control system 50 can generate candidate steering angles for the vehicle 100 based on the relative position and distance between the vehicle 100 and the stationary object SO calculated using the map MP, and the relative position and distance between the vehicle 100 and other moving objects MO calculated using the sensor detection results. In this way, the control system 50 can calculate the relative position and distance between the vehicle 100 and the stationary object SO without detecting the stationary object SO with sensors every time. Therefore, the control system 50 can easily generate candidate steering angles for the vehicle 100. In addition, the control system 50 can generate candidate steering angles for the vehicle 100 by considering not only the presence of stationary objects SO but also the presence of other moving objects MO, thus enabling it to flexibly determine a reliable driving allowable range DP that corresponds to changes in the surrounding environment of the vehicle 100.

[0100] It should be noted that the method for generating candidate steering angles for vehicle 100 is not limited to the above. Control system 50 may also generate candidate steering angles for vehicle 100 based on the relative position and distance between vehicle 100 and other objects, without detecting the approach of other moving objects MO. That is, in control system 50, the detection unit 213 is not a necessary structure, and using map MP is not necessary when generating candidate steering angles for vehicle 100.

[0101] Furthermore, according to the first embodiment described above, when other moving objects MO do not approach the vehicle 100, the control system 50 can operate as follows: In this case, the control system 50 can use a map MP representing preset values ​​DV of the driving speed in each region DA1-DA5 of the drivable area DA of the vehicle 100 to obtain a preset value DV of the driving speed corresponding to the position of the vehicle 100. Then, the control system 50 can generate a candidate driving speed of the vehicle 100 with the preset value DV obtained using the map MP as its maximum value. Furthermore, the control system 50 can generate a candidate time corresponding to the preset value DV obtained using the map MP as a grace period for the driving of the vehicle 100. In this way, the control system 50 can easily generate candidates of the driving speed of the vehicle 100 and the grace period for the driving of the vehicle 100 using the preset value DV of the driving speed corresponding to the position of the vehicle 100 without having to detect a stationary object SO with a sensor every time.

[0102] Furthermore, according to the first embodiment described above, when another moving object MO approaches the vehicle 100, the control system 50 can be configured as follows: In this case, the control system 50 can use the detection results of the sensors to calculate the distance between the vehicle 100 and the other moving object MO. Furthermore, the control system 50 can generate a candidate speed for the vehicle 100 with a variable value VV corresponding to the distance between the vehicle 100 and the other moving object MO calculated using the sensor detection results as its maximum value. Moreover, the control system 50 can generate a candidate time corresponding to the variable value VV as a grace period for the vehicle 100's travel, where the variable value VV corresponds to the distance between the vehicle 100 and the other moving object MO calculated using the sensor detection results. In this way, the control system 50 can calculate the distance between the vehicle 100 and the stationary object SO without detecting the stationary object SO with the sensors every time. Therefore, the control system 50 can easily generate candidates for the vehicle 100's speed and candidates for the grace period for the vehicle 100's travel. Furthermore, the control system 50 is able to generate candidate speeds for the vehicle 100 and allowable timeframes for the vehicle 100's travel, taking into account not only stationary objects SO but also other moving objects MO. Therefore, the control system 50 can flexibly determine a highly reliable driving allowable range DP corresponding to changes in the vehicle 100's surrounding environment.

[0103] Furthermore, according to the first embodiment described above, when other moving objects MO approach vehicle 100, the control system 50 can adjust the vehicle 100's speed and the grace period for its travel based on the distance between vehicle 100 and other moving objects MO. Specifically, when other moving objects MO approach vehicle 100 and contact cannot be avoided even if vehicle 100 turns, the control system 50 sets at least one of the maximum speed CV and the maximum grace period CT to zero. This allows the control system 50 to stop vehicle 100. When other moving objects MO approach vehicle 100 but contact can be avoided by turning vehicle 100, or when multiple other moving objects MO approach vehicle 100 but can pass between them, the control system 50 sets the maximum speed CV to less than a preset value DV. This allows the control system 50 to decelerate vehicle 100 while it is traveling near other moving objects MO to ensure safety, and to allow vehicle 100 to continue traveling. In this way, it is possible to avoid stopping vehicle 100 regardless of its distance from other moving objects MO. That is, it can prevent the vehicle 100 from making unnecessary stops whenever other moving objects MO intrude into the drivable area DA. Therefore, the control system 50 can ensure the safety of the vehicle 100 when driving near other moving objects MO and reduce the possibility of the vehicle 100 stopping. It should be noted that in this embodiment, the control system 50 is used in the factory FC. Therefore, by making the driving speed of the vehicle 100 and the grace time involved in the driving of the vehicle 100 variable, the control system 50 can ensure the safety of the vehicle 100 when driving near other moving objects MO such as workers and reduce the possibility of the vehicle 100 stopping during production.

[0104] It should be noted that the method for generating candidate speeds for vehicle 100 is not limited to the methods described above. Similarly, the method for generating the grace time involved in the movement of vehicle 100 is not limited to the methods described above. The control system 50 may also generate candidate speeds for vehicle 100 and candidate grace times for vehicle 100 based on the distance between vehicle 100 and other objects, without detecting the approach of other moving objects MO. That is, in the control system 50, the detection unit 213 is not a necessary structure, and using the map MP is not necessary when generating candidate speeds for vehicle 100 and candidate grace times for vehicle 100.

[0105] Furthermore, according to the first embodiment described above, the control system 50 can generate candidates for the driving differentiation PD of the vehicle 100 based on the gear position of the vehicle 100. In this way, the control system 50 can easily generate candidates for the driving differentiation PD of the vehicle 100 by obtaining the gear position of the vehicle 100.

[0106] It should be noted that the method for generating candidates for the travel differentiation PD of vehicle 100 is not limited to the method described above. For example, the control system 50 may also generate candidates for the travel differentiation PD of vehicle 100 based on the rotation direction of the driving motor mounted on vehicle 100 and the rotation speed of the wheels.

[0107] Furthermore, according to the first embodiment described above, the driving control of the vehicle 100 using a driving control signal and the stopping control of the vehicle 100 using a driving allowable range DP are performed via different communication paths CP1 and CP2. In this way, by redundanting the normal driving control and the stopping control based on the driving allowable range DP, a stop signal can be sent to the vehicle 100 via either communication path CP1 or CP2 when it is preferable to stop the vehicle 100. Therefore, when it is preferable to stop the vehicle 100, the control system 50 can stop the vehicle 100 more reliably.

[0108] Furthermore, according to the first embodiment described above, the first communication path CP1 for driving control of the vehicle 100 can transmit and receive more information compared to the second communication path CP2 for stopping control of the vehicle 100. In this way, the control system 50 can flexibly control the driving of the vehicle 100 based on more information.

[0109] Furthermore, according to the first embodiment described above, the second communication path CP2 for stopping control of the vehicle 100 achieves higher reliability by limiting the amount of information that can be transmitted and received compared to the first communication path CP1 for driving control of the vehicle 100. In this way, when it is preferable to stop the vehicle 100, the control system 50 can use the driving allowable range DP to stop the vehicle 100 more reliably.

[0110] Furthermore, in the first embodiment described above, the decision unit 131 and the stop control unit 132 are implemented as a function of the communication device 130 mounted on the vehicle 100. The communication device 130 can also be detachably mounted on the vehicle 100. In this manner, by mounting the communication device 130 on the vehicle 100 during the autonomous driving control period, the driving state of the vehicle 100 performing autonomous driving control can be controlled.

[0111] B. Second implementation method: Figure 13This is an explanatory diagram showing the schematic structure of the control system 50v in the second embodiment. In this embodiment, the control system 50v differs from the first embodiment in that it does not include the server 200. Furthermore, the vehicle 100v in this embodiment is capable of autonomous operation through the autonomous control of the vehicle 100v. Other structural details are the same as in the first embodiment unless otherwise specified.

[0112] In this embodiment, the processor 111v of the vehicle control device 110v executes the program PG1 stored in the memory 112v, functioning as the vehicle control unit 115v, the first generation unit 116, the second generation unit 117, the decision unit 118, and the stop control unit 119. The first generation unit 116, similar to the first generation unit 211 in the first embodiment, generates a first candidate parameter defining the driving permissible range DP. The second generation unit 117, similar to the second generation unit 212 in the first embodiment, generates a second candidate parameter defining the driving permissible range DP. The decision unit 118, similar to the decision unit 131 in the first embodiment, determines the overlapping range of the first and second candidates as the driving permissible range DP, and sends the determined driving permissible range DP to the stop control unit 119. The stop control unit 119, similar to the stop control unit 132 in the first embodiment, generates a stop signal when the driving state of the vehicle 100 deviates from the driving permissible range DP received from the decision unit 131, and sends the generated stop signal to the vehicle control unit 115v, thereby stopping the vehicle 100. The vehicle control unit 115v acquires the output results from the sensors, generates a driving control signal using the output results, and outputs the generated driving control signal to activate the actuator assembly 120, thereby enabling autonomous control to drive the vehicle 100v. In this embodiment, in addition to the program PG1, the memory 112v also stores the detection model DM and the reference path RR in advance. Furthermore, when the vehicle control unit 115v receives a stop signal from the stop control unit 119, it uses the stop signal to control the actuator assembly 120, thereby stopping the vehicle 100v.

[0113] Figure 14 This is a flowchart illustrating the processing sequence of the vehicle 100V's driving control in the second embodiment. Figure 14 In the processing sequence, the processor 111v of the vehicle 100v functions as the vehicle control unit 115v by executing program PG1.

[0114] In step S901, the processor 111v of the vehicle control device 110v obtains vehicle position information using the detection results output from the camera, which is an external sensor 300. In step S902, the processor 111v determines the target location that the vehicle 100v should go to next. In step S903, the processor 111v generates a driving control signal to make the vehicle 100v move toward the determined target location. In step S904, the processor 111v uses the generated driving control signal to control the actuator assembly 120, thereby making the vehicle 100v move according to the parameters represented by the driving control signal. The processor 111v repeats the acquisition of vehicle position information, determination of target location, generation of driving control signal, and control of actuators at a predetermined cycle. According to the control system 50v in this embodiment, the vehicle 100v can be driven autonomously even without remote control of the vehicle 100v through the server 200.

[0115] C. Other implementation methods: C-1. Other implementation methods 1: In the above embodiments, at least a portion of the functions of server 200 can be implemented as a function of communication device 130 mounted on vehicle 100, 100V, as a function of vehicle control device 110, 110V, or as a sensor. Similarly, at least a portion of the functions of communication device 130 mounted on vehicle 100, 100V can be implemented as a function of server 200, as a function of vehicle control device 110, 110V, or as a sensor. Likewise, at least a portion of the functions of vehicle control device 110, 110V can be implemented as a function of server 200, as a function of communication device 130 mounted on vehicle 100, 100V, or as a sensor. According to this approach, the structure of control system 50, 50V can be appropriately modified.

[0116] C-2. Other implementation methods 2: The relative positions and distances of vehicles 100 and 100v to other objects vary depending on the overall length and width of vehicles 100 and 100v. Consequently, the maximum steering angle CL, CR, maximum speed CV, and maximum grace time CT sometimes differ depending on the overall length and width of vehicles 100 and 100v. Therefore, the first generation unit 211 and the second generation unit 212 can also generate candidates for at least one of the following based on the dimensions of vehicles 100 and 100v: the steering angle, the speed, and the grace time involved in the travel of vehicles 100 and 100v. In this way, control systems 50 and 50v can generate more accurate candidates for steering angle, speed, and grace time. Therefore, control systems 50 and 50v can use more accurate candidates to determine the driving allowable range DP, thus easily determining a more reliable driving allowable range DP.

[0117] C-3. Other implementation methods 3: In the above embodiments, the control systems 50 and 50v may also include a confirmation unit. The confirmation unit confirms that the driving allowable range DP sent by the decision unit 131 matches the driving allowable range DP received by the control units 119 and 132 of the vehicles 100 and 100v. In this way, the control systems 50 and 50v can confirm that the driving allowable range DP from the decision units 118 and 131 to the control units 119 and 132 of the vehicles 100 and 100v is correctly transmitted and received. Therefore, the control systems 50 and 50v can ensure the reliability of the driving allowable range DP.

[0118] C-4. Other implementation methods 4: In the above embodiments, the first generation units 116, 211 and the second generation units 117, 212 satisfy the first condition that the first sensor and the second sensor are different sensors. Furthermore, in the above embodiments, the first generation units 116, 211 and the second generation units 117, 212 satisfy the first condition because the sensor installation locations are different. In contrast, in other embodiments, the first generation units 116, 211 and the second generation units 117, 212 only need to satisfy at least one of the first condition and the second condition that the first acquisition method and the second acquisition method are different acquisition methods. For example, it could also be in the manner described in (1) to (3) below.

[0119] (1) The types of sensors used by the first generation units 116, 211 and the second generation units 117, 212 to obtain the detection results of the vehicles 100, 100v when acquiring their positions and orientations can also be different. That is, the first generation units 116, 211 and the second generation units 117, 212 can also satisfy the first condition by using different types of sensors. In this way, the control systems 50, 50v can use the positions and orientations of the vehicles 100, 100v obtained by multiple sensors of different types to determine the driving allowable range DP. In addition, even in this way, the control systems 50, 50v, like in the above embodiments, can easily determine the driving allowable range DP with high reliability by determining the overlapping range of the first candidate and the second candidate as the driving allowable range DP.

[0120] (2) The methods for obtaining the position and orientation of vehicles 100, 100v in the first generation units 116, 211 and the second generation units 117, 212 can also be different. That is, the first generation units 116, 211 and the second generation units 117, 212 can also satisfy the second condition. In this way, the control systems 50, 50v can use the position and orientation of vehicles 100, 100v obtained by different methods to determine the driving allowable range DP. In addition, even in this way, the control systems 50, 50v, like in the above embodiments, can easily determine the driving allowable range DP with high reliability by determining the overlapping range of the first candidate and the second candidate as the driving allowable range DP.

[0121] (3) The sensors used to obtain the detection results when obtaining the position and orientation of vehicles 100 and 100v, and the methods for obtaining the position and orientation of vehicles 100 and 100v, may differ between the first generation units 116 and 211 and the second generation units 117 and 212. That is, the first generation units 116 and 211 and the second generation units 117 and 212 may satisfy both the first condition and the second condition. In this manner, the more different the conditions for obtaining the position and orientation of vehicles 100 and 100v, the more likely the position and orientation of vehicles 100 and 100v will differ, and the greater the difference between the first candidate and the second candidate will be. Since the driving allowable range DP is determined as the overlapping range of the first candidate and the second candidate, the greater the difference between the first candidate and the second candidate, the narrower the range can be determined as the driving allowable range DP. Therefore, the control system 50 and 50v can easily determine the driving allowable range DP with higher reliability.

[0122] C-5. Other implementation methods 5: Control systems 50 and 50v can also generate three or more candidates for the same parameter, and the overlapping range of the three or more candidates is determined as the driving allowable range DP. In this case, the position and orientation of the vehicle 100 and 100v used in generating the parameter candidates are obtained, for example, using the detection results of three or more sensors of the same or different types through the same or different acquisition methods. Alternatively, the position and orientation of the vehicle 100 and 100v used in generating the parameter candidates can be obtained using the detection result of a single sensor through three or more different acquisition methods. According to this approach, the more candidates there are for the parameter, the easier it is to narrow the overlapping range of each candidate. Therefore, control systems 50 and 50v can easily determine the driving allowable range DP with higher reliability.

[0123] C-6. Other implementation methods 6: In the above embodiments, the positions and orientations of the generated candidate vehicles 100 and 100v for parameters can also be obtained using methods different from those used to detect the shape of vehicles 100 and 100v from captured images using a detection model DM. The positions and orientations of vehicles 100 and 100v can also be obtained, for example, using bounding boxes generated by estimating regions containing vehicles 100 and 100v from captured images. A bounding box is a bounding rectangle enclosing a region within each region constituting the captured image that is estimated to represent a region of vehicle 100 or 100v. Bounding boxes can be obtained, for example, by inputting the captured image into a rectangle generation model applied with artificial intelligence. The rectangle generation model is prepared, for example, within or outside the control system 50, and pre-stored in memories 112v and 202. Examples of rectangle generation models include, for instance, well-learned machine learning models that have been trained to perform pattern matching. In this approach, the control systems 50 and 50v also use the position and orientation of the vehicle 100 and 100v to generate more than two candidate parameters. The overlapping range of the two or more candidates is determined as the driving allowable range DP, thereby enabling the determination of a highly reliable driving allowable range DP.

[0124] C-7. Other implementation methods 7: In the above embodiments, the position and orientation of vehicles 100 and 100v used in generating candidate parameters can be obtained by replacing external sensor 300 or by using detection results from internal sensors in addition to external sensor 300. When using detection results from internal sensors, the position and orientation of vehicles 100 and 100v can be obtained, for example, based on the relative position and angle of vehicles 100 and 100v relative to dividing lines such as white lines marked on the driving road TR. In this manner, control systems 50 and 50v also use the position and orientation of vehicles 100 and 100v to generate two or more candidate parameters, and determine the overlapping range of the two or more candidates as the driving allowable range DP, thereby enabling the simple determination of a highly reliable driving allowable range DP.

[0125] C-8. Other implementation methods 8: In the above embodiments, the external sensor 300 is not limited to a camera; for example, it can be a ranging device. The ranging device could be, for example, LiDAR (Light Detection and Ranging). In this case, the detection result output by the external sensor 300 can also be three-dimensional point group data representing vehicles 100 and 100v. In this case, the server 200 and vehicles 100 and 100v can also obtain vehicle position information by matching the three-dimensional point group data as the detection result with a template of pre-prepared reference point group data.

[0126] C-9. Other implementation methods 9: In the first embodiment, the server 200 performs the process from obtaining vehicle location information to generating a driving control signal. In contrast, the vehicle 100 may also perform at least a portion of the process from obtaining vehicle location information to generating a driving control signal. For example, it may be in the manner described in (1) to (3) below.

[0127] (1) Server 200 can also obtain vehicle location information, determine the target location that vehicle 100 should go to next, and generate a path from the current location of vehicle 100 to the target location as indicated by the obtained vehicle location information. Server 200 can generate a path up to the target location between the current location and the destination, or a path up to the destination. Server 200 can also send the generated path to vehicle 100. Vehicle 100 can also generate a driving control signal to make vehicle 100 travel on the path received from server 200, and use the generated driving control signal to control actuator group 120.

[0128] (2) The server 200 can also obtain vehicle location information and send the obtained vehicle location information to the vehicle 100. The vehicle 100 can also decide the target location that the vehicle 100 should go to next, generate a path from the current location of the vehicle 100 represented by the received vehicle location information to the target location, generate a driving control signal to make the vehicle 100 drive on the generated path, and use the generated driving control signal to control the actuator group 120.

[0129] (3) In the methods described in (1) and (2) above, the vehicle 100 may be equipped with internal sensors, and at least one of the path generation and driving control signal generation may use the detection results output from the internal sensors. The internal sensors are sensors mounted on the vehicle 100. For example, the internal sensors may include sensors that detect the motion state of the vehicle 100, sensors that detect the motion state of various parts of the vehicle 100, and sensors that detect the surrounding environment of the vehicle 100. Specifically, the internal sensors may include, for example, cameras, LiDAR, millimeter-wave radar, ultrasonic sensors, GPS sensors, accelerometers, gyroscopes, etc. For example, in the method described in (1) above, the server 200 may also obtain the detection results from the internal sensors and reflect these results in the path when generating the path. In the method described in (1) above, the vehicle 100 may also obtain the detection results from the internal sensors and reflect these results in the driving control signal when generating the driving control signal. In the method described in (2) above, the vehicle 100 may also obtain the detection results from the internal sensors and reflect these results in the path when generating the path. In the manner described in (2) above, the vehicle 100 can also obtain 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.

[0130] C-10. Other implementation methods 10: In the second embodiment described above, the vehicle 100v may also be equipped with internal sensors, and the detection results output from the internal sensors may be used in at least one of the path generation and driving control signal generation. For example, the vehicle 100v may also acquire the detection results of the internal sensors and reflect these results in the path generation process. Similarly, the vehicle 100v may acquire the detection results of the internal sensors and reflect these results in the driving control signal when generating the driving control signal.

[0131] C-11. Other implementation methods 11: In the second embodiment described above, vehicle 100v uses the detection results of external sensor 300 to obtain vehicle position information. Alternatively, vehicle 100v may be equipped with internal sensors. Vehicle 100v uses the detection results of these internal sensors to obtain vehicle position information, determines the target location to which vehicle 100v should proceed, generates a path from its current location to the target location as indicated by the obtained vehicle position information, generates a driving control signal for traveling along the generated path, and uses the generated driving control signal to control actuator assembly 120. In this case, vehicle 100v can travel without using the detection results of external sensor 300. It should be noted that vehicle 100v can also obtain target arrival time and congestion information from outside vehicle 100v, so that at least one of the path and driving control signal reflects the target arrival time and congestion information. Furthermore, the functional structure of control system 50v can be entirely implemented within vehicle 100v. That is, the processing implemented by control system 50v in this disclosure can also be implemented solely by vehicle 100v.

[0132] C-12. Other implementation methods 12: In the first embodiment described above, the server 200 automatically generates a driving control signal to be sent to the vehicle 100. Alternatively, the server 200 may also generate a driving control signal to be sent to the vehicle 100 according to the operation of an external operator located outside the vehicle 100. For example, the external operator may operate a control device equipped with a display showing images captured from external sensors 300, a steering wheel for remotely operating the vehicle 100, an accelerator pedal, a brake pedal, and a communication device for communicating with the server 200 via wired or wireless communication, and the server 200 generates a driving control signal corresponding to the operation applied to the control device.

[0133] C-13. Other Embodiment 13: In the above embodiments, vehicles 100 and 100v only need to have a structure capable of moving autonomously. For example, they can also be platforms with the structures described below. Specifically, for vehicles 100 and 100v to perform the three functions of "driving," "turning," and "stopping" autonomously, they only need to have a vehicle control device 110 and an actuator assembly 120. When vehicles 100 and 100v need to obtain information from the outside for autonomous driving, they also need to have a communication device 130. That is, vehicles 100 and 100v that can move autonomously may not have at least some of the interior components such as a driver's seat and dashboard, nor at least some of the exterior components such as bumpers and mudguards, nor a body shell. In this scenario, before vehicles 100 and 100v leave the factory (FC), the remaining components, such as the body shell, can be installed on vehicles 100 and 100v. Alternatively, the remaining components, such as the body shell, can be installed on vehicles 100 and 100v after they leave the factory (FC), without the body shell or other remaining components being installed. Each component can be installed from any direction on vehicles 100 and 100v, such as the top, bottom, front, rear, right, or left side. They can be installed from the same direction or from different directions. It should be noted that the platform's position can be determined in the same way as in the first embodiment for vehicles 100 and 100v.

[0134] C-14. Other implementation methods 14: Vehicles 100 and 100v can also be manufactured by combining multiple modules. A module refers to a unit composed of one or more components based on the structure and function of vehicles 100 and 100v. For example, the platform of vehicles 100 and 100v can be manufactured by combining a front module constituting the front of the platform, a central module constituting the central part of the platform, and a rear module constituting the rear of the platform. Furthermore, the number of modules constituting the platform is not limited to three; it can be two or fewer, or four or more. In addition to or replacing the platform, parts of vehicles 100 and 100v that differ from the platform can be modularized. Furthermore, various modules can include any exterior components such as bumpers and grilles, and any interior components such as seats and consoles. Moreover, not limited to vehicles 100 and 100v, any type of moving body can be manufactured by combining multiple modules. Such modules can be manufactured, for example, by joining multiple components using welding, fasteners, etc., or by integrally molding at least a portion of the module into a single component using casting. A molding method that integrally forms at least a portion of a module as a single component is also known as giga-casting or mega-casting. By using giga-casting, it is possible to form the various parts of a moving body, which were previously formed by joining multiple components, into a single component. For example, the aforementioned front module, central module, and rear module can also be manufactured using giga-casting.

[0135] C-15. Other Embodiment 15: The use of autonomous vehicles 100 and 100v to transport vehicles 100 and 100v is also referred to as "self-driving transport." Furthermore, the structure used to implement self-driving transport is called a "vehicle remote-controlled autonomous driving transport system." Additionally, the production method that utilizes self-driving transport to produce vehicles 100 and 100v is called "self-driving production." In self-driving production, for example, in factory FC where vehicles 100 and 100v are manufactured, at least a portion of the transport of vehicles 100 and 100v is achieved through self-driving transport.

[0136] C-16. Other Embodiment 16: In the above embodiments, some or all of the functions and processes implemented in software can also be implemented in hardware. Conversely, some or all of the functions and processes implemented in hardware can also be implemented in software. As the hardware for implementing the various functions in the above embodiments, various circuits such as integrated circuits and discrete circuits can also be used.

[0137] This disclosure is not limited to the embodiments described above, and can be implemented in various structures without departing from its spirit. For example, technical features of embodiments corresponding to the technical features in the various methods described in the Summary of the Invention section can be appropriately replaced or combined to solve some or all of the above-mentioned problems, or to achieve some or all of the above-mentioned effects. In addition, if a technical feature is not described as a necessary feature in this specification, it can be appropriately deleted.

Claims

1. A control system for controlling a mobile body capable of moving autonomously, wherein, The control system includes: The first generation unit uses the position and orientation of the moving body obtained by a predetermined first acquisition method using the detection result of the first sensor to generate a first candidate for a driving permissible range in which the moving body can move in a manner that does not contact other objects. The second generation unit uses the position and orientation of the moving body, obtained by a predetermined second acquisition method using the detection results of the second sensor, to generate a second candidate for the driving permissible range; and The decision unit determines the overlapping range between the first candidate and the second candidate as the driving permission range, and sends the determined driving permission range to the control unit of the mobile body. The first generating unit and the second generating unit satisfy at least one of the first condition and the second condition, wherein the first condition is that the first sensor and the second sensor are different sensors, and the second condition is that the first acquisition method and the second acquisition method are different acquisition methods.

2. The control system according to claim 1, wherein, The first generation unit and the second generation unit satisfy both the first condition and the second condition.

3. The control system according to claim 1, wherein, The permissible driving range is defined by at least one of the following parameters: the steering angle of the moving body that is allowed to move, the speed of the moving body that is allowed to move, and the grace period for the continuation of the movement of the moving body. The first generation unit and the second generation unit respectively generate candidates for each of the parameters. The decision unit determines the overlap range for each parameter and determines the determined overlap range as the driving allowable range.

4. The control system according to claim 3, wherein, The permitted driving range is further defined by the distinction between forward and backward movement of the moving body.

5. The control system according to claim 3 or 4, wherein, The control system also includes: The detection unit detects when another moving object, which is one of the other objects, approaches the moving body; and The memory stores a map representing the movable area of ​​the moving body as determined by a stationary object relative to the other objects. When the detection unit does not detect any other moving object approaching the moving body, the first generation unit and the second generation unit respectively generate the candidate turning angle based on the relative position and distance between the moving body and the stationary object calculated using the map. When the detection unit detects that another moving object is approaching the moving body, the first generation unit and the second generation unit respectively generate the candidate for the turning angle based on the relative position and distance between the moving body and the stationary object calculated using the map and the relative position and distance between the moving body and the other moving object calculated using the detection results of the sensor.

6. The control system according to claim 3 or 4, wherein, The control system also includes: The detection unit detects when another moving object, which is one of the other objects, approaches the moving body; and The memory stores a map representing preset values ​​for the movement speed in each region of the movable body's movable area, determined based on the stationary object being the other object. When the detection unit does not detect any other moving object approaching the moving body, the first generation unit and the second generation unit respectively generate a candidate for the moving speed with the preset value obtained using the map set to the maximum value, and generate a candidate for the grace time corresponding to the preset value. When the detection unit detects that another moving object is approaching the moving body, the first generation unit and the second generation unit respectively generate a candidate for the moving speed with a variable value set to the maximum value, and generate a candidate for the grace time corresponding to the variable value, wherein the variable value is a value corresponding to the distance between the moving body and the other moving object calculated using the detection result of the sensor.

7. The control system according to claim 3 or 4, wherein, The first generation unit and the second generation unit respectively generate candidates for at least one of the steering angle, the moving speed and the grace time based on the size of the moving body.

8. The control system according to claim 4, wherein, The first generation unit and the second generation unit respectively generate the candidates for the travel distinction based on the gear position of the moving body.

9. The control system according to claim 3 or 4, wherein, The control system further includes a confirmation unit that confirms whether the driving permission range sent by the decision unit is consistent with the driving permission range received by the control unit.

10. A control method for a mobile body capable of moving autonomously, wherein, include: In the first generation step, the position and orientation of the moving body, obtained by a predetermined first acquisition method using the detection results of the first sensor, are used to generate a first candidate for a driving permissible range that allows the moving body to move in a manner that does not contact other objects. In the second generation step, the position and orientation of the moving body, obtained by a predetermined second acquisition method using the detection results of the second sensor, are used to generate a second candidate for the driving permissible range; and The decision-making process involves determining the overlap range between the first candidate and the second candidate as the permitted driving range, and sending the determined permitted driving range to the control unit of the mobile body. In the first generation process and the second generation process, at least one of the first condition and the second condition is satisfied. The first condition is that the first sensor and the second sensor are different sensors, and the second condition is that the first acquisition method and the second acquisition method are different acquisition methods.

Images