Vehicle control system and vehicle control method

Abstract

To improve safety when controlling a vehicle traveling in a prescribed area.SOLUTION: A vehicle control system controls a vehicle traveling in a prescribed area. The vehicle control system acquires vehicle information indicating a position of the vehicle, and sets a determination region around the vehicle on the basis of the vehicle information. The vehicle control system also acquires an image captured by an infrastructure camera that is installed outside the vehicle and captures images of a situation in the prescribed area. The vehicle control system further determines whether or not a target exists in the determination region on the basis of the image captured by the infrastructure camera. If a target exists in the determination region, the vehicle control system reduces a speed of the vehicle.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present disclosure relates to a technology for controlling a vehicle traveling within a predetermined area.

Background Art

[0002] Patent Document 1 discloses a driving support device for a vehicle. The driving support device sets a determination area for determining a collision risk in front of the vehicle. Further, the driving support device uses an in-vehicle camera to detect a preceding vehicle in front of the vehicle. When the preceding vehicle enters the determination area, the driving support device determines that there is a collision risk and issues an alarm to the occupant.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] According to the technology described in Patent Document 1, only the targets visible by the in-vehicle camera are the targets for determining the collision risk. For example, since a target ahead of a curve in front of the vehicle cannot be seen by the in-vehicle camera, the collision risk regarding that target cannot be determined. If the target enters the field of view of the in-vehicle camera after approaching the target considerably, there is a possibility of sudden braking.

[0005] One object of the present disclosure is to provide a technology capable of improving the safety when controlling a vehicle traveling within a predetermined area.

Means for Solving the Problems

[0006] A first aspect relates to a vehicle control system for controlling a vehicle traveling within a predetermined area. The vehicle control system includes one or more processors. One or more processors acquire vehicle information indicating the vehicle's location. One or more processors set a determination area around the vehicle based on vehicle information. One or more processors acquire images captured by infrastructure cameras installed outside the vehicle to photograph the conditions of a designated area. One or more processors determine whether or not a target exists in the determination area based on images captured by the infrastructure camera. If a target is present in the detection area, one or more processors will slow down the vehicle.

[0007] The second aspect relates to a vehicle control method that uses a computer to control a vehicle traveling within a predetermined area. The vehicle control method is, Obtaining vehicle information that indicates the vehicle's location, Based on vehicle information, a judgment area is set around the vehicle, This involves acquiring images captured by infrastructure cameras installed on the exterior of the vehicle to photograph the conditions of a designated area, and Based on images captured by infrastructure cameras, it is determined whether or not a target exists in the judgment area, If a target is present in the detection area, the vehicle will be slowed down. Includes. [Effects of the Invention]

[0008] According to this disclosure, infrastructure cameras are used for vehicle control. By using infrastructure cameras, it becomes possible to detect targets that cannot be detected by on-board sensors such as on-board cameras. Furthermore, vehicle control is performed taking into account targets that cannot be detected by on-board sensors. Specifically, if a target is present in the detection area around the vehicle, the vehicle will decelerate. Because targets that cannot be detected by on-board sensors are also taken into consideration, the vehicle can be decelerated with ample margin, reducing the need for sudden braking. Consequently, safety when controlling the vehicle is improved. [Brief explanation of the drawing]

[0009] [Figure 1] It is a conceptual diagram for explaining the outline of a vehicle control system according to the first embodiment. [Figure 2] It is a conceptual diagram for explaining an example of a determination area used for risk avoidance control according to the first embodiment. [Figure 3] It is a conceptual diagram for explaining another example of the determination area used for risk avoidance control according to the first embodiment. [Figure 4] It is a block diagram showing a configuration example of an in-vehicle system according to the first embodiment. [Figure 5] It is a block diagram showing a configuration example of a vehicle control system according to the first embodiment. [Figure 6] It is a flowchart schematically showing processes related to risk avoidance control according to the first embodiment. [Figure 7] It is a diagram for explaining a method of updating the front boundary of a front determination area according to the second embodiment. [Figure 8] It is a diagram for explaining an example of updating the front boundary of a front determination area according to the second embodiment. [Figure 9] It is a diagram for explaining an example of block setting according to vehicle speed according to the second embodiment. [Figure 10] It is a conceptual diagram for explaining a front determination area and a rear determination area according to the third embodiment. [Figure 11] It is a diagram for explaining a method of updating a rear determination area according to the fifth embodiment. [Figure 12] It is a diagram for explaining an example of updating a rear determination area according to the fifth embodiment. [Figure 13] It is a diagram for explaining an example of block setting according to the fifth embodiment.

Embodiments for Carrying Out the Invention

[0010] Embodiments of the present disclosure will be described with reference to the accompanying drawings.

[0011] 1. First Embodiment 1-1. Overview FIG. 1 is a conceptual diagram for explaining the overview of the vehicle control system 100 according to the first embodiment. The vehicle control system 100 controls the vehicle 1 traveling within a predetermined area AR.

[0012] The predetermined area AR in which the vehicle 1 travels is, for example, an elongated area extending in the first direction S. It can be said that the first direction S is the longitudinal direction of the predetermined area AR. Examples of the predetermined area AR include a roadway (expressway, general road), a passage in a parking lot, a passage in a factory, etc. The center line of the predetermined area AR parallel to the first direction S may coincide with the center line of the roadway or passage. On the other hand, the width of the predetermined area AR orthogonal to the first direction S does not necessarily have to exactly match the width of the roadway or passage. The width of the predetermined area AR may be the width of a general vehicle plus a margin width. The width of the predetermined area AR may be widened in a curve section.

[0013] The vehicle control system 100 may include at least a part of the in-vehicle system 10 mounted on the vehicle 1. The in-vehicle system 10 acquires the current position of the vehicle 1 using GNSS (Global Navigation Satellite System). Also, the in-vehicle system 10 acquires an image captured by an in-vehicle camera. The in-vehicle system 10 may control the vehicle 1 based on the image captured by the in-vehicle camera. For example, the in-vehicle system 10 may control the automatic driving of the vehicle 1 based on the image captured by the in-vehicle camera. That is, the vehicle 1 may be an autonomous vehicle. Here, autonomous driving means automatically performing at least a part of the steering, acceleration, and deceleration of the vehicle 1 independently of the driver's operation. As an example, the autonomous driving may be at level 3 or higher.

[0014] The vehicle control system 100 may include external devices located outside of the vehicle 1. For example, the external device may be a management server that manages the vehicle 1. The management server may be a distributed server that performs distributed processing. The external device communicates with the vehicle 1 (in-vehicle system 10) and remotely controls the vehicle 1.

[0015] The vehicle control system 100 may be distributed between the in-vehicle system 10 and external devices.

[0016] According to this embodiment, an "infrastructure camera CAM" installed outside the vehicle 1 is also used to control the vehicle 1. The infrastructure camera CAM is installed so as to be able to photograph a predetermined area AR and its surroundings. Typically, multiple infrastructure camera CAMs are installed along the longitudinal direction (first direction S) of the predetermined area AR. The fields of view of each of the multiple infrastructure camera CAMs may partially overlap. Image 250 is an image taken by the infrastructure camera CAM and shows the predetermined area AR and its surroundings.

[0017] The vehicle control system 100 communicates with the infrastructure camera CAM and acquires images 250 captured by the infrastructure camera CAM. Images 250 may contain target objects (TGTs) located within a predetermined area (AR). Here, a target object (TGT) is an object other than the vehicle 1 being controlled. Examples of target objects (TGTs) include pedestrians, bicycles, other vehicles (e.g., preceding vehicles, parked vehicles), etc.

[0018] The vehicle control system 100 can detect (recognize) target objects TGTs located within a predetermined area AR based on images 250 captured by an infrastructure camera CAM. For example, the vehicle control system 100 uses image recognition AI to recognize target objects TGTs shown in image 250. The image recognition AI is pre-generated through machine learning. The installation information of the infrastructure camera CAM (installation position, orientation, field of view, etc.) is known information. Based on the installation information of the infrastructure camera CAM and the image position of the target objects TGTs in image 250, the vehicle control system 100 can detect target objects TGTs located within a predetermined area AR and further calculate the position of the target objects TGTs in an absolute coordinate system.

[0019] By using an infrastructure camera (CAM), it may be possible to detect targets (TGT) that cannot be detected by on-board sensors such as on-board cameras. For example, in Figure 1, a target TGT is located within a predetermined area (AR) beyond a curve in front of vehicle 1. The target TGT beyond the curve in front of vehicle 1 cannot be detected by on-board sensors, but it can be detected by the infrastructure camera (CAM). The same applies if there is a steep slope in front of vehicle 1.

[0020] A target TGT located within a designated area AR can pose a "risk" to a vehicle 1 traveling within that area AR. Therefore, the vehicle control system 100 performs "risk avoidance control" as needed to avoid the risk. Specifically, the vehicle control system 100 automatically performs at least one of steering or deceleration of the vehicle 1 to avoid a collision between the vehicle 1 and the target TGT. In other words, risk avoidance control includes at least one of steering control and deceleration control.

[0021] The following section will provide a detailed explanation of deceleration control, a key component of risk avoidance control. In addition to the deceleration control described below, steering control may also be implemented.

[0022] Figure 2 is a conceptual diagram illustrating an example of a "decision area D" used in risk avoidance control. The decision area D is the area used to determine whether or not to activate risk avoidance control. If a target TGT is present within the decision area D, risk avoidance control (deceleration control) is activated. As shown in Figure 2, the decision area D is set around the vehicle 1. Typically, the decision area D is set to extend in the first direction S, similar to a predetermined area AR. The width of the decision area D perpendicular to the first direction S may be the same as the width of the predetermined area AR. Alternatively, the width of the decision area D perpendicular to the first direction S may be slightly larger than the width of the predetermined area AR.

[0023] Vehicle position PV is the position of vehicle 1 in the absolute coordinate system. Direction of travel X is the direction in which vehicle 1 is moving. "Forward direction" is direction of travel X, and "rearward direction" is the direction opposite to direction of travel X. The judgment area D may be divided into "forward judgment area Df" and "rearward judgment area Dr".

[0024] The forward determination area Df is the determination area D in front of vehicle 1, located in the forward direction (direction of travel X) when viewed from vehicle position PV. The forward boundary DBf is the front end of the forward determination area Df. The forward determination area Df can be said to be the area between the forward boundary DBf and vehicle position PV. The forward distance Lf is the distance from vehicle position PV to the forward boundary DBf along the first direction S. The forward distance Lf is set to a distance at which vehicle 1 can stop with ample margin. The position of the forward boundary DBf may change in conjunction with the vehicle position PV. In that case, the forward determination area Df will also change in conjunction with the vehicle position PV.

[0025] On the other hand, the rear determination area Dr is the determination area D behind vehicle 1, located in the rear direction when viewed from the vehicle position PV. The rear boundary DBr is the rear end of the rear determination area Dr. The rear determination area Dr can be said to be the area between the rear boundary DBr and the vehicle position PV. The rear distance Lr is the distance from the vehicle position PV to the rear boundary DBr along the first direction S. The position of the rear boundary DBr may change in conjunction with the vehicle position PV. In that case, the rear determination area Dr also changes in conjunction with the vehicle position PV.

[0026] The vehicle control system 100 sets a determination area D (forward determination area Df, rear determination area Dr) based on the vehicle position PV. Also, as described above, the vehicle control system 100 detects targets TGT within a predetermined area AR based on the image 250 captured by the infrastructure camera CAM. Furthermore, the vehicle control system 100 calculates the position of the targets TGT in an absolute coordinate system based on the installation information of the infrastructure camera CAM (installation position, installation orientation, field of view, etc.). In addition, the vehicle control system 100 may detect targets TGT around the vehicle 1 using on-board sensors such as on-board cameras.

[0027] The vehicle control system 100 then determines whether or not a target TGT exists in the determination area D. An example of this determination process is as follows: The vehicle control system 100 sets up a target area that covers the detected target TGT and its vicinity. For example, the target area has a circular shape. As the size of the target TGT increases, the target area also increases. The target area may also increase as the movement speed of the target TGT increases. The target area may have a shape that widens the direction of movement of the target TGT. If such a target area and the determination area D overlap at least partially, the vehicle control system 100 determines that the target TGT is present in the determination area D.

[0028] If a target TGT is present in the determination area D, the vehicle control system 100 activates risk avoidance control (deceleration control). That is, if a target TGT is present in the determination area D, the vehicle control system 100 decelerates vehicle 1. Here, deceleration is a concept that also includes decelerating and stopping the vehicle. In other words, the vehicle control system 100 may stop vehicle 1.

[0029] Figure 3 is a conceptual diagram illustrating another example of determination region D. In the example shown in Figure 3, determination region D is divided into a first determination region D1 and a second determination region D2. The first determination region D1 is located inside, and the second determination region D2 is located outside. In other words, the second determination region D2 surrounds the first determination region D1.

[0030] The forward determination area Df is divided into a first forward determination area D1f and a second forward determination area D2f. The first forward determination area D1f is located on the inside, and the second forward determination area D2f is located on the outside. In other words, the second forward determination area D2f surrounds the first forward determination area D1f. The first forward boundary DB1f is the front end of the first forward determination area D1f. The second forward boundary DB2f is the front end of the second forward determination area D2f.

[0031] The rear detection area Dr is divided into a first rear detection area D1r and a second rear detection area D2r. The first rear detection area D1r is located on the inside, and the second rear detection area D2r is located on the outside. In other words, the second rear detection area D2r surrounds the first rear detection area D1r. The first rear boundary DB1r is the rear end of the first rear detection area D1r. The second rear boundary DB2r is the rear end of the second rear detection area D2r.

[0032] The vehicle control system 100 determines whether or not a target TGT exists in the determination area D. If a target TGT exists in the inner first determination area D1, the vehicle control system 100 decelerates and stops the vehicle 1. This corresponds to emergency stop control. On the other hand, if a target TGT exists in the outer second determination area D2, the vehicle control system 100 decelerates the vehicle 1 more gradually than in the case of emergency stop control. This corresponds to normal deceleration control. The deceleration in normal deceleration control is lower than the deceleration in emergency stop control.

[0033] As described above, according to this embodiment, an infrastructure camera CAM is used to control the vehicle 1. By using the infrastructure camera CAM, it becomes possible to detect targets TGT that cannot be detected by on-board sensors such as on-board cameras. For example, a target TGT located around a curve ahead of the vehicle 1 can also be detected by the infrastructure camera CAM. Then, the control of the vehicle 1 is performed taking into account targets TGT that cannot be detected by on-board sensors. Specifically, if a target TGT is present in the determination area D around the vehicle 1, the vehicle 1 is decelerated. Since targets TGT that cannot be detected by on-board sensors are also taken into consideration, the vehicle 1 can be decelerated with ample margin, reducing the need for sudden braking. Therefore, safety when controlling the vehicle 1 is improved.

[0034] 1-2. Examples of in-vehicle systems Figure 4 is a block diagram showing an example configuration of an in-vehicle system 10 mounted on vehicle 1. The in-vehicle system 10 includes a sensor group 20, a communication device 30, a driving device 40, and a control device 50.

[0035] The sensor group 20 includes recognition sensors, vehicle state sensors, and position sensors. The recognition sensors recognize (detect) the surrounding conditions of vehicle 1. Examples of recognition sensors include cameras, LIDAR (Laser Imaging Detection and Ranging), radar, etc. The vehicle state sensors detect the state of vehicle 1. For example, vehicle state sensors include speed sensors, acceleration sensors, yaw rate sensors, steering angle sensors, etc. The position sensors detect the position and orientation of vehicle 1. For example, position sensors include GNSS sensors.

[0036] The communication device 30 communicates with the outside world via a communication network. For example, the communication device 30 communicates with infrastructure cameras (CAM), management servers, etc.

[0037] The running gear 40 includes a steering gear, a drive gear, and a braking gear. The steering gear steers the wheels. For example, the steering gear includes an electric power steering (EPS) system. The drive gear is a power source that generates driving force. Examples of drive gears include an engine, an electric motor, an in-wheel motor, etc. The braking gear generates braking force.

[0038] The control device 50 is a computer that controls the vehicle 1. The control device 50 includes one or more processors 60 (hereinafter simply referred to as processor 60) and one or more storage devices 70 (hereinafter simply referred to as storage devices 70). The processors 60 perform various processes. Examples of processors 60 include CPU (Central Processing Unit), GPU (Graphics Processing Unit), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), etc. The storage devices 70 store various information. Examples of storage devices 70 include HDD (Hard Disk Drive), SSD (Solid State Drive), volatile memory, non-volatile memory, etc.

[0039] The vehicle control program 80 is a computer program for controlling the vehicle 1. The functions of the control device 50 may be realized through the cooperation of the processor 60 that executes the vehicle control program 80 and the storage device 70. The vehicle control program 80 is stored in the storage device 70. Alternatively, the vehicle control program 80 may be recorded on a computer-readable recording medium.

[0040] The control device 50 acquires driving environment information 90 that indicates the driving environment of vehicle 1. The driving environment information 90 is stored in the storage device 70.

[0041] The driving environment information 90 includes surrounding situation information obtained based on recognition sensors. For example, the surrounding situation information includes images captured by a camera. As another example, the surrounding situation information may include point cloud information obtained by LIDAR. The surrounding situation information also includes object information regarding objects (targets) around the vehicle 1. Examples of objects around the vehicle 1 include pedestrians, other vehicles, obstacles, white lines, landmarks, traffic lights, etc. The object information indicates the relative position and relative velocity of the object with respect to the vehicle 1.

[0042] The driving environment information 90 further includes position information indicating the vehicle position PV (current position of vehicle 1) in an absolute coordinate system. The control device 50 acquires position information from the detection results of the position sensor. Alternatively, the control device 50 may acquire highly accurate position information by using a well-known self-position estimation process (localization) that utilizes object information and map information.

[0043] The driving environment information 90 further includes vehicle condition information detected by the vehicle condition sensor.

[0044] Furthermore, the control device 50 performs vehicle driving control to control the movement of the vehicle 1. Vehicle driving control includes steering control, acceleration control, and deceleration control. The control device 50 performs vehicle driving control by controlling the driving device 40 (steering device, drive device, braking device).

[0045] Furthermore, the control device 50 may perform autonomous driving control to control the autonomous driving of the vehicle 1. Here, autonomous driving means that at least a portion of the steering, acceleration, and deceleration of the vehicle 1 are performed automatically, independently of the driver's operation. Based on the driving environment information 90, the control device 50 generates a driving plan for the vehicle 1. Examples of driving plans include maintaining the current driving lane, changing lanes, turning left or right, and avoiding collisions with objects. Furthermore, the control device 50 generates a target trajectory to realize the driving plan. The target trajectory includes the target position and target speed of the vehicle 1. The control device 50 then performs vehicle driving control so that the vehicle 1 follows the target trajectory.

[0046] 1-3. Examples of Vehicle Control Systems Figure 5 is a block diagram showing an example configuration of a vehicle control system 100. The vehicle control system 100 includes one or more processors 110 (hereinafter simply referred to as processor 110), one or more storage devices 120 (hereinafter simply referred to as storage devices 120), and a communication device 130. The processor 110 performs various processes. Examples of processors 110 include CPU, GPU, ASIC, FPGA, etc. The storage devices 120 store various information. Examples of storage devices 120 include HDD, SSD, volatile memory, non-volatile memory, etc. The communication device 130 communicates with the outside world via a communication network. For example, the communication device 130 communicates with an infrastructure camera CAM. The communication device 130 may also communicate with a vehicle 1 (in-vehicle system 10).

[0047] The vehicle control program 140 is a computer program for controlling vehicle 1. The functions of the vehicle control system 100 may be realized through the cooperation of a processor 110 that executes the vehicle control program 140 and a storage device 120. The vehicle control program 140 is stored in the storage device 120. Alternatively, the vehicle control program 140 may be recorded on a computer-readable recording medium.

[0048] The vehicle control system 100 may be partially common with the in-vehicle system 10 described above. That is, the processor 60 and the processor 110 may be the same. The storage device 70 and the storage device 120 may be the same. The vehicle control program 80 and the vehicle control program 140 may be the same.

[0049] The processor 110 acquires various types of information 200. The various types of information 200 are stored in the storage device 120. The various types of information 200 include map information 210, vehicle information 220, judgment area information 230, infrastructure camera information 240, images 250, target information 260, etc.

[0050] Map information 210 is map information for a predetermined area AR on which vehicle 1 travels. Map information 210 is provided to the vehicle control system 100 in advance.

[0051] Vehicle information 220 is information about the vehicle 1 to be controlled. Vehicle information 220 includes at least position information indicating the vehicle position PV (current position of vehicle 1) in an absolute coordinate system. Position information is obtained from the on-board system 10. Vehicle information 220 may also include information on the direction of travel X of vehicle 1. The direction of travel X of vehicle 1 can be determined based on the vehicle position PV. Vehicle information 220 may further include speed information of vehicle 1. Speed ​​information is also obtained from the on-board system 10.

[0052] The judgment area information 230 is information about the judgment area D used for risk avoidance control. For example, the judgment area information 230 includes a setting policy for setting the judgment area D. The judgment area information 230 may include a setting value for the forward distance Lf from the vehicle position PV along the first direction S to the forward boundary DBf. The judgment area information 230 may also include a setting value for the rear distance Lr from the vehicle position PV along the first direction S to the rear boundary DBr.

[0053] The infrastructure camera information 240 indicates the installation position, orientation, field of view, etc., of each infrastructure camera CAM. The infrastructure camera information 240 is provided to the vehicle control system 100 in advance.

[0054] Image 250 is an image captured by the infrastructure camera CAM, showing the designated area AR and its surroundings. The processor 110 acquires image 250 from the infrastructure camera CAM via the communication device 130.

[0055] The target information 260 is information about target TGTs located within a predetermined area AR. The processor 110 detects target TGTs located within the predetermined area AR based on images 250 captured by the infrastructure camera CAM. For example, the processor 110 uses image recognition AI to recognize target TGTs shown in images 250. The processor 110 also calculates the position of the target TGTs in an absolute coordinate system based on the infrastructure camera information 240 and the in-image position of the target TGTs in images 250. Additionally, the target information 260 may include information about targets detected by the in-vehicle system 10.

[0056] Furthermore, the controlled vehicle 1 and other target TGTs are distinguished from each other. For example, vehicle 1 and other target TGTs can be distinguished by comparing the vehicle position PV with the position of the target TGT. For example, a target region is set that covers the detected target TGT and its vicinity. If the vehicle position PV is within the target region, that target TGT is considered to be the controlled vehicle 1.

[0057] The processor 110 controls the vehicle 1. If the vehicle control system 100 includes the in-vehicle system 10, the processor 110 controls the vehicle 1 by controlling the running gear 40. If the vehicle control system 100 is outside the in-vehicle system 10, the processor 110 remotely controls the vehicle 1 by issuing control instructions to the in-vehicle system 10 via the communication device 130.

[0058] In particular, the processor 110 performs risk avoidance control to avoid a collision between the vehicle 1 and the target TGT. Figure 6 is a flowchart that summarizes the processes related to risk avoidance control.

[0059] In step S100, the processor 110 acquires various pieces of information 200.

[0060] In step S110, the processor 110 sets the determination area D based on the map information 210, vehicle information 220, and determination area information 230. The processor 110 may also set the forward determination area Df and the rear determination area Dr, taking into account the direction of travel X of the vehicle 1.

[0061] In step S120, the processor 110 determines whether or not a target TGT exists in the determination area D based on the target information 260 and the determination area D. For example, the processor 110 sets a target area that covers the target TGT and its vicinity. For example, the target area has a circular shape. As the size of the target TGT increases, the target area also increases. The target area may also increase as the movement speed of the target TGT increases. The target area may have a shape that widens the direction of movement of the target TGT. If such a target area and the determination area D overlap at least partially, the processor 110 determines that the target TGT exists in the determination area D.

[0062] If the target TGT is not located within the determination area D (step S120; No), the process proceeds to step S130. In step S130, the processor 110 performs normal vehicle driving control.

[0063] On the other hand, if the target TGT is within the determination area D (step 120; Yes), the process proceeds to step S140. In step S140, the processor 110 performs deceleration control to slow down the vehicle 1. The processor 110 may slow down the vehicle 1 and bring it to a stop.

[0064] 1-4. Effects As described above, according to this embodiment, an infrastructure camera CAM is used to control the vehicle 1. By using the infrastructure camera CAM, it becomes possible to detect targets TGT that cannot be detected by on-board sensors such as on-board cameras. For example, a target TGT located around a curve ahead of the vehicle 1 can also be detected by the infrastructure camera CAM. Then, the control of the vehicle 1 is performed taking into account targets TGT that cannot be detected by on-board sensors. Specifically, if a target TGT is present in the determination area D around the vehicle 1, the vehicle 1 is decelerated. Since targets TGT that cannot be detected by on-board sensors are also taken into consideration, the vehicle 1 can be decelerated with ample margin, reducing the need for sudden braking. Therefore, safety when controlling the vehicle 1 is improved.

[0065] Other embodiments will be described below. The configuration of the in-vehicle system 10 and the vehicle control system 100 is the same as in the first embodiment.

[0066] 2. Second Embodiment Figure 7 shows an example of updating the forward boundary DBf of the forward determination area Df. The horizontal axis represents time, and the vertical axis represents the vehicle position PV and the forward boundary DBf. The forward determination area Df is the area between the vehicle position PV and the forward boundary DBf. The forward distance Lf between the vehicle position PV and the forward boundary DBf is set to a distance that allows vehicle 1 to stop with ample margin.

[0067] According to pattern (A) in Figure 7, the forward boundary DBf is updated each time the vehicle position PV is updated. In other words, the update frequency of the forward boundary DBf is the same as the update frequency (sampling frequency) of the vehicle position PV. It can be said that the forward boundary DBf changes in complete synchronization with the vehicle position PV. However, if the update frequency of the forward boundary DBf increases, the processing load on the processor 110 also increases. Increasing the update frequency of the forward boundary DBf more than necessary is undesirable from the standpoint of processing load.

[0068] Therefore, according to the second embodiment, as shown in pattern (B) in Figure 7, the update frequency of the forward boundary DBf of the forward determination area Df is set lower than the update frequency of the vehicle position PV. In other words, the processor 110 updates the forward boundary DBf of the forward determination area Df at a lower frequency than the update frequency of the vehicle position PV (i.e., vehicle information 220). This makes it possible to reduce the processing load on the processor 110.

[0069] The processor 110 may reduce the update frequency of the forward boundary DBf as the speed of vehicle 1 decreases. The speed of vehicle 1 is obtained from vehicle information 220. The update frequency of the forward boundary DBf may decrease monotonically or in stages depending on the speed of vehicle 1. For example, the update frequency when the speed of vehicle 1 is above a predetermined threshold is the first update frequency, and the update frequency when the speed of vehicle 1 is below the predetermined threshold is the second update frequency, which is lower than the first update frequency. By changing the update frequency of the forward boundary DBf while also considering the speed of vehicle 1, it is possible to more effectively reduce the processing load on the processor 110.

[0070] Figure 8 illustrates an example of updating the forward boundary DBf of the forward determination area Df. The predetermined area AR on which vehicle 1 travels is divided into multiple blocks BK along a first direction S. Each block BK is the area between the forward block boundary BKBf and the rear block boundary BKBr. The forward block boundary BKBf is located in the direction X of travel of vehicle 1, as seen from the rear block boundary BKBr. The block length Lbk is the length of block BK along the first direction S. In other words, the block length Lbk of each block BK is the length between the forward block boundary BKBf and the rear block boundary BKBr along the first direction S. The block length Lbk is set to a distance that allows vehicle 1 to stop with ample margin.

[0071] Block placement information indicates the arrangement of multiple blocks BK in an absolute coordinate system. In other words, block placement information indicates the positions of the forward block boundary BKBf and the backward block boundary BKBr of each block BK in an absolute coordinate system. Such block placement information is pre-registered in map information 210.

[0072] The processor 110 sets and updates the forward boundary DBf of the forward determination area Df based on the vehicle position PV and block arrangement information. For the purpose of this explanation, the block BK in which vehicle 1 is currently located will be referred to as "first block BK1" below. The block BK adjacent to the first block BK1 will be referred to as "second block BK2" below. In other words, the second block BK2 is located in the direction of travel X of vehicle 1 as seen from the first block BK1. The processor 110 recognizes the first block BK1 and the second block BK2 based on the vehicle position PV and block arrangement information. Then, the processor 110 sets the forward block boundary BKBf of the second block BK2 as the forward boundary DBf of the forward determination area Df.

[0073] In the example shown in Figure 8, initially, vehicle 1 is located in block BK(i). That is, the first block BK1 is block BK(i), and the second block BK2 is block BK(i+1). At this time, the forward boundary DBf of the forward determination region Df is the forward block boundary BKBf(i+1) of block BK(i+1). While vehicle 1 is moving within block BK(i), the forward boundary DBf remains unchanged.

[0074] Eventually, vehicle 1 approaches the front block boundary BKBf(i) of block BK(i). Based on the vehicle position PV and block arrangement information, processor 110 determines whether a predetermined portion of vehicle 1 has passed the front block boundary BKBf(i) of block BK(i). The predetermined portion is arbitrary. If a predetermined portion of vehicle 1 has passed the front block boundary BKBf(i) of block BK(i), processor 110 determines that vehicle 1 has passed the front block boundary BKBf(i) and entered block BK(i+1).

[0075] When vehicle 1 enters block BK(i+1), block BK(i+1) becomes the new first block BK1, and block BK(i+2) becomes the new second block BK2. In other words, the first block BK1 and the second block BK2 are updated. Therefore, the processor 110 sets the forward block boundary BKBf(i+2) of block BK(i+2) to the new forward boundary DBf. That is, the forward boundary DBf of the forward determination area Df is updated.

[0076] The same process is repeated thereafter. Each time vehicle 1 passes the forward block boundary BKBf of the first block BK1, processor 110 updates the forward boundary DBf of the first block BK1, the second block BK2, and the forward determination area Df. This method makes it possible to update the forward boundary DBf of the forward determination area Df at a lower frequency than updating the vehicle position PV.

[0077] As shown in Figure 9, the block length Lbk of each block BK may increase as the speed of vehicle 1 increases. The block length Lbk may change monotonically or stepwise depending on the speed of vehicle 1. In the example shown in Figure 9, the block length Lbk when the speed of vehicle 1 is below a predetermined threshold is the first block length Lbk-l. The block length Lbk when the speed of vehicle 1 is above the predetermined threshold is the second block length Lbk-h, which is longer than the first block length Lbk-l. Block arrangement information for each case of the first block length Lbk-l and the second block length Lbk-h is registered in the map information 210. The speed of vehicle 1 is obtained from vehicle information 220. The processor 110 obtains block arrangement information corresponding to the speed of vehicle 1. <Effects> As described above, according to the second embodiment, the update frequency of the forward boundary DBf of the forward determination area Df is set lower than the update frequency of the vehicle position PV. This makes it possible to reduce the processing load on the processor 110. In particular, when controlling a large number of vehicles 1 simultaneously and in parallel based on images 250 captured by a large number of infrastructure cameras CAM, reducing the processing load is desirable.

[0078] As shown in Figure 8, the forward boundary DBf of the forward determination area Df may be set and updated based on block BK. This reduces the frequency of updating the forward boundary DBf and alleviates the processing load. Furthermore, when a pre-set block BK is used, the processor 110 does not need to consider the road shape for each instance when drawing the forward boundary DBf. This also contributes to reducing the processing load. In addition, it prevents the forward boundary DBf from becoming an unnatural line.

[0079] 3. Third Embodiment Figure 10 is a conceptual diagram illustrating the forward detection area Df and the rear detection area Dr according to the third embodiment. The forward detection area Df is the area that vehicle 1 will pass through. On the other hand, the rear detection area Dr is the area that vehicle 1 has already passed through. Even if there is a target TGT in the rear detection area Dr, the risk is relatively low. If the rear detection area Dr is set too wide, deceleration control may be activated even though the target TGT is far away from vehicle 1. Excessive deceleration control worsens the ability to continue driving and causes discomfort to the user of vehicle 1.

[0080] Therefore, according to the third embodiment, the rear determination area Dr is set to be narrower than the front determination area Df. More specifically, the processor 110 sets the front determination area Df and the rear determination area Dr such that the rear distance Lr is shorter than the front distance Lf (Lf > Lr). The front distance Lf and the rear distance Lr may each be predetermined values.

[0081] According to the third embodiment, it is possible to suppress excessive operation of deceleration control while ensuring safety. As a result, continuity of driving is ensured. Furthermore, discomfort for the user of vehicle 1 is also suppressed.

[0082] 4. Fourth Embodiment A combination of the second and third embodiments described above is also possible. In this case, the update frequency of the forward boundary DBf of the forward determination area Df is set lower than the update frequency of the vehicle position PV. Also, the rear determination area Dr is set to be narrower than the forward determination area Df. This provides the effect of reducing the processing load and suppressing excessive operation of the deceleration control.

[0083] 5. Fifth Embodiment In the fifth embodiment, the update frequency of the rear boundary DBr of the rear determination area Dr is set lower than the update frequency of the vehicle position PV. Descriptions that overlap with the second embodiment described above are omitted as appropriate.

[0084] Figure 11 shows an example of updating the rear boundary DBr of the rear determination area Dr. According to pattern (A), the rear boundary DBr is updated every time the vehicle position PV is updated. In other words, the update frequency of the rear boundary DBr is the same as the update frequency (sampling frequency) of the vehicle position PV. In this case, the processing load is high. On the other hand, according to pattern (B), the update frequency of the rear boundary DBr is lower than the update frequency of the vehicle position PV. Therefore, the processing load on the processor 110 is reduced.

[0085] The processor 110 may reduce the update frequency of the rear boundary DBr as the speed of vehicle 1 decreases. This makes it possible to more effectively reduce the processing load.

[0086] Figure 12 illustrates an example of updating the rear boundary DBr of the rear determination area Dr. The first block BK1 is the block BK in which vehicle 1 is currently located. The second block BK2 is the rear block BK adjacent to the first block BK1. That is, the second block BK2 is located in the opposite direction to the direction of travel X of vehicle 1 when viewed from the first block BK1. The processor 110 recognizes the first block BK1 and the second block BK2 based on the vehicle position PV and block arrangement information. The processor 110 then sets the rear block boundary BKBr of the second block BK2 as the rear boundary DBr of the rear determination area Dr. Each time vehicle 1 passes the front block boundary BKBf of the first block BK1, the processor 110 updates the rear boundary DBr of the first block BK1, the second block BK2, and the rear determination area Dr. By this method, the update frequency of the rear boundary DBr of the rear determination area Dr can be made lower than the update frequency of the vehicle position PV.

[0087] According to the fifth embodiment, it is possible to reduce the processing load on the processor 110. In particular, when controlling a large number of vehicles 1 simultaneously and in parallel based on images 250 captured by a large number of infrastructure cameras CAM, reducing the processing load is desirable.

[0088] A combination of the fifth embodiment and any of the embodiments described above is also possible.

[0089] Figure 13 is a diagram illustrating a combination of the fifth and fourth embodiments. When setting the forward boundary DBf of the forward determination region Df, a block BK with block length Lbk-f is used. On the other hand, when setting the rear boundary DBr of the rear determination region Dr, a block BK with block length Lbk-r is used. Block length Lbk-r is shorter than block length Lbk-f. As a result, the rear distance Lr becomes shorter than the forward distance Lf. This provides the effect of reducing processing load and suppressing excessive operation of deceleration control. [Explanation of Symbols]

[0090] 1 vehicle 10 In-vehicle systems 100 Vehicle control systems AR designated area BK Block CAM infrastructure camera D Judgment area Df forward judgment area Dr rear judgment area DBf forward boundary DBr rear boundary

Claims

1. A vehicle control system that controls vehicles traveling within a predetermined area, Equipped with one or more processors, The one or more processors described above are: Vehicle information indicating the location of the aforementioned vehicle is acquired, Based on the vehicle information, a determination area is set around the vehicle. Images are acquired from an infrastructure camera installed on the exterior of the vehicle, which captures the conditions of the predetermined area. Based on the image captured by the infrastructure camera, it is determined whether or not a target exists in the determination area. If the target is present in the determination area, the vehicle is decelerated. It is configured in such a way, The determination region includes a first determination region and a second determination region surrounding the first determination region. Decelerating the aforementioned vehicle is If the target exists in the first determination area, stop control is performed to decelerate and stop the vehicle. If the target is present in the second determination area, the vehicle will be decelerated more gradually than in the case of the stop control. including Vehicle control system.

2. A vehicle control system according to claim 1, The aforementioned vehicle information further indicates the direction of travel of the vehicle. The one or more processors further include: Based on the vehicle information, a forward determination area, which is the determination area in front of the vehicle, is set. The front end of the forward determination area is updated at a frequency lower than the update frequency of the vehicle information. It is configured in such a way Vehicle control system.

3. A vehicle control system according to claim 2, The one or more processors are further configured to reduce the update frequency of the front end of the forward determination area as the vehicle speed decreases. Vehicle control system.

4. A vehicle control system according to claim 2, The predetermined area extends in a first direction and is divided into a plurality of blocks along the first direction. Each of the aforementioned multiple blocks is a region between the front block boundary and the rear block boundary, The aforementioned front block boundary is located in the direction of travel of the vehicle, as viewed from the rear block boundary. The plurality of blocks include a first block in which the vehicle is located and a second block located in the direction of travel of the vehicle as seen from the first block. The one or more processors further include: Based on the vehicle information, the first block and the second block are recognized. The forward block boundary of the second block is set as the front end of the forward determination area, Each time the vehicle passes the front block boundary of the first block, the first block, the second block, and the front end of the forward determination area are updated. It is configured in such a way Vehicle control system.

5. A vehicle control system according to claim 4, The block length is the length of each of the plurality of blocks along the first direction, The length of the block increases as the vehicle's speed increases. Vehicle control system.

6. A vehicle control system according to any one of claims 1 to 5, The aforementioned vehicle information further indicates the direction of travel of the vehicle. The one or more processors are further configured to set a forward determination area, which is the determination area in front of the vehicle, and a rear determination area, which is the determination area behind the vehicle, based on the vehicle information. Vehicle control system.

7. A vehicle control system according to claim 6, The forward distance is the distance from the position of the vehicle to the front end of the forward determination area. The rear distance is the distance from the position of the vehicle to the rear end of the rear determination area. The one or more processors are further configured to set the forward determination area and the backward determination area such that the backward distance is shorter than the forward distance. Vehicle control system.

8. A vehicle control system according to claim 7, The aforementioned rear distance is a predetermined distance. Vehicle control system.

9. A vehicle control system according to claim 6, The one or more processors are further configured to update the rear end of the rear determination area at a frequency lower than the update frequency of the vehicle information. Vehicle control system.

10. A vehicle control method that uses a computer to control a vehicle traveling within a predetermined area, To obtain vehicle information indicating the location of the aforementioned vehicle, Based on the aforementioned vehicle information, a determination area is set around the vehicle, The acquisition of images captured by an infrastructure camera installed on the exterior of the vehicle and used to photograph the conditions of the predetermined area, Based on the image captured by the infrastructure camera, it is determined whether or not a target exists in the determination area. If the target is present in the determination area, the vehicle shall be decelerated. Includes, The determination region includes a first determination region and a second determination region surrounding the first determination region. Decelerating the aforementioned vehicle is If the target exists in the first determination area, stop control is performed to decelerate and stop the vehicle. If the target is present in the second determination area, the vehicle will be decelerated more gradually than in the case of the stop control. including Vehicle control method.

Images