Vehicle Control Systems

Abstract

To appropriately avoid a risk while taking also sense of an operator into consideration, in the middle of automatic operation of a vehicle.SOLUTION: A vehicle control system executes automatic operation control of controlling automatic operation of a vehicle. The automatic operation control includes risk avoidance control of avoiding a collision with a target around the vehicle. When receiving a notification that shows a risk level around the vehicle in the middle of the automatic operation control, the vehicle control system relaxes a condition for starting the risk avoidance control or increases a control amount in the risk avoidance control, as the risk level rises.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present disclosure relates to an automatic driving technology for a vehicle. [Background technology]

[0002] Patent Document 1 discloses an autonomous vehicle. The autonomous vehicle is provided with a touch panel for an operator to operate. When the operator presses a speed change button during autonomous driving, the autonomous vehicle changes the speed accordingly and continues autonomous driving. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-008160 Summary of the Invention [Problem to be solved by the invention]

[0004] According to the technology described in Patent Document 1, the speed of the vehicle is changed according to the operation of the operator during automatic driving of the vehicle. However, this alone may not be enough to ensure a proper safety margin between the vehicle and surrounding obstacles.

[0005] One objective of the present disclosure is to provide a technology that can appropriately avoid risks while taking into account the operator's senses during automatic driving of a vehicle. [Means for solving the problem]

[0006] The first aspect relates to a vehicle control system. The vehicle control system includes one or more processors that execute automatic driving control for controlling automatic driving of the vehicle. The autonomous driving control includes risk avoidance control to avoid collisions with objects around the vehicle. When a notification is received from the operator during autonomous driving control indicating the risk level around the vehicle, the one or more processors relax the operating conditions of the risk avoidance control or increase the amount of control in the risk avoidance control as the risk level increases.

[0007] The second aspect includes the first aspect, further including the following features. Autonomous driving control is Calculating a probability density distribution of a future position of the target by predicting the motion of the target around the vehicle; determining a collision probability between the vehicle and the target based on the probability density distribution; Activating risk avoidance control according to the possibility of collision; Includes. The one or more processors increase the variance of the probability density distribution as the risk level increases, thereby relaxing the operating conditions of the risk aversion control or increasing the amount of control in the risk aversion control.

[0008] The third aspect includes the first aspect, further including the following features. Autonomous driving control involves generating a target route for a vehicle and controlling the vehicle to follow the target route. The one or more processors generate a target path in risk avoidance control such that the lateral distance to the target increases as the risk level increases, thereby increasing the control amount in the risk avoidance control.

[0009] A fourth aspect of the present invention is any one of the first to third aspects, further including the following features. The one or more processors may further comprise: Generate a deceleration plan in which the deceleration rate increases as the risk level increases; comparing a risk avoidance speed plan, which is a speed plan for risk avoidance control, with a deceleration plan, and selecting one of the risk avoidance speed plan and the deceleration plan that results in a lower vehicle speed; The speed of the vehicle is controlled according to the selected one.

[0010] A fifth aspect of the present invention is any one of the first to third aspects, further including the following features. The one or more processors may further comprise: The number of button presses or the duration of button presses by the operator are received as a notification representing the risk level, The risk level is set higher as the number of times or duration of button presses increases. Effect of the Invention

[0011] According to the present disclosure, a notification indicating a risk level around the vehicle may be input by an operator during automatic driving control. In this case, as the risk level increases, risk avoidance control becomes more likely to be activated, or the control amount in risk avoidance control increases. Therefore, it becomes possible to appropriately avoid risk while taking into account the operator's sense. [Brief description of the drawings]

[0012] [Figure 1] 1 is a block diagram showing an example of the configuration of a vehicle control system according to an embodiment; [Diagram 2] FIG. 1 is a conceptual diagram for explaining risk avoidance control according to an embodiment. [Diagram 3] 2 is a block diagram showing an example of a functional configuration related to risk avoidance control according to an embodiment. FIG. [Figure 4] 10 is a conceptual diagram for explaining an example of a target position prediction process taking into account a risk level according to an embodiment. FIG. [Diagram 5] 11 is a conceptual diagram for explaining an example of a route generation process taking into account a replay level in the embodiment. FIG. [Figure 6] 11 is a conceptual diagram for explaining an example of a speed planning process taking into account a risk level according to an embodiment. FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] Embodiments of the present disclosure will be described with reference to the accompanying drawings.

[0014] 1. Vehicle Control System 1 is a conceptual diagram for explaining an overview of a vehicle control system 10 according to the present embodiment. The vehicle control system 10 controls a vehicle 1. Typically, the vehicle control system 10 is mounted on the vehicle 1. Alternatively, at least a part of the vehicle control system 10 may be disposed in an external device and control the vehicle 1 remotely.

[0015] The vehicle control system 10 includes a group of sensors mounted on the vehicle 1. The group of sensors includes a recognition sensor 20, a vehicle state sensor 30, and a position sensor 40. The recognition sensor 20 recognizes (detects) the surrounding situation of the vehicle 1. Examples of the recognition sensor 20 include a camera, a LIDAR (Laser Imaging Detection and Ranging), a radar, and the like. The vehicle state sensor 30 detects the state of the vehicle 1. For example, the vehicle state sensor 30 includes a speed sensor, an acceleration sensor, a yaw rate sensor, a steering angle sensor, and the like. The position sensor 40 detects the position and orientation of the vehicle 1. For example, the position sensor 40 includes a GNSS (Global Navigation Satellite System).

[0016] The vehicle control system 10 includes a traveling device 50. The traveling device 50 includes a steering device, a drive device, and a braking device. The steering device steers the wheels. For example, the steering device includes an electric power steering (EPS) device. The drive device is a power source that generates a driving force. Examples of the drive device include an engine, an electric motor, and an in-wheel motor. The braking device generates a braking force.

[0017] The vehicle control system 10 includes an HMI (Human Machine Interface) 60. The HMI 60 is an interface for receiving input from an operator O of the vehicle 1 and presenting various information to the vehicle 1. Typically, the operator O is in the vehicle 1. As another example, the operator O may be a remote operator who provides remote support (remote monitoring, remote assistance, remote driving) for the vehicle 1. The HMI 60 includes an input device and an output device. Examples of the input device include a touch panel, a button, a keyboard, and the like. Examples of the output device include a touch panel, a display, a speaker, and the like.

[0018] The vehicle control system 10 further includes a control device 100. The control device 100 is a computer that controls the vehicle 1. The control device 100 includes one or more processors 101 (hereinafter simply referred to as the processor 101) and one or more storage devices 102 (hereinafter simply referred to as the storage device 102). The processor 101 executes various processes. For example, the processor 101 includes a CPU (Central Processing Unit). The storage device 102 stores various information. Examples of the storage device 102 include a volatile memory, a non-volatile memory, a HDD (Hard Disk Drive), an SSD (Solid State Drive), and the like.

[0019] The vehicle control program 103 is a computer program for controlling the vehicle 1. The processor 101 executes the vehicle control program 103 to realize the functions of the control device 100. The vehicle control program 103 is stored in the storage device 102. Alternatively, the vehicle control program 103 may be recorded in a computer-readable recording medium.

[0020] The control device 100 acquires driving environment information 200 indicating the driving environment of the vehicle 1. The driving environment information 200 is stored in the storage device 102. The driving environment information 200 includes map information, surrounding situation information, vehicle state information, vehicle position information, and the like.

[0021] The map information includes a general navigation map, and may indicate lane layouts and road shapes.

[0022] The surrounding situation information is information obtained based on the recognition sensor 20, and indicates the situation around the vehicle 1. For example, the surrounding situation information includes an image captured by a camera. As another example, the surrounding situation information may include point cloud information obtained by a LIDAR. Furthermore, the surrounding situation information includes target information regarding targets (objects) around the vehicle 1. Examples of targets (objects) around the vehicle 1 include pedestrians, other vehicles, obstacles, etc. The target information indicates the relative position and relative speed of the target with respect to the vehicle 1. For example, by analyzing an image obtained by a camera, it is possible to identify the target and calculate the relative position of the target. In addition, it is also possible to identify the target and obtain the relative position and relative speed of the target based on the point cloud information obtained by a LIDAR.

[0023] The vehicle state information is information detected by the vehicle state sensor 30, and indicates the traveling state of the vehicle 1. The traveling state of the vehicle 1 includes the vehicle speed, steering angle, acceleration, yaw rate, and the like.

[0024] The vehicle position information is information detected by the position sensor 40, and indicates the position of the vehicle 1. Furthermore, the control device 100 may acquire highly accurate vehicle position information by a well-known self-position estimation process (Localization) using map information and target information.

[0025] The control device 100 also executes vehicle driving control for controlling the driving of the vehicle 1. The vehicle driving control includes steering control, acceleration control, and deceleration control. The control device 100 executes the vehicle driving control by controlling the driving device 50 (steering device, driving device, braking device).

[0026] Furthermore, the control device 100 performs automatic driving control for controlling automatic driving of the vehicle 1. Here, automatic driving means that the steering, acceleration, and deceleration of the vehicle 1 are performed automatically independent of the driver's operation. For example, automatic driving is assumed to be performed under the premise that the driver does not necessarily have to concentrate 100% on driving (so-called automatic driving of level 3 or higher). The control device 100 generates a driving plan for the vehicle 1 based on the driving environment information 200. Examples of the driving plan include maintaining the current driving lane, changing lanes, turning right or left, avoiding obstacles, and the like. Furthermore, the control device 100 generates a target trajectory required for the vehicle 1 to drive according to the driving plan based on the driving environment information 200. The target trajectory includes a target position and a target speed. Then, the control device 100 performs vehicle driving control so that the vehicle 1 follows the target trajectory. More specifically, the control device 100 calculates a control amount required for the vehicle 1 to follow the target trajectory TR. Then, the vehicle driving control unit 150 controls the driving device 50 according to the control amount.

[0027] 2.Risk avoidance control FIG. 2 is a conceptual diagram for explaining the "risk avoidance control" according to this embodiment. The risk avoidance control is a control for avoiding a collision with a target T around the vehicle 1, and is included in the automatic driving control. Examples of the target T around the vehicle 1 include a pedestrian, another vehicle, and the like. The control device 100 performs at least one of steering and deceleration to avoid a collision with the target T. More specifically, the control device 100 generates a target trajectory TR for avoiding a collision with the target T, that is, a target trajectory TR for risk avoidance control. The target trajectory TR includes a target position and a target speed. Then, the control device 100 performs vehicle travel control so that the vehicle 1 follows the target trajectory TR.

[0028] 3 is a block diagram showing an example of a functional configuration related to risk avoidance control. The control device 100 includes, as functional blocks, a target detection unit 110, a target position prediction unit 120, a route generation unit 130, a speed planning unit 140, a vehicle driving control unit 150, and a risk notification acquisition unit 160. These functional blocks are realized, for example, by cooperation between a processor 101 that executes a vehicle control program 103 and a storage device 102.

[0029] The target detection unit 110 detects targets T around the vehicle 1 based on the recognition sensor 20, and acquires the above-mentioned target information. The target information indicates the relative position and relative speed of the target T with respect to the vehicle 1.

[0030] The target position prediction unit 120 predicts the movement (behavior) of the target T detected by the target detection unit 110. A well-known movement prediction model is used to predict the movement of the target T. The target position prediction unit 120 calculates the future position of the target T by predicting the movement of the target T. As shown in FIG. 2, the future position of the target T is given as a probability density distribution.

[0031] The route generating unit 130 determines the possibility of collision between the vehicle 1 and the target T. More specifically, the route generating unit 130 calculates a predicted trajectory of the vehicle 1 based on the current position and speed of the vehicle 1. The current position and speed of the vehicle 1 are obtained from the vehicle position information and the vehicle state information, respectively. Furthermore, the route generating unit 130 determines the possibility of collision (degree of interference) between the vehicle 1 and the target T based on the probability density distribution of the predicted trajectory of the vehicle 1 and the future position of the target T. If the possibility of collision exceeds a threshold, the route generating unit 130 determines that risk avoidance control is necessary. If it is determined that risk avoidance control is necessary, the route generating unit 130 determines a target route for risk avoidance control taking into account the possibility of collision. For example, the route generating unit 130 generates a plurality of target route candidates, and then selects one of the plurality of target route candidates as a target route taking into account the possibility of collision.

[0032] The speed planning unit 140 determines a speed plan required to avoid a collision between the vehicle 1 and the target T, based on the collision possibility (degree of interference) and the target route. For example, the speed planning unit 140 sets a higher deceleration as the collision possibility increases.

[0033] The combination of the target route and the speed plan thus determined corresponds to the target trajectory TR. The vehicle driving control unit 150 performs vehicle driving control so that the vehicle 1 follows the target trajectory TR.

[0034] 3.Autonomous Driving Control Taking into Account Risk Notifications from Operators 3-1. Overview During the automatic driving control, there may be a case where the operator O of the vehicle 1 notices a risk around the vehicle 1 separately from the vehicle control system 10. For example, the operator O may notice that the preceding vehicle is decelerating before the vehicle control system 10. As another example, the operator O may predict that a target T may appear from a blind spot in front of the vehicle 1. In other words, the risk that the operator O notices may be an actual risk or a potential risk. The operator O may perceive (recognize), predict, or vaguely feel the risk around the vehicle 1. The operator O's perception, prediction, feeling, opinion, etc. regarding such risks are collectively referred to as the "operator O's sense regarding risks."

[0035] If the operator O's sense of risk around the vehicle 1 can be notified (transmitted) to the vehicle control system 10, the vehicle control system 10 can execute automatic driving control taking it into consideration, which is useful. Therefore, the vehicle control system 10 according to the present embodiment is configured to be able to receive information regarding risk notified by the operator O. The configuration for this purpose is the risk notification acquisition unit 160 shown in FIG. 3.

[0036] The risk notification acquisition unit 160 receives a risk notification INF from the operator O via the HMI 60. The risk notification INF is information that indicates a risk level RL (degree of risk) around the vehicle 1. The risk level RL is based on the operator O's perception.

[0037] For example, the HMI 60 includes a button to be pressed by the operator O. When the operator O notices a risk during automatic driving control, the operator O presses the button. If the operator O feels that the risk level RL is high, the operator O may press the button repeatedly or for a long time. In other words, the risk level RL is proportional to the number of times the button is pressed or the time the button is pressed. If the button is not pressed by the operator O, there is no risk that the operator O notices, and the risk level RL is zero. The risk notification acquisition unit 160 receives information on the number of times the button is pressed or the time the button is pressed, which is included in the HMI 60, as a risk notification INF. Then, the risk notification acquisition unit 160 sets the risk level RL higher as the number of times the button is pressed or the time the button is pressed increases.

[0038] It should be noted that the risk notification INF does not include an explicit instruction to slow down or stop by the operator O. The risk notification INF merely represents the risk level RL based on the operator O's perception.

[0039] In this way, the control device 100 receives the risk notification INF from the operator O and obtains the risk level RL represented by the risk notification INF. Even after receiving the risk notification INF from the operator O, the control device 100 continues the automatic driving control without terminating it. However, the control device 100 performs the automatic driving control (particularly the risk avoidance control) taking into account the risk level RL based on the feeling of the operator O. More specifically, the control device 100 relaxes the operating conditions of the risk avoidance control or increases the control amount in the risk avoidance control as the risk level RL increases. Relaxing the operating conditions of the risk avoidance control means making it easier to operate the risk avoidance control. Examples of the control amount in the risk avoidance control include deceleration, steering amount, etc. As the control amount in the risk avoidance control increases, the avoidance action for the vehicle 1 to avoid the risk becomes greater. A specific example of the risk avoidance control taking into account the risk level RL will be described later.

[0040] As described above, according to this embodiment, the risk notification INF indicating the risk level RL of the surroundings of the vehicle 1 can be input by the operator O during the automatic driving control. In this case, as the risk level RL increases, the risk avoidance control becomes more likely to operate, or the control amount in the risk avoidance control increases. Therefore, it becomes possible to appropriately avoid risk while also taking into account the sense of the operator O.

[0041] As a comparative example, consider a case where the operator O gives an explicit instruction to decelerate or stop the vehicle control system 10. In this case, the vehicle control system 10 decelerates or stops the vehicle 1 according to the instruction from the operator O. However, in this case, the operator O cannot properly grasp or control the distance between the vehicle 1 and the obstacle. Therefore, in the comparative example, there is a possibility that a safety margin between the vehicle 1 and the surrounding obstacles cannot be properly secured.

[0042] On the other hand, according to this embodiment, the operator O notifies the vehicle control system 10 of a risk level RL based on his / her own perception. The vehicle control system 10 executes risk avoidance control at its own discretion while taking into account the risk level RL based on the perception of the operator O. Therefore, it becomes possible to appropriately ensure a safety margin between the vehicle 1 and an obstacle.

[0043] A specific example of risk avoidance control taking into account the risk level RL will be described below.

[0044] 3-2. Target position prediction processing considering risk level 3, the risk notification acquisition unit 160 notifies the risk level RL to the target position prediction unit 120. The target position prediction unit 120 performs target position prediction processing taking into account the risk level RL.

[0045] 4 is a conceptual diagram for explaining an example of a target position prediction process taking into account a risk level RL. In this example, the risk level RL is represented by the number of times N that an operator O presses a button. As described above, the target position prediction unit 120 calculates a probability density distribution of the future position of the target T by predicting the movement (behavior) of the target T. At this time, the target position prediction unit 120 increases the variance σ of the probability density distribution as the risk level RL increases. In other words, the target position prediction unit 120 expands the probability density distribution as the risk level RL increases.

[0046] For example, the motion prediction model used to predict the motion of the target T includes constraint parameters such as the upper limit speed, upper limit acceleration, and upper limit yaw rate of the target T. The target position prediction unit 120 increases the constraint parameters as the risk level RL increases, thereby increasing the variance σ of the probability density distribution. For example, when N=0, the constraint parameters are set to a default value P0. When N>1, the control parameters are set to N×coefficient α×default value P0.

[0047] As shown in Fig. 4, as the probability density distribution of the future position of the target T expands, the possibility of collision (degree of interference) between the vehicle 1 and the target T increases. As a result, the risk avoidance control that operates according to the possibility of collision becomes easier to operate. In addition, the control amount (e.g., deceleration, steering amount) in the risk avoidance control calculated according to the possibility of collision increases.

[0048] 3-3. Route generation process considering risk level 3, the risk notification acquisition unit 160 notifies the risk level RL to the route generation unit 130. The route generation unit 130 performs route generation processing taking into account the risk level RL.

[0049] 5 is a conceptual diagram for explaining an example of a route generation process that takes into account a risk level RL. In this example, the risk level RL is also represented by the number of times N that an operator O presses a button. As described above, the route generation unit 130 generates a target route for risk avoidance control. At this time, the route generation unit 130 generates the target route such that the lateral distance (distance in the Y direction) to the target T increases as the risk level RL increases.

[0050] In the example shown in FIG. 5, the path Pa is a reference path. For example, the reference path Pa is set to follow the center of the lane. When N=1, the path generating unit 130 sets the reference path Pa as a target path. When N=2, the path generating unit 130 generates path candidates Pb and Pc by offsetting the reference path Pa in the left-right direction. Furthermore, the path generating unit 130 calculates a collision probability for each of the path candidates Pb and Pc based on the probability density distribution of the path candidates Pb and Pc and the future position of the target T. Then, the path generating unit 130 selects the path candidate with a lower collision probability (Pc in the example shown in FIG. 5(A)) as the target path. When N=3, the path generating unit 130 generates path candidates Pd and Pe by offsetting the reference path Pa in the left-right direction. The offset amount when N=3 is larger than the offset amount when N=2. Then, the route generating unit 130 selects the route candidate with the lower collision probability (Pe in the example shown in FIG. 5A) as the target route. In this manner, the target route is generated so that the lateral distance to the target T increases as the risk level RL increases.

[0051] 5B shows a case where the collision possibility does not change even if the offset amount is changed. In this case, the reference path Pa is set as the target path.

[0052] As described above, the target route is generated so that the lateral distance to the target T increases as the risk level RL increases. Therefore, the amount of control (steering amount) required to follow the target route increases as the risk level RL increases.

[0053] 3-4. Speed ​​planning process considering risk level 3, the risk notification acquisition unit 160 notifies the risk level RL to the speed planning unit 140. The speed planning unit 140 performs speed planning processing taking into account the risk level RL.

[0054] FIG. 6 is a conceptual diagram for explaining an example of a speed planning process taking into account a risk level RL. In this example, the risk level RL is also represented by the number of times N that the operator O presses a button. FIG. 6 shows a speed plan for the vehicle 1. The vertical axis represents the speed V of the vehicle 1, and the horizontal axis represents time. The speed planning unit 140 generates a "deceleration plan" in which the deceleration increases as the risk level RL increases. When the target T is not detected by the vehicle control system 10, the control device 100 performs vehicle travel control according to this deceleration plan. That is, deceleration control is performed based on the feeling of the operator O.

[0055] On the other hand, when the target T is detected by the vehicle control system 10, the above-mentioned path generation unit 130 generates a target path for risk avoidance control. The speed planning unit 140 determines a speed plan required to avoid a collision between the vehicle 1 and the target T based on the collision possibility (degree of interference) and the target path. Such a speed plan for risk avoidance control is hereinafter referred to as a "risk avoidance speed plan." The speed planning unit 140 compares the risk avoidance speed plan with the above-mentioned deceleration plan, and selects one of the risk avoidance speed plan and the deceleration plan that lowers the speed V of the vehicle 1. Then, the control device 100 performs vehicle travel control according to the selected one of the speed plans. In this way, as the risk level RL increases, the control amount (deceleration) in the risk avoidance control increases.

[0056] 3-5.Other A combination of the processes described in the above sections 3-2 to 3-4 is also possible. Alternatively, only one of the processes described in the above sections 3-2 to 3-4 may be performed. In other words, the risk notification acquisition unit 160 only needs to notify at least one of the target position prediction unit 120, the route generation unit 130, and the speed planning unit 140 of the risk level RL. At least an effect can be obtained if at least one of the target position prediction unit 120, the route generation unit 130, and the speed planning unit 140 performs a process taking into account the risk level RL.

[0057] 4.Effects As described above, according to this embodiment, the risk notification INF indicating the risk level RL of the surroundings of the vehicle 1 can be input by the operator O during the automatic driving control. In this case, as the risk level RL increases, the risk avoidance control becomes more likely to operate, or the control amount in the risk avoidance control increases. Therefore, it becomes possible to appropriately avoid risk while also taking into account the sense of the operator O.

[0058] The technology according to the present embodiment may be applied to Level 2+ operation for development, verification, and evaluation of Level 4 autonomous driving. In Level 2+ operation, autonomous driving control is performed based on the Level 4 autonomous driving system with a safety monitoring operator disposed in the vehicle 1. If the safety monitoring operator notices a risk before the autonomous driving system does, he or she may intervene in the autonomous driving. For example, if there is a delay in the recognition or deceleration by the autonomous driving system, the safety monitoring operator may intervene in the autonomous driving at his or her own discretion. However, if the safety monitoring operator intervenes every time even for a low-risk event, it is not possible to verify or evaluate whether the autonomous driving system is truly capable of dealing with the event. In such a case, if the safety monitoring operator inputs a risk notification INF, the autonomous driving system can carefully continue the autonomous driving control without terminating it. This makes it possible to verify and evaluate the autonomous driving system. That is, the efficiency of verifying and evaluating the autonomous driving system is improved. [Explanation of symbols]

[0059] 1...vehicle, 10...vehicle control system, 60...HMI, 100...control device, 110...target detection unit, 120...target position prediction unit, 130...route generation unit, 140...speed planning unit, 150...vehicle driving control unit, INF...risk notification, O...operator, RL...risk level

Claims

1. The vehicle control system includes one or more processors that execute automatic driving control to control automatic driving of the vehicle. The autonomous driving control includes a risk avoidance control for avoiding a collision with a target around the vehicle, When a notification indicating a risk level around the vehicle is received from an operator during the automatic driving control, the one or more processors relax the operating conditions of the risk avoidance control or increase the control amount in the risk avoidance control as the risk level increases; The automatic driving control is calculating a probability density distribution of a future position of the target by predicting a motion of the target around the vehicle; determining a possibility of a collision between the vehicle and the target based on the probability density distribution; activating the risk avoidance control in response to the collision possibility; Including, The one or more processors increase the variance of the probability density distribution as the risk level increases, thereby relaxing the operating condition of the risk aversion control or increasing the control amount in the risk aversion control. Vehicle control system.

2. The vehicle control system includes one or more processors that execute automatic driving control to control automatic driving of the vehicle. The autonomous driving control includes a risk avoidance control for avoiding a collision with a target around the vehicle, When a notification indicating a risk level around the vehicle is received from an operator during the automatic driving control, the one or more processors relax the operating conditions of the risk avoidance control or increase the control amount in the risk avoidance control as the risk level increases; The autonomous driving control includes generating a target route for the vehicle and controlling the vehicle to follow the target route; The one or more processors generate the target path in the risk avoidance control such that a lateral distance to the target increases as the risk level increases, thereby increasing the control amount in the risk avoidance control. Vehicle control system.

3. 3. A vehicle control system according to claim 1, The one or more processors further include: When the target is detected around the vehicle, a default speed plan for the risk avoidance control is generated as a risk avoidance speed plan; generating a deceleration plan in which the deceleration rate increases as the risk level increases; comparing the risk avoidance speed plan and the deceleration plan, and selecting one of the risk avoidance speed plan and the deceleration plan that results in a lower speed of the vehicle as a speed plan in the risk avoidance control; Controlling the speed of the vehicle in accordance with the selected one. Vehicle control system.

4. 3. A vehicle control system according to claim 1, The one or more processors further include: receiving the notification representing the risk level in the form of the number of button presses or the duration of button presses by the operator; The risk level is set higher as the number of times or the duration of pressing the button increases. Vehicle control system.

Images