Automated driving system and control method for automated driving system

Abstract

To present a travel state change factor and the change in the travel state to a user at the time of decision of the change of the travel state of automated driving control using a machine learning model.SOLUTION: An automated driving system for deciding to change a travel state of an own vehicle using a machine learning model in an automated driving control for the own vehicle includes: an automated driving control unit configured to decide to change the travel state of the own vehicle using the machine learning model on the basis of a preset target route and position information of the own vehicle and map information, or a detection result of an external sensor of the own vehicle; and an information presentation unit configured to present a travel state change factor, which is a main cause of the change in the travel state, and the change in the travel state of the own vehicle to a user of the own vehicle when the automated driving control unit decides to change the travel state of the own vehicle.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to an automated driving system and a control method for an automated driving system. [Background technology]

[0002] Japanese Patent Application Laid-Open Publication No. 2017-166913 is known as a technical document related to an autonomous driving system. This publication describes a vehicle equipped with an autonomous driving function that generates an overhead view displayed on a display screen installed in the vehicle cabin and notifies the driver by displaying a planned trajectory line indicating the future behavior of the vehicle when a lane change event occurs. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2017-166913 A Summary of the Invention [Problem to be solved by the invention]

[0004] The use of machine learning models to control vehicle driving by autonomous driving systems is being considered. However, machine learning models are not necessarily able to make appropriate decisions in all driving situations. For this reason, users are required to properly understand information about the reasons for the machine learning model's decisions. [Means for solving the problem]

[0005] One aspect of the present invention is an autonomous driving system that determines changes in the driving state of a host vehicle using a machine learning model in autonomous driving control of the host vehicle, and includes: an autonomous driving control unit that determines changes in the driving state of the host vehicle using a machine learning model based on a predetermined target route of the host vehicle and position information and map information of the host vehicle, or detection results from an external sensor of the host vehicle; and an information presentation unit that, when a change in the driving state of the host vehicle is determined by the autonomous driving control unit, presents to a user of the host vehicle driving state change factors that are the main causes of the change in the driving state and the change in the driving state of the host vehicle.

[0006] According to an autonomous driving system according to one embodiment of the present invention, when a change in driving state of autonomous driving control is determined by a machine learning model, the factors that cause the change in the driving state and the change in the driving state can be presented to the user.

[0007] In an autonomous driving system according to one embodiment of the present invention, a driving condition change factor may include the approach of another vehicle traveling in an adjacent lane in front of the vehicle toward the vehicle's own lane, and the change in driving condition may include changing the vehicle's driving position within the vehicle's own lane to a position away from the adjacent lane. According to this autonomous driving system, when a vehicle in an adjacent lane moves toward the vehicle and the machine learning model changes the vehicle's driving position within the vehicle's lane to a position away from the adjacent lane, the system can inform the user that a vehicle in the adjacent lane is moving toward the vehicle and of the change in the vehicle's driving position.

[0008] In an autonomous driving system according to one aspect of the present invention, the information presentation unit may adjust the amount of information presented to a user based on the usage history of the autonomous driving system of the host vehicle. With this autonomous driving system, the presentation of driving condition change factors can be annoying for accustomed users, so by adjusting the amount of information presented to the user based on the usage history of the autonomous driving system of the vehicle, it is possible to prevent the user from feeling annoyed by the presentation.

[0009] In an autonomous driving system according to one aspect of the present invention, the autonomous driving system further includes a feedback receiving unit that receives user feedback in response to the presentation to the user of driving condition change factors and changes in the driving condition of the vehicle by the information presentation unit, and the autonomous driving control unit may adjust the timing of the change in the driving condition of the vehicle or the control amount of the change in the driving condition of the vehicle based on the results of the feedback. According to this autonomous driving system, the timing of changes in the vehicle's driving conditions or the control amount of changes in the vehicle's driving conditions can be adjusted based on feedback from the user, thereby enabling autonomous driving control to be tailored to the user's sensibilities.

[0010] Another aspect of the present invention is a control method for an autonomous driving system that determines a change in the driving state of a host vehicle using a machine learning model in the autonomous driving control of the host vehicle, and determines a change in the driving state of the host vehicle using a machine learning model based on a predetermined target route of the host vehicle and position information and map information of the host vehicle, or detection results of an external sensor of the host vehicle, and when a change in the driving state of the host vehicle is determined, presents a driving state change factor that is the main cause of the change in the driving state and the change in the driving state of the host vehicle to a user of the host vehicle.

[0011] According to another aspect of the control method for an autonomous driving system of the present invention, when a change in the driving state of autonomous driving control is determined by a machine learning model, the factors that cause the change in the driving state and the change in the driving state can be presented to the user. Effect of the Invention

[0012] According to each aspect of the present invention, when a change in driving conditions in autonomous driving control is determined by a machine learning model, the factors that cause the change in the driving conditions and the change in the driving conditions can be presented to the user. [Brief description of the drawings]

[0013] [Figure 1] FIG. 1 is a block diagram showing an autonomous driving system according to an embodiment. [Diagram 2]13A and 13B are diagrams illustrating an example of information presentation when a decision is made to accelerate the host vehicle. [Diagram 3] 13A and 13B are diagrams illustrating an example of information presented when a decision has been made to ensure a lateral distance from an adjacent vehicle. [Figure 4] FIG. 13 is a diagram showing an example of a feedback option display. [Diagram 5] 13 is a flowchart illustrating an example of an information presentation process. [Figure 6] 13 is a flowchart illustrating an example of a feedback process. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0015] FIG. 1 is a block diagram showing an autonomous driving system 100 according to an embodiment. The autonomous driving system 100 shown in FIG. 1 is mounted on a vehicle such as a passenger car or a freight vehicle, and executes autonomous driving control of the vehicle. Hereinafter, a vehicle equipped with the autonomous driving system 100 is referred to as a host vehicle. Note that some functions of the autonomous driving system 100 may be executed on a server capable of communicating with the host vehicle.

[0016] Autonomous driving control is vehicle control that automatically drives a vehicle along the road on which the vehicle is traveling without the driver performing any driving operation. The autonomous driving system 100 starts autonomous driving control of the vehicle when a user, such as the driver of the vehicle, performs an operation to start autonomous driving control (for example, pressing a button to start autonomous driving control). The vehicle may be an autonomous vehicle that does not require a driver. In that case, the user becomes a passenger of the vehicle.

[0017] In the autonomous driving system 100, autonomous driving control is performed using a machine learning model. In the autonomous driving system 100, a machine learning model is used for at least one of recognizing the external environment, generating a driving plan for autonomous driving control (including generating a trajectory along which the host vehicle will travel), and generating instructions for autonomous driving control. The machine learning model will be described in detail later. The autonomous driving system 100 presents information to the user regarding changes in the driving state of the host vehicle determined by the machine learning model.

[0018] [Autonomous Driving System Configuration] Hereinafter, the configuration of an autonomous driving system 100 according to this embodiment will be described with reference to Fig. 1. As shown in Fig. 1, the autonomous driving system 100 includes an autonomous driving ECU [Electronic Control Unit] 10 that performs overall management of the devices.

[0019] The autonomous driving ECU 10 is an electronic control unit having a central processing unit (CPU) and a storage unit. The storage unit is composed of, for example, a read-only memory (ROM), a random access memory (RAM), and an electrically erasable programmable read-only memory (EEPROM). In the autonomous driving ECU 10, for example, various functions are realized by the CPU executing a program stored in the storage unit. The autonomous driving ECU 10 may be composed of multiple electronic units.

[0020] The autonomous driving ECU 10 is connected to a GNSS receiver 1, an external sensor 2, an internal sensor 3, a map database 4, a usage history database 5, an actuator 6, and an HMI [Human Machine Interface] 7.

[0021] The GNSS receiver 1 measures the position of the vehicle (for example, the latitude and longitude of the vehicle) by receiving signals from positioning satellites. The GNSS receiver 1 transmits the measured position information of the vehicle to the autonomous driving ECU 10.

[0022] The external sensor 2 is a detection device that detects the situation around the vehicle. The external sensor 2 includes at least one of a camera and a radar sensor. The camera is an imaging device that captures the external situation of the vehicle. The camera is provided, for example, on the back side of the windshield of the vehicle and captures the image in front of the vehicle. The camera transmits the captured image related to the external situation of the vehicle to the autonomous driving ECU 10. The radar sensor is a detection device that detects objects around the vehicle using radio waves (for example, millimeter waves) or light. The radar sensor includes, for example, millimeter wave radar or LIDAR (Light Detection and Ranging). The radar sensor transmits information on the detected objects to the autonomous driving ECU 10.

[0023] The internal sensor 3 is a detection device that detects the driving state of the host vehicle. The internal sensor 3 includes a vehicle speed sensor and a yaw rate sensor. The vehicle speed sensor is a detector that detects the speed of the host vehicle. The vehicle speed sensor transmits the detected vehicle speed information (wheel speed information) to the autonomous driving ECU 10.

[0024] The yaw rate sensor is a detector that detects the yaw rate (rotational angular velocity) around the vertical axis of the center of gravity of the vehicle. For example, a gyro sensor can be used as the yaw rate sensor. The yaw rate sensor transmits the detected yaw rate information of the vehicle to the automatic driving ECU 10.

[0025] The map database 4 is a database that stores map information. The map database 4 is formed, for example, in a storage device such as a HDD (Hard Disk Drive) mounted on the vehicle. The map information includes road position information, road shape information (for example, curves, types of straight sections, curvature of curves, etc.), intersection and branch point position information, and structure position information. The map database 4 may be formed in a server that can communicate with the vehicle. Furthermore, it is not necessarily necessary to use map information in the autonomous driving control.

[0026] The usage history database 5 is a database in which the usage history of the autonomous driving control of the vehicle is recorded. The usage history database 5 records the time period during which the autonomous driving control of the vehicle was executed. If the vehicle is equipped with a personal authentication function for the user, the usage history database 5 may record the usage history of the autonomous driving control for each user separately.

[0027] The actuator 6 is a device used to control the host vehicle. The actuator 6 includes at least a drive actuator, a brake actuator, and a steering actuator. The drive actuator controls the amount of air supplied to the engine (throttle opening) in response to a control signal from the automatic driving ECU 10, thereby controlling the driving force of the host vehicle. If the host vehicle is a hybrid vehicle [HEV: Hybrid Electric Vehicle], in addition to the amount of air supplied to the engine, a control signal from the automatic driving ECU 10 is input to a motor serving as a power source to control the driving force. If the host vehicle is an electric vehicle [BEV: Battery Electric Vehicle], a control signal from the automatic driving ECU 10 is input to a motor serving as a power source to control the driving force. The motor serving as a power source in these cases constitutes the actuator 6.

[0028] The brake actuator controls the brake system in response to a control signal from the autonomous driving ECU 10, and controls the braking force applied to the wheels of the host vehicle. For example, a hydraulic brake system can be used as the brake system. The steering actuator controls the drive of an assist motor that controls the steering torque of the electric power steering system in response to a control signal from the autonomous driving ECU 10. In this way, the steering actuator controls the steering torque of the host vehicle.

[0029] The HMI 7 is an interface for inputting and outputting information between the autonomous driving ECU 10 and the driver. The HMI 7 includes, for example, a display and a speaker provided in the vehicle cabin. The HMI 7 outputs images from the display and sounds from the speaker in response to a control signal from the autonomous driving ECU 10. The display may function as a touch panel. The display may be a center display, a display for navigation, or a HUD [Head Up Display]. The HUD presents information to the user by projecting an image onto the windshield of the vehicle.

[0030] Next, a description will be given of the functional configuration of the autonomous driving ECU 10. The autonomous driving ECU 10 has an external environment recognition unit 11, a driving state recognition unit 12, an autonomous driving control unit 13, an information presentation unit 14, and a feedback reception unit 15.

[0031] The external environment recognition unit 11 recognizes the external environment of the vehicle based on the detection result of the external sensor 2. The external environment includes the relative positions of surrounding objects with respect to the vehicle. The external environment may include the relative speed and movement direction of surrounding objects with respect to the vehicle. The external environment may include information on the types of objects, such as other vehicles, pedestrians, and bicycles. The external environment recognition unit 11 may recognize the external environment of the vehicle based on the detection result of the external sensor 2 using a machine learning model.

[0032] The running state recognition unit 12 recognizes the running state of the host vehicle based on the detection result of the internal sensor 3. The running state includes the speed, acceleration, and yaw rate of the host vehicle. Specifically, the running state recognition unit 12 recognizes the speed of the host vehicle based on the vehicle speed information of the vehicle speed sensor. The running state recognition unit 12 recognizes the acceleration of the host vehicle based on the vehicle speed information of the acceleration sensor. The running state recognition unit 12 recognizes the direction of the host vehicle based on the yaw rate information of the yaw rate sensor.

[0033] The autonomous driving control unit 13 executes autonomous driving control of the host vehicle based on the external environment (surrounding environment) recognized by the external environment recognition unit 11 and the traveling state of the host vehicle recognized by the traveling state recognition unit 12. The autonomous driving control unit 13 may further use the position information of the host vehicle measured by the GNSS receiving unit 1 and the map information of the map database 4 to perform autonomous driving control.

[0034] The automatic driving control unit 13 performs automatic driving control of the vehicle using the machine learning model 13a. The machine learning model 13a is, for example, a neural network such as a convolutional neural network (CNN). The neural network can include multiple layers including multiple convolution layers and pooling layers. As the neural network, a deep learning network using deep learning is used. As the machine learning model 13a, a recurrent neural network [RNN: Recurrent neural network] can be used.

[0035] The autonomous driving control unit 13 sets a target route for autonomous driving control based on, for example, a destination set by a user, position information of the vehicle, and map information. The target route is a route along which the vehicle travels under autonomous driving control. The destination may be a point automatically proposed by the autonomous driving system 100. Alternatively, the target route may be set in advance in a well-known navigation system, and may be acquired by the autonomous driving system 100 from the navigation system.

[0036] The automatic driving control unit 13 generates a driving plan for automatic driving control based on the target route, the position information of the vehicle, and the map information. The driving plan includes a vehicle speed plan and a route plan of the vehicle. The vehicle speed plan is data in which a target vehicle speed in automatic driving control is associated with a set vertical position set at a predetermined interval (for example, 1 m) on the target route. The set vertical position may be set based on the driving time of the vehicle rather than the distance. The route plan is data regarding a route [path] on the target route. The route is a trajectory along which the vehicle under automatic driving control is scheduled to travel on the target route. The route plan can be data on the steering angle or lateral position of the vehicle according to the set vertical position on the target route.

[0037] The automatic driving control unit 13 generates a driving plan using, for example, the machine learning model 13a. The automatic driving control unit 13 inputs the target route, the position information of the vehicle, and map information to cause the machine learning model 13a to output the driving plan. In this case, the machine learning model 13a may be a neural network that has been trained to output a driving plan from the target route, the position information of the vehicle, and map information. The automatic driving control unit 13 may further input the current external environment and driving state to the machine learning model 13a to re-output (correct) the driving plan. In this case, the machine learning model 13a is a neural network that has been trained to output a driving plan using the target route, the position information of the vehicle, map information, the external environment, and the driving state as inputs. The machine learning model 13a may be given the previously output driving plan as input.

[0038] The autonomous driving control unit 13 executes autonomous driving control by changing the driving state of the host vehicle by transmitting a control signal to the actuator 6 based on the current position information of the host vehicle and the driving plan. The autonomous driving control unit 13 may generate a control signal to the actuator 6 from the machine learning model 13a using the current position information of the host vehicle and the driving plan as input. In this case, the machine learning model 13a is a neural network that has been trained to generate a control signal to the actuator 6 using the current position information of the host vehicle and the driving plan as input.

[0039] The autonomous driving control unit 13 determines a change in the driving state of the host vehicle as autonomous driving control by modifying the driving plan based on the current external environment or by generating a control signal to the actuator 6. The change in the driving state is, for example, a change in the speed of the host vehicle, a change in the route of the host vehicle, etc. The change in the route of the host vehicle includes changing the driving position of the host vehicle in the host lane to a position away from an adjacent lane. A specific example will be described later. After determining the change in the driving state of the host vehicle, the autonomous driving control unit 13 executes the change in the driving state of the host vehicle as autonomous driving control by transmitting a control signal to the actuator 6.

[0040] The information presentation unit 14 presents information regarding a change in the driving state of the vehicle under automatic driving control to the user. When a change in the driving state of the vehicle is determined by the automatic driving control unit 13, the information presentation unit 14 presents to the user a driving state change factor that is the main cause of the change in the driving state and the change in the driving state of the vehicle. The driving state change factor is the main cause by which the machine learning model 13a determined the change in the driving state of the vehicle under automatic driving control.

[0041] The information presentation unit 14 presents information to the user after the change in the running state of the vehicle is determined by the automatic driving control unit 13 and before the change in the running state of the vehicle is executed. The information presentation unit 14 may present information after the change in the running state of the vehicle is executed. The user can also switch the presentation of information ON / OFF.

[0042] FIG. 2 is a diagram showing an example of information presentation when a decision is made to accelerate the vehicle. FIG. 2 shows the vehicle's own lane R1 on which the vehicle is traveling, a white line L1 on the left side of the vehicle's own lane R1, a white line L2 on the right side of the vehicle's own lane R1, an adjacent lane R2, and a white line L3 on the right side of the adjacent lane R2. The white line L2 is a boundary line between the vehicle's own lane R1 and the adjacent lane R2. FIG. 2 also shows an arrow P1 indicating that there is no preceding vehicle and that there is an open space ahead of the vehicle as a driving state change factor, and a speed change display D as a change in the vehicle's driving state (acceleration of the vehicle). The speed change display D shows in text that the vehicle's speed will be accelerated from 25 km / h to 50 km / h. The speed change display D does not need to be in text, and may be expressed as a meter display or other image.

[0043] For example, when a decision is made to accelerate the vehicle as a decision to change the driving state of the vehicle, the information presentation unit 14 presents the driving state change factor and the change in the driving state of the vehicle to the user by displaying an arrow P1 and a speed change display D as images as shown in Fig. 2. As an example, the information presentation unit 14 displays the view in front of the vehicle captured by a camera of an external sensor of the vehicle on the display of the HMI 7, and then displays the arrow P1 and the speed change display D as images. This allows the user to understand the reason for the change in the driving state in the autonomous driving control determined using the machine learning model 13a.

[0044] The information presenter 14 may present the driving condition change factors and the change in the driving condition of the vehicle to the user by projecting and displaying an arrow P1 and a speed change display D on the windshield of the vehicle using the HUD of the HMI 7.

[0045] Furthermore, the information presentation unit 14 does not necessarily need to display the scenery ahead of the vehicle on the display, and may present the driving condition change factors and the change in the driving condition of the vehicle to the user by displaying only the arrow P1 and the speed change display D. In addition to the arrow P1 and the speed change display D, the information presentation unit 14 may display lines corresponding to the white lines L1, L2 of the vehicle's lane R1 on the display, and may display icons corresponding to other vehicles around the vehicle on the display.

[0046] Fig. 3 is a diagram showing an example of information presentation when a decision is made to secure a lateral distance from an adjacent vehicle. The adjacent vehicle is another vehicle traveling in an adjacent lane of the vehicle. Fig. 3 shows an adjacent vehicle N traveling in an adjacent lane R2, an approach indication H indicating that the adjacent vehicle N is approaching the vehicle's lane R1, and an arrow P2 indicating a behavior of the vehicle moving to the left as a change in the traveling state of the vehicle in order to secure a lateral distance from the adjacent vehicle N. In Fig. 3, the adjacent vehicle N is traveling ahead of the vehicle and is approaching the vehicle's lane R1 side in order to change lanes to the vehicle's lane R1.

[0047] For example, when a decision is made to change the driving condition of the vehicle by moving the vehicle to the left in order to secure a lateral distance from an adjacent vehicle N, the information presentation unit 14 presents the cause of the change in the driving condition and the change in the driving condition of the vehicle to the user by displaying an arrow P2 and an approaching display H as images as shown in Figure 3.

[0048] Another example of a combination of a driving state change factor and a change in the driving state is deceleration of the vehicle caused by the approach of the vehicle ahead to the vehicle ahead. In this case, the information presentation unit 14 presents, for example, a short arrow indicating that the distance between the vehicle ahead and the vehicle ahead is getting shorter as a driving state change factor, and presents deceleration of the vehicle ahead as shown in the speed change display D of FIG. 2 as a change in the driving state. In this case, the color of the arrow may be red. The color of the arrow P1 in the case of accelerating the vehicle ahead may be blue. In addition, in the speed change display D in this case, for example, a text indicates that the speed of the vehicle ahead will be decelerated from 50 km / h to 25 km / h (or the same speed as the vehicle ahead). The speed change display D may be expressed as an image.

[0049] The driving condition change factor of the vehicle deceleration may include detection of a speed limit zone such as a school zone. In this case, the information presentation unit 14 may display road signs and road markings as driving condition change factors in an emphasized manner.

[0050] The information presentation unit 14 may adjust the amount of information presented to the user based on the usage history of the automatic driving control recorded in the usage history database 5. When the usage history of the automatic driving control of the vehicle is less than a certain period, the information presentation unit 14 may reduce the amount of information compared to when the usage history is equal to or longer than a certain period. Reducing the amount of information means, for example, shortening the presented time, making the displayed image smaller, making the color of the image lighter, or making the color of the image closer to black and white. Reducing the amount of information may include omitting the content of the speed change display D shown in FIG. 2 to only the text "accelerate." The information presentation unit 14 may be configured to gradually reduce the amount of information as the usage history becomes longer.

[0051] Reducing the amount of information also includes not presenting information to the user at all. For example, when the usage history of the autonomous driving control of the vehicle is less than a certain period, and the information presenting unit 14 presents information to the user when the vehicle decelerates at a red traffic light, the information presenting unit 14 may not present the information if the usage history of the autonomous driving control of the vehicle is equal to or longer than the certain period. This is because, when the driving state change factor is a red traffic light, the user can easily understand the reason for the deceleration of the vehicle.

[0052] When the information presenting unit 14 has performed personal authentication of the user, the information presenting unit 14 may determine whether the usage history of each user is for a certain period of time or more. In addition, the usage history may record the frequency or number of times that information has been presented to the user for each driving condition change factor.

[0053] If it is considered that the user fully understands the reason for the change in the driving condition of the vehicle (driving condition change factor) determined by the machine learning model 13a, the information presentation unit 14 may be configured not to present information to the user on the driving condition change factor.

[0054] For example, the information presentation unit 14 may determine that the user fully understands the driving condition change factors when the number of times information has been presented to the user for each driving condition change factor is equal to or greater than a certain value. Even when the information presentation unit 14 determines that the user fully understands the driving condition change factors, the information presentation unit 14 may resume the presentation of information based on the driving condition change factors a certain number of times when a predetermined period has elapsed since the last time information was presented to the user. The information presentation unit 14 may take into consideration the position information of the vehicle and determine that the user is familiar with the road on which the vehicle is currently traveling if the number of times the vehicle has passed through the road is equal to or greater than a certain number of times, and may not present information on repeated driving condition change factors on the road.

[0055] The information presentation unit 14 may be configured not to present information if a certain time has passed since the previous presentation of information about the same driving state change factor. The information presentation unit 14 can suppress the user from feeling annoyed by frequent presentation of information to the user due to the approach of the preceding vehicle to the own vehicle, for example, when the own vehicle is in a traffic jam.

[0056] When the usage history includes information on the location where information was presented to the user, the information presenting unit 14 may increase the amount of information when it is the first time the information is presented to the user at that location, compared to when it is not the first time. Increasing the amount of information means, for example, lengthening the presentation time, enlarging the displayed image, darkening the color of the image, or making the color of the image closer to a conspicuous color (such as red). Increasing the amount of information may include increasing the amount of text in the speed change display D shown in FIG. 2 to provide a more detailed explanation.

[0057] The information presenting unit 14 may be configured to request the user to input feedback when the information is presented to the user. Here, Fig. 4 is a diagram showing an example of feedback option display. Fig. 4 shows an Accept display T1 and a Reject display T2. The display in Fig. 4 is a touch panel. The user can provide feedback on the presented information by touching the Accept display T1 or the Reject display T2.

[0058] The information presenting unit 14 does not necessarily need to request feedback from the user every time, and does not need to request feedback when presenting information about the same driving condition change factor within a certain period of time.

[0059] The feedback receiving unit 15 receives user feedback regarding the presentation of information. The feedback may be a physical button input instead of a touch panel input as shown in Fig. 4, or may be a voice input. When the user selects Accept, the feedback receiving unit 15 maintains the current settings regarding the presentation of information.

[0060] The feedback receiving unit 15 may adjust the amount of information, etc., based on the user's feedback. When the user inputs "Reject", the feedback receiving unit 15 may display a parameter adjustment screen that allows the user to adjust whether or not to present information regarding the current driving state change factor, the timing of presenting the information, the amount of information, etc.

[0061] The feedback receiving unit 15 may adjust the timing of the change in the running state of the vehicle in the automatic driving control or the control amount of the change in the running state of the vehicle based on the user's feedback. After the information is presented and the feedback options are displayed, the feedback receiving unit 15 may adjust the timing of the change in the running state of the vehicle based on the relationship between the timing when the running state of the vehicle actually changes and the timing when the user inputs the feedback "Reject."

[0062] For example, when the timing at which the user inputs the Reject feedback is earlier than the timing at which the vehicle changes its driving state by a certain time or more, the feedback receiving unit 15 adjusts the timing of the change in the driving state of the vehicle due to the current driving state change factor to be earlier. When the timing at which the user inputs the Reject feedback is later than the timing at which the vehicle changes its driving state by a certain time or more, the feedback receiving unit 15 adjusts the timing of the change in the driving state of the vehicle due to the current driving state change factor to be later. This allows the change in the driving state due to the automatic driving control to be adapted to the user's sense.

[0063] In addition, when the user inputs the feedback of Reject during deceleration of the host vehicle, the feedback receiving unit 15 may adjust the control amount of the automatic driving control so as to make the deceleration gentler. The same applies to the case of acceleration of the host vehicle or the case of route change (change of steering angle) of the host vehicle.

[0064] The feedback receiving unit 15 may analyze the scene based on the user's feedback, the external environment of the vehicle, and the driving state, classify the scene as related to safety / security / comfort, and may be configured to be in a mode in which the presentation of information cannot be turned off for a scene associated with safety as a risk scene. Since what is classified as security or comfort depends on the user's preference, the feedback receiving unit 15 adjusts the timing of the change in the driving state and the amount of control so that the user's Accept input increases so that the system can be tailored to the user. Note that the feedback receiving unit 15 ends the reception of feedback if the user does not input anything for a certain period of time even if feedback options are displayed.

[0065] [Control method of autonomous driving system] Next, a control method of the autonomous driving system 100 according to this embodiment will be described with reference to the drawings. Fig. 5 is a flowchart showing an example of information presentation processing. The information presentation processing is performed, for example, by the autonomous driving ECU 10 determining a change in the running state of the host vehicle that is to be a predetermined information presentation target.

[0066] 5, the autonomous driving ECU 10 of the autonomous driving system 100 determines a change in the driving state of the host vehicle by the autonomous driving control unit 13 using the machine learning model 13a as S10. The autonomous driving control unit 13 determines a change in the driving state of the host vehicle as autonomous driving control by the machine learning model 13a based on the target route, the position information of the host vehicle, and map information, or the detection result of the external sensor 2 of the host vehicle. After that, the autonomous driving ECU 10 proceeds to S11.

[0067] In S11, the autonomous driving ECU 10 adjusts the amount of information based on the user's usage history through the information presentation unit 14. The information presentation unit 14 recognizes the usage history related to the current change in the driving state based on the usage history recorded in the usage history database 5, and adjusts the amount of information presented to the user. After that, the autonomous driving ECU 10 proceeds to S12.

[0068] In S12, the autonomous driving ECU 10 presents the driving state change factors and the change in the driving state of the host vehicle through the information presentation unit 14. The information presentation unit 14 presents the driving state change factors and the change in the driving state of the host vehicle to the user, for example, as shown in Figures 2 and 3. Thereafter, the autonomous driving ECU 10 ends this information presentation process.

[0069] Fig. 6 is a flowchart showing an example of the feedback process. The feedback process is executed when information is presented in S12 of Fig. 5. Note that the feedback process may be executed only when a predetermined condition is satisfied so as not to bother the user. The predetermined condition may be, for example, that no feedback has been input for a certain period of time for the same driving state change factor.

[0070] As shown in Fig. 6, in S20, the autonomous driving ECU 10 displays feedback options using the information presenter 14. For example, the information presenter 14 displays the Accept display T1 and the Reject display T2 shown in Fig. 4. After that, the autonomous driving ECU 10 proceeds to S21.

[0071] In S21, the autonomous driving ECU 10 determines whether or not the user has input feedback via the feedback receiving unit 15. If the autonomous driving ECU 10 determines that the user has input feedback (S21: NO), the autonomous driving ECU 10 proceeds to S22. If the autonomous driving ECU 10 determines that the user has input feedback (S21: YES), the autonomous driving ECU 10 proceeds to S23.

[0072] In S22, the autonomous driving ECU 10 judges whether a certain time has passed since the feedback option was displayed. If the autonomous driving ECU 10 does not judge that the certain time has passed (S22: NO), the process returns to S21 and the judgment is repeated. If the autonomous driving ECU 10 judges that the certain time has passed (S22: YES), the autonomous driving ECU 10 ends the current feedback process.

[0073] In S23, the autonomous driving ECU 10 adjusts the amount of information, the timing of the change in the running state of the host vehicle, or the control amount of the change in the running state of the host vehicle from the user's feedback via the feedback receiving unit 15. The feedback receiving unit 15 adjusts various parameters to suit the user's senses.

[0074] According to the autonomous driving system 100 of this embodiment described above, when the machine learning model 13a determines a change in the driving state of the autonomous driving control, the factors that cause the change in the driving state and the change in the driving state can be presented to the user (see Figure 2).

[0075] In addition, according to the autonomous driving system 100, in the situation shown in Figure 3, when the adjacent vehicle N moves toward the vehicle and the machine learning model 13a changes the driving position within the vehicle's lane R1 to a position away from the adjacent lane R2, the user can be informed that the adjacent vehicle N is moving toward the vehicle's lane R1 and of the change in the vehicle's driving position.

[0076] In addition, according to the autonomous driving system 100, since the presentation of driving condition change factors may be annoying to accustomed users, the amount of information presented to the user can be adjusted based on the usage history of the autonomous driving control of the vehicle (or the usage history of autonomous driving control for each user), thereby preventing the user from feeling annoyed by the presentation.

[0077] Furthermore, according to the autonomous driving system 100, the timing of changes in the vehicle's driving state or the control amount of changes in the vehicle's driving state can be adjusted based on feedback results from the user, thereby enabling autonomous driving to be performed in accordance with the user's perceptions.

[0078] Although the embodiment of the present invention has been described above, the present invention is not limited to the above-mentioned embodiment. The present invention can be embodied in various forms including the above-mentioned embodiment and various modifications and improvements based on the knowledge of those skilled in the art.

[0079] The autonomous driving system 100 does not necessarily have to provide feedback to the user. The autonomous driving ECU 10 does not necessarily have to include a feedback receiving unit 15. The autonomous driving system 100 does not necessarily have to use the usage history of the autonomous driving control. The autonomous driving ECU 10 does not necessarily have to be connected to the usage history database 5. [Explanation of symbols]

[0080] 1...GNSS receiver unit, 2...external sensor, 3...internal sensor, 4...map database, 5...usage history database, 6...actuator, 7...HMI, 10...autonomous driving ECU, 11...external environment recognition unit, 12...driving state recognition unit, 13...autonomous driving control unit, 13a...machine learning model, 14...information presentation unit, 15...feedback reception unit, 100...autonomous driving system.

Claims

1. An autonomous driving system that determines a change in a driving state of a vehicle by using a machine learning model in autonomous driving control of the vehicle, An autonomous driving control unit that determines a change in a driving state of the vehicle using the machine learning model based on a preset target route of the vehicle, position information and map information of the vehicle, or a detection result of an external sensor of the vehicle; an information presentation unit that presents, when a change in the driving state of the vehicle is determined by the autonomous driving control unit, a driving state change factor that is a main cause of the change in the driving state of the vehicle and the change in the driving state of the vehicle to a user of the vehicle; An autonomous driving system.

2. The driving condition change factor includes an approach of another vehicle traveling in an adjacent lane in front of the host vehicle to the host vehicle's own lane side, The autonomous driving system according to claim 1 , wherein the change in the driving state includes changing a driving position of the host vehicle within the host vehicle's own lane to a position away from the adjacent lane.

3. The autonomous driving system according to claim 1 or 2, wherein the information presentation unit adjusts an amount of information presented to the user based on a usage history of the autonomous driving control of the host vehicle.

4. A feedback receiving unit that receives feedback from the user in response to the presentation to the user of a driving state change factor and a change in the driving state of the vehicle by the information presentation unit, The autonomous driving system according to claim 1 or 2, wherein the autonomous driving control unit adjusts a timing of a change in the driving state of the host vehicle or a control amount of the change in the driving state of the host vehicle based on a result of the feedback.

5. A control method for an autonomous driving system that determines a change in a driving state of a host vehicle using a machine learning model in autonomous driving control of the host vehicle, Determine a change in the running state of the host vehicle using the machine learning model based on a preset target route of the host vehicle and position information and map information of the host vehicle, or a detection result of an external sensor of the host vehicle; A control method for an autonomous driving system, which, when a change in the driving state of the vehicle is determined, presents a driving state change factor that is the main cause of the change in the driving state and the change in the driving state of the vehicle to a user of the vehicle before the change in the driving state.

Images