JP7233299B2 - Driving behavior control method and driving behavior control device - Google Patents

Description

The present invention relates to a driving behavior control method and a driving behavior control device.

Patent Literature 1 listed below discloses a technique for switching the driving characteristics of an automatic driving device of a vehicle according to the driver.

Japanese Unexamined Patent Application Publication No. 2017-61168

However, there are various driving situations between the starting point and the destination. With the technique of Patent Literature 1, the driving behavior cannot be changed according to changes in driving conditions.
An object of the present invention is to set the driving behavior of an autonomous vehicle according to the driving situation and the preference of the occupant.

In a driving behavior control method according to one aspect of the present invention, a parameter that determines the driving behavior of an autonomous vehicle is set according to a specific driving situation, a passenger's feedback on the driving behavior caused by the parameter is detected, and the feedback is detected. determines the driving behavior when the autonomous vehicle again encounters the specific driving situation or a driving situation similar to the specific driving situation, based on the changed parameters according to the parameters.

According to one aspect of the present invention, the driving behavior of an autonomous vehicle can be set according to driving conditions and occupant preferences.

BRIEF DESCRIPTION OF THE DRAWINGS It is a figure which shows an example of schematic structure of the vehicle which mounts the driving assistance device of embodiment. FIG. 2 illustrates examples of multiple driving situations that exist during a ride from a starting point to a destination; FIG. 2 is an explanatory diagram of driving behavior determined according to driving conditions; It is a block diagram showing an example of functional composition of a driving support device. It is a flow chart of an example of the driving behavior control method of the embodiment.

BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, embodiments of the present invention will be described with reference to the drawings.
(composition)
BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, embodiments of the present invention will be described with reference to the drawings. Note that each drawing is schematic and may differ from the actual one. Further, the embodiments of the present invention shown below are examples of apparatuses and methods for embodying the technical idea of the present invention. are not specific to the following: Various modifications can be made to the technical idea of the present invention within the technical scope defined by the claims.

The host vehicle 1 includes a driving support device 10 that assists the drive of the host vehicle 1 . Driving support by the driving support device 10 includes autonomous driving control (also called automatic driving control) that automatically drives the own vehicle 1 without the involvement of the driver based on the driving environment around the own vehicle 1. , running control for controlling at least one of driving, braking and steering of the own vehicle 1 .
Driving control may be, for example, automatic steering, automatic braking, preceding vehicle follow-up control, constant speed driving control, lane keeping control, merging support control, and the like.
Driving assistance may include output of information (messages) prompting the driver to perform steering operation, acceleration operation, and deceleration operation, in addition to autonomous driving control and driving control.

The driving assistance device 10 includes a positioning device 11, a map database 12, an ambient environment sensor 13, a vehicle sensor 14, a communication device 15, a user interface device 16, a navigation system 17, a controller 18, and an actuator 19. Prepare.
In the drawings, the map database is denoted as "map DB", and the user interface device is denoted as "user I/F device".

The positioning device 11 measures the current position of the own vehicle 1 . The positioning device 11 may for example comprise a Global Positioning System (GNSS) receiver. The GNSS receiver is, for example, a global positioning system (GPS) receiver or the like, and measures the current position of the vehicle 1 by receiving radio waves from a plurality of navigation satellites. The positioning device 11 may measure the current position of the own vehicle 1 by, for example, odometry.

The map database 12 may store high-precision map data (hereinafter simply referred to as "high-precision map") suitable as a map for autonomous driving. A high-precision map is map data with higher precision than map data for navigation (hereinafter simply referred to as "navigation map"), and includes more detailed lane-by-lane information than road-by-road information.
For example, a high-definition map includes lane node information indicating a reference point on a lane reference line (for example, a central line within a lane) and lane link information indicating a section of a lane between lane nodes as information for each lane. including.

The lane node information includes the identification number of the lane node, the position coordinates, the number of connected lane links, and the identification number of the connected lane link. The lane link information includes the lane link identification number, lane type, lane width, lane boundary line type, lane shape, lane marking line shape, and lane reference line shape. The high-precision map further includes the types and positional coordinates of features such as traffic lights, stop lines, signs, buildings, utility poles, curbs, crosswalks, etc. that exist on or near the lane, and lane nodes corresponding to the positional coordinates of the features. includes feature information, such as the identification number of the lane and the identification number of the lane link.

Since the high-precision map includes node and link information for each lane, it is possible to specify the lane in which the vehicle 1 travels on the travel route. The high-precision map has coordinates that can express the position in the extension direction and width direction of the lane. A high-precision map has coordinates (for example, longitude, latitude and altitude) that can represent a position in a three-dimensional space, and lanes and the features can be described as shapes in the three-dimensional space.

The map database 12 may also store a navigation map. A navigation map contains information on a road-by-road basis. For example, a navigation map includes, as information for each road, road node information that indicates a reference point on a road reference line (for example, a line in the center of a road) and road link information that indicates a section of a road between road nodes. . The road node information includes the road node identification number, position coordinates, the number of connected road links, and the connected road link identification number.
The road link information includes the road link identification number, road standard, link length, number of lanes, road width, and speed limit.

The surrounding environment sensor 13 detects various information (surrounding environment information) about the surrounding environment of the own vehicle 1 , for example, objects around the own vehicle 1 . The ambient environment sensor 13 detects the ambient environment of the first vehicle, such as objects existing around the vehicle 1, the relative position between the vehicle 1 and the object, the distance between the vehicle 1 and the object, and the direction in which the object exists. do.
The ambient environment sensor 13 may include a rangefinder such as a laser range finder (LRF) or radar, or a camera. The camera may be, for example, a stereo camera. The camera may be a monocular camera, or the same object may be photographed from a plurality of viewpoints by the monocular camera, and the distance to the object may be calculated. Also, the distance to the object may be calculated based on the grounding position of the object detected from the captured image.

The vehicle sensor 14 detects various information (vehicle information) obtained from the own vehicle 1 . The vehicle sensor 14 includes, for example, a vehicle speed sensor that detects the running speed (vehicle speed) of the vehicle 1, a wheel speed sensor that detects the rotation speed of each tire of the vehicle 1, acceleration in three axial directions of the vehicle 1 ( 3-axis acceleration sensor (G sensor) that detects deceleration), steering angle sensor that detects steering angle (including turning angle), gyro sensor that detects angular velocity generated in own vehicle 1, yaw rate that detects yaw rate Sensors include an accelerator sensor that detects the accelerator opening of the vehicle 1 and a brake sensor that detects the amount of brake operation by the driver.

The communication device 15 performs wireless communication with a communication device outside the vehicle 1 . The communication device 15 may communicate with a cloud database that collects vehicle information of other vehicles, for example, through road-to-vehicle communication or a public communication line, or may communicate with other vehicles around the host vehicle 1 through vehicle-to-vehicle communication. .
The user interface device 16 is a human machine interface (HMI) for exchanging information with the occupant, and exchanging information with a plurality of different modalities (paths). The user interface device 16 may be an information terminal (for example, a smart phone or a tablet device) separate from the driving support device 10 . In addition to the driver, the occupant includes an occupant and a fellow passenger who have operation instruction authority related to the autonomous travel control of the own vehicle 1 .

User interface device 16 may include, for example, a speaker and a microphone for transmitting and receiving audio information. User interface device 16 may also include a display device that provides visual information. The user interface device 16 may include a keyboard, buttons, dials, sliders, mice, touch panels, levers, joysticks, touch pads, etc. that are physically operated by the occupant.
The user interface device 16 may also include a camera that captures the facial expression, face orientation, posture, and hand movement of the occupant. The user interface device 16 may include sensors that detect health indicators such as the occupant's posture, hand movements, and heart rate.

The navigation system 17 recognizes the current position of the vehicle 1 using the positioning device 11 and acquires map information for the current position from the map database 12 . The navigation system 17 sets the travel route to the destination input by the passenger, and provides route guidance to the passenger according to the travel route.
The navigation system 17 also outputs information on the set travel route to the controller 18 . During autonomous travel control, the controller 18 automatically drives the first vehicle so as to autonomously travel along the travel route set by the navigation system 17 .

The controller 18 is an electronic control unit (ECU) that performs driving support control of the own vehicle 1 . The controller 18 is an example of the driving behavior control device described in the claims.
Controller 18 includes a processor 20 and peripheral components such as storage device 21 . The processor 20 may be, for example, a CPU (Central Processing Unit) or an MPU (Micro-Processing Unit).
The storage device 21 may include a semiconductor storage device, a magnetic storage device, an optical storage device, or the like. The storage device 21 may include memories such as a register, a cache memory, a ROM (Read Only Memory) used as a main memory, and a RAM (Random Access Memory).
The functions of the controller 18 to be described below are realized, for example, by the processor 20 executing a computer program stored in the storage device 21 .

Note that the controller 18 may be formed of dedicated hardware for executing each information processing described below.
For example, controller 18 may comprise functional logic circuitry implemented in a general purpose semiconductor integrated circuit. For example, controller 18 may comprise a programmable logic device (PLD), such as a Field-Programmable Gate Array (FPGA), or the like.

The controller 18 estimates the current position of the vehicle 1, the estimated current position, the road map data in the map database 12, the route information output from the navigation system 17, the surrounding environment, and the running state of the vehicle 1. , the scheduled route along which the vehicle 1 should travel is determined.
For example, the controller 18 sets a target travel trajectory along which the vehicle 1 should travel as a planned route. The controller 18 performs autonomous travel control and driving support control of the own vehicle 1 based on the determined planned route, and drives the actuator 19 to control travel of the own vehicle 1 .

The actuator 19 operates the steering wheel, the accelerator opening, and the braking device of the own vehicle 1 according to the control signal from the controller 18 to generate the vehicle behavior of the own vehicle 1 . The actuator 19 includes a steering actuator, an accelerator opening actuator, and a brake control actuator. The steering actuator controls the steering direction and amount of steering of the vehicle 1 . The accelerator opening actuator controls the accelerator opening of the vehicle 1 . The brake control actuator controls the braking operation of the brake system of the host vehicle 1 .

Furthermore, the controller 18 sets driving operation characteristics (hereinafter referred to as “driving behavior”) by the autonomous driving control according to the current driving situation of the own vehicle 1 .
Driving behavior is an index that expresses the characteristics of driving operations characterized by parameters such as target steering angle and target vehicle speed upper limit, steering speed, speed of acceleration/deceleration, vehicle-to-vehicle distance, vehicle-to-vehicle time, and time to avoid collision. be.
Driving behavior can be classified according to various aspects of evaluating driving maneuvers.

For example, the driving behavior can be classified from the viewpoint of driving safety of the own vehicle 1 .
For example, driving behavior may be categorized into five levels of "very safe", "safe", "normal", "active" and "very active". The types and number of classifications of these driving behaviors may be determined in advance.

Here, "safety" refers to cautious driving characteristics that give priority to the sense of security of the occupants. , the driving characteristic of driving at a speed lower than the average surrounding vehicle or the legal speed.
On the other hand, "aggressive" refers to driving characteristics that give priority to vehicle speed, efficiency, and maneuvering speed. It is a driving characteristic of limiting speed or driving at a higher speed than the average surrounding vehicle.

The controller 18 controls at least one of acceleration/deceleration and steering according to the set driving behavior. That is, the controller 18 sets parameters that determine the driving behavior of the own vehicle 1 . The parameters that determine the driving behavior may include, for example, upper limit of target vehicle speed, upper limit of target steering angle, upper limit of acceleration/deceleration and steering speed, inter-vehicle distance, inter-vehicle time, avoidance start collision margin time.
For example, the controller 18 sets the target vehicle speed in the order of "very safe" driving behavior, "safe" driving behavior, "normal" driving behavior, "active" driving behavior and "very aggressive" driving behavior. lower the upper limit of
Also, for example, the target steering angle is determined in the order of "very safe" driving behavior, "safe" driving behavior, "normal" driving behavior, "active" driving behavior and "very active" driving behavior. set a smaller upper limit value. Also, for example, acceleration/deceleration and Decrease the upper limit of the steering speed. Also, for example, in order of "very safe" driving behavior, "safe" driving behavior, "normal" driving behavior, "active" driving behavior, and "very active" driving behavior, the following distance, Set a longer headway time and avoidance start collision margin time.

On the other hand, the “driving situation” is the situation in which the own vehicle 1 is placed during driving, and includes driving scenes (for example, intersections, merging sections, lane changes, construction sections, etc.) and external conditions that determine the difficulty of driving. It is determined by conditions (for example, weather, time of day, traffic volume, road surface conditions, accidents, specific events, etc.).
2A and 2B show examples of driving situations. A plurality of driving situations A to D occur in one ride from the starting point to the destination. For example, the first driving situation A is a driving situation in which the driver passes through the T-junction 30 under the external condition of the normal difficulty level, and the next driving situation B is the driving situation in which the merging section 32 is passed under the external condition of the normal difficulty level. . The next driving situation C is a driving situation in which the vehicle passes through the construction section 33 under normal difficulty external conditions, and the final driving situation D is a driving situation in which the vehicle passes through the T-junction 31 under high difficulty external conditions.

The controller 18 sets driving behavior according to these driving conditions. When these or similar driving situations are encountered for the first time, the controller 18 sets default values for the driving behavior accordingly.
For example, the controller 18 calculates the uncertainty of autonomous driving according to each driving situation, and sets the specified value of the driving behavior based on the uncertainty of autonomous driving. Here, "autonomous driving uncertainty" represents the possibility of stopping autonomous driving and switching to manual driving in the middle of the driving situation.

For example, the controller 18 may calculate the uncertainty of autonomous driving based on external conditions that define the degree of difficulty of driving in each driving situation.
In the example of FIG. 2B, in driving situations A, B, and C, the uncertainty of autonomous driving is calculated as "high" according to the "external conditions of normal difficulty level", and "safe" driving behavior is set. In the driving situation D, the uncertainty of autonomous driving is calculated as "extremely high" according to the "external conditions with a high degree of difficulty", and a "extremely safe" driving behavior is set.
In addition to or instead of the external conditions, the controller 18 controls the internal conditions of the own vehicle 1 (soundness of each sensor, positioning accuracy, processor load of the controller 18, network state, algorithm bug, temperature of the controller 18, etc.). ) may be used to calculate the uncertainty of autonomous driving.

However, there are individual differences in preference for driving behavior, and the occupant of the vehicle 1 is not always satisfied with the driving behavior of the specified value set by the controller 18 . In the example of FIG. 2B, the occupant of the own vehicle 1 prefers "normal" driving behavior to "safe" driving behavior in driving situation A, and "active" rather than "safe" driving behavior in driving situation B. prefers "safe" driving behavior, and in driving situation D prefers "safe" driving behavior to "very safe" driving behavior.
Accordingly, the controller 18 senses occupant feedback on the set driving behavior in a particular driving situation, and, in response to the sensed feedback, sets when the particular driving situation or similar particular driving situation is encountered again. adjust the driving behavior.

The driving behavior control by the controller 18 will be described in detail below. Please refer to FIG. The controller 18 includes an object recognition unit 40, a map generation unit 41, a driving behavior determination unit 42, a traveling trajectory generation unit 43, a driving control unit 44, an uncertainty determination unit 45, and a driving behavior setting unit 46. , a parameter setting unit 47 and a feedback detection unit 48 .

The object recognition unit 40 predicts the behavior of mobile objects around the vehicle 1 based on the surrounding environment information input from the surrounding environment sensor 13 and the high-precision map stored in the map database 12 .
Based on the surrounding environment information, the high-precision map, and the prediction result by the object recognition unit 40, the map generation unit 41 generates a route space map expressing the route around the own vehicle 1 and the presence or absence of objects, and the danger of the driving area. Generate a quantified risk map.

The driving action determining unit 42 generates a driving action plan for automatically causing the vehicle 1 to travel on the traveling route based on the traveling route set by the navigation system 17, the route space map, and the risk map.
A driving behavior plan is a plan of driving behavior at the lane level (lane level) in a range of medium and long distances, which defines lanes in which the vehicle is to be driven and driving behaviors required for driving in these lanes. is.

The driving behavior determined by the driving behavior determining unit 42 may be, for example, a right turn, a left turn, or a straight run at an intersection on the driving route, or a lane change when traveling on multiple lanes.
The driving action plan may be, for example, a plan of driving action such as how many meters before the intersection the lane should be changed to the right turn lane in a scene of turning right at an intersection existing ahead.
The traveling trajectory generating unit 43 generates candidates for a traveling trajectory and a speed profile along which the own vehicle 1 travels based on the driving action plan generated by the driving action determining unit 42, the motion characteristics of the own vehicle 1, and the route space map.

The travel trajectory generation unit 43 evaluates the future risk of each candidate based on the risk map, selects the optimum travel trajectory and speed profile, and sets them as the target travel trajectory and target speed profile for the vehicle 1 to travel.
The travel control unit 44 drives the actuator 19 so that the vehicle 1 travels on the target travel trajectory at a speed according to the target speed profile generated by the travel trajectory generator 43 .
The uncertainty determination unit 45 determines the uncertainty of autonomous driving based on the above external conditions and/or internal conditions that determine the difficulty level of driving the own vehicle 1 .

The driving behavior setting unit 46 determines the current driving situation of the own vehicle 1 . For example, the driving behavior setting unit 46 sets driving scenes (for example, intersections, merging sections, lane changes, construction sections, etc.), target driving trajectories, road characteristics (number of lanes, traffic lights, stop signs, presence or absence of obstacles), The current driving situation is determined based on multiple criteria such as the speed limit and external conditions that determine the degree of difficulty.

Based on these judgment criteria, the driving behavior setting unit 46 judges whether the current driving situation of the vehicle 1 is a driving situation encountered for the first time, or whether it is the same as or similar to a driving situation already encountered in the past. do.
These criteria include qualitative criteria and quantitative criteria. Examples of qualitative judgment criteria are driving scene, target driving trajectory, presence/absence of traffic lights and stop signs, presence/absence of obstacles, weather, traffic volume, presence/absence of specific events, and the like. Examples of quantitative criteria are the number of lanes, speed limits, time of day, and the like.

The driving behavior setting unit 46 determines whether the driving situations are identical or similar based on whether or not the qualitative criteria match.
The driving behavior setting unit 46 classifies the quantitative judgment criteria into a plurality of categories and value ranges, and determines the identity of the driving situation based on whether the categories and value ranges to which the quantitative judgment criteria belong match. or similarity.

For example, the criteria for determining the number of lanes are classified into "1 lane", "2 or 3 lanes", and "3 or more lanes". The criteria for determining speed limits are categorized into "less than 40 kilometers per hour," "40 kilometers per hour or more and less than 70 kilometers per hour," and "70 kilometers per hour or more." The criteria for determining the time are ``5:00 am to 5:30 pm'' (dawn), ``5:30 am to 6:00 pm'' (daytime), ``6:00 pm to 6:30 pm'' (evening), and `` 6:30 p.m. to 5:00 a.m.” (night).

The driving behavior setting unit 46 determines that the driving conditions are the same when all of the determination criteria match.
The driving behavior setting unit 46 determines that the driving situations are similar when a predetermined ratio or more of the plurality of judgment criteria match. For example, it may be determined that the driving conditions are similar when a predetermined percentage (e.g., 80% or more) of some high-priority criteria among a plurality of criteria match.

The priority of the judgment criteria may be determined according to the driving scene (intersection, merging section, lane change, construction section) of each driving situation.
For example, in the driving situation of driving through an intersection, priority is given to the target driving trajectory, the presence or absence of traffic signs (traffic signals, stop signs, YIELD signs), the presence or absence of obstacles that block the view of the vehicle 1, traffic volume, and weather. It may be used as a high degree criterion to determine the similarity of driving situations.
For example, in driving situations where lane changes are required, the number of lanes, speed limit, traffic volume, road surface conditions (whether the lane markings are clear, etc.), and weather are used as high-priority judgment criteria to determine the driving situation. may determine the similarity of

If the current driving situation of the host vehicle 1 is not the same or similar to the driving situation that has already been encountered in the past, and is the driving situation that has been encountered for the first time, the driving behavior setting unit 46 determines that the uncertainty determination unit 45 is currently setting the driving behavior of a specified value (default value) that is determined based on the uncertainty of autonomous driving calculated in the driving situation.
For example, if the uncertainty is ``very high'', ``high'', ``normal'', ``low'' and ``very low'', the corresponding default values ``very safe'', ``safe'' , “Normal”, “Active” and “Very Active” driving behaviors.

Alternatively, the driving behavior setting unit 46 may set a prescribed value of driving behavior according to the driving safety in the current driving situation. The driving behavior setting unit 46 may determine driving safety based on the above external conditions and/or internal conditions that determine the degree of difficulty of driving the own vehicle 1 .

The driving behavior setting unit 46 further determines the driving behavior in the current driving situation determined by the driving behavior determining unit 42, the current driving situation determined by the driving trajectory generating unit 43, and A prescribed value of driving behavior may be determined in accordance with the target travel trajectory in .
In addition, the driving behavior setting unit 46 acquires information on the driving behavior of other vehicles corresponding to the same or similar driving situations in the past from the cloud database by the communication device 15, and sets the prescribed value of driving behavior according to this information. may be determined.
Further, information on the driving behavior of other vehicles corresponding to the current driving situation around the own vehicle 1 may be acquired, and the prescribed value of driving behavior may be determined according to this information. Information on the driving behavior of the other vehicle may be acquired, for example, through inter-vehicle communication, or may be estimated based on the detection result of the other vehicle by the ambient environment sensor 13 .

The parameter setting unit 47 sets parameters for determining driving behavior based on the driving behavior set by the driving behavior setting unit 46 . As described above, the parameters may include, for example, the target vehicle speed upper limit, the target steering angle upper limit, the acceleration/deceleration and steering speed upper limits, the inter-vehicle distance, the inter-vehicle time, and the avoidance start collision margin time.
The parameter setting unit 47 outputs the set parameters to the travel trajectory generation unit 43 . The traveling trajectory generator 43 sets the target traveling trajectory and the target speed profile according to these parameters.

The travel control unit 44 drives the actuator 19 according to the target travel trajectory and the target speed profile, thereby causing vehicle behavior corresponding to the driving behavior set by the driving behavior setting unit 46 .
The feedback detection unit 48 detects the feedback of the passenger when the vehicle behavior occurs using the user interface device 16, and acquires the feedback as the feedback of the passenger regarding the driving behavior.

The feedback detector 48 may detect feedback of multiple different modalities. The feedback detection unit 48 may detect feedback by voice of the passenger.
For example, the feedback detection unit 48 may output, from the speaker of the user interface device 16, a voice message inquiring about the passenger's opinion, impression, and impression of the driving behavior.
The feedback detection unit 48 may detect a voice response to this as feedback with a microphone. Also, physical manipulations of keyboards, buttons, dials, sliders, mice, touch panels, levers, joysticks, and touch pads of the user interface device 16 may be detected as feedback.

The feedback detection unit 48 may detect feedback on whether or not the passenger is satisfied with the driving behavior, or whether or not the driver feels that the driving behavior is excessively safe or active, based on the feedback of these voices and physical operations. .
In addition, based on health indicators such as the occupant's facial expression, face direction, posture, and hand movement captured by a camera, and the occupant's posture, hand movement, and heart rate detected by a sensor, the occupant's satisfaction with driving behavior is determined. It may be estimated whether or not and detected as feedback.

Further, for example, the feedback detection unit 48 may detect an override operation of the steering wheel, the accelerator pedal, and the brake pedal by the passenger as feedback. Whether or not the driver is satisfied with the driving behavior may be estimated based on the presence or absence of these override operations. It may also be estimated whether or not the driver felt overly safe or aggressive driving behavior in response to the override operation.

The feedback detection section 48 outputs the detected feedback to the driving behavior setting section 46 .
After setting the driving behavior according to the driving situation of the own vehicle 1, the driving behavior setting unit 46 adjusts the driving behavior at this time according to the feedback of the passenger on the driving behavior, and sets the same or similar driving situation as the driving situation. is stored as a driving behavior to be set when encountering again. This changes the parameters that define the driving behavior when the same or similar driving situation as this driving situation is encountered again.

For example, if the driver is not satisfied with the driving behavior and feels that the driving behavior is too safe, a more active driving behavior should be set when the same or similar driving situation is encountered again. remember as
If the occupant is not satisfied with the driving behavior and feels that the driving behavior is overly aggressive, a safer driving behavior is stored as the driving behavior to be set when the same or similar driving situation is encountered again. do.
On the other hand, when the passenger is satisfied with the driving behavior, the driving behavior setting unit 46 stores the set driving behavior as the driving behavior suitable for the passenger in this driving situation.

When the own vehicle 1 again encounters a driving situation that is the same as or similar to a specific driving situation encountered in the past (hereinafter sometimes referred to as a "specific driving situation"), the driving behavior setting unit 46 sets the specific driving situation. The stored driving behavior is set as the driving behavior for driving the own vehicle 1 in the current driving situation.
The parameter setting unit 47 sets parameters based on the set driving behavior. The travel trajectory generator 43 and the travel controller 44 drive the vehicle 1 according to these parameters.

At this time, if the set driving behavior is a driving behavior that is stored as a driving behavior suitable for the specific driving situation, the driving behavior setting unit 46 no longer adjusts the driving behavior based on the feedback of the occupant.
On the other hand, if the set driving behavior is not the driving behavior stored as a suitable driving behavior, the driving behavior setting unit 46 acquires feedback from the passenger on the driving behavior from the feedback detection unit 48 .

If the passenger is not satisfied with the driving behavior, the driving behavior is adjusted and stored according to the feedback of the passenger, as described above. When the driver is satisfied with the driving behavior, the driving behavior is stored as suitable for the specific driving situation. It may be stored as a driving behavior suitable for the current driving situation.
In this manner, the driving behavior setting unit 46 changes the driving behavior in the specific driving situation (that is, the parameters that determine the driving behavior) according to the feedback from the passenger until the driving behavior suitable for the passenger in the specific driving situation is determined.

In the above example, the driving behavior is adjusted and stored, but the driving behavior setting unit 46 may directly store parameters that define the driving behavior instead of the driving behavior. The driving behavior setting unit 46 may directly adjust the parameters that determine the driving behavior according to feedback from the passenger.

The driving behavior setting unit 46 may change the driving behavior (that is, the parameter that determines the driving behavior) after detecting feedback a plurality of times. At this time, the presence or absence of an abnormal event or an unexpected event may be determined, and the driving behavior may be changed by excluding feedback when an abnormal event or an unexpected event occurs.
The abnormal event or sudden event may be, for example, a pedestrian ignoring traffic rules while crossing, an accident, or an encounter with an ambulance or police vehicle.
The driving behavior can be set appropriately by changing the driving behavior in response to multiple feedbacks and by removing noise such as abnormal events and sudden events.

Further, the driving behavior setting unit 46 may determine whether or not to change the driving behavior in the driving situation based on the uncertainty of the autonomous driving in the driving situation of the own vehicle 1 based on feedback from the occupant. That is, depending on the degree of uncertainty of autonomous driving, the change in driving behavior based on the feedback of the passenger may be stopped. The performance of the own vehicle 1 may be considered in addition to the uncertainty of autonomous driving.

For example, in a driving situation where the uncertainty of autonomous driving is low (such as driving on a highway), driving with autonomous driving control is easy, so the occupants feel less danger. In such a case, there is little need for occupant feedback because individual differences in driving behavior preferences are small.
On the other hand, in driving situations where the uncertainty of autonomous driving is low (intersections with YIELD signs and stop signs, merging sections, overtaking obstacles), the difficulty of driving with autonomous driving control is high, and the preference for driving behavior is high. There are large individual differences in

The driving behavior setting unit 46 may set the driving behavior based on the manual operation (including voice operation) of the user interface device 16 by the passenger. Thus, the occupant has the option of manually setting the driving behavior.
Further, the driving behavior setting unit 46 may set different driving behaviors for each passenger. The driving behavior setting unit 46 may identify the occupant based on the occupant's ID input or biometric authentication such as face authentication or fingerprint authentication.

(motion)
Next, an example of an abnormal state notification method in the embodiment will be described. FIG. 4 is a flowchart of an example of the driving behavior control method of the embodiment.
In step S<b>1 , the driving behavior setting unit 46 determines the current driving situation of the own vehicle 1 .
In step S2, the driving behavior setting unit 46 determines whether or not the current driving situation has been encountered for the first time (that is, whether or not the driving situation that is the same as or similar to the current driving situation has never been encountered).

If the current driving situation is encountered for the first time (step S2: Y), the process proceeds to step S3. If the current driving situation is the same as or similar to the specific driving situation encountered in the past (step S2: N), the process proceeds to step S12.
In step S3, the uncertainty determination unit 45 determines the uncertainty of autonomous travel.
In step S4, the driving behavior setting unit 46 sets a prescribed value of driving behavior based on the uncertainty of autonomous driving determined in step S3. The parameter setting unit 47 sets parameters based on the set driving behavior. The travel trajectory generator 43 and the travel controller 44 drive the vehicle 1 according to these parameters.

In step S5, the driving behavior setting unit 46 determines whether the driving situation determined in step S1 has ended and the next driving situation has started (that is, whether the driving situation has changed). At step S5: Y), the process proceeds to step S6. If the driving condition continues (step S5: N), the process returns to step S4.

In step S6, the feedback detection unit 48 detects the feedback of the passenger on the driving behavior.
In step S7, the driving behavior setting unit 46 determines whether the passenger is satisfied with the driving behavior based on the detected feedback. If the passenger is satisfied with the driving behavior (step S7: Y), the process proceeds to step S8. If the occupant is not satisfied with the driving behavior (step S7: N), the process proceeds to step S9.

In step S8, the driving behavior setting unit 46 stores the driving behavior set in step S4 as driving behavior suitable for the passenger in the driving situation determined in step S1. After that, the process proceeds to step S16.
In step S9, the driving behavior setting unit 46 determines whether or not the feedback detected in step S6 indicates that the occupant feels that the driving behavior is excessively safe. If the driver feels that the driving behavior is excessively safe (step S9: Y), the process proceeds to step S10.

If the driver did not feel that the driving behavior was overly safe (that is, the driver felt that the driving behavior was overly aggressive) (step S9: N), the process proceeds to step S11.
In step S10, the driving behavior setting unit 46 changes the driving behavior set in step S4 to a more active driving behavior. Then, it is stored as the driving behavior when encountering the same or similar driving situation as the driving situation determined in step S1 again. After that, the process proceeds to step S16.
In step S11, the driving behavior setting unit 46 changes the driving behavior set in step S4 to a safer driving behavior. Then, it is stored as the driving behavior when encountering the same or similar driving situation as the driving situation determined in step S1 again. After that, the process proceeds to step S16.

On the other hand, if the vehicle has encountered a specific driving situation that is the same as or similar to the current driving situation, the driving behavior setting unit 46 reads the driving behavior stored for this specific driving situation in step S12. The driving behavior setting unit 46 determines whether or not the read driving behavior is suitable for the specific driving situation. If the driving behavior is suitable for the specific driving situation (step S12: Y), the process proceeds to step S13. If the driving behavior is not suitable for the specific driving situation (step S12: N), the process proceeds to step S14.

In step S13, the driving behavior setting unit 46 sets the read driving behavior (that is, the driving behavior suitable for the specific driving situation) as the driving behavior for driving the own vehicle 1 in the current driving situation. The parameter setting unit 47 sets parameters based on the set driving behavior. The travel trajectory generator 43 and the travel controller 44 drive the vehicle 1 according to these parameters. After that, the process proceeds to step S16.

In step S14, the driving behavior setting unit 46 sets the read driving behavior as the driving behavior of driving the own vehicle 1 under the current driving situation. As described above, this driving behavior is the driving behavior that was adjusted according to the feedback of the occupant when it was previously set as the driving behavior for driving the own vehicle 1 in a specific driving situation (steps S9 to S11). The parameter setting unit 47 sets parameters based on the set driving behavior. The travel trajectory generator 43 and the travel controller 44 drive the vehicle 1 according to these parameters.

In step S15, the driving behavior setting unit 46 determines whether the driving situation determined in step S1 has ended and the next driving situation has started (that is, whether the driving situation has changed). At step S15: Y), the process proceeds to step S6. If the driving condition continues (step S15: N), the process returns to step S14.
In subsequent step S6, the feedback detection unit 48 detects the feedback of the driver regarding the driving behavior, and in step S7, the driving behavior setting unit 46 determines whether the driver is satisfied with the driving behavior.

If the passenger is satisfied with the driving behavior (step S7: Y), the driving behavior setting unit 46 stores the driving behavior set in step S14 as a suitable driving behavior for the passenger in the specific driving situation (step S8). After that, the process proceeds to step S16.
When the passenger is not satisfied with the driving behavior (step S7: N), the driving behavior setting unit 46 adjusts the driving behavior set in step S14 according to the feedback of the passenger to bring the driving situation to the same or similar driving situation as the specific driving situation. It is stored as a driving behavior when encountering again (steps S9 to S11). After that, the process proceeds to step S16.

In step S16, the controller 18 determines whether or not the ignition switch (IGN) of the vehicle 1 has been turned off. When the ignition switch of the host vehicle 1 is turned off (step S16: Y), the process ends. If the ignition switch of the host vehicle 1 is not turned off (step S16: N), the process returns to step S1.

(Effect of Embodiment)
(1) The driving behavior setting unit 46 and the parameter setting unit 47 set parameters that determine the driving behavior of the own vehicle 1 according to specific driving conditions. A feedback detector 48 detects the occupant's feedback on the driving behavior caused by the parameters. The driving behavior setting unit 46, the parameter setting unit 47, and the traveling trajectory generating unit 43 re-establish the specific driving situation or a driving situation similar to the specific driving situation based on the parameters changed according to the feedback. Determine driving behavior when encountering.

Thereby, the driving behavior of the autonomous vehicle can be set according to the driving situation and the occupant's preference.
For example, even if there are various driving situations between the departure point and the destination, the driving behavior can be changed to suit each of these driving situations. In addition, various parameters that determine driving behavior can be changed according to the driving situation. Furthermore, the driving behavior can be changed according to the passenger's preference.

(2) The feedback detection unit 48 detects feedback from a plurality of user interfaces with different modalities. This makes it possible to detect occupant feedback with an appropriate modality according to the occupant's preferences and circumstances.
(3) The driving behavior setting unit 46 and the parameter setting unit 47 change the parameters that determine the driving behavior in the specific driving situation according to the feedback until the driving behavior suitable for the passenger in the specific driving situation is determined. Thereby, it is possible to set driving behavior suitable for the passenger in a specific driving situation.

(4) The driving behavior setting unit 46 and the parameter setting unit 47 detect multiple times of feedback, and change the parameters from the multiple times of feedback, excluding the feedback when an abnormal event occurs. As a result, it is possible to eliminate feedback noise when an abnormal event or sudden event occurs, and to set the driving behavior more appropriately.

(5) The driving behavior setting unit 46 determines whether or not the driving conditions are similar based on a plurality of criteria for which priority is determined according to the driving scene of the own vehicle 1 . By changing the criteria used for similarity determination according to the driving scene in this way, it is possible to more accurately determine the similarity of driving situations in each driving scene.
(6) The driving behavior setting unit 46 and the parameter setting unit 47 set parameters based on the uncertainty of continuation of autonomous driving in a specific driving situation when the specific driving situation is encountered for the first time. Thereby, the driving behavior can be set according to the degree of difficulty of driving in each driving situation.

(7) When the driving behavior setting unit 46 and the parameter setting unit 47 encounter a specific driving situation for the first time, the driving behavior setting unit 46 and the parameter setting unit 47 further determine the driving plan determined for the specific driving situation and the driving of other vehicles in the specific driving situation. Set parameters based on at least one of the behaviors. This makes it possible to set a more appropriate driving behavior in the first encountered driving situation.
(8) The driving behavior setting unit 46 determines whether or not to change the parameters that determine the driving behavior in the specific driving situation based on the uncertainty of the continuation of the autonomous driving in the specific driving situation in accordance with the feedback. . As a result, for example, when the uncertainty of continuation of autonomous driving is high and there is little individual difference in preference for driving behavior, it is possible to omit adjustment of driving behavior based on passenger feedback.

Reference Signs List 1 Own vehicle 10 Driving support device 11 Positioning device 12 Map database 13 Surrounding environment sensor 14 Vehicle sensor 15 Communication device 16 User interface device 17 Navigation system 18 Controller 19 Actuator 20 Processor 21 Storage device 40 Object recognition unit 41 Map generation unit 42 Driving action determination unit 43 Traveling trajectory generation unit 44 Travel control unit 45 Disabled Certainty determination unit 46 Driving behavior setting unit 47 Parameter setting unit 48 Feedback detection unit

Claims (7)

the controller
Setting parameters that determine driving behavior, which is the characteristic of driving operation by autonomous driving control of an autonomous vehicle, according to a specific driving situation,
detecting occupant feedback on said driving behavior caused by said parameter;
determining a driving behavior when the autonomous vehicle re-encounters the particular driving situation or a driving situation similar to the particular driving situation based on the parameters modified in response to the feedback;
Selecting one of the plurality of classifications of driving behavior when a specific driving situation is encountered for the first time based on the uncertainty of continuation of autonomous driving in the specific driving situation;
setting the parameter based on the selected one of the classifications;
A driving behavior control method characterized by: 2. The controller according to claim 1 , wherein the controller changes, in accordance with the feedback, a parameter that determines driving behavior in the specific driving situation until driving behavior suitable for the occupant in the specific driving situation is determined. The driving behavior control method described. The controller is
detecting said feedback multiple times;
changing the parameter from the multiple times of the feedback, excluding feedback when an abnormal event occurs;
The driving behavior control method according to claim 1 or 2, characterized in that: Claims 1 to 3 , wherein the controller determines whether or not the driving conditions are similar, based on a plurality of determination criteria prioritized according to driving scenes of the autonomous vehicle. The driving behavior control method according to any one of . When the specific driving situation is encountered for the first time, the controller further controls the driving plan based on at least one of the determined driving plan for the specific driving situation and the driving behavior of other vehicles in the specific driving situation. The driving behavior control method according to any one of claims 1 to 4 , characterized in that a parameter is set. The controller determines whether or not to change a parameter defining driving behavior in the specific driving situation based on the uncertainty of continuation of autonomous driving in the specific driving situation in accordance with the feedback. The driving behavior control method according to any one of claims 1 to 5 . A driving behavior control device comprising a controller for controlling a driving behavior that is a characteristic of a driving operation by autonomous driving control of an autonomous vehicle,
The controller is
setting a parameter that determines the driving behavior of the autonomous vehicle according to a specific driving situation;
detecting occupant feedback on said driving behavior caused by said parameter;
determining a driving behavior when the autonomous vehicle re-encounters the particular driving situation or a driving situation similar to the particular driving situation based on the parameters modified in response to the feedback ;
Selecting one of the plurality of classifications of driving behavior when a specific driving situation is encountered for the first time based on the uncertainty of continuation of autonomous driving in the specific driving situation;
setting the parameter based on the selected one of the classifications;
A driving behavior control device characterized by:

Images