JP6917406B2 - Vehicle control system - Google Patents

Description

The present invention relates to a vehicle control system that performs automatic driving.

A vehicle stop device for forcibly stopping a vehicle at a place that does not obstruct the passage of another vehicle when a driver's consciousness decline is detected is known (for example, Patent Document 1). The vehicle stop device detects lane markers such as a roadside (roadside) and a white line in front by a stereo camera or a radar sensor, and determines the stop position of the vehicle from the inside of the road shoulder based on this information.

Japanese Unexamined Patent Publication No. 2007-331652

However, when the vehicle is stopped at the determined stop position by automatic driving, the target trajectory (traveling route) of the vehicle up to the stop position becomes important. For example, when the width of the road shoulder is wide and the road surface condition is good, the influence of the vehicle on the passage of other following vehicles can be reduced by decelerating the road shoulder. However, when the roadside cannot be detected or the road surface condition of the roadside is rough, it is not preferable for the vehicle to travel on the roadside.

In view of the above background, it is an object of the present invention to create an appropriate target trajectory to a stop position when a vehicle is stopped in a vehicle control system that performs automatic driving.

In order to solve the above problems, one aspect of the present invention is a vehicle control system (1), which is a control device (15) that automatically performs either speed control or steering control of the vehicle, and the surroundings of the vehicle. It has an outside world recognition device (6) capable of detecting a situation, and the control device satisfies a predetermined condition that it is difficult for the control device or the driver to continue running the vehicle while the vehicle is running. At that time, a stop process for stopping the vehicle at a predetermined stop position is executed, and the control device determines the stop position based on the detection result of the outside world recognition device in the stop process, and determines the stop position on the shoulder of the road. The state is acquired, and at least one of the speed of entering the road shoulder and the distance between the position of entering the road shoulder and the stop position is changed according to the state of the road shoulder.

According to this aspect, when the vehicle is stopped, an appropriate target trajectory to the stop position can be set. For example, when the condition of the shoulder is good, it is advisable to let the vehicle enter the shoulder at a relatively early stage and drive the vehicle while decelerating toward the stop position in the shoulder. As a result, it is possible to prevent the vehicle from obstructing the passage of the following vehicle. Further, when the condition of the road shoulder is bad, the vehicle can be stopped more safely by approaching the stop position and then allowing the vehicle to enter the road shoulder.

In the above aspect, the control device sets a determination value based on the state of the road shoulder in the stop processing, and the determination value allows the vehicle to safely travel with respect to the state of the road shoulder. The first deceleration process is executed when it is equal to or more than the traveling reference value, the second deceleration process is executed when the determination value is less than the traveling reference value, and the second deceleration process is compared with the first deceleration process. It is advisable to reduce the speed at which the vehicle enters the shoulder.

According to this aspect, when the condition of the road shoulder is bad, the vehicle is made to enter the road shoulder in a state where the speed is further reduced, so that the vehicle can be driven more safely on the road shoulder.

In the above aspect, in the second deceleration process, the distance between the position of entering the road shoulder and the stop position of the control device may be shorter than that of the first deceleration process.

According to this aspect, when the condition of the road shoulder is bad, the distance traveled by the vehicle on the road shoulder can be shortened, and the vehicle can be driven more safely.

In the above aspect, the control device may increase the deceleration amount before entering the road shoulder in the second deceleration process as compared with the first deceleration process.

According to this aspect, the vehicle can be safely decelerated in a lane more suitable for traveling than on the shoulder.

In the above aspect, the control device causes the vehicle to enter the road shoulder after the speed becomes equal to or lower than the first reference speed in the first deceleration process, and the speed is higher than the first reference speed in the second deceleration process. It is advisable to allow the vehicle to enter the shoulder after the speed becomes lower than the lower second reference speed.

According to this aspect, when the condition of the road shoulder is bad, the vehicle is made to enter the road shoulder in a state where the speed is further reduced, so that the vehicle can be driven more safely on the road shoulder.

In the above aspect, the control device may increase the deceleration amount in the road shoulder in the first deceleration process as compared with the second deceleration process.

According to this aspect, when the condition of the road shoulder is good, the influence on the following vehicle can be reduced by mainly decelerating in the road shoulder.

In the above aspect, the control device sets the stop position in the traveling lane when the determination value is less than the stop reference value unsuitable for stopping the vehicle with respect to the state of the shoulder. It is advisable to perform a third deceleration process for decelerating in the traveling lane.

According to this aspect, when the condition of the road shoulder is bad and the vehicle is not suitable for stopping, the vehicle can safely stop in the traveling lane while avoiding the stop on the road shoulder.

In the above aspect, the state of the road shoulder may include at least one of the degree of recognition of the boundary line between the road shoulder and the lane, the degree of recognition of the road edge, the road surface condition of the road shoulder, and the width of the road shoulder.

According to this aspect, the state of the road shoulder can be appropriately recognized.

According to the above configuration, in the vehicle control system for automatic driving, when the vehicle is stopped, an appropriate traveling locus to the stop position can be set.

Functional configuration diagram of the vehicle equipped with the vehicle control system Flow chart of stop processing Flowchart of stop execution process Flowchart of driving eligibility judgment processing Flowchart of stop eligibility judgment process Explanatory drawing showing (A) the target trajectory by the first deceleration process and (B) the target trajectory by the second deceleration process. Explanatory drawing showing the target trajectory by the third deceleration process

Hereinafter, embodiments of the vehicle control system according to the present invention will be described with reference to the drawings. Hereinafter, an example in which the vehicle control system according to the present invention is applied to a system for controlling a vehicle traveling in a country or region where left-side driving is adopted will be described.

As shown in FIG. 1, the vehicle control system 1 is included in the vehicle system 2 mounted on the vehicle. The vehicle system 2 includes a propulsion device 3, a braking device 4, a steering device 5, an outside world recognition device 6, a vehicle sensor 7, a communication device 8, a navigation device 9 (map device), a driving operation device 10, an occupant monitoring device 11, and an HMI 12 ( It has a Human Machine Interface), an automatic driving level changeover switch 13, an outside notification device 14, and a control device 15. Each configuration of the vehicle system 2 is connected to each other so that signals can be transmitted by a communication means such as CAN 16 (Control Area Network).

The propulsion device 3 is a device that applies a driving force to the vehicle, and includes, for example, a power source and a transmission. The power source has at least one of an internal combustion engine such as a gasoline engine and a diesel engine and an electric motor. The brake device 4 is a device that applies a braking force to a vehicle, and includes, for example, a brake caliper that presses a pad against a brake rotor and an electric cylinder that supplies hydraulic pressure to the brake caliper. The brake device 4 may include a parking brake device that regulates the rotation of the wheels by a wire cable. The steering device 5 is a device for changing the steering angle of the wheels, and includes, for example, a rack and pinion mechanism for steering the wheels and an electric motor for driving the rack and pinion mechanism. The propulsion device 3, the brake device 4, and the steering device 5 are controlled by the control device 15.

The outside world recognition device 6 is a device that detects an object or the like outside the vehicle. The outside world recognition device 6 includes sensors for detecting electromagnetic waves and light from the periphery of the vehicle to detect objects outside the vehicle, for example, a radar 17, a lidar 18, and an outside camera 19. The outside world recognition device 6 may also be a device that receives a signal from the outside of the vehicle and detects an object or the like outside the vehicle. The outside world recognition device 6 outputs the detection result to the control device 15.

The radar 17 emits radio waves such as millimeter waves around the vehicle and captures the reflected waves to detect the position (distance and direction) of the object. At least one radar 17 is attached to any part of the vehicle. The radar 17 includes at least a front radar that irradiates radio waves toward the front of the vehicle, a rear radar that irradiates radio waves toward the rear of the vehicle, and a pair of left and right side radars that irradiate radio waves toward the side of the vehicle. Is preferable.

The rider 18 irradiates the surroundings of the vehicle with light such as infrared rays and captures the reflected light to detect the position (distance and direction) of the object. At least one rider 18 is provided at any position on the vehicle.

The outside camera 19 captures the surroundings of the vehicle including objects existing around the vehicle (for example, peripheral vehicles and pedestrians), guardrails, curbs, walls, medians, road shapes, road markings drawn on the roads, and the like. Take an image. The vehicle exterior camera 19 may be, for example, a digital camera using a solid-state image sensor such as a CCD or CMOS. At least one external camera 19 is provided at an arbitrary position in the vehicle. The outside camera 19 may include at least a front camera that images the front of the vehicle, a rear camera that images the rear of the vehicle, and a pair of side cameras that image the left and right sides of the vehicle. The external camera 19 may be, for example, a stereo camera.

The vehicle sensor 7 includes a vehicle speed sensor that detects the speed of the vehicle, an acceleration sensor that detects the acceleration, a yaw rate sensor that detects the angular velocity around the vertical axis, an orientation sensor that detects the direction of the vehicle, and the like. The yaw rate sensor is, for example, a gyro sensor.

The communication device 8 mediates communication between the control device 15 and the navigation device 9 and peripheral vehicles and servers located outside the vehicle. The control device 15 can perform wireless communication with neighboring vehicles via the communication device 8. Further, the control device 15 can communicate with a server that provides traffic regulation information via the communication device 8. Further, the control device 15 can communicate with a mobile terminal owned by a person existing outside the vehicle via the communication device 8. Further, the control device 15 can communicate with the emergency call center that receives an emergency call from the vehicle via the communication device 8.

The navigation device 9 is a device that acquires the current position of the vehicle and guides the route to the destination, and has a GNSS receiving unit 21, a map storage unit 22, a navigation interface 23, and a route determining unit 24. The GNSS receiving unit 21 identifies the position (latitude and longitude) of the vehicle based on the signal received from the artificial satellite (positioning satellite). The map storage unit 22 is configured by a known storage device such as a flash memory or a hard disk, and stores map information. The navigation interface 23 accepts input such as a destination from the occupant and presents various information to the occupant by display or voice. The navigation interface 23 may include, for example, a touch panel display, a speaker, or the like. In other embodiments, the GNSS receiver 21 may be configured as part of the communication device 8. Further, the map storage unit 22 may be configured as a part of the control device 15, or may be configured as a part of a server device capable of communicating via the communication device 8.

Map information includes road types such as highways, toll roads, national roads, and prefectural roads, the number of lanes on the road, the central position of each lane (three-dimensional coordinates including longitude, latitude, and height), and road lane markings and lanes. The shape of road markings such as boundaries, the presence or absence of sidewalks, rim stones, fences, etc., the position of intersections, the position of lane confluences and branch points, the area of emergency parking zones, the width of each lane, roads such as signs provided on the road Contains information. In addition, the map information may include traffic regulation information, address information (address / zip code), facility information, telephone number information, and the like.

The route determination unit 24 determines the route to the destination based on the position of the vehicle specified by the GNSS receiving unit 21, the destination input from the navigation interface 23, and the map information. Further, when determining the route, the route determining unit 24 may determine the target lane, which is the lane in which the vehicle should travel, by referring to the positions of the lane merging and branching points in the map information.

The driving operation device 10 receives an input operation performed by the driver to control the vehicle. The driving operation device 10 includes, for example, a steering wheel, an accelerator pedal, and a brake pedal. Further, the operation operation device 10 may include a shift lever, a parking brake lever, and the like. A sensor for detecting the amount of operation is attached to each operation operation device 10. The operation operation device 10 outputs a signal indicating the operation amount to the control device 15.

The occupant monitoring device 11 monitors the condition of the occupants in the vehicle interior. The occupant monitoring device 11 includes, for example, an indoor camera 26 that captures an image of an occupant seated on a seat in the vehicle interior, and a grip sensor 27 provided on the steering wheel. The indoor camera 26 is a digital camera that uses a solid-state image sensor such as a CCD or CMOS. The grip sensor 27 is a sensor that detects whether or not the driver is gripping the steering wheel and outputs the presence or absence of gripping as a detection signal. The grip sensor 27 may be formed by, for example, a capacitance sensor or a piezoelectric element provided on the steering wheel. The occupant monitoring device 11 may include a heart rate sensor provided on the steering wheel or the seat and a seating sensor provided on the seat. The occupant monitoring device 11 may also be a wearable device worn by the occupant and capable of detecting vital information including at least one of the worn occupant's heart rate and blood pressure. At this time, it is preferable that the occupant monitoring device 11 is configured to be able to communicate with the control device 15 by a known wireless communication means. The occupant monitoring device 11 outputs the captured image and the detection signal to the control device 15.

The vehicle outside notification device 14 is a device that notifies the outside of the vehicle by sound or light, and includes, for example, a warning light and a horn. Headlights (front lights), tail lights (tail lights), brake lights, hazard lights, and interior lights may function as warning lights.

The HMI 12 notifies the occupant of various information by display or voice, and accepts an input operation by the occupant. The HMI 12 includes, for example, at least one of a display device 31 such as a touch panel or indicator light containing a liquid crystal or organic EL, a sound generator 32 such as a buzzer or a speaker, and an input interface 33 such as a GUI switch or a mechanical switch on the touch panel. include. The navigation interface 23 may be configured to function as the HMI 12.

The automatic operation level changeover switch 13 is a switch that receives an instruction from the occupant to start execution of automatic operation. The automatic driving level changeover switch 13 may be a mechanical switch or a GUI switch displayed on the touch panel, and is arranged at an appropriate position in the vehicle interior. The automatic operation level changeover switch 13 may be configured by the input interface 33 of the HMI 12, or may be configured by the navigation interface 23.

The control device 15 is an electronic control unit (ECU) composed of a CPU, a ROM, a RAM, and the like. The control device 15 executes various vehicle controls by executing arithmetic processing according to the program on the CPU. The control device 15 may be configured as one hardware, or may be configured as a unit composed of a plurality of hardware. Further, at least a part of each functional unit of the control device 15 may be realized by hardware such as LSI, ASIC, FPGA, or may be realized by a combination of software and hardware.

The control device 15 combines various vehicle controls to perform at least level 0 to level 3 automatic driving control (hereinafter, automatic driving). The level is based on the definition of SAE J3016 and is defined in relation to the degree of intervention of the driver in driving maneuvers and vehicle perimeter monitoring.

In level 0 automatic driving, the control device 15 does not control the vehicle, and the driver performs all driving operations. That is, level 0 automatic operation means so-called manual operation.

In the level 1 automatic driving, the control device 15 performs a part of the driving operation, and the driver performs the remaining driving operation. For example, Level 1 autonomous driving includes constant speed driving and inter-vehicle distance control (ACC; Adaptive Cruise Control) and lane keeping support control (LKAS; Lane Keeping Assistance System). The level 1 automatic driving is executed when the condition that there is no abnormality in various devices (for example, the outside world recognition device 6 and the vehicle sensor 7) required for executing the level 1 automatic driving is satisfied.

In level 2 automatic operation, the control device 15 performs all operation operations. Level 2 autonomous driving is when the driver monitors the surroundings of the vehicle and satisfies the condition that the vehicle is within a predetermined area and that there are no abnormalities in various devices required to execute level 2 autonomous driving. Will be executed.

In level 3 automatic operation, the control device 15 performs all operation operations. Level 3 autonomous driving is a posture in which the driver can monitor the surroundings of the vehicle as needed, the vehicle is within a predetermined area, and various devices required to perform level 3 autonomous driving. It is executed when the condition that there is no abnormality in is satisfied. The conditions under which level 3 autonomous driving is executed include, for example, when the vehicle is traveling on a congested road. Whether or not the vehicle is traveling on a congested road may be determined based on the traffic regulation information provided from the server outside the vehicle, and the vehicle speed acquired by the vehicle speed sensor may be determined over a predetermined time. , The determination may be made based on a predetermined slow-moving determination value (for example, 30 km / h) or less.

As described above, in the level 1 to level 3 automatic operation, the control device 15 executes at least one of steering, acceleration, deceleration, and peripheral monitoring. When the control device 15 is in the automatic operation mode, the control device 15 executes level 1 to level 3 automatic operation. In the following, steering, acceleration and deceleration will be described as driving operations, and driving operations and peripheral monitoring will be described as driving, if necessary.

In the present embodiment, when the control device 15 receives the execution instruction of the automatic driving in the automatic driving level changeover switch 13, the vehicle is based on the detection result of the outside world recognition device 6 and the position of the vehicle acquired by the navigation device 9. Select the level of automatic driving according to the driving environment and change the level. However, the control device 15 may change the level according to the input to the automatic operation level changeover switch 13.

As shown in FIG. 1, the control device 15 includes an automatic operation control unit 35, an abnormal state determination unit 36, a state management unit 37, a travel control unit 38, and a storage unit 39.

The automatic driving control unit 35 includes an outside world recognition unit 40, a vehicle position recognition unit 41, and an action planning unit 42. The outside world recognition unit 40 recognizes obstacles located around the vehicle, the shape of the road, the presence or absence of sidewalks, and road markings based on the detection result of the outside world recognition device 6. Obstacles include, for example, people such as guardrails, utility poles, peripheral vehicles, and pedestrians. The outside world recognition unit 40 can acquire states such as the position, speed, and acceleration of surrounding vehicles from the detection result of the outside world recognition device 6. The position of the peripheral vehicle may be recognized as a representative point such as the position of the center of gravity or the corner of the peripheral vehicle, or a region represented by the outline of the peripheral vehicle.

The own vehicle position recognition unit 41 recognizes the traveling lane, which is the lane in which the vehicle is traveling, and the relative position and angle of the vehicle with respect to the traveling lane. The own vehicle position recognition unit 41 may recognize the traveling lane based on, for example, the map information held by the map storage unit 22 and the position of the vehicle acquired by the GNSS receiving unit 21. Further, it is preferable to extract the lane marking around the vehicle drawn on the road surface from the map information and compare it with the shape of the lane marking imaged by the outside camera 19 to recognize the relative position and angle of the vehicle with respect to the traveling lane. ..

The action planning unit 42 sequentially creates an action plan for driving the vehicle along the route. More specifically, the action planning unit 42 first determines an event for traveling in the target lane determined by the route determination unit 24 without the vehicle coming into contact with an obstacle. The event includes a constant-speed driving event in which the vehicle travels in the same driving lane at a constant speed, a preceding vehicle traveling in the same driving lane at a speed less than or equal to the set speed set by the occupant or the speed determined based on the driving environment of the vehicle. Follow-up event to follow, lane change event to change the driving lane of the vehicle, overtaking event to overtake the vehicle in front, merging event to join the vehicle at the merging point of the road, drive the vehicle in the desired direction at the junction of the road When a branching event, an automatic driving end event that ends automatic driving to manual driving, and a predetermined condition indicating that it is difficult for the control device 15 or the driver to continue driving while the vehicle is running are satisfied. Includes a stop event to stop the vehicle.

The condition for the action planning unit 42 to determine the stop event is the indoor camera 26, the grip sensor 27, or the grip sensor 27 from the driver in response to the driver's intervention request (handover request) for driving while driving in automatic driving. The case where the input to the automatic operation level changeover switch 13 is not detected is included. An intervention request is a warning that notifies the driver that part of the driving authority will be delegated and requires the driver to perform at least one of the driving operation and vehicle peripheral monitoring corresponding to the delegated driving authority. be. The condition for the action planning unit 42 to determine the stop event is that the action planning unit 42 determines that the driving operation and the vehicle peripheral monitoring corresponding to the driving authority that the driver should bear are not executed while the vehicle is running. May be included. Further, the condition for the action planning unit 42 to determine the stop event is that the action planning unit 42 determines the stop event, for example, the driver is in a heartbeat stop state based on a signal from the heartbeat sensor or the indoor camera 26 while the vehicle is running. It is good to include the case where it is determined that there is an abnormality in which the driving operation cannot be executed.

During the execution of these events, the action planning unit 42 determines an avoidance event for avoiding obstacles, etc., based on the surrounding conditions of the vehicle (presence of surrounding vehicles and pedestrians, lane narrowing due to road construction, etc.). You may.

The action planning unit 42 generates a target trajectory for the vehicle to travel in the future based on the determined event. The target track is a sequence of track points that the vehicle should reach at each time. The action planning unit 42 may generate a target trajectory based on the target speed and the target acceleration set for each event. At this time, the information of the target velocity and the target acceleration is expressed by the interval of the orbital points.

The travel control unit 38 controls the propulsion device 3, the brake device 4, and the steering device 5 so that the vehicle passes the target track generated by the action planning unit 42 on time.

The storage unit 39 is composed of a ROM, a RAM, or the like, and stores information required for processing by the automatic operation control unit 35, the abnormal state determination unit 36, the state management unit 37, and the travel control unit 38.

The abnormal state determination unit 36 includes a vehicle condition determination unit 51 and an occupant condition determination unit 52. The vehicle state determination unit 51 analyzes the signals of various devices (for example, the outside world recognition device 6 and the vehicle sensor 7) that affect the level of automatic driving during execution, and it is difficult to maintain the automatic driving during execution by the various devices. Judge whether or not an abnormality has occurred.

The occupant state determination unit 52 determines whether or not the driver's condition is in an abnormal state based on the signal from the occupant monitoring device 11. The abnormal state includes a state in which it is difficult for the driver to steer in the automatic driving in which the driver of level 1 or lower is obliged to steer. The states in which it is difficult for the driver to steer are specifically the state in which the driver is sleeping, the state in which the driver is unable to move due to illness or injury, or the state in which the driver is unconscious, or the driver is in cardiac arrest. Including state etc. The occupant state determination unit 52 determines that the driver's condition is in an abnormal state when there is no input from the occupant to the grip sensor 27 in the automatic driving in which the driver of level 1 or lower is obliged to steer. You may. In addition, the occupant state determination unit 52 determines the open / closed state of the driver's eyelids from the extracted face image. The occupant state determination unit 52 sleeps when the driver's eyelids are closed for a predetermined time or when the number of times the eyelids are closed per unit time is equal to or greater than a predetermined threshold value. Even if it is determined that the driver is in a state where it is difficult to perform a driving operation and the driver's state is abnormal because he / she feels strong drowsiness, is unconscious, or is in a state of cardiac arrest. good. The occupant state determination unit 52 further acquires the driver's posture from the captured image, and operates when the driver's posture is not suitable for the driving operation and the state in which the posture does not change is maintained for a predetermined time. It may be determined that the person is unable to move due to illness or injury and the driver's condition is abnormal.

In addition, in automatic driving at a level where there is an obligation to monitor the surroundings, that is, in automatic driving at level 2 or lower, the abnormal state includes a state in which the driver neglects the obligation to monitor the surroundings of the vehicle. The state in which the driver neglects to monitor the surroundings of the vehicle includes either a state in which the driver does not hold the steering wheel or a state in which the driver's line of sight does not face the front of the vehicle. The occupant state determination unit 52 detects whether or not the driver is gripping the steering wheel based on, for example, a signal from the grip sensor 27, and when the driver is not gripping the steering wheel, the driver It is determined that the vehicle is in an abnormal state where the obligation to monitor the surroundings of the vehicle is neglected. Further, the occupant state determination unit 52 determines whether or not the driver's condition is in an abnormal state based on the image captured by the indoor camera 26. For example, the occupant state determination unit 52 extracts the driver's face region from the captured image by using a known image analysis means. The occupant state determination unit 52 further extracts an iris portion (hereinafter, black eye) including the inner corner of the eye, the outer corner of the eye, and the pupil from the extracted face region. When the occupant state determination unit 52 acquires the driver's line-of-sight direction based on the extracted positions of the inner and outer corners of the eye, the black eye, the contour shape of the black eye, and the like, and the driver's line of sight is not facing the front of the vehicle. It is determined that the driver is in a state of neglecting the obligation to monitor the surroundings of the vehicle.

In addition, in automatic driving at a level where there is no obligation to monitor the surroundings, that is, in level 3 automatic driving, an abnormal state is a state in which a driver cannot change driving promptly when a request for changing driving occurs. means. The state in which the driving cannot be changed includes the state in which the system cannot be monitored, and the situation in which the system cannot be monitored is the situation in which the driver cannot monitor the screen display for displaying the alarm, and the driver is sleeping. , And the situation of looking backwards. In the present embodiment, in the level 3 automatic driving, the abnormal state includes a state in which the duty of vehicle peripheral monitoring cannot be fulfilled when the driver is notified to perform vehicle peripheral monitoring. In the present embodiment, the occupant state determination unit 52 causes the display device 31 of the HMI 12 to display a predetermined screen, and instructs the driver to look at the display device 31. After that, the occupant state determination unit 52 detects the driver's line of sight with the indoor camera 26, and when it is determined that the driver's line of sight is not toward the display device 31 of the HMI 12, the duty of monitoring the surroundings of the vehicle cannot be fulfilled. Determined to be in a state.

The occupant state determination unit 52 detects whether or not the driver is gripping the steering wheel based on, for example, a signal from the grip sensor 27, and when the driver is not gripping the steering wheel, the driver It is determined that the vehicle is in an abnormal state where the obligation to monitor the surroundings of the vehicle is neglected. Further, the occupant state determination unit 52 determines whether or not the driver's state is in an abnormal state based on the image captured by the indoor camera 26. For example, the occupant state determination unit 52 extracts the driver's face region from the captured image by using a known image analysis means. The occupant state determination unit 52 further extracts an iris portion (hereinafter, black eye) including the inner corner of the eye, the outer corner of the eye, and the pupil from the extracted face region. When the occupant state determination unit 52 acquires the driver's line-of-sight direction based on the extracted positions of the inner and outer corners of the eye, the black eye, the contour shape of the black eye, and the like, and the driver's line of sight is not facing the front of the vehicle. It is determined that the driver is in a state of neglecting the obligation to monitor the surroundings of the vehicle.

The state management unit 37 determines the level of automatic driving based on at least one of the position of the own vehicle, the operation of the automatic driving level changeover switch 13, and the determination result of the abnormal state determination unit 36. Further, the state management unit 37 controls the action planning unit 42 based on the determined level to perform automatic operation according to each level. For example, when the state management unit 37 executes the constant speed driving control in the level 1 automatic driving, the event determined by the action planning unit 42 is limited to the constant speed driving event.

The state management unit 37 raises and lowers the level in addition to executing the automatic operation according to the set level.

More specifically, when the condition for performing automatic operation of the level after the transition is satisfied, and the automatic operation level changeover switch 13 is input to instruct the level of automatic operation to increase, the state management unit 37 satisfies the condition. , Raise the level.

When the condition for performing automatic operation of the level being executed is not satisfied, or when an input instructing the level to be lowered is made to the automatic operation level changeover switch 13, the state management unit 37 performs intervention request processing. In the intervention request processing, the state management unit 37 first notifies the driver of the handover request. The notification to the driver may be performed by displaying a message or an image on the display device 31 or generating a voice or a warning sound from the sound generator 32. The notification to the driver may be configured to continue for a predetermined time after the intervention request processing is started. Further, the notification to the driver may be configured to be continued until the input is detected by the occupant monitoring device 11.

When the conditions for performing automatic driving at the running level are not satisfied, when the vehicle moves to an area where only automatic driving at a level lower than the level currently running is possible, or when the abnormal state determination unit 36 is the driver or This includes when it is determined that a difficult abnormality has occurred in order to continue automatic driving of the vehicle.

After notifying the driver, the state management unit 37 detects whether the indoor camera 26 or the grip sensor 27 has received an input indicating intervention in driving from the driver. The method of detecting the presence or absence of input is determined depending on the level after migration. When shifting to level 2, the state management unit 37 extracts the driver's line of sight from the image acquired by the indoor camera 26, and when the driver's line of sight is facing the front of the vehicle, the driver changes to driving. It is determined that there was an input indicating the intervention of. When shifting to level 1 or level 0, the state management unit 37 determines that there is an input indicating intervention in driving when the grip sensor 27 detects the grip of the driver's steering wheel. That is, the indoor camera 26 and the grip sensor 27 function as an intervention detection device that detects the driver's intervention in driving. Further, the state management unit 37 may detect whether or not there is an input indicating intervention in operation based on the input to the automatic operation level changeover switch 13.

The state management unit 37 lowers the level when an input indicating intervention in driving is detected within a predetermined time from the start of the intervention request processing. At this time, the level of automatic operation after descent may be level 0, or may be the highest level in the feasible range.

The state management unit 37 causes the action planning unit 42 to generate a stop event when the input corresponding to the driver's intervention in driving is not detected within a predetermined time from the execution of the intervention request processing. The stop event is an event in which the vehicle is stopped at a safe position (for example, an emergency parking zone, a roadside zone, a shoulder, a parking area, etc.) while degenerating the vehicle control. Here, a series of procedures executed in this stop event is referred to as MRM (Minimal Risk Maneuver).

When the stop event is generated, the control device 15 shifts from the automatic operation mode to the automatic stop mode, and the action planning unit 42 executes the stop process. Hereinafter, an outline of the stop processing will be described with reference to FIG.

In the stop process, the notification process is executed first (ST1). In the notification process, the action planning unit 42 operates the vehicle outside notification device 14 to notify the outside of the vehicle. For example, the action planning unit 42 operates the horn included in the outside notification device 14 to periodically generate a warning sound. The notification process continues until the stop process is completed. After the notification process is completed, the action planning unit 42 may operate the horn according to the situation and continue to generate the warning sound.

Next, the degeneracy process is executed (ST2). The degeneracy process is a process of limiting the events that can be generated by the action planning unit 42. The degeneracy process prohibits the generation of, for example, a lane change event to an overtaking lane, an overtaking event, a merging event, and the like. Further, the degeneracy process may limit the upper limit speed and the upper limit acceleration of the vehicle in various events as compared with the case where the stop process is not executed.

Next, the stop area determination process is executed (ST3). The stop area determination process refers to map information based on the position of the own vehicle, and extracts a plurality of stop areas that are suitable for stopping, such as a road shoulder and an evacuation space in the traveling direction of the own vehicle. Then, one stop area is selected from the plurality of stop areas based on the size of the stop area, the distance between the stop area and the own vehicle position, and the like.

Next, the move process is executed (ST4). In the movement process, a route for reaching the stop area is determined, various events for traveling on the route are generated, and a target trajectory is determined. The travel control unit 38 controls the propulsion device 3, the brake device 4, and the steering device 5 based on the target trajectory determined by the action planning unit 42. As a result, the vehicle travels along the route and reaches the stop area.

Next, the stop position determination process is executed (ST5). In the stop position determination process, the stop position is determined based on obstacles located around the vehicle recognized by the outside world recognition unit 40, road markings, and the like. In the stop position determination process, the stop position may not be determined within the stop area due to the presence of surrounding vehicles and obstacles. When the stop position cannot be determined in the stop position determination process (the determination in ST6 is No), the stop area determination process (ST3), the movement process (ST4), and the stop position determination process (ST5) are repeated in this order.

When the stop position can be determined in the stop position determination process (the determination in ST6 is Yes), the stop execution process is executed (ST7). The action planning unit 42 generates a target trajectory based on the current location of the vehicle and the stop position in the stop execution process. The travel control unit 38 controls the propulsion device 3, the brake device 4, and the steering device 5 based on the target trajectory determined by the action planning unit 42. As a result, the vehicle moves toward the stop position and stops at the stop position.

After the stop execution process is executed, the stop maintenance process is executed (ST8). In the vehicle stop maintenance process, the travel control unit 38 drives the parking brake device in response to a command from the action planning unit 42 to maintain the vehicle at the stop position. After that, the action planning unit 42 may send an emergency call to the emergency call center by the communication device 8. When the stop maintenance process is completed, the stop process ends.

The vehicle control system 1 according to the present embodiment has at least an outside world recognition unit 40 that recognizes the outside world based on a signal from the outside world recognition device 6 that can detect the surrounding situation of the vehicle, and a control device 15, and stops. In the process, the target trajectory of the vehicle toward the stop position is changed according to the condition of the shoulder. Hereinafter, the details of the stop position determination process executed by the vehicle control system 1 according to the present embodiment will be described with reference to FIG.

The action planning unit 42 first acquires road shoulder information from the outside world recognition unit 40 in the stop position determination process (ST11). The road shoulder information includes at least one of a degree of recognition of the outside line of the road, a degree of recognition of the road edge, a width of the road shoulder, and a road surface condition of the road shoulder.

The lane outside line 101 is a display line drawn on the road surface, and is a boundary line that separates the lane 102 and the road shoulder 103 (see FIG. 5). The outside world recognition unit 40 acquires the recognition degree of the road outside line by using, for example, pattern matching. The degree of recognition of the outside line of the road is, for example, a numerical value expressed as a percentage. The outside world recognition unit 40 extracts the road outside line 101 from the image captured by the vehicle outside camera 19, calculates the degree of coincidence between the extracted road outside line 101 and the model image of the road outside line stored in advance, and this degree of coincidence. Set the degree of recognition of the outside line of the vehicle according to. The degree of recognition of the vehicle outer line increases as the degree of coincidence between the extracted road outer line 101 and the model image of the vehicle outer line increases.

The roadside 104 is an end of the road and is defined by curbs, walls, guard fences for vehicles such as guardrails and guard cables, and sidewalks. The degree of recognition of the roadside is, for example, a numerical value expressed as a percentage. The outside world recognition unit 40 may acquire the recognition degree of the roadside by using, for example, pattern matching, as well as the recognition degree of the roadside line. The outside world recognition unit 40 extracts the roadside 104 from the image captured by the vehicle outside camera 19, calculates the degree of coincidence between the extracted roadside 104 and the pre-stored model image of the roadside 104, and responds to the degree of coincidence. Set the degree of roadside recognition. The degree of recognition of the roadside becomes larger as the degree of coincidence between the extracted roadside 104 and the model image of the roadside 104 increases.

The width of the road shoulder 103 is the distance between the roadside line 101 and the roadside 104. The outside world recognition unit 40 extracts the roadside line 101 and the roadside 104 from the image of the road shoulder 103 captured by the vehicle outside camera 19, and acquires the distance between the roadside line 101 and the roadside 104 by measuring the distance between the roadside line 101 and the roadside 104.

The road surface condition of the road shoulder 103 includes at least one of a road surface uneven condition, a pavement condition, the presence or absence of deposits such as gravel, snow, and water, and a frozen road surface condition. The outside world recognition unit 40 acquires the road surface state of the road shoulder 103 by performing image processing on the image detected by the vehicle outside camera 19 of the outside world recognition device 6. The outside world recognition unit 40 sets a road surface score according to the road surface condition of the road shoulder 103. The road surface score becomes smaller as the unevenness of the road surface becomes larger, becomes smaller as the pavement condition of the road surface becomes worse, becomes smaller as the amount of gravel accumulated on the road surface increases, and becomes smaller as the amount of snow accumulated on the road surface increases. It becomes a value, and it becomes a small value as the amount of water existing on the road surface increases, and it becomes a small value when the road surface is frozen. That is, the better the road surface condition, the higher the road surface score.

The action planning unit 42 determines whether the road shoulder condition is suitable for safe driving of the vehicle based on the acquired road shoulder information (ST12). In this judgment, a judgment value is set based on the road shoulder information, and whether or not the judgment value is equal to or higher than the driving reference value set as the judgment standard that the vehicle can safely drive with respect to the condition of the road shoulder. It is done by judgment. The determination value may be set for at least one of a plurality of road shoulder information representing the state of the road shoulder. Further, the traveling reference value may be set for each determination value set for each road shoulder information. The road shoulder information includes at least one of a degree of recognition of the outside line of the road, a degree of recognition of the road edge, a width of the road shoulder, and a road surface condition of the road shoulder. The determination in step ST12 may be performed based on the road shoulder travel eligibility determination process shown in FIG. 4 as an example.

In the driving eligibility determination process shown in FIG. 4, the action planning unit 42 first sets the recognition degree (first determination value) of the road outer line included in the road shoulder information with respect to the recognition degree of the road outer line. It is determined whether or not it is equal to or higher than the reference value (ST21). According to the determination in step S21, when the road outer line 101 is clearly drawn on the road surface and is not covered with deposits such as snow and rain, the recognition degree of the road outer line becomes equal to or higher than the driving reference value. , It is judged that the condition of the road shoulder is suitable for the safe running of the vehicle. On the other hand, when a part of the road outer line 101 disappears due to deterioration of the road surface, or when the road outer line 101 is covered with deposits such as snow and rain, the recognition degree of the road outer line 101 runs. It becomes less than the standard value, and it is judged that the condition of the road shoulder is not suitable for safe driving of the vehicle.

When the recognition degree of the roadside line is equal to or higher than the driving reference value (ST21 determination is Yes), the action planning unit 42 recognizes the roadside recognition degree (second determination value) included in the road shoulder information. It is determined whether or not it is equal to or higher than the traveling reference value set for the degree (ST22). According to the determination in step ST22, when the roadside 104 is clearly partitioned by a curb or a vehicle guard fence, the degree of recognition of the roadside becomes equal to or higher than the driving reference value, and the condition of the road shoulder makes the vehicle safe to drive. It is judged to be suitable. On the other hand, if a structure for partitioning the roadside 104 such as a curb or a vehicle guard fence is not provided or is missing, the degree of recognition of the roadside becomes less than the traveling reference value and the condition of the road shoulder becomes poor. It is determined that the vehicle is not suitable for safe driving.

When the degree of recognition of the roadside is equal to or higher than the travel reference value (ST22 determination is Yes), the action planning unit 42 determines that the width of the roadside 104 (third determination value) included in the road shoulder information is the width of the roadside 104. It is determined whether or not it is equal to or higher than the traveling reference value set for (ST23). The travel reference value used in step ST23 is set to a width required for the vehicle to travel safely. The traveling reference value is set to, for example, 2 m to 3 m. By the determination in step S23, it can be determined whether or not the road shoulder 103 has a width sufficient for the vehicle to travel safely.

When the width of the road shoulder 103 is equal to or greater than the travel reference value (ST23 determination is Yes), the action planning unit 42 determines that the road surface condition (fourth determination value) of the road shoulder 103 is based on the road shoulder information with respect to the road surface condition of the road shoulder. It is determined whether or not it is equal to or higher than the set travel reference value (ST24). The road surface condition of the road shoulder may be the road surface score described above. When the unevenness of the road surface on the road shoulder is small, the pavement condition is good, and there is little deposit, the road surface score is equal to or higher than the driving standard value, and it is judged that the road surface condition on the road shoulder is suitable for safe driving of the vehicle. ..

When the road surface condition of the road shoulder 103 is equal to or higher than the travel reference value (the determination of ST24 is Yes), the action planning unit 42 determines that the road shoulder condition is suitable for traveling of the vehicle (ST25). On the other hand, when the recognition degree of the road outside line is less than the driving reference value (ST21 determination is No), and the roadside recognition degree is less than the driving reference value (ST22 determination is No), the width of the road shoulder 103 is the driving reference. If it is less than the value (ST23 determination is No) or the road surface condition (road surface score) is less than the driving reference value (ST24 determination is No), the action planning unit 42 determines that the road shoulder condition is the vehicle. It is determined that the vehicle is not suitable for running (ST26).

The driving eligibility determination process described above is an example, and can be changed as appropriate. For example, each of the processes of steps ST21 to 24 is not essential, and a part may be omitted. That is, the travel eligibility determination process may include at least one of the processes of steps ST21 to 24.

When the action planning unit 42 determines that the road shoulder condition is not suitable for traveling by the vehicle (the determination in ST12 is No), the action planning unit 42 determines whether or not the road shoulder condition is suitable for stopping the vehicle (ST14). This determination is made by determining whether or not the determination value for each road shoulder information is equal to or greater than the stop reference value defined as the determination criterion for the vehicle to safely stop with respect to the state of the road shoulder. Further, the stop reference value may be set for each determination value set for each road shoulder information. The stop reference value is set to a value lower than the travel reference value. The determination in step ST14 may be performed based on the roadside stop eligibility determination process shown in FIG. 5 as an example.

In the stop eligibility determination process shown in FIG. 5, the action planning unit 42 first sets the recognition degree (first determination value) of the road outside line included in the road shoulder information with respect to the recognition degree of the road outside line. It is determined whether or not it is equal to or higher than the reference value (ST31). The stop reference value set for the recognition degree of the outside line of the roadway is set to a value lower than the travel reference value set for the recognition degree of the outside line of the roadway.

When the recognition degree of the roadside line is equal to or higher than the stop reference value (ST31 judgment is Yes), the action planning unit 42 recognizes the roadside recognition degree (second judgment value) included in the road shoulder information. It is determined whether or not the vehicle is at least the set stop reference value for the degree (ST32). The stop reference value set for the roadside recognition degree is set to a value lower than the traveling reference value set for the roadside recognition degree.

When the degree of recognition of the roadside is equal to or higher than the stop reference value (ST32 determination is Yes), the action planning unit 42 determines that the width of the roadside 104 (third determination value) included in the road shoulder information is the width of the roadside 104. It is determined whether or not the vehicle is equal to or greater than the stop reference value set for (ST33). The stop reference value set for the width of the roadside 104 is set to a value lower than the travel reference value set for the width of the roadside 104.

When the width of the road shoulder 103 is equal to or greater than the stop reference value (ST33 determination is Yes), the action planning unit 42 determines that the road surface condition (fourth determination value) of the road shoulder 103 is based on the road shoulder information with respect to the road surface condition of the road shoulder. It is determined whether or not the vehicle is equal to or greater than the set stop reference value (ST34). The road surface condition of the road shoulder may be the road surface score described above. The stop reference value set for the road surface condition of the road shoulder is set to a value lower than the travel reference value set for the road surface condition of the road shoulder.

When the road surface condition of the road shoulder 103 is equal to or higher than the stop reference value (the determination of ST34 is Yes), the action planning unit 42 determines that the road shoulder condition is suitable for stopping the vehicle (ST35). On the other hand, when the recognition degree of the outside line of the road is less than the stop reference value (ST31 judgment is No), and the roadside recognition degree is less than the stop reference value (ST32 judgment is No), the width of the road shoulder 103 is the stop reference. If it is less than the value (ST33 determination is No) or the road surface condition (road surface score) is less than the stop reference value (ST34 determination is No), the action planning unit 42 determines that the road shoulder condition is the vehicle. It is determined that the vehicle is not suitable for stopping the vehicle (ST36).

When the action planning unit 42 determines that the road shoulder condition is suitable for the vehicle to travel (the determination in ST12 is Yes), the action planning unit 42 creates a target track 108 for stopping the vehicle 106 at the stop position 107 by the first deceleration process. (ST13). Further, when the action planning unit 42 determines that the road shoulder condition is not suitable for driving the vehicle (ST12 determination is No) and determines that the road shoulder condition is suitable for stopping the vehicle (ST14 determination is Yes). ), A target track 108 for stopping the vehicle 106 at the stop position 107 is created by the second deceleration process (ST15). Further, when the action planning unit 42 determines that the road shoulder condition is not suitable for stopping the vehicle (the determination in ST14 is No), the action planning unit 42 performs a third deceleration process on the target track 1098 for stopping the vehicle 106 in the traveling lane. Create (ST16).

The travel control unit 38 controls the propulsion device 3, the brake device 4, and the steering device 5 so that the vehicle 106 passes the target track 108 generated by the action planning unit 42 on time. The target trajectory 108 created by the first deceleration process is shown in FIG. 6 (A), the target trajectory 108 created by the second deceleration process is shown in FIG. 6 (B), and the target trajectory created by the third deceleration process is shown. 108 is shown in FIG. The dots shown in FIGS. 6A, 6B, and 7 are track points 109, which are points that the vehicle 106 should reach at each time, and the target track 108 is formed by connecting the track points. The shorter the distance between the track points 109, the smaller the vehicle speed.

The target track 108 in the first deceleration process is a track that enters the road shoulder 103 from the lane 102 at a relatively early timing and decelerates toward the stop position 107 on the road shoulder 103. On the other hand, the target track 108 in the second deceleration process enters the road shoulder 103 from the lane 102 at a timing later than the timing of approaching the road shoulder 103 from the lane 102 in the first deceleration process after decelerating in the lane 102. ..

In the second deceleration process, the distance between the position and the stop position 107 when entering the road shoulder 103 is shorter than that in the first deceleration process. That is, the target track 108 by the second deceleration process enters the road shoulder 103 at a later timing than the target track 108 by the first deceleration process, and enters the road shoulder 103 at a position closer to the stop position 107.

In the second deceleration process, the amount of deceleration before entering the road shoulder 103 is larger than that in the first deceleration process. That is, in the second deceleration process, the deceleration amount in the lane 102 is larger than that in the first deceleration process. As a result, in the second deceleration process, the speed (vehicle speed) when entering the road shoulder 103 becomes smaller than in the first deceleration process. Further, in the first deceleration process, the vehicle 106 enters the road shoulder 103 after the speed becomes equal to or less than the first reference speed, and in the second deceleration process, after the speed becomes lower than the first reference speed to the second reference speed or less. The vehicle 106 is made to enter the road shoulder 103.

In the target track 108 of the second deceleration process, the distance traveled by the vehicle 106 on the road shoulder 103 is shorter and the distance traveled in the lane 102 is longer than that of the target track 108 of the first deceleration process.

In the third deceleration process, the stop position 107 in the preset road shoulder 103 is offset in the lateral direction, and a new stop position 110 is set in the traveling lane 102. The target track 108 in the third deceleration process is a locus that travels straight in the lane 102 in which the vehicle travels and decelerates toward the stop position 110.

According to the above configuration, the action planning unit 42 can stop the vehicle 106 on the road shoulder 103 safely or so as not to obstruct the passage of the following vehicle based on the state of the road shoulder 103. When the condition of the road shoulder 103 is good, the vehicle 106 can enter the road shoulder 103 at a relatively early stage and travel while decelerating toward the stop position 107 within the road shoulder 103. As a result, it is possible to prevent the vehicle 106 from obstructing the passage of the following vehicle. Further, when the condition of the road shoulder 103 is poor, the vehicle 106 can be safely stopped by entering the road shoulder 103 after the vehicle 106 approaches the stop position 107.

When the condition of the road shoulder 103 is not suitable for the safe driving of the vehicle, the speed at which the vehicle 106 enters the road shoulder 103 from the lane 102 is smaller than that when the condition of the road shoulder 103 is suitable for the safe traveling of the vehicle. Become. Therefore, the vehicle 106 can travel on the shoulder 103 more safely. Further, when the condition of the road shoulder 103 is bad, the distance traveled by the vehicle 106 on the road shoulder 103 is shorter than when the condition of the road shoulder 103 is good. Therefore, the vehicle 106 can safely reach the stop position 107.

Further, when the condition of the road shoulder is bad and the vehicle is not suitable for stopping, the vehicle can safely stop in the traveling lane while avoiding the stop on the road shoulder.

Although the description of the specific embodiment is completed above, the present invention can be widely modified without being limited to the above embodiment. For example, the shoulder information may include weather information and temperature information. For example, the action planning unit 42 may determine that the road surface condition is not good when the weather is snow or rain based on the weather information. Further, the action planning unit 42 may determine that the road surface condition is not good because the road shoulder 103 may be frozen when the temperature is below freezing, for example, based on the air temperature information.

1: Vehicle control system 2: Vehicle system 6: External world recognition device 17: Radar 18: Rider 19: Vehicle external camera 35: Automatic driving control unit 38: Driving control unit 40: External world recognition unit 42: Action planning unit 101: Road outside line 102: Lane 103: Shoulder 104: Roadside 106: Vehicle 107: Stop position 108: Target track 109: Track point

Claims (7)

It ’s a vehicle control system.
A control device that automatically controls the speed or steering of the vehicle,
It has an outside world recognition device that can detect the situation around the vehicle.
The control device stops the vehicle at a predetermined stop position when a predetermined condition that it is difficult for the control device or the driver to continue the running of the vehicle is satisfied while the vehicle is running. And
In the stop processing, the control device determines the stop position based on the detection result of the outside world recognition device, acquires the state of the road shoulder, sets a determination value based on the state of the road shoulder, and makes the determination. The first deceleration process is executed when the value is equal to or more than the travel reference value at which the vehicle can travel with respect to the state of the shoulder, and the second deceleration process is executed when the determination value is less than the travel reference value. In the second deceleration process, the speed at which the vehicle enters the road shoulder is reduced as compared with the first deceleration process. The vehicle control system according to claim 1 , wherein the control device shortens the distance between the position of entering the road shoulder and the stop position in the second deceleration process as compared with the first deceleration process. Said control device, a vehicle control system according to claim 1 or claim 2 wherein the second reduction processing to increase the deceleration amount before entering the shoulder than the first deceleration processing. The control device causes the vehicle to enter the road shoulder after the speed becomes equal to or lower than the first reference speed in the first deceleration process, and the second reference speed in which the speed is lower than the first reference speed in the second deceleration process. The vehicle control system according to any one of claims 1 to 3 , wherein the vehicle enters the road shoulder after the following conditions are met. The vehicle control system according to any one of claims 1 to 4 , wherein the control device increases the amount of deceleration in the road shoulder in the first deceleration process as compared with the second deceleration process. When the determination value is less than the stop reference value at which the vehicle can stop with respect to the state of the road shoulder, the control device sets the stop position in the traveling lane and in the traveling lane. The vehicle control system according to any one of claims 1 to 5 , which performs a third deceleration process for decelerating. The state of the road shoulder is any one of claims 1 to 6 , which includes at least one of the degree of recognition of the boundary line between the road shoulder and the lane, the degree of recognition of the road edge, the road surface condition of the road shoulder, and the width of the road shoulder. The vehicle control system according to one section.

Images