JP7613438B2 - Vehicle device and vehicle estimation method - Google Patents

Description

The present disclosure relates to a vehicle device and a vehicle estimation method.

Patent document 1 discloses a technology that detects that a driver is unable to drive if the driver's head, detected based on an image of the driver's seat captured by a camera, is outside the range of the image.

Also, a technology for performing automatic driving of a vehicle is known. For example, the automation levels of automatic driving are classified into levels 0 to 5 defined by the SAE. Level 0 is a level where the driver performs all driving tasks without intervention of the system. Level 0 corresponds to so-called manual driving. Level 1 is a level where the system assists with either steering or acceleration/deceleration. Level 2 is a level where the system assists with both steering and acceleration/deceleration. Automatic driving at levels 1 and 2 is automatic driving where the driver has the supervisory responsibility (hereinafter, simply the supervisory responsibility) for safe driving. Level 3 is a level where the system can perform all driving tasks in specific locations such as highways, and the driver performs driving operations in emergencies. Level 4 is a level where the system can perform all driving tasks except under specific circumstances such as unsupported roads and extreme environments. Level 5 is a level where the system can perform all driving tasks in all environments. Automatic driving at levels 3 and above is automatic driving where the driver does not have the supervisory responsibility. Automatic driving at levels 4 and above is automatic driving where the driver is allowed to sleep.

JP 2018-173996 A

A driver's posture can be disrupted whether they are asleep or in an abnormal state such as poor physical condition. Therefore, with the technology disclosed in Patent Document 1, it was difficult to distinguish between a driver's asleep state and an abnormal state and detect it.

In response to this, it is conceivable that increasing the number of types of sensors used to estimate the driver's state would make it possible to distinguish between the driver's sleeping state and an abnormal state. However, increasing the number of types of sensors used to estimate the driver's state is conceivable to increase waste depending on the level of automation. For example, in automated driving at level 4 or higher, the driver is permitted to sleep, which reduces the likelihood that the driver will touch operating components such as the steering wheel. Here, if such operating components are provided with sensors used to estimate the driver's state, using these sensors to estimate the driver's state would increase wasteful processing.

One objective of this disclosure is to provide a vehicle device and a vehicle estimation method that make it possible to easily distinguish and estimate an abnormal state of the driver from a sleeping state according to the automation level of the vehicle, while also reducing unnecessary processing.

The above object is achieved by a combination of features recited in the independent claims, and the subclaims define further advantageous embodiments of the disclosure. The reference characters in parentheses in the claims indicate a correspondence with the specific means described in the embodiments described below as one aspect, and do not limit the technical scope of the present disclosure.

In order to achieve the above object, a first vehicle device disclosed herein is a vehicle device that can be used in a vehicle that switches between sleep-permitting autonomous driving, which is an autonomous driving level at which the driver is permitted to sleep, and sleep-non-permitting driving, which is an autonomous driving level at which the driver is not permitted to sleep, and includes a driver state estimation unit (103) that can estimate whether the driver is in an abnormal state where he or she is not asleep using multiple types of sensors, and a driving identification unit (102) that identifies whether the vehicle is in sleep-permitting autonomous driving or sleep-non-permitting driving, and when the driving identification unit identifies that the vehicle is in sleep-non-permitting driving, the driver state estimation unit determines whether the driver is in an abnormal state using the multiple types of sensors. On the other hand, when the driving identification unit determines that the driver is in sleep-permitted automatic driving mode, it estimates whether the driver is in an abnormal state by using fewer types of sensors than when it determines that the driver is in sleep-non-permitted automatic driving mode , and the driver state estimation unit is capable of estimating whether the driver is in an abnormal state using an imaging device that images the driver and a bio-sensor that measures the driver's bio-information, and when the driving identification unit determines that the driver is in sleep-non-permitted automatic driving mode, it estimates whether the driver is in an abnormal state using the imaging device and the bio-sensor, while when the driving identification unit determines that the driver is in sleep-permitted automatic driving mode, it estimates whether the driver is in an abnormal state using the imaging device but not the bio-sensor .
In order to achieve the above object, a second vehicle device disclosed herein is a vehicle device that can be used in a vehicle that switches between sleep-permitting autonomous driving, which is an autonomous driving level at which the driver is permitted to sleep, and sleep-non-permitting driving, which is an autonomous driving level at which the driver is not permitted to sleep, and includes a driver state estimation unit (103) that can estimate whether the driver is in an abnormal state where he or she is not asleep using multiple types of sensors, and a driving identification unit (102) that identifies whether the vehicle is in sleep-permitting autonomous driving or sleep-non-permitting driving, and when the driving identification unit identifies that the vehicle is in sleep-non-permitting driving, the driver state estimation unit While several types of sensors are used to estimate whether the driver is in an abnormal state, when the driving identification unit determines that the driver is in sleep-permitted automatic driving, the type of sensors used is reduced to estimate whether the driver is in an abnormal state compared to when sleep-non-permitted driving is determined; the driver state estimation unit estimates whether the driver is in an abnormal state using fewer types of sensors than when sleep-non-permitted driving is determined, and if it estimates that the driver is in an abnormal state, even when the driving identification unit determines that the driver is in sleep-permitted automatic driving, it re-estimates whether the driver is in an abnormal state using the same number of types of sensors as when sleep-non-permitted driving is determined.
In order to achieve the above object, a third vehicle device of the present disclosure is a vehicle device that can be used in a vehicle that switches between sleep-permitted autonomous driving, which is an autonomous driving level at which the driver is permitted to sleep, and sleep-non-permitted driving, which is an autonomous driving level at which the driver is not permitted to sleep, and includes a driver state estimation unit (103) that can estimate whether the driver is in an abnormal state where he or she is not asleep using multiple types of sensors, and a driving identification unit (102) that identifies whether the vehicle is in sleep-permitted autonomous driving or sleep-non-permitted driving, and when the driving identification unit identifies that the vehicle is in sleep-non-permitted driving, the driver state estimation unit estimates whether the driver is in an abnormal state using multiple types of sensors, while the driving identification unit When it is determined that the driver is in sleep-permitted automatic driving mode, the number of sensors used is reduced compared to when it is determined that the driver is in sleep-non-permitted automatic driving mode to estimate whether the driver is in an abnormal state, and the vehicle is provided with a seat control instruction unit (111) that controls the reclining angle of the vehicle's electric seat, and when the driver state estimation unit estimates that the driver is in an abnormal state and the reclining angle of the electric seat of the vehicle's driver's seat is a sleep angle where the angle of the seat back with respect to the vehicle floor surface is reclined less than a first specified angle, the seat control instruction unit returns the reclining angle of the electric seat of the driver's seat to a reference angle where the angle of the seat back with respect to the floor surface is raised to or above a second specified angle which is greater than the first specified angle.
In order to achieve the above object, a fourth vehicle device of the present disclosure is a vehicle device that can be used in a vehicle that switches between sleep-permitting automatic driving, which is an automated driving level at which the driver is permitted to sleep, and sleep-non-permitting driving, which is an automated driving level at which the driver is not permitted to sleep, and includes a driver state estimation unit (103) that can estimate whether the driver is in an abnormal state where he or she is not asleep using multiple types of sensors, and a driving identification unit (102) that identifies whether the vehicle is in sleep-permitting automatic driving or sleep-non-permitting driving, and when the driving identification unit identifies that the vehicle is in sleep-permitting automatic driving, the driver state estimation unit estimates whether the driver is in an abnormal state using multiple types of sensors, while when the driving identification unit identifies that the vehicle is in sleep-permitting automatic driving, the driver state estimation unit uses multiple types of sensors to estimate whether the driver is in an abnormal state, while when the driving identification unit identifies that the vehicle is in sleep-permitting automatic driving, the driver state estimation unit uses more sensors than when the vehicle is in sleep-non-permitting driving. The vehicle is provided with a third evacuation instruction unit (112) that, based on at least the driver state estimation unit's estimation that the driver is in an abnormal state, causes the vehicle to take automatic evacuation action and make an emergency call to the center. If a specified evacuation area reachable by sleep-permitted autonomous driving exists, the third evacuation instruction unit causes the vehicle to take an evacuation action of driving to the evacuation area by sleep-permitted autonomous driving and then stopping the vehicle, whereas if no evacuation area reachable by sleep-permitted autonomous driving exists, the third evacuation instruction unit causes the vehicle to take an evacuation action of making an emergency stop, and if the vehicle is driven to the evacuation area by sleep-permitted autonomous driving and then stopped, causes an emergency call to be made when the vehicle is not scheduled to change lanes and is able to drive a specified distance or more.
In order to achieve the above object, a fifth vehicle device of the present disclosure is a vehicle device that can be used in a vehicle that switches between sleep-permitted automatic driving, which is an automated driving level where the driver is permitted to sleep, and sleep-non-permitted driving, which is an automated driving level where the driver is not permitted to sleep, and is equipped with a driver state estimation unit (103) that can estimate whether the driver is in an abnormal state where he or she is not asleep using multiple types of sensors, and a driving identification unit (102) that identifies whether the vehicle is in sleep-permitted automatic driving or sleep-non-permitted driving, and when the driving identification unit identifies that the vehicle is in sleep-non-permitted driving, the driver state estimation unit estimates whether the driver is in an abnormal state using multiple types of sensors. On the other hand, when the driving identification unit determines that the vehicle is in sleep-permitted automatic driving mode, the number of sensors used is reduced compared to when the vehicle is in sleep-non-permitted driving mode to estimate whether the driver is in an abnormal state, and the vehicle is provided with a passenger state estimation unit (105b) capable of estimating whether passengers other than the driver are in an abnormal state, and a second evacuation instruction unit (112b) that causes the vehicle to at least automatically take evacuation action when it is estimated that multiple occupants are in an abnormal state based on the estimation results from the driver state estimation unit and the passenger state estimation unit, and the second evacuation instruction unit causes the vehicle to take evacuation action without confirming with the occupants whether they are in an abnormal state when it is estimated that multiple occupants are in an abnormal state.

In order to achieve the above object, a first estimation method for a vehicle disclosed herein is an estimation method for a vehicle that can be used in a vehicle that switches between sleep-permitting autonomous driving, which is an autonomous driving level at which the driver is permitted to sleep, and sleep-non-permitting driving, which is an autonomous driving level at which the driver is not permitted to sleep, and includes a driver state estimation step executed by at least one processor, capable of estimating whether the driver is in an abnormal state where he/she is not asleep using multiple types of sensors, and a driving identification step of identifying whether the vehicle is in sleep-permitting autonomous driving or sleep-non-permitting driving, and in the driver state estimation step, when it is identified in the driving identification step that the vehicle is in sleep-non-permitting driving, the method includes: While estimating whether the driver is in an abnormal state, if the driving identification process determines that the driver is in sleep-permitted automatic driving mode, the number of types of sensors used to estimate whether the driver is in an abnormal state is reduced compared to when the driver is in sleep-non-permitted driving mode ; in the driver state estimation process, it is possible to estimate whether the driver is in an abnormal state using an imaging device that images the driver and a bio-sensor that measures the driver's bio-information; if the driving identification process determines that the driver is in sleep-non-permitted automatic driving mode, the imaging device and the bio-sensor are used to estimate whether the driver is in an abnormal state, while if the driving identification process determines that the driver is in sleep-permitted automatic driving mode, the imaging device but not the bio-sensor is used to estimate whether the driver is in an abnormal state .
In order to achieve the above object, a second estimation method for a vehicle disclosed herein is an estimation method for a vehicle that can be used in a vehicle that switches between sleep-permitting autonomous driving, which is an autonomous driving level at which the driver is permitted to sleep, and sleep-non-permitting driving, which is an autonomous driving level at which the driver is not permitted to sleep, and includes a driver state estimation step executed by at least one processor, capable of estimating whether the driver is in an abnormal state other than a sleeping state using multiple types of sensors, and a driving identification step of identifying whether the vehicle is in sleep-permitting autonomous driving or sleep-non-permitting driving, and in the driver state estimation step, In this case, multiple types of sensors are used to estimate whether the driver is in an abnormal state, whereas in the driving identification process, if the driver is identified as being in sleep-permitted automatic driving, fewer types of sensors are used to estimate whether the driver is in an abnormal state than when the driver is identified as being in sleep-non-permitted driving.In the driver state estimation process, fewer types of sensors are used to estimate whether the driver is in an abnormal state than when the driver is identified as being in sleep-non-permitted driving, and if it is determined that the driver is in an abnormal state, even if the driver is identified as being in sleep-permitted automatic driving in the driving identification process, whether the driver is in an abnormal state is re-estimated using the same number of types of sensors as when the driver is identified as being in sleep-non-permitted driving.
In order to achieve the above object, a third estimation method for a vehicle disclosed herein is an estimation method for a vehicle that can be used in a vehicle that switches between sleep-permitting autonomous driving, which is an autonomous driving level at which the driver is permitted to sleep, and sleep-non-permitting driving, which is an autonomous driving level at which the driver is not permitted to sleep, and includes a driver state estimation step executed by at least one processor, capable of estimating whether the driver is in an abnormal state where he or she is not asleep using multiple types of sensors, and a driving identification step that identifies whether the vehicle is in sleep-permitting autonomous driving or sleep-non-permitting driving, and in the driver state estimation step, if it is identified in the driving identification step that the driver is in sleep-non-permitting driving, the driver state estimation step uses multiple types of sensors to infer whether the driver is in an abnormal state. On the other hand, when the driving identification process determines that the driver is in sleep-permitted automatic driving mode, the number of sensors used is reduced to estimate whether the driver is in an abnormal state compared to when the driver is in sleep-non-permitted driving mode, and the process includes a seat control instruction process for controlling the reclining angle of the vehicle's electric seat, and when the driver state estimation process determines that the driver is in an abnormal state and the reclining angle of the electric seat of the vehicle's driver's seat is a sleep angle where the angle of the seat back relative to the floor of the vehicle is reclined less than a first specified angle, the seat control instruction process returns the reclining angle of the electric seat of the driver's seat to a reference angle where the angle of the seat back relative to the floor is raised to or above a second specified angle which is greater than the first specified angle.
In order to achieve the above object, a fourth estimation method for a vehicle disclosed herein is an estimation method for a vehicle that can be used in a vehicle that switches between sleep-permitting automatic driving, which is an automated driving level at which the driver is permitted to sleep, and sleep-non-permitting driving, which is an automated driving level at which the driver is not permitted to sleep, and includes a driver state estimation step executed by at least one processor, capable of estimating whether the driver is in an abnormal state where he or she is not asleep using multiple types of sensors, and a driving identification step that identifies whether the vehicle is in sleep-permitting automatic driving or sleep-non-permitting driving, and in the driver state estimation step, if the driving identification step identifies that the vehicle is in sleep-permitting automatic driving, the multiple types of sensors are used to estimate whether the driver is in an abnormal state, while if the driving identification step identifies that the vehicle is in sleep-permitting automatic driving, the method includes a driver state estimation step that estimates whether the driver is in an abnormal state using multiple types of sensors, This method estimates whether the driver is in an abnormal state by using fewer types of sensors than when determining that the driver is in an abnormal state, and includes a third evacuation instruction step of having the vehicle perform automatic evacuation action and make an emergency call to a center based on at least the driver state estimation step estimating that the driver is in an abnormal state, and in the third evacuation instruction step, if a specified evacuation area reachable by sleep-permitted automatic driving exists, an evacuation action is performed in which the vehicle is driven to the evacuation area by sleep-permitted automatic driving and then stopped, whereas if no evacuation area reachable by sleep-permitted automatic driving exists, an evacuation action is performed to make an emergency stop of the vehicle, and in the case where the vehicle is driven to the evacuation area by sleep-permitted automatic driving and then stopped, an emergency call is made when the vehicle is not scheduled to change lanes and is able to travel more than a specified distance.
In order to achieve the above object, a fifth estimation method for a vehicle disclosed herein is an estimation method for a vehicle that can be used in a vehicle that switches between sleep-permitting autonomous driving, which is an autonomous driving level at which the driver is permitted to sleep, and sleep-non-permitting driving, which is an autonomous driving level at which the driver is not permitted to sleep, and includes a driver state estimation step executed by at least one processor, capable of estimating whether the driver is in an abnormal state where he/she is not asleep using multiple types of sensors, and a driving identification step that identifies whether the vehicle is in sleep-permitting autonomous driving or sleep-non-permitting driving, and in the driver state estimation step, if it is identified in the driving identification step that the driver is in sleep-non-permitting driving, the method includes detecting whether the driver is abnormally asleep using multiple types of sensors. The method includes a passenger state estimation step that estimates whether or not a passenger other than the driver is in an abnormal state, and a second evacuation instruction step that causes the vehicle to at least automatically take evacuation action when it is estimated that multiple occupants are in an abnormal state based on the estimation results in the driver state estimation step and the passenger state estimation step, and in the second evacuation instruction step, when it is estimated that multiple occupants are in an abnormal state, the evacuation action is taken without confirming with the occupants whether or not they are in an abnormal state, when it is estimated that multiple occupants are in an abnormal state.

According to the above configuration, during sleep-unauthorized driving, which is an automated driving level where the driver is not allowed to sleep, multiple types of sensors are used to estimate whether the driver is in an abnormal state, making it easier to distinguish the driver's abnormal state from a sleeping state. On the other hand, during sleep-permitted automated driving, which is an automated driving level where the driver is allowed to sleep, fewer types of sensors are used to estimate whether the driver is in an abnormal state than when sleep-unauthorized driving is specified. Therefore, it is possible to estimate whether the driver is in an abnormal state without using sensors that may not be available during sleep-permitted automated driving. As a result, it is possible to easily distinguish the driver's abnormal state from a sleeping state and estimate it according to the automation level of the vehicle, while also reducing wasteful processing.

1 is a diagram illustrating an example of a schematic configuration of a vehicle system 1. FIG. FIG. 2 is a diagram illustrating an example of a schematic configuration of an HCU 10. 10 is a flowchart showing an example of the flow of an abnormality estimation-related process in the HCU 10. 11 is a flowchart showing an example of a flow of abnormality processing in the HCU 10. 1 is a diagram showing an example of a schematic configuration of a vehicle system 1a; FIG. 2 is a diagram illustrating an example of a schematic configuration of an HCU 10a. FIG. 2 is a diagram showing an example of a schematic configuration of a vehicle system 1b. FIG. 2 is a diagram illustrating an example of a schematic configuration of an HCU 10b. FIG. 2 is a diagram showing an example of a schematic configuration of a vehicle system 1c. FIG. 2 is a diagram illustrating an example of a schematic configuration of an HCU 10c.

Several embodiments for disclosure will be described with reference to the drawings. For ease of explanation, parts in several embodiments that have the same functions as parts shown in the drawings used in the previous explanations may be given the same reference numerals and their explanations may be omitted. For parts given the same reference numerals, the explanations in other embodiments may be referred to.

(Embodiment 1)
<General configuration of vehicle system 1>
Hereinafter, a first embodiment of the present disclosure will be described with reference to the drawings. A vehicle system 1 shown in FIG. 1 can be used in a vehicle capable of automatic driving (hereinafter, an automatic driving vehicle). As shown in FIG. 1, the vehicle system 1 includes an HCU (Human Machine Interface Control Unit) 10, a communication module 11, a locator 12, a map database (hereinafter, a map DB) 13, a vehicle state sensor 14, a surroundings monitoring sensor 15, a vehicle control ECU 16, an automatic driving ECU 17, a seat ECU 18, an interior camera 19, a biosensor 20, an alarm device 21, and a user input device 22. For example, the HCU 10, the communication module 11, the locator 12, the map DB 13, the vehicle state sensor 14, the surroundings monitoring sensor 15, the vehicle control ECU 16, the automatic driving ECU 17, and the seat ECU 18 may be configured to be connected to an in-vehicle LAN (see the LAN in FIG. 1). Although the vehicle using the vehicular system 1 is not necessarily limited to an automobile, the following description will be given taking an example in which the system is used in an automobile.

There can be multiple levels of autonomous driving for autonomous vehicles (hereafter referred to as "automation levels"), as defined by the SAE, for example. Automation levels are classified into LV0 to 5, for example, as follows:

LV0 is the level at which the driver performs all driving tasks without the system intervening. The driving task may be referred to as a dynamic driving task. Driving tasks include, for example, steering, acceleration/deceleration, and surrounding monitoring. LV0 corresponds to so-called manual driving. LV1 is the level at which the system assists with either steering or acceleration/deceleration. LV1 corresponds to so-called driving assistance. LV2 is the level at which the system assists with both steering and acceleration/deceleration. LV2 corresponds to so-called partial driving automation. Note that LV1-2 are also considered to be part of automated driving.

For example, automated driving at LV1-2 is automated driving where the driver has a duty to monitor safe driving (hereinafter, simply referred to as the duty to monitor). In other words, it corresponds to automated driving with a duty to monitor. The duty to monitor includes visual monitoring of the surroundings. Autonomous driving at LV1-2 can be said to be automated driving where a second task is not permitted. A second task is an action other than driving that is permitted for the driver, and is a specific action that is specified in advance. A second task can also be said to be a secondary activity, other activity, etc. It is considered that a second task must not prevent the driver from responding to a request from the automated driving system to take over driving operations. As an example, actions such as watching content such as videos, operating a smartphone, reading, and eating are assumed to be second tasks.

LV3 autonomous driving is a level where the system can perform all driving tasks under certain conditions, and the driver performs driving operations in an emergency. In LV3 autonomous driving, the driver is required to be able to respond quickly when the system requests a handover of driving. This handover of driving can also be said to be a transfer of the responsibility of monitoring the surroundings from the vehicle's system to the driver. LV3 corresponds to so-called conditional driving automation. LV3 includes area-limited LV3 that is limited to a specific area. The specific area referred to here may be a highway. The specific area may be, for example, a specific lane. LV3 also includes traffic jam-limited LV3 that is limited to times of traffic congestion. The traffic jam-limited LV3 may be configured to be limited to times of traffic congestion on a highway, for example. The highway may include a motorway.

LV4 autonomous driving is a level where the system can perform all driving tasks, except in specific situations such as on unmanageable roads or in extreme environments. LV4 corresponds to so-called highly automated driving. LV5 autonomous driving is a level where the system can perform all driving tasks in any environment. LV5 corresponds to so-called fully automated driving. LV4 and LV5 autonomous driving can be performed, for example, on driving sections where high-precision map data has been developed. High-precision map data will be described later.

For example, autonomous driving at levels 3 to 5 is autonomous driving where the driver has no obligation to monitor. In other words, it corresponds to autonomous driving without a monitoring obligation. Autonomous driving at levels 3 to 5 can be said to be autonomous driving where a second task is permitted. Of the autonomous driving levels 3 to 5, autonomous driving at level 4 or higher corresponds to autonomous driving where the driver is permitted to sleep. In other words, it corresponds to sleep-permitted autonomous driving. Of the autonomous driving levels 3 to 5, autonomous driving where the driver is not permitted to sleep. The autonomous driving vehicle of this embodiment is assumed to be capable of switching the automation level. The automation level may be configured to be switchable only between some of the levels 0 to 5. The autonomous driving vehicle of this embodiment is assumed to be capable of at least sleep-permitted autonomous driving and driving at levels 3 or lower (hereinafter referred to as sleep-non-permitted driving). Sleep-non-permitted driving may include manual driving at level 0.

The communication module 11 transmits and receives information via wireless communication with a center outside the vehicle. In other words, it performs wide-area communication. The communication module 11 receives congestion information, etc. from the center via wide-area communication. The communication module 11 may transmit and receive information with other vehicles via wireless communication. In other words, it may perform vehicle-to-vehicle communication. The communication module 11 may transmit and receive information via wireless communication with a roadside device installed on the roadside. In other words, it may perform road-to-vehicle communication. When performing road-to-vehicle communication, the communication module 11 may receive information about surrounding vehicles transmitted from surrounding vehicles of the vehicle via the roadside device. The communication module 11 may also receive information about surrounding vehicles transmitted from surrounding vehicles of the vehicle via the center via wide-area communication.

The locator 12 includes a GNSS (Global Navigation Satellite System) receiver and an inertial sensor. The GNSS receiver receives positioning signals from multiple positioning satellites. The inertial sensor includes, for example, a gyro sensor and an acceleration sensor. The locator 12 sequentially measures the position of the vehicle (hereinafter, the vehicle position) on which the locator 12 is mounted, by combining the positioning signals received by the GNSS receiver with the measurement results of the inertial sensor. The vehicle position may be expressed, for example, in latitude and longitude coordinates. Note that the vehicle position may also be measured using a travel distance calculated from a signal sequentially output from a vehicle speed sensor mounted on the vehicle.

The map DB 13 is a non-volatile memory that stores high-precision map data. The high-precision map data is map data with higher precision than the map data used for route guidance in the navigation function. The map DB 13 may also store map data used for route guidance. The high-precision map data includes information that can be used for automated driving, such as three-dimensional shape information of the road, information on the number of lanes, and information indicating the permitted traveling direction for each lane. In addition, the high-precision map data may include node point information indicating the positions of both ends of road markings such as dividing lines. The locator 12 may be configured not to use a GNSS receiver by using three-dimensional shape information of the road. For example, the locator 12 may be configured to identify the vehicle position using three-dimensional shape information of the road and the detection results of a surrounding monitoring sensor 15 such as a LIDAR (Light Detection and Ranging/Laser Imaging Detection and Ranging) that detects a point cloud of characteristic points of the road shape and structures or a surrounding monitoring camera. The three-dimensional shape information of the road may be generated based on captured images using Road Experience Management (REM).

Map data distributed from an external server may be received by wide area communication via the communication module 11 and stored in the map DB 13. In this case, the map DB 13 may be a volatile memory, and the communication module 11 may be configured to sequentially acquire map data for an area corresponding to the vehicle position.

The vehicle state sensor 14 is a group of sensors for detecting various states of the vehicle. The vehicle state sensor 14 includes a vehicle speed sensor, a seating sensor, a steering torque sensor, an accelerator sensor, a brake sensor, etc. The vehicle speed sensor detects the speed of the vehicle. The seating sensor is a sensor for detecting the seating state of the user in the seat. As an example, a pressure-sensitive element provided on the seat surface of the seat may be used as the seating sensor.

The steering torque sensor detects the steering torque applied to the steering wheel. The accelerator sensor detects whether the accelerator pedal is depressed. The accelerator sensor may be an accelerator depression force sensor that detects the depression force applied to the accelerator pedal. The accelerator sensor may be an accelerator stroke sensor that detects the amount of depression of the accelerator pedal. The accelerator sensor may be an accelerator switch that outputs a signal according to whether the accelerator pedal is depressed. The brake sensor detects whether the brake pedal is depressed. The brake sensor may be a brake depression force sensor that detects the depression force applied to the brake pedal. The brake sensor may be a brake stroke sensor that detects the amount of depression of the brake pedal. The brake sensor may be a brake switch that outputs a signal according to whether the brake pedal is depressed.

The vehicle condition sensor 14 outputs the detected sensing information to the in-vehicle LAN. The sensing information detected by the vehicle condition sensor 14 may be configured to be output to the in-vehicle LAN via an ECU installed in the vehicle.

The perimeter monitoring sensor 15 monitors the environment around the vehicle. As an example, the perimeter monitoring sensor 15 detects obstacles around the vehicle, such as moving objects such as pedestrians and other vehicles, and stationary objects such as objects fallen on the road. In addition, the perimeter monitoring sensor 15 detects road markings such as lane markings around the vehicle. The perimeter monitoring sensor 15 is, for example, a perimeter monitoring camera that captures a predetermined range around the vehicle, a millimeter wave radar that transmits a search wave to a predetermined range around the vehicle, a sonar, a LIDAR, or other sensor. The predetermined range may be a range that at least partially includes the front, rear, left and right of the vehicle. The perimeter monitoring camera sequentially outputs the captured images to the automatic driving ECU 17 as sensing information. The sonar, millimeter wave radar, LIDAR, or other sensor that transmits a search wave reflected by an obstacle sequentially outputs the scanning result based on the received signal obtained when receiving the reflected wave to the automatic driving ECU 17 as sensing information. The sensing information detected by the perimeter monitoring sensor 15 may be output to the automatic driving ECU 17 without passing through the in-vehicle LAN.

The vehicle control ECU 16 is an electronic control device that controls the driving of the vehicle. Driving control includes acceleration/deceleration control and/or steering control. The vehicle control ECU 16 includes a steering ECU that controls steering, a power unit control ECU that controls acceleration/deceleration, and a brake ECU. The vehicle control ECU 16 controls driving by outputting control signals to each driving control device installed in the vehicle, such as an electronically controlled throttle, a brake actuator, and an EPS (Electric Power Steering) motor.

The autonomous driving ECU 17 includes, for example, a processor, memory, I/O, and a bus connecting these, and executes control programs stored in the memory to perform processes related to autonomous driving. The memory referred to here is a non-transitory tangible storage medium that non-temporarily stores computer-readable programs and data. The non-transitory tangible storage medium is realized by a semiconductor memory or a magnetic disk, for example. The autonomous driving ECU 17 includes, as functional blocks, a driving environment recognition unit, an action determination unit, and a control execution unit.

The driving environment recognition unit recognizes the driving environment of the vehicle from the vehicle position acquired from the locator 12, the map data acquired from the map DB 13, and the sensing information acquired from the surrounding monitoring sensor 15. As an example, the driving environment recognition unit uses this information to recognize the positions, shapes, and movement states of objects around the vehicle, and generates a virtual space that reproduces the actual driving environment. The driving environment recognition unit may also recognize the presence, relative positions, and relative speeds of vehicles around the vehicle as part of the driving environment from the sensing information acquired from the surrounding monitoring sensor 15. The driving environment recognition unit may recognize the vehicle position on the map from the vehicle position and map data. If the driving environment recognition unit can acquire position information, speed information, and the like of surrounding vehicles via the communication module 11, it may also use this information to recognize the driving environment.

The driving environment recognition unit may also determine whether the driving area is a manual driving area (hereinafter, MD area) in the driving area of the vehicle. The driving environment recognition unit may also determine whether the driving area is an automatic driving area (hereinafter, AD area) in the driving area of the vehicle. The driving environment recognition unit may also determine whether the driving area is an ST section and a non-ST section (described below) in the AD area.

MD areas are areas where automated driving is prohibited. In other words, MD areas are areas where the driver is required to perform all of the vehicle's longitudinal control, lateral control, and surrounding monitoring. The longitudinal direction is the direction that corresponds to the front-to-rear direction of the vehicle. The lateral direction is the direction that corresponds to the width direction of the vehicle. Longitudinal control corresponds to the acceleration/deceleration control of the vehicle. Lateral control corresponds to the steering control of the vehicle. For example, an MD area may be a general road. An MD area may also be a driving section of a general road where high-precision map data is not available.

An AD area is an area where autonomous driving is permitted. In other words, an AD area is an area where it is specified that the vehicle can take over one or more of longitudinal control, lateral control, and periphery monitoring. For example, an AD area may be a highway. An AD area may also be a driving section for which high-precision map data is available. For example, autonomous driving of area-limited LV3 may be permitted only on highways. Autonomous driving of traffic jam-limited LV3 may be permitted only when there is a traffic jam in an AD area.

AD areas are divided into ST sections and non-ST sections. ST sections are sections where area-limited LV3 autonomous driving (hereinafter area-limited autonomous driving) is permitted. Non-ST sections are sections where LV2 or lower autonomous driving and congestion-limited LV3 autonomous driving are possible. In this embodiment, there is no distinction between non-ST sections where LV1 autonomous driving is permitted and non-ST sections where LV2 autonomous driving is permitted. Non-ST sections may be sections of AD areas that do not fall under the ST section.

The behavior determination unit switches the control of driving operations between the driver and the vehicle's system. When the system has control of driving operations, the behavior determination unit determines a driving plan for driving the vehicle based on the results of recognition of the driving environment by the driving environment recognition unit. The driving plan may determine the route to the destination and the behavior that the vehicle should take to reach the destination. Examples of behavior include going straight, turning right, turning left, changing lanes, etc.

The behavior determination unit also switches the automation level of the vehicle's autonomous driving as necessary. The behavior determination unit determines whether or not it is possible to increase the automation level. For example, when the vehicle moves from an MD area to an AD area, it may determine that it is possible to switch from autonomous driving at LV4 or below to autonomous driving at LV4 or above. If the behavior determination unit determines that it is possible to increase the automation level and if the driver approves the increase in the automation level, it may increase the automation level.

The behavior determination unit may lower the automation level when it determines that a lowering of the automation level is necessary. Examples of cases where it is determined that a lowering of the automation level is necessary include when an override is detected, when a planned driving changeover is performed, and when an unplanned driving changeover is performed. An override is an operation by which the driver of the vehicle spontaneously acquires control of the vehicle. In other words, an override is an operational intervention by the driver of the vehicle. The behavior determination unit may detect an override from sensing information obtained from the vehicle state sensor 14. For example, the behavior determination unit may detect an override when the steering torque detected by the steering torque sensor exceeds a threshold value. The behavior determination unit may detect an override when the accelerator sensor detects depression of the accelerator pedal. Alternatively, the behavior determination unit may detect an override when the brake sensor detects depression of the brake pedal. A planned driving changeover is a planned driving changeover determined by the system. An unplanned driving changeover is an unplanned and sudden driving changeover determined by the system.

When the control authority for driving operations is in the vehicle's system, the control execution unit executes acceleration/deceleration control and steering control of the vehicle in accordance with the driving plan determined by the action determination unit in cooperation with the vehicle control ECU 16. The control execution unit executes, for example, ACC (Adaptive Cruise Control), LTA (Lane Tracing Assist), and LCA (Lane Change Assist).

ACC control is a control that allows the host vehicle to travel at a constant speed at a set vehicle speed, or to follow a preceding vehicle. In following travel, acceleration/deceleration control is performed to maintain the distance between the host vehicle and the nearest preceding vehicle at a target distance. The target distance may be set according to the speed of the host vehicle, for example. LTA control is a control that keeps the host vehicle traveling within its lane. In LTA control, steering control is performed to keep the host vehicle traveling within its lane. LCA control is a control that automatically changes lanes from the host vehicle's lane to an adjacent lane. In LCA control, lane changes are made by performing acceleration/deceleration control and steering control.

The seat ECU 18 is an electronic control device that executes various processes related to the control of the seat environment, such as adjusting the seat position of the vehicle's seat. Here, the description will be given assuming that the vehicle's seat is an electric seat whose slide position and reclining angle can be electrically changed. Examples of the seat include the driver's seat, the passenger seat, and the rear seat. The electric seat may be only some of the driver's seat, the passenger seat, and the rear seat. The seat ECU 18 adjusts the seat position by controlling a motor (hereinafter, referred to as the seat motor) for adjusting the seat position of the vehicle. Examples of the seat motor include a slide motor that adjusts the slide position and a reclining motor that adjusts the reclining position. The slide position indicates the adjustment position of the seat in the fore-and-aft direction of the vehicle. The reclining position indicates the adjustment angle of the inclination of the seat back. The seat back can be referred to as the backrest. The seat ECU 18 sequentially detects the slide position and the reclining position. The seat ECU 18 may detect the slide position, for example, from the rotation angle of the slide motor. The seat ECU 18 detects the reclining position from the rotation angle of the reclining motor.

The interior camera 19 captures an image of a predetermined range in the vehicle cabin. This interior camera 19 corresponds to an imaging device. It is preferable that the interior camera 19 captures an image of at least an area including the driver's seat of the vehicle. It is more preferable that the interior camera 19 captures an area including the driver's seat of the vehicle, the passenger seat, and the rear seat. The interior camera 19 is composed of, for example, a near-infrared light source and a near-infrared camera, and a control unit that controls them. The interior camera 19 captures an occupant of the vehicle irradiated with near-infrared light by the near-infrared light source using the near-infrared camera. The image captured by the near-infrared camera is analyzed by the control unit. The control unit performs image analysis on the captured image to detect the facial features of the occupant. The control unit may detect the facial direction of the occupant, the posture of the occupant, the degree of awakening, the inability to drive, etc. based on the detected features of the upper body including the face of the occupant. The detection of the degree of awakening may be detected, for example, by the degree of opening and closing of the eyelids. The inability to drive state may be detected based on the continuation of the face facing downward and the deterioration of posture. The indoor camera 19 may attempt to distinguish and detect whether the inability to drive state is a sleeping state or an abnormal state such as fainting based on representative features of each. However, it is considered difficult to distinguish and detect whether the inability to drive state is a sleeping state or an abnormal state using only the indoor camera 19. The sleeping state is not considered to be an abnormal state.

The biosensor 20 measures bioinformation of the vehicle occupant. The biosensor 20 sequentially outputs the measured bioinformation to the HCU 10. The biosensor 20 is provided in the vehicle. The biosensor 20 is provided in a part of the vehicle that the skin of the driver of the vehicle comes into contact with while the vehicle is traveling. The biosensor 20 may be provided, for example, in the steering wheel of the vehicle. In the following, the description will be continued assuming that the biosensor 20 is provided in the steering wheel. Examples of bioinformation measured by the biosensor 20 include respiration, pulse, heart rate, etc. Note that the biosensor 20 may be configured to measure bioinformation other than respiration, pulse, and heart rate. For example, the biosensor 20 may measure heart rate fluctuation, sweating, body temperature, blood pressure, skin conductance, etc.

The notification device 21 is installed in the vehicle and presents information to the interior of the vehicle. In other words, the notification device 21 notifies the occupants of the vehicle. The notification device 21 notifies according to the control of the HCU 10. Examples of the notification device 21 include a display and an audio output device.

The display device issues notifications by displaying information. Examples of the display device that can be used include a meter MID (Multi Information Display), a CID (Center Information Display), and a HUD (Head-Up Display). The audio output device issues notifications by outputting audio. Examples of audio output devices include speakers.

The meter MID is a display provided in front of the driver's seat inside the vehicle cabin. As an example, the meter MID may be configured to be provided on a meter panel. The CID is a display provided in the center of the vehicle's instrument panel. The HUD is provided in the vehicle cabin, for example, on the instrument panel. The HUD projects a display image formed by a projector onto a predetermined projection area on the front windshield as a projection member. The light of the image reflected by the front windshield into the vehicle cabin is perceived by the driver sitting in the driver's seat. This allows the driver to view a virtual image of the display image formed in front of the front windshield superimposed on a part of the foreground. The HUD may be configured to project a display image onto a combiner provided in front of the driver's seat instead of the front windshield.

The user input device 22 accepts input from the user. The user input device 22 may be an operation device that accepts operation input from the user. The operation device may be a mechanical switch or a touch switch integrated with a display. Note that the user input device 22 is not limited to an operation device that accepts operation input, so long as it is a device that accepts input from the user. For example, the user input device 22 may be a voice input device that accepts voice input of commands from the user.

The HCU 10 is mainly composed of a computer equipped with a processor, volatile memory, non-volatile memory, I/O, and a bus connecting these. The HCU 10 is connected to an interior camera 19, a biosensor 20, an alarm device 21, and a user input device 22. The HCU 10 executes a control program stored in the non-volatile memory to perform processing related to estimating the state of the occupants. This HCU 10 corresponds to a vehicle device. In this embodiment, the HCU 10 is used in a vehicle that is capable of switching at least between sleep-permitting automatic driving and sleep-non-permitting driving. The configuration of the HCU 10 will be described in detail below.

<General configuration of HCU 10>
Next, the schematic configuration of the HCU 10 will be described with reference to Fig. 2. As shown in Fig. 2, the HCU 10 includes an ECU communication unit 101, a driving identification unit 102, a driver state estimation unit 103, a passenger presence/absence identification unit 104, a passenger state estimation unit 105, and a notification control unit 106 as functional blocks. The execution of processing of each functional block of the HCU 10 by a computer corresponds to the execution of an estimation method for a vehicle. Note that some or all of the functions executed by the HCU 10 may be configured as hardware using one or more ICs or the like. Also, some or all of the functional blocks included in the HCU 10 may be realized by a combination of software execution by a processor and hardware members.

The ECU communication unit 101 performs processing to output information to ECUs of the vehicle other than the HCU 10, and processing to acquire information from ECUs of the vehicle other than the HCU 10. For example, the ECU communication unit 101 may be configured to perform processing to output information to the automatic driving ECU 17 and the seat ECU 18. The ECU communication unit 101 may also be configured to perform processing to acquire information from the automatic driving ECU 17 and the seat ECU 18. The ECU communication unit 101 includes a seat processing unit 111 and an evacuation processing unit 112 as sub-functional blocks. The processing in the seat processing unit 111 and the evacuation processing unit 112 will be described later.

The driving identification unit 102 identifies whether the current automation level of the vehicle is LV3 or lower, or LV4 or higher. In other words, the driving identification unit 102 identifies whether the vehicle is in sleep-permitted automatic driving or sleep-non-permitted automatic driving. This processing by the driving identification unit 102 corresponds to the driving identification step. The driving identification unit 102 can identify whether the vehicle is in sleep-permitted automatic driving or sleep-non-permitted automatic driving from the information acquired by the ECU communication unit 101 from the automatic driving ECU 17.

The driver state estimation unit 103 estimates the state of the driver of the vehicle. The driver state estimation unit 103 is capable of estimating whether or not an abnormal state exists using multiple types of sensors. The processing in this driver state estimation unit 103 corresponds to the driver state estimation process. In this embodiment, the driver state estimation unit 103 is capable of estimating whether or not an abnormal state exists using the indoor camera 19 and the biometric sensor 20. The indoor camera 19 and the biometric sensor 20 correspond to sensors.

When the driving identification unit 102 identifies that the driver is in a sleep-unpermitted driving state, the driver state estimation unit 103 uses multiple types of sensors to estimate whether the driver is in an abnormal state. The driver state estimation unit 103 may estimate whether the driver is in an abnormal state using the indoor camera 19 and the biosensor 20. By using the biosensor 20, it is possible to estimate whether the driver is in an abnormal state using the driver's bioinformation. Therefore, by using the biosensor 20 in addition to the indoor camera 19, it becomes easier to estimate whether the driver is in an abnormal state, distinguishing it from a sleeping state. Therefore, even if it is difficult to accurately estimate whether the driver is in an abnormal state using only the indoor camera 19, it becomes possible to more accurately estimate whether the driver is in an abnormal state. In addition, during sleep-unpermitted driving, it is highly likely that the driver's skin is in contact with the biosensor 20, such as when the driver grips the steering wheel in preparation for a sudden change of driving. When the biosensor 20 is provided on the steering wheel as in the example of this embodiment, this possibility becomes higher. Therefore, even if the biosensor 20 is used to estimate whether the driver is in an abnormal state, there is a high possibility that the process using the biosensor 20 will not be wasted.

On the other hand, when the driving identification unit 102 identifies that the vehicle is in sleep-permitted automatic driving, the driver state estimation unit 103 estimates whether the driver is in an abnormal state by using fewer types of sensors than when the driving identification unit 102 identifies that the vehicle is in sleep-permitted automatic driving. When the driving identification unit 102 identifies that the vehicle is in sleep-permitted automatic driving, the driver state estimation unit 103 uses the interior camera 19 but does not use the biosensor 20 to estimate whether the driver is in an abnormal state. During sleep-permitted automatic driving, the driver may be asleep, and the driver may not be gripping the steering wheel, increasing the possibility that the driver's skin is not in contact with the biosensor 20. Therefore, by estimating whether the driver is in an abnormal state without using the biosensor 20, it is possible to eliminate unnecessary processing that uses the biosensor 20. According to the above configuration, it is possible to easily distinguish the driver's abnormal state from a sleeping state and estimate the abnormal state according to the automation level of the vehicle, while also reducing unnecessary processing.

The driver state estimation unit 103 estimates whether the driver is in an abnormal state by using fewer types of sensors than when determining that the driver is in sleep-unpermitted driving, and when it is determined that the driver is in an abnormal state, it is preferable to re-estimate whether the driver is in an abnormal state using the same number of types of sensors as when determining that the driver is in sleep-unpermitted driving, even when the driving identification unit 102 determines that the driver is in sleep-permitted automatic driving. As a specific example, when the driver is in an abnormal state during sleep-permitted automatic driving and the biosensor 20 is not used, the interior camera 19 and the biosensor 20 may be used to re-estimate whether the driver is in an abnormal state. Furthermore, if the result changes as a result of the re-estimation, the re-estimated result may be updated as the estimation result.

Accordingly, even during sleep-permitted automatic driving, if it is possible to estimate whether the driver is in an abnormal state using the biosensor 20, it becomes possible to more accurately re-estimate whether the driver is in an abnormal state using the biosensor 20. Note that if it is possible to estimate that the driver is not in an abnormal state using only the indoor camera 19, the biosensor 20 is not used to re-estimate whether the driver is in an abnormal state, so that it is possible to avoid wasting time using the biosensor 20 when it is highly likely that the driver is not in an abnormal state. Therefore, during sleep-permitted automatic driving, it becomes possible to accurately re-estimate whether the driver is in an abnormal state while minimizing the waste of using the biosensor 20.

The passenger presence/absence determination unit 104 determines whether or not there is a passenger in the vehicle. A passenger is any occupant of the vehicle other than the driver. The passenger presence/absence determination unit 104 may determine whether or not there is a passenger in the vehicle using a seat occupancy sensor provided in a seat other than the driver's seat. The passenger presence/absence determination unit 104 may determine whether or not there is a passenger in the vehicle based on whether or not a person can be detected by image recognition from an image captured by the interior camera 19 of a range including the passenger seat and rear seats (hereinafter, passenger range image).

The passenger state estimation unit 105 estimates the state of the passenger of the vehicle. The passenger state estimation unit 105 may estimate whether the passenger is in an awake state or not. This passenger state estimation unit 105 corresponds to the awake identification unit. The passenger state estimation unit 105 may estimate whether the passenger is in an awake state or not based on the passenger range image captured by the interior camera 19. The passenger state estimation unit 105 may estimate whether the passenger is in an awake state or not from the passenger's awake level detected by the interior camera 19. The interior camera 19 may detect the passenger's awake level from the facial features of the passenger in the passenger range image. Note that the interior camera 19 may be configured not to detect the passenger's awake level. In this case, the passenger state estimation unit 105 may detect the passenger's awake level based on the passenger range image acquired from the interior camera 19, and estimate whether the passenger is in an awake state or not.

For example, if the passenger presence/absence determination unit 104 determines that there is no passenger, the passenger state estimation unit 105 does not need to perform processing to estimate the state of the passenger in the vehicle. This makes it possible to eliminate unnecessary processing.

The notification control unit 106 causes the notification device 21 to issue a notification to the occupants of the vehicle. When the driver state estimation unit 103 estimates that the driver is in an abnormal state, the notification control unit 106 preferably causes the notification control unit 106 to issue a notification (hereinafter, a confirmation prompt notification) that prompts the occupants to confirm whether or not the driver is in an abnormal state. The confirmation prompt notification may be issued by displaying on a display device or by audio output from an audio output device. The occupants to whom the confirmation prompt notification is issued may be not limited to the driver but may also include passengers. For example, the confirmation prompt notification may be a notification that prompts the user to make an input to the user input device 22 indicating whether or not the driver is in an abnormal state. This makes it possible for the occupants, including the driver, to confirm whether or not the driver is in an abnormal state.

The notification control unit 106 may be configured to issue a confirmation prompt notification when the driver state estimation unit 103 estimates that the driver is in an abnormal state without using the biosensor 20 during sleep-permitted automatic driving. The notification control unit 106 may be configured not to issue a confirmation prompt notification during sleep-non-permitted automatic driving. This is because, during sleep-permitted automatic driving, the vehicle itself runs smoothly even if time is spent checking whether the driver is in an abnormal state. When a confirmation prompt notification is issued, if the driver is not in an abnormal state, it is possible to input to the user input device 22 an indication that the driver is not in an abnormal state. When a confirmation prompt notification is issued, if there is a passenger, it is possible for the passenger to input to the user input device 22 an indication of whether the driver is in an abnormal state. In addition, according to the above configuration, even if the estimation accuracy is poor by estimating an abnormal state without using the biosensor 20, it is possible for the occupant to confirm the estimation result.

When the driver state estimation unit 103 estimates that an abnormal state exists, the passenger presence/absence determination unit 104 determines that there is a passenger, and the passenger state estimation unit 105 estimates that the passenger is awake, it is preferable for the notification control unit 106 to issue a notification (hereinafter, a possible abnormality notification) to the passenger informing the passenger that the driver may be in an abnormal state. The possible abnormality notification may be issued by displaying on a display device or by audio output from an audio output device. The notification control unit 106 may issue a possible abnormality notification to the passenger by displaying on a display device that is easily visible to the passenger, such as a CID. The notification control unit 106 may issue a possible abnormality notification to the passenger by outputting audio from an audio output device near the passenger's seat. If the audio output device is a directional speaker, the notification control unit 106 may output audio toward the passenger's seat, thereby notifying the passenger of the possibility of an abnormality.

The notification control unit 106 may be configured to issue a possible abnormality notification when the driver state estimation unit 103 estimates that the driver is in an abnormal state without using the biosensor 20 during sleep-permitted automatic driving, the passenger presence/absence determination unit 104 identifies the presence of a passenger, and the passenger state estimation unit 105 estimates that the passenger is in an awake state. The notification control unit 106 may be configured not to issue a possible abnormality notification during sleep-non-permitted automatic driving. With this, even if the estimation accuracy is poor by estimating an abnormal state without using the biosensor 20, if the passenger is in an awake state, it is possible to have the passenger confirm the estimation result. Furthermore, if the estimation result is correct, it is possible to have the passenger take action to address the driver's abnormal state.

When the vehicle changes lanes during sleep-permitted autonomous driving, the notification control unit 106 issues a notification (hereinafter, lane change notification) to notify the driver that a lane change is about to occur. The lane change notification may be a display or audio output notifying the driver that a lane change is scheduled to begin. The lane change notification may include a display or audio output notifying the driver of the direction of the change in course due to the lane change. In this embodiment, the lane change notification includes at least an audio output.

The seat processing unit 111 outputs information to the seat ECU 18, causing the seat ECU 18 to control the reclining angle of the electric seat. This seat processing unit 111 corresponds to a seat control instruction unit.

When the driver state estimation unit 103 estimates that an abnormal state exists, and the reclining angle of the electric seat of the driver's seat of the vehicle is a sleep angle, the seat processing unit 111 preferably returns the reclining angle of the electric seat of the driver's seat to a reference angle. The sleep angle is an angle at which the seat back is reclined with respect to the floor surface of the vehicle to less than a first specified angle. The sleep angle is an angle of the seat back for sleeping set when the occupant is sleeping. The first specified angle can be set arbitrarily. For example, an angle less than 45 degrees may be set as the first specified angle. The reference angle is an angle at which the seat back is raised with respect to the floor surface of the vehicle to a second specified angle or more that is greater than the first specified angle. The reference angle is an angle of the standard seat back set when the occupant is not sleeping. The second specified angle can be set arbitrarily. For example, an angle of 45 degrees or more may be set as the second specified angle. For the driver's seat, the angle set as the angle of the seat back when the driver is operating the vehicle may be set. When the seat back is at the standard angle, it is easier to protect the occupant from impact than when it is at the sleeping angle. Therefore, with the above configuration, it is possible to more easily protect the driver from impact when an abnormal state of the driver is estimated.

The seat processing unit 111 may be configured to return the reclining angle of the electric driver's seat to a reference angle when the driver state estimation unit 103 estimates that the driver is in an abnormal state without using the biosensor 20 during sleep-permitted automatic driving and when the reclining angle of the electric driver's seat of the vehicle is at a sleep angle. The seat processing unit 111 may be configured not to perform processing to return the reclining angle of the electric driver's seat to the reference angle during sleep-non-permitted automatic driving. It is highly unlikely that the seat back of the driver's seat is at a sleep angle during sleep-non-permitted automatic driving. Therefore, by setting the condition as being during sleep-permitted automatic driving, it is possible to suppress unnecessary processing.

When the driver state estimation unit 103 estimates that an abnormal state has occurred, the passenger presence/absence determination unit 104 determines that a passenger is present, and the reclining position of the electric seat of the passenger's seat (hereinafter, passenger seat) is at a sleep angle, it is preferable for the seat processing unit 111 to return the reclining position of the electric seat of the passenger's seat to the reference angle. This makes it possible to put the passenger in a position that makes it easier to deal with the driver's abnormal state when it is estimated that the driver is in an abnormal state. It also makes it easier to protect the passenger from impacts when an abnormal state of the driver is estimated. The seat processing unit 111 may determine whether the reclining position of the electric seat of the passenger's seat is at a sleep angle based on information acquired from the seat ECU 18.

The seat processing unit 111 may be configured to return the reclining position of the electric seat of the passenger seat to the reference angle when the driver state estimation unit 103 estimates that the driver is in an abnormal state without using the biosensor 20 during sleep-permitted automatic driving, the passenger presence/absence determination unit 104 determines that there is a passenger, and the reclining position of the electric seat of the passenger seat is at a sleep angle. The seat processing unit 111 may be configured not to perform processing to return the reclining angle of the electric seat of the passenger seat to the reference angle during sleep-non-permitted automatic driving. It is also possible that the seat back of the passenger seat may not be legally permitted to be at a sleep angle during sleep-non-permitted driving. In such cases, it is possible to suppress unnecessary processing by setting the condition to be during sleep-permitted automatic driving.

The evacuation processing unit 112 causes the vehicle to automatically perform evacuation action and make an emergency report to the center. The center may be, for example, an operator center that responds to an emergency situation involving the vehicle. This evacuation processing unit 112 corresponds to a third evacuation instruction unit. The evacuation processing unit 112 includes a stop processing unit 1121 and a report processing unit 1122.

The stop processing unit 1121 outputs information to the automatic driving ECU 17, thereby causing the automatic driving ECU 17 to control the stopping of the vehicle. This stop processing unit 1121 corresponds to the stop instruction unit. When the driving identification unit 102 identifies that the vehicle is in sleep-permitted automatic driving and the driver state estimation unit 103 estimates that the vehicle is in an abnormal state, the stop processing unit 1121 preferably stops the vehicle after automatically driving the vehicle to a specific area recommended as an emergency evacuation area in an area where sleep-permitted automatic driving is possible, rather than immediately making an emergency stop of the vehicle. This is because, during sleep-permitted automatic driving, it is easier to protect the occupants by continuing to drive and stopping the vehicle in a specific area, rather than making an emergency stop immediately after estimating that the driver is in an abnormal state. The specific area is an area recommended as an emergency evacuation area in an area where sleep-permitted automatic driving is possible. Examples of the specific area include a service area and an emergency parking area on a highway. The specific area may be a parking area of a hospital. This specific area corresponds to a predetermined evacuation area.

When the driving identification unit 102 identifies that the vehicle is in sleep-permitted automated driving and the driver state estimation unit 103 estimates that the vehicle is in an abnormal state, the stop processing unit 1121 may perform the following. When a specific area reachable by sleep-permitted automated driving exists, the stop processing unit 1121 executes an evacuation action of driving the vehicle to the specific area by sleep-permitted automated driving and then stopping the vehicle. This evacuation action is hereinafter referred to as area evacuation. Whether or not a specific area reachable by sleep-permitted automated driving exists may be determined from the vehicle's position and map data. On the other hand, when there is no specific area reachable by sleep-permitted automated driving, the stop processing unit 1121 may execute an evacuation action of bringing the vehicle to an emergency stop. This evacuation action is hereinafter referred to as emergency stop. The emergency stop may be stopping the vehicle by pulling over to the shoulder of the road or stopping within the driving lane.

The notification processor 1122 makes an emergency call to the center. The notification processor 1122 may make an emergency call to the center via the communication module 11. When the notification processor 1122 makes the aforementioned emergency stop, it may make an emergency call to the center after the vehicle stops. When the notification processor 1122 makes the aforementioned area evacuation, it may make an emergency call when the vehicle is not scheduled to change lanes and can travel a predetermined distance or more. The predetermined distance may be set arbitrarily. The predetermined distance may be a distance at which the emergency call can be completed before a lane change notification is issued for the next lane change. The timing when the vehicle is not scheduled to change lanes and can travel a predetermined distance or more is a timing at which the lane change notification and the emergency call do not overlap. This makes it possible to prevent the sounds of the lane change notification and the emergency call from being mixed together.

<Abnormality Estimation Related Processing in HCU 10>
Here, an example of the flow of processing related to the estimation of an abnormal state of the driver in the HCU 10 (hereinafter, abnormality estimation related processing) will be described with reference to the flowchart of Fig. 3. The flowchart of Fig. 3 may be configured to be started when, for example, a switch for starting the internal combustion engine or the motor generator of the vehicle (hereinafter, a power switch) is turned on.

First, in step S1, the driving identification unit 102 identifies whether the current automation level of the vehicle is LV3 or lower, or LV4 or higher. Then, if the automation level is LV4 or higher (YES in S1), the process proceeds to step S6. In other words, if the vehicle is in sleep-permitted automated driving, the process proceeds to S6. On the other hand, if the automation level is LV3 or lower (NO in S1), the process proceeds to step S2.

In step S2, the driver state estimation unit 103 uses the interior camera 19 and the biosensor 20 to estimate whether the driver is in an abnormal state. In step S3, if the driver state estimation unit 103 estimates that the driver is in an abnormal state (YES in S3), the process proceeds to step S4. On the other hand, if the driver state estimation unit 103 estimates that the driver is not in an abnormal state (NO in S3), the process proceeds to step S5. Note that when the automation level is LV3 or lower, if the driver state estimation unit 103 estimates that the driver is asleep, processing to wake up the driver may be performed. On the other hand, when the automation level is LV4 or higher, even if the driver state estimation unit 103 estimates that the driver is asleep, processing to wake up the driver may not be performed.

In step S4, the stop processing unit 1121 brings the vehicle to an emergency stop and ends the abnormality estimation-related processing. The stop processing unit 1121 may bring the vehicle to an emergency stop on the nearest road shoulder. In this case, the HCU 10 may make an emergency report to the center via the communication module 11.

In step S5, if it is time to end the abnormality estimation-related processing (YES in S5), the abnormality estimation-related processing is ended. On the other hand, if it is not time to end the abnormality estimation-related processing (NO in S5), the process returns to S1 and is repeated. An example of the timing to end the abnormality estimation-related processing is when the power switch of the vehicle is turned off.

In step S6, the driver state estimation unit 103 estimates whether the driver is in an abnormal state using only the indoor camera 19 out of the indoor camera 19 and the biosensor 20. In step S7, if the driver state estimation unit 103 estimates that the driver is in an abnormal state (YES in S7), the process proceeds to step S8. On the other hand, if the driver state estimation unit 103 estimates that the driver is not in an abnormal state (NO in S7), the process proceeds to step S5.

In step S8, the driver state estimation unit 103 re-estimates whether the driver is in an abnormal state using the interior camera 19 and the biosensor 20. In step S9, if the driver state estimation unit 103 estimates that the driver is in an abnormal state (YES in S9), the process proceeds to step S10. On the other hand, if the driver state estimation unit 103 estimates that the driver is not in an abnormal state (NO in S9), the process proceeds to step S5.

In step S10, abnormality processing is performed and the abnormality estimation-related processing is terminated. Here, an example of the flow of abnormality processing is described using the flowchart in FIG. 4.

First, in step S101, if the reclining angle of the electric driver's seat of the vehicle is the sleep angle (YES in S101), the process proceeds to step S102. On the other hand, if the reclining angle of the electric driver's seat of the vehicle is not the sleep angle (NO in S101), the process proceeds to step S103. Whether the reclining angle of the electric driver's seat of the vehicle is the sleep angle can be determined by the HCU 10 based on information obtained from the seat ECU 18 by the ECU communication unit 101. In step S102, the seat processing unit 111 returns the reclining angle of the electric driver's seat to the reference angle, and the process proceeds to step S103.

In step S103, the notification control unit 106 issues a confirmation prompt notification to the occupants. In step S104, if the passenger presence/absence determination unit 104 determines that there is a passenger (YES in S104), the process proceeds to step S105. On the other hand, if the passenger presence/absence determination unit 104 determines that there is no passenger (NO in S104), the process proceeds to step S109.

In step S105, if the reclining angle of the electric passenger seat of the host vehicle is the sleep angle (YES in S105), the process proceeds to step S106. On the other hand, if the reclining angle of the electric passenger seat of the host vehicle is not the sleep angle (NO in S105), the process proceeds to step S107. Whether the reclining angle of the electric passenger seat of the host vehicle is the sleep angle can be determined by the HCU 10 based on information obtained from the seat ECU 18 by the ECU communication unit 101. In step S106, the seat processing unit 111 returns the reclining angle of the electric passenger seat to the reference angle, and the process proceeds to step S107.

In step S107, the passenger state estimation unit 105 estimates whether the passenger of the vehicle is in an awake state. If it is estimated that the passenger is in an awake state (YES in S107), the process proceeds to step S108. On the other hand, if it is estimated that the passenger is not in an awake state (NO in S107), the process proceeds to step S109. In step S108, the notification control unit 106 issues a possible abnormality notification to the passenger, and the process proceeds to step S109. In step S109, the stop processing unit 1121 automatically drives the vehicle to a specific area and then stops the vehicle, and ends the abnormality estimation related process. Note that the same process as S6 may be repeated until the vehicle is stopped, and if it is estimated that the vehicle is not in an abnormal state, the stopping may be stopped and the vehicle may continue to run. Alternatively, the same process as S6 may be performed before the process of S109, and if it is determined that the vehicle is not in an abnormal state, the process proceeds to S5 without moving to S109. Verification that no abnormal conditions exist can be performed based on input by the driver and passengers to the user input device 22 in response to the verification prompt notification.

In the flowchart of FIG. 3, the processing of S8 to S9 may be omitted. In this case, if S7 is YES, the process may proceed to S10. In the flowchart of FIG. 3, if S3 is YES, the process may be the same as S103. In the flowchart of FIG. 3, if S3 is YES, the process may be the same as S108. In this case, the conditions may be that the passenger presence/absence determination unit 104 determines that there is a passenger, and that the passenger state estimation unit 105 estimates that the passenger is in an awake state. In the flowchart of FIG. 3, the processing of S101 to S102 may be omitted. In the flowchart of FIG. 3, the processing of S103 may be omitted. In the flowchart of FIG. 3, the processing of S107 to S108 may be omitted. In the flowchart of FIG. 3, the processing of S105 to S106 may be omitted. In the flowchart of FIG. 3, the processing of S104 to S108 may be omitted. In this case, the HCU 10 may be configured not to include the passenger presence/absence determination unit 104 and the passenger state estimation unit 105. In the flowchart of FIG. 3, the process of S109 may be omitted.

(Embodiment 2)
The configuration is not limited to that of the above-described embodiment, and may be that of the following embodiment 2. An example of the configuration of embodiment 2 will be described below with reference to the drawings.

<General Configuration of Vehicle System 1a>
The vehicle system 1a shown in Fig. 5 can be used in an autonomous vehicle. As shown in Fig. 5, the vehicle system 1a includes an HCU 10a, a communication module 11, a locator 12, a map DB 13, a vehicle state sensor 14, a surrounding monitoring sensor 15, a vehicle control ECU 16, an autonomous driving ECU 17, a seat ECU 18, an interior camera 19, a biosensor 20, an alarm device 21a, and a user input device 22. The vehicle system 1a includes an HCU 10a instead of the HCU 10. The vehicle system 1a includes an alarm device 21a instead of the alarm device 21. Except for these points, the vehicle system 1a is similar to the vehicle system 1 of the first embodiment.

The notification device 21a is similar to the notification device 21 of the first embodiment, except that it must include a display for the driver and a display visible to passengers. The notification device 21a includes a first display 211, a second display 212, and an audio output device 213.

The first display 211 is a display dedicated to the driver. The first display 211 corresponds to the first display. The first display 211 may be, for example, the meter MID or HUD described above. The second display 212 is a display that can be viewed by passengers other than the driver. The second display 212 corresponds to the second display. The second display 212 may be, for example, the CID described above. The audio output device 213 may be the same as the audio output device described in embodiment 1.

The user input device 22a is similar to the user input device 22 of the first embodiment, except that the user input device 22a distinguishes between input from the driver and input from passengers. The user input device 22a includes a first input device 221 and a second input device 222. The first input device 221 receives input from the driver. The first input device 221 may be a switch, a microphone, etc. provided near the driver's seat. The first input device 221 may be a switch provided on the steering wheel, for example. The second input device 222 may be a switch, a microphone, etc. provided near the passenger seat and the rear seat. The user input device 22a may distinguish between voice input from the driver and passengers and receive voice input from the driver and passengers using voiceprints registered in advance to distinguish between the driver and passengers.

<General configuration of HCU 10a>
Next, the schematic configuration of the HCU 10a will be described with reference to Fig. 6. As shown in Fig. 6, the HCU 10a includes an ECU communication unit 101a, a driving identification unit 102, a driver state estimation unit 103a, a passenger presence/absence identification unit 104, a passenger state estimation unit 105, a notification control unit 106a, and a response reception unit 107 as functional blocks. The HCU 10a includes the ECU communication unit 101a instead of the ECU communication unit 101. The HCU 10a includes the driver state estimation unit 103a instead of the driver state estimation unit 103. The HCU 10a includes the notification control unit 106a instead of the notification control unit 106. The HCU 10a includes the response reception unit 107. Except for these points, the HCU 10a is similar to the HCU 10 of the first embodiment. This HCU 10a also corresponds to a vehicle device. Furthermore, the execution of the processing of each functional block of the HCU 10a by the computer corresponds to the execution of the estimation method for a vehicle.

The driver state estimation unit 103a is similar to the driver state estimation unit 103 of the first embodiment, except for some differences in processing. The differences will be described below. The driver state estimation unit 103a distinguishes and identifies the type of abnormal state. As described above, the abnormal state does not include a sleeping state. Examples of the types of abnormal states include fainting, illness, and stress. The driver state estimation unit 103a may distinguish and identify the type of abnormal state based on the feature amount for each type of abnormal state. When the indoor camera 19 is used, this feature amount is a feature amount detected from a captured image. When the biosensor 20 is used, this feature amount is bioinformation. For example, the driver state estimation unit 103a may distinguish and identify the type of abnormal state using a learning device that has performed machine learning.

The notification control unit 106a is the same as the notification control unit 106 of the first embodiment, except for some differences in processing. The differences will be described below. The notification control unit 106a notifies the occupants of the vehicle by displaying at least the first display 211 and the second display 212. When the driver state estimation unit 103a estimates that the driver is in an abnormal state, the notification control unit 106a displays the type of the abnormal state (hereinafter, abnormality type display). The notification control unit 106a displays the abnormality type on both the first display 211 and the second display 212. The abnormality type display may be text or an icon. In this way, by informing the passenger of the type of abnormal state, the passenger can more easily respond to the abnormal state of the driver. In addition, when the driver is conscious, it is possible to make the driver aware that the driver is in an abnormal state and the type of the abnormal state.

The answer receiving unit 107 receives a correct or incorrect answer input from a passenger of the vehicle in response to the abnormality type display. This correct or incorrect answer input is referred to as a correct or incorrect answer input. Hereinafter, an answer input indicating that the abnormal state of the driver indicated by the abnormality type display is correct is referred to as a correct answer input. Hereinafter, an answer input indicating that the abnormal state of the driver indicated by the abnormality type display is incorrect is referred to as an incorrect answer input. The answer receiving unit 107 includes a first receiving unit 171 and a second receiving unit 172 as sub-functional blocks. The first receiving unit 171 receives a correct or incorrect answer input from the driver. The first receiving unit 171 may receive a correct or incorrect answer input from the driver via the first input device 221. The second receiving unit 172 receives a correct or incorrect answer input from a passenger. The second receiving unit 172 may receive a correct or incorrect answer input from a passenger via the second input device 222.

The ECU communication unit 101a has a sheet processing unit 111 and an evacuation processing unit 112a as sub-functional blocks. The ECU communication unit 101a is similar to the ECU communication unit 101 of the first embodiment, except that the ECU communication unit 101a has the evacuation processing unit 112a instead of the evacuation processing unit 112. The evacuation processing unit 112a has a stop processing unit 1121a and a notification processing unit 1122a. The evacuation processing unit 112a is similar to the stop processing unit 1121 of the first embodiment, except that some processing is different. The following describes these differences.

The evacuation processing unit 112a at least automatically performs evacuation action of the vehicle based on the answer receiving unit 107 receiving the correct answer input. In other words, the stop processing unit 1121a performs evacuation action based on the answer receiving unit 107 receiving the correct answer input. The notification processing unit 1122a may perform an emergency notification based on the answer receiving unit 107 receiving the correct answer input. This evacuation processing unit 112a corresponds to the first evacuation instruction unit. With the above configuration, it becomes possible to at least automatically perform evacuation action of the vehicle when the driver is in an abnormal state. As a result, it becomes easier to deal with the driver's abnormal state.

When the second reception unit 172 receives a correct answer input, the evacuation processing unit 112a may at least cause the vehicle to automatically perform an evacuation action. When the first reception unit 171 and the second reception unit 172 receive answer inputs that are different in correctness or incorrectness, the evacuation processing unit 112a may do the following. The evacuation processing unit 112a may prioritize the answer input received by the second reception unit 172 over the answer input received by the first reception unit 171. In other words, when the evacuation processing unit 112a receives a correct answer input from a passenger, it may cause the evacuation processing unit 112a to perform an evacuation action even if an incorrect answer input is received from the driver. This is because the answer input from a passenger is considered to be more reliable than the answer input from a driver who is suspected of being in an abnormal state.

When only the first reception unit 171 of the first reception unit 171 and the second reception unit 172 receives an answer input, the evacuation processing unit 112a may follow the answer input. In other words, the evacuation processing unit 112a may receive an answer input only from the driver, and if the answer input is a correct answer input, perform an evacuation action. The evacuation processing unit 112a may receive an answer input only from the driver, and if the answer input is an incorrect answer input, not perform an evacuation action. This makes it possible to follow the answer input from the driver when there is no answer input from a passenger. Note that the first reception unit 171 and the second reception unit 172 may determine that the answer input was not received if the answer input is not received within a specified time after the start of the abnormality type display.

When the evacuation processing unit 112a performs an evacuation action and there is a specific area that can be reached by sleep-permitted automatic driving, the notification control unit 106a preferably displays evacuation route information. The evacuation route information is information that guides the route from the current position of the vehicle to the specific area (hereinafter, evacuation route). As described above, the specific area is an area that is recommended as an emergency evacuation location in an area where sleep-permitted automatic driving is possible. The evacuation route information may be displayed on at least one of the first display 211 and the second display 212. As an example, the evacuation route information may be information that shows the evacuation route by superimposing it on an electronic map. On the other hand, when the evacuation processing unit 112a performs an evacuation action and there is no specific area that can be reached by sleep-permitted automatic driving, the notification control unit 106a may cause an emergency stop notification to be made. The emergency stop notification is a notification that indicates that an emergency stop of the vehicle will be made. The emergency stop notification is made by the notification device 21a. The emergency stop notification may be a display or an audio output. With the above configuration, it is possible to make a notification according to the type of evacuation action.

(Embodiment 3)
The configuration is not limited to that of the above-described embodiment, and may be that of the following embodiment 3. An example of the configuration of embodiment 3 will be described below with reference to the drawings.

<Overall configuration of vehicle system 1b>
The vehicle system 1b shown in Fig. 7 can be used in an autonomous driving vehicle. As shown in Fig. 7, the vehicle system 1b includes an HCU 10b, a communication module 11, a locator 12, a map DB 13, a vehicle state sensor 14, a surrounding monitoring sensor 15, a vehicle control ECU 16, an autonomous driving ECU 17, a seat ECU 18, an interior camera 19, a biosensor 20, an alarm device 21, and a user input device 22. The vehicle system 1b is similar to the vehicle system 1 of the first embodiment, except that the vehicle system 1b includes an HCU 10b instead of the HCU 10.

<General configuration of HCU 10b>
Next, the schematic configuration of the HCU 10b will be described with reference to Fig. 8. As shown in Fig. 6, the HCU 10b includes an ECU communication unit 101b, a driving identification unit 102, a driver state estimation unit 103, a passenger presence/absence identification unit 104, a passenger state estimation unit 105b, and a notification control unit 106 as functional blocks. The HCU 10b includes an ECU communication unit 101b instead of the ECU communication unit 101. The HCU 10b includes a passenger state estimation unit 105b instead of the passenger state estimation unit 105. Except for these points, the HCU 10b is similar to the HCU 10 of the first embodiment. This HCU 10b also corresponds to a vehicle device. In addition, the execution of the processing of each functional block of the HCU 10b by a computer corresponds to the execution of an estimation method for a vehicle.

The passenger state estimation unit 105b is similar to the passenger state estimation unit 105 of the first embodiment, except for some different processing. The following describes these differences. The passenger state estimation unit 105b estimates whether or not the passenger is in an abnormal state. The passenger state estimation unit 105b may distinguish and identify the type of abnormal state. As described above, the abnormal state does not include a sleeping state. Types of abnormal states include fainting, illness, stress, and the like. The passenger state estimation unit 105b may estimate the abnormal state of the passenger in the same manner as the driver state estimation unit 103a. The passenger state estimation unit 105b may estimate whether or not the passenger is in an abnormal state, for example, based on a passenger range image captured by the interior camera 19.

The ECU communication unit 101b has a sheet processing unit 111 and an evacuation processing unit 112b as sub-functional blocks. The ECU communication unit 101b is similar to the ECU communication unit 101 of the first embodiment, except that it has the evacuation processing unit 112b instead of the evacuation processing unit 112. The evacuation processing unit 112b has a stop processing unit 1121b and a notification processing unit 1122b. The evacuation processing unit 112b is similar to the stop processing unit 1121 of the first embodiment, except that some processing is different. The following describes these differences.

The evacuation processing unit 112b at least automatically performs evacuation action of the vehicle when it is estimated that multiple occupants are in an abnormal state. In other words, when it is estimated that multiple occupants are in an abnormal state, the evacuation processing unit 112b performs evacuation action without confirming with the occupants whether or not the occupants are in an abnormal state. Confirmation of whether or not the occupants are in an abnormal state may be performed by the above-mentioned confirmation promotion notification and abnormality possibility notification. The stop processing unit 1121b performs evacuation action when it is estimated that multiple occupants are in an abnormal state. The notification processing unit 1122b may perform an emergency notification when it is estimated that multiple occupants are in an abnormal state. This evacuation processing unit 112b corresponds to the second evacuation instruction unit. The evacuation processing unit 112b may estimate that multiple occupants are in an abnormal state based on the estimation results of the driver state estimation unit 103 and the passenger state estimation unit 105b. The case where the driver and the passenger are estimated to be in an abnormal state corresponds to the case where multiple occupants are estimated to be in an abnormal state. If multiple passengers are suspected to be in an abnormal state, this also falls under the case where multiple occupants are suspected to be in an abnormal state.

When multiple passengers are estimated to be in an abnormal state, it is highly likely that the occupants are in an abnormal state. According to the configuration of embodiment 3, when it is highly likely that an occupant is in an abnormal state, it is possible to omit confirmation of whether the occupant is in an abnormal state and to implement evacuation action when such a state is likely. This makes it possible to omit less necessary processing and quickly deal with the occupant's abnormal state.

(Embodiment 4)
The configuration is not limited to that of the above-described embodiment, and may be that of the following embodiment 4. An example of the configuration of embodiment 4 will be described below with reference to the drawings.

<General Configuration of Vehicle System 1c>
The vehicle system 1c shown in FIG. 9 can be used in an autonomous vehicle. As shown in FIG. 9, the vehicle system 1c includes an HCU 10c, a communication module 11, a locator 12, a map DB 13, a vehicle state sensor 14, a surrounding monitoring sensor 15, a vehicle control ECU 16, an autonomous driving ECU 17, a seat ECU 18, an interior camera 19, a biosensor 20, an alarm device 21a, and a user input device 22. The vehicle system 1c includes an HCU 10c instead of the HCU 10. The vehicle system 1c includes an alarm device 21a instead of the alarm device 21. Except for these points, the vehicle system 1c is similar to the vehicle system 1 of the first embodiment. The alarm device 21a is similar to the alarm device 21a of the second embodiment. The alarm device 21a includes a first display 211, a second display 212, and an audio output device 213.

<General configuration of HCU 10c>
Next, the schematic configuration of the HCU 10c will be described with reference to FIG. 10. As shown in FIG. 10, the HCU 10c includes an ECU communication unit 101, a driving identification unit 102, a driver state estimation unit 103, a passenger presence/absence identification unit 104, a passenger state estimation unit 105b, and a notification control unit 106c as functional blocks. The HCU 10c includes a passenger state estimation unit 105b instead of the passenger state estimation unit 105. The HCU 10c includes a notification control unit 106c instead of the notification control unit 106. Except for these points, the HCU 10c is similar to the HCU 10 of the first embodiment. This HCU 10c also corresponds to a vehicle device. In addition, the execution of the processing of each functional block of the HCU 10c by a computer corresponds to the execution of an estimation method for a vehicle. The passenger state estimation unit 105b is similar to the passenger state estimation unit 105b of the second embodiment.

The notification control unit 106c is similar to the notification control unit 106 of the first embodiment, except for some differences in processing. The differences are described below. The notification control unit 106c causes the notification device 21a to issue a notification to at least the driver. The notification to the driver may be issued by display on the first display 211. If the audio output device is a directional speaker, the notification to the driver may be issued by audio output from this directional speaker.

When the notification control unit 106c estimates that the passenger is in an abnormal state, it causes the notification device 21a to issue a notification to the driver suggesting that an emergency call be made. The passenger state estimation unit 105b estimates whether the passenger is in an abnormal state or not. This makes it possible for the driver to prompt the passenger to deal with the passenger's abnormal state when the driver is not in an abnormal state but the passenger is.

(Embodiment 5)
In the above embodiment, the HCU 10, 10a, 10b, 10c is provided with the seat processing unit 111, but this is not necessarily limited to the above. For example, the function of the seat processing unit 111 may be performed by a unit other than the HCU 10, 10a, 10b, 10c. As an example, the seat ECU 18 may perform the function of the seat processing unit 111. In this case, the configuration including the HCU 10, 10a, 10b, 10c and the seat ECU 18 corresponds to a vehicle device. Also, the vehicle system 1, 1a, 1b, 1c may not include the seat processing unit 111.

(Embodiment 6)
In the first embodiment, the configuration in which the HCUs 10, 10a, 10b, and 10c are provided with the stop processing units 1121, 1121a, and 1121b is shown, but this is not necessarily limited to this. For example, the functions of the stop processing units 1121, 1121a, and 1121b may be performed by a unit other than the HCUs 10, 10a, 10b, and 10c. As an example, the automatic driving ECU 17 may perform the functions of the stop processing units 1121, 1121a, and 1121b. In this case, the configuration including the HCUs 10, 10a, 10b, and 10c and the automatic driving ECU 17 corresponds to a vehicle device. Also, the vehicle systems 1, 1a, 1b, and 1c may not include the stop processing units 1121, 1121a, and 1121b.

Note that the present disclosure is not limited to the above-described embodiment, and various modifications are possible within the scope of the claims. The technical scope of the present disclosure also includes embodiments obtained by appropriately combining the technical means disclosed in different embodiments. The control unit and the method described in the present disclosure may be realized by a dedicated computer that constitutes a processor programmed to execute one or more functions embodied in a computer program. Alternatively, the device and the method described in the present disclosure may be realized by a dedicated hardware logic circuit. Alternatively, the device and the method described in the present disclosure may be realized by one or more dedicated computers that are configured by combining a processor that executes a computer program with one or more hardware logic circuits. Furthermore, the computer program may be stored in a computer-readable non-transient tangible recording medium as instructions executed by the computer.

(Disclosed technical idea)
This specification discloses multiple technical ideas described in the following multiple dependent claims. Some of the claims may be described in a multiple dependent form, in which the subsequent claim alternatively refers to the preceding claim. Furthermore, some of the claims may be described in a multiple dependent form, in which the subsequent claim alternatively refers to the preceding claim. The claims described in these multiple dependent forms define multiple technical ideas.

(Technical Concept 1)
A vehicle device that can be used in a vehicle that switches between sleep-permitted automated driving, which is an automated driving level at which the driver is permitted to sleep, and sleep-non-permitted driving, which is an automated driving level at which the driver is not permitted to sleep,
A driver state estimation unit (103) capable of estimating whether the driver is in an abnormal state other than a sleeping state by using a plurality of types of sensors;
A driving identification unit (102) that identifies whether the vehicle is in the sleep-permitting automatic driving mode or the sleep-non-permitting automatic driving mode,
The vehicle device, wherein when the driving identification unit determines that the driver is currently driving while sleep is not permitted, the driver state estimation unit uses multiple types of sensors to estimate whether the driver is in the abnormal state, and when the driving identification unit determines that the driver is currently driving while sleep is permitted, the vehicle device estimates whether the driver is currently driving while sleep is not permitted by using fewer types of sensors than when the driving identification unit determines that the driver is currently driving while sleep is not permitted.

(Technical Concept 2)
The vehicle device according to Technical Concept 1,
The driver state estimation unit is capable of estimating whether or not the abnormal state exists using an imaging device that images the driver and a bio-sensor that measures bio-information of the driver, and when the driving identification unit determines that the driver is in the sleep-non-permitted automatic driving state, it estimates whether or not the abnormal state exists using the imaging device and the bio-sensor, while when the driving identification unit determines that the driver is in the sleep-permitted automatic driving state, it uses the imaging device but not the bio-sensor to estimate whether or not the abnormal state exists.

(Technical Concept 3)
The vehicle device according to Technical Concept 2,
The driver state estimation unit is capable of estimating whether or not the abnormal state exists using the imaging device and the bio-sensor provided on the steering wheel of the vehicle for measuring bio-information of the driver holding the steering wheel, and when the driving identification unit determines that the driver is in the sleep-non-permitted automatic driving state, it estimates whether or not the abnormal state exists using the imaging device and the bio-sensor provided on the steering wheel, while when the driving identification unit determines that the driver is in the sleep-permitted automatic driving state, it uses the imaging device but does not use the bio-sensor provided on the steering wheel to estimate whether or not the abnormal state exists.

(Technical Concept 4)
A vehicle device according to any one of technical concepts 1 to 3,
The driver state estimation unit estimates whether or not the abnormal state exists by using fewer types of sensors than when the driver determines that the vehicle is in sleep-permitted automatic driving, and if the driver state estimation unit determines that the vehicle is in an abnormal state, the vehicle state estimation unit re-estimates whether or not the abnormal state exists using the same number of types of sensors as when the driver determines that the vehicle is in sleep-permitted automatic driving, even if the driving identification unit determines that the vehicle is in sleep-permitted automatic driving.

(Technical Concept 5)
A vehicle device according to any one of technical concepts 1 to 4,
a notification control unit (106) that causes a notification device (21) to notify a passenger of the vehicle;
The notification control unit is a vehicle device that, when the driver's state estimation unit estimates that the driver is in the abnormal state, issues a notification to prompt the driver to confirm whether or not the driver is in the abnormal state.

(Technical Concept 6)
The vehicle device according to Technical Concept 5,
The driver state estimation unit distinguishes and identifies the type of the abnormal state,
a notification control unit (106a) that notifies a passenger of the vehicle by displaying at least a display (211, 212);
The notification control unit is a vehicle device that, when the driver state estimation unit estimates that the driver is in an abnormal state, displays an abnormality type display, which displays the type of the abnormal state, on both a first display dedicated to the driver and a second display visible to passengers other than the driver.

(Technical Concept 7)
The vehicle device according to Technical Concept 6,
an answer receiving unit (107) for receiving an answer input of whether the abnormality type display is correct or not from the occupant;
and a first evacuation instruction unit (112a) that causes the vehicle to at least automatically perform evacuation action based on the answer input from the occupant that the abnormal state of the driver indicated by the abnormality type display is correct, when the answer receiving unit receives such answer input.

(Technical Concept 8)
A vehicle device according to Technical Concept 7,
a first reception unit (171) serving as the answer reception unit, which receives a correct or incorrect answer input from the driver;
a second reception unit (172) that receives a correct or incorrect answer input from the passenger as the answer reception unit,
The first evacuation instruction unit, when receiving answer inputs whose correctness differs between the first and second receiving units, prioritizes the answer input received by the second receiving unit over the answer input received by the first receiving unit.

(Technical Concept 9)
A vehicle device according to Technical Concept 8,
The first evacuation instruction unit is a vehicle device that follows the answer input when the answer input is received only by the first reception unit out of the first reception unit and the second reception unit.

(Technical Concept 10)
A vehicle device according to any one of Technical Ideas 7 to 9,
The notification control unit, when the first evacuation instruction unit causes the evacuation action to be carried out and a specified evacuation area that can be reached by the sleep-permitted automatic driving exists, causes the display to display information guiding the route from the current location of the vehicle to the evacuation area, while, when the first evacuation instruction unit causes the evacuation action to be carried out and the evacuation area that can be reached by the sleep-permitted automatic driving does not exist, causes the notification device to issue a notification indicating that an emergency stop of the vehicle will be performed.

(Technical Concept 11)
A vehicle device according to any one of technical concepts 1 to 10,
A seat control instruction unit (111) for controlling the reclining angle of an electric seat of the vehicle is provided,
The seat control instruction unit is a vehicle device that, when the driver's state estimation unit estimates that the abnormal state exists and the reclining angle of the electric seat of the driver's seat of the vehicle is a sleeping angle in which the angle of the seat back relative to the floor surface of the vehicle is reclined less than a first specified angle, returns the reclining angle of the electric seat of the driver's seat to a reference angle in which the angle of the seat back relative to the floor surface is raised to a second specified angle or more that is greater than the first specified angle.

(Technical Concept 12)
A vehicle device according to Technical Concept 11,
A passenger presence/absence identification unit (104) for identifying the presence or absence of a passenger other than the driver of the vehicle,
The seat control instruction unit is a vehicle device that returns the reclining position of the electric seat of the passenger's seat to the reference angle when the driver's state estimation unit estimates that the abnormal state is present, the passenger presence determination unit determines that there is a passenger, and the reclining position of the electric seat of the passenger's seat in the vehicle is at the sleep angle.

(Technical Concept 13)
A vehicle device according to any one of technical concepts 1 to 12,
a passenger presence/absence identification unit (104) for identifying the presence or absence of a passenger other than the driver of the vehicle;
and a notification control unit (106) that causes the notification device (21) to notify the occupant.
The vehicle also includes an awake identification unit (105) for estimating whether the passenger is in an awake state,
The notification control unit is a vehicle device that, when the driver state estimation unit estimates that the driver is in an abnormal state, the passenger presence determination unit determines that there is a passenger, and the wakefulness determination unit estimates that the passenger is in an wakeful state, issues a notification to the passenger to inform the passenger that the driver may be in the abnormal state.

(Technical Concept 14)
A vehicle device according to any one of technical concepts 1 to 13,
A vehicle device comprising: a stop instruction unit (1121) that, when the driving identification unit identifies that the sleep-permitted automatic driving is in progress and the driver state estimation unit estimates that the abnormal state is in progress, does not immediately make an emergency stop of the vehicle, but instead automatically drives the vehicle to a specific area recommended as an emergency evacuation location in an area where the sleep-permitted automatic driving is possible and then stops the vehicle.

(Technical Concept 15)
A vehicle device according to any one of technical concepts 1 to 14,
a passenger state estimation unit (105b) capable of estimating whether a passenger other than the driver is in the abnormal state;
and a second evacuation instruction unit (112b) that causes the vehicle to at least automatically perform an evacuation action when it is estimated that multiple occupants are in the abnormal state based on the estimation results by the driver state estimation unit and the passenger state estimation unit.

(Technical Concept 16)
A vehicle device according to any one of technical concepts 1 to 15,
a passenger state estimation unit (105b) capable of estimating whether a passenger other than the driver is in the abnormal state;
and a notification control unit (106c) that causes a notification device (21a) to notify at least the driver,
The notification control unit is a vehicle device that, when it is estimated that the passenger is in the abnormal state, causes the notification device to issue a notification to the driver suggesting that an emergency call be made.

(Technical Concept 17)
A vehicle device according to any one of technical concepts 1 to 16,
A third evacuation instruction unit (112) that causes the vehicle to automatically take an evacuation action and make an emergency call to a center based on at least the driver state estimation unit estimating that the driver is in an abnormal state,
The third evacuation instruction unit is
When a predetermined evacuation area reachable by the sleep-permitting autonomous driving exists, the evacuation action is implemented by driving the vehicle to the evacuation area by the sleep-permitting autonomous driving and then stopping the vehicle, whereas when the evacuation area reachable by the sleep-permitting autonomous driving does not exist, the evacuation action is implemented by making an emergency stop of the vehicle,
When the vehicle is driven to the evacuation area using the sleep-permitted automatic driving method and then stopped, the vehicle device makes the emergency call when the vehicle is able to travel a predetermined distance or more without any plans to change lanes.

1, 1a, 1b, 1c Vehicle system, 10, 10a, 10b, 10c HCU (vehicle device), 19 Interior camera (sensor), 20 Biometric sensor (sensor), 21, 21a Notification device, 101 ECU communication unit, 102 Driving identification unit, 103 Driver state estimation unit, 104 Passenger presence/absence identification unit, 105 Passenger state estimation unit (awake identification unit), 105b Passenger state estimation unit, 106, 106a, 106c Notification control unit, 107 Response reception unit, 111 Seat processing unit (seat control instruction unit), 112 Evacuation processing unit (third evacuation instruction unit), 112a Evacuation processing unit (first evacuation instruction unit), 112b Evacuation processing unit (second evacuation instruction unit), 171 First reception unit, 172 Second reception unit, 211 First display (display unit), 212 Second display (display), 1121 Stop processing unit (stop instruction unit)

Claims (22)

A vehicle device that can be used in a vehicle that switches between sleep-permitted automated driving, which is an automated driving level at which the driver is permitted to sleep, and sleep-non-permitted driving, which is an automated driving level at which the driver is not permitted to sleep,
A driver state estimation unit (103) capable of estimating whether the driver is in an abnormal state other than a sleeping state by using a plurality of types of sensors;
A driving identification unit (102) that identifies whether the vehicle is in the sleep-permitting automatic driving mode or the sleep-non-permitting automatic driving mode,
the driver state estimation unit, when the driving identification unit identifies that the driver is in the sleep non-permitted driving, estimates whether or not the driver is in the abnormal state using a plurality of types of sensors, whereas, when the driving identification unit identifies that the driver is in the sleep permitted automatic driving, estimates whether or not the driver is in the abnormal state by using fewer types of sensors than when the driving identification unit identifies that the driver is in the sleep non-permitted driving ,
The driver state estimation unit is capable of estimating whether or not the abnormal state exists using an imaging device that images the driver and a bio-sensor that measures bio-information of the driver, and when the driving identification unit determines that the driver is in the sleep-non-permitted automatic driving state, it estimates whether or not the abnormal state exists using the imaging device and the bio-sensor, while when the driving identification unit determines that the driver is in the sleep-permitted automatic driving state, it uses the imaging device but not the bio-sensor to estimate whether or not the abnormal state exists . The vehicle device according to claim 1 ,
The driver state estimation unit is capable of estimating whether or not the abnormal state exists using the imaging device and the bio-sensor provided on the steering wheel of the vehicle for measuring bio-information of the driver holding the steering wheel, and when the driving identification unit determines that the driver is in the sleep-non-permitted automatic driving state, it estimates whether or not the abnormal state exists using the imaging device and the bio-sensor provided on the steering wheel, while when the driving identification unit determines that the driver is in the sleep-permitted automatic driving state, it uses the imaging device but does not use the bio-sensor provided on the steering wheel to estimate whether or not the abnormal state exists. A vehicle device that can be used in a vehicle that switches between sleep-permitted automated driving, which is an automated driving level at which the driver is permitted to sleep, and sleep-non-permitted driving, which is an automated driving level at which the driver is not permitted to sleep,
A driver state estimation unit (103) capable of estimating whether the driver is in an abnormal state other than a sleeping state by using a plurality of types of sensors;
A driving identification unit (102) that identifies whether the vehicle is in the sleep-permitting automatic driving mode or the sleep-non-permitting automatic driving mode,
the driver state estimation unit, when the driving identification unit identifies that the driver is in the sleep non-permitted driving, estimates whether or not the driver is in the abnormal state using a plurality of types of sensors, whereas, when the driving identification unit identifies that the driver is in the sleep permitted automatic driving, estimates whether or not the driver is in the abnormal state by using fewer types of sensors than when the driving identification unit identifies that the driver is in the sleep non-permitted driving ,
The driver state estimation unit estimates whether or not the abnormal state exists by using fewer types of sensors than when the driver determines that the vehicle is in sleep-permitted automatic driving, and if the driver state estimation unit determines that the vehicle is in an abnormal state, the vehicle state estimation unit re-estimates whether or not the abnormal state exists using the same number of types of sensors as when the driver determines that the vehicle is in sleep-permitted automatic driving, even if the driving identification unit determines that the vehicle is in sleep-permitted automatic driving . A vehicle device that can be used in a vehicle that switches between sleep-permitted automated driving, which is an automated driving level at which the driver is permitted to sleep, and sleep-non-permitted driving, which is an automated driving level at which the driver is not permitted to sleep,
A driver state estimation unit (103) capable of estimating whether the driver is in an abnormal state other than a sleeping state by using a plurality of types of sensors;
A driving identification unit (102) that identifies whether the vehicle is in the sleep-permitting automatic driving mode or the sleep-non-permitting automatic driving mode,
the driver state estimation unit, when the driving identification unit identifies that the driver is in the sleep non-permitted driving, estimates whether or not the driver is in the abnormal state using a plurality of types of sensors, whereas, when the driving identification unit identifies that the driver is in the sleep permitted automatic driving, estimates whether or not the driver is in the abnormal state by using fewer types of sensors than when the driving identification unit identifies that the driver is in the sleep non-permitted driving ,
A seat control instruction unit (111) for controlling the reclining angle of an electric seat of the vehicle is provided,
The seat control instruction unit is a vehicle device that, when the driver's state estimation unit estimates that the abnormal state exists and the reclining angle of the electric seat of the driver's seat of the vehicle is a sleeping angle in which the angle of the seat back relative to the floor surface of the vehicle is reclined less than a first specified angle, returns the reclining angle of the electric seat of the driver's seat to a reference angle in which the angle of the seat back relative to the floor surface is raised to a second specified angle or more that is greater than the first specified angle . The vehicle device according to claim 4 ,
A passenger presence/absence identification unit (104) for identifying the presence or absence of a passenger other than the driver of the vehicle,
The seat control instruction unit is a vehicle device that returns the reclining position of the electric seat of the passenger's seat to the reference angle when the driver's state estimation unit estimates that the abnormal state is present, the passenger presence determination unit determines that there is a passenger, and the reclining position of the electric seat of the passenger's seat in the vehicle is at the sleep angle. A vehicle device that can be used in a vehicle that switches between sleep-permitted automated driving, which is an automated driving level at which the driver is permitted to sleep, and sleep-non-permitted driving, which is an automated driving level at which the driver is not permitted to sleep,
A driver state estimation unit (103) capable of estimating whether the driver is in an abnormal state other than a sleeping state by using a plurality of types of sensors;
A driving identification unit (102) that identifies whether the vehicle is in the sleep-permitting automatic driving mode or the sleep-non-permitting automatic driving mode,
the driver state estimation unit, when the driving identification unit identifies that the driver is in the sleep non-permitted driving, estimates whether or not the driver is in the abnormal state using a plurality of types of sensors, whereas, when the driving identification unit identifies that the driver is in the sleep permitted automatic driving, estimates whether or not the driver is in the abnormal state by using fewer types of sensors than when the driving identification unit identifies that the driver is in the sleep non-permitted driving ,
A third evacuation instruction unit (112) that causes the vehicle to automatically take an evacuation action and make an emergency call to a center based on at least the driver state estimation unit estimating that the driver is in an abnormal state,
The third evacuation instruction unit is
When a predetermined evacuation area reachable by the sleep-permitting autonomous driving exists, the evacuation action is implemented by driving the vehicle to the evacuation area by the sleep-permitting autonomous driving and then stopping the vehicle, whereas when the evacuation area reachable by the sleep-permitting autonomous driving does not exist, the evacuation action is implemented by making an emergency stop of the vehicle,
When the vehicle is driven to the evacuation area using the sleep-permitted automatic driving method and then stopped, the vehicle device makes the emergency call when the vehicle is able to travel a predetermined distance or more without any plans to change lanes . A vehicle device that can be used in a vehicle that switches between sleep-permitted automated driving, which is an automated driving level at which the driver is permitted to sleep, and sleep-non-permitted driving, which is an automated driving level at which the driver is not permitted to sleep,
A driver state estimation unit (103) capable of estimating whether the driver is in an abnormal state other than a sleeping state by using a plurality of types of sensors;
A driving identification unit (102) that identifies whether the vehicle is in the sleep-permitting automatic driving mode or the sleep-non-permitting automatic driving mode,
the driver state estimation unit, when the driving identification unit identifies that the driver is in the sleep non-permitted driving, estimates whether or not the driver is in the abnormal state using a plurality of types of sensors, whereas, when the driving identification unit identifies that the driver is in the sleep permitted automatic driving, estimates whether or not the driver is in the abnormal state by using fewer types of sensors than when the driving identification unit identifies that the driver is in the sleep non-permitted driving ,
a passenger state estimation unit (105b) capable of estimating whether a passenger other than the driver is in the abnormal state;
A second evacuation instruction unit (112b) that causes the vehicle to at least automatically perform an evacuation action when it is estimated that a plurality of occupants are in the abnormal state based on the estimation results by the driver state estimation unit and the passenger state estimation unit,
The second evacuation instruction unit is a vehicle device that, when it is estimated that multiple occupants are in the abnormal state, carries out the evacuation action without confirming with the occupants whether or not they are in the abnormal state . The vehicle device according to any one of claims 1 to 7 ,
a notification control unit (106) that causes a notification device (21) to notify a passenger of the vehicle;
The notification control unit is a vehicle device that, when the driver's state estimation unit estimates that the driver is in the abnormal state, issues a notification to prompt the driver to confirm whether or not the driver is in the abnormal state. The vehicle device according to claim 8 ,
The driver state estimation unit distinguishes and identifies the type of the abnormal state,
a notification control unit (106a) that notifies a passenger of the vehicle by displaying at least a display (211, 212);
The notification control unit is a vehicle device that, when the driver state estimation unit estimates that the driver is in an abnormal state, displays an abnormality type display, which displays the type of the abnormal state, on both a first display dedicated to the driver and a second display visible to passengers other than the driver. 10. The vehicle device according to claim 9 ,
an answer receiving unit (107) for receiving an answer input of whether the abnormality type display is correct or not from the occupant;
and a first evacuation instruction unit (112a) that causes the vehicle to at least automatically perform evacuation action based on the answer input from the occupant that the abnormal state of the driver indicated by the abnormality type display is correct, when the answer receiving unit receives such answer input. The vehicle device according to claim 10 ,
a first reception unit (171) serving as the answer reception unit, which receives a correct or incorrect answer input from the driver;
a second reception unit (172) that receives a correct or incorrect answer input from the passenger as the answer reception unit,
The first evacuation instruction unit, when receiving answer inputs whose correctness differs between the first and second receiving units, prioritizes the answer input received by the second receiving unit over the answer input received by the first receiving unit. The vehicle device according to claim 11 ,
The first evacuation instruction unit is a vehicle device that follows the answer input when the answer input is received only by the first reception unit out of the first reception unit and the second reception unit. The vehicle device according to claim 10 ,
The notification control unit, when the first evacuation instruction unit causes the evacuation action to be carried out and a specified evacuation area that can be reached by the sleep-permitted automatic driving exists, causes the display to display information guiding the route from the current location of the vehicle to the evacuation area, while, when the first evacuation instruction unit causes the evacuation action to be carried out and the evacuation area that can be reached by the sleep-permitted automatic driving does not exist, causes the notification device to issue a notification indicating that an emergency stop of the vehicle will be performed. The vehicle device according to any one of claims 1 to 7 ,
a passenger presence/absence identification unit (104) for identifying the presence or absence of a passenger other than the driver of the vehicle;
and a notification control unit (106) that causes the notification device (21) to notify the occupant.
The vehicle also includes an awake identification unit (105) for estimating whether the passenger is in an awake state,
The notification control unit is a vehicle device that, when the driver state estimation unit estimates that the driver is in an abnormal state, the passenger presence determination unit determines that there is a passenger, and the wakefulness determination unit estimates that the passenger is in an wakeful state, issues a notification to the passenger to inform the passenger that the driver may be in the abnormal state. The vehicle device according to any one of claims 1 to 7 ,
A vehicle device comprising: a stop instruction unit (1121) that, when the driving identification unit identifies that the sleep-permitted automatic driving is in progress and the driver state estimation unit estimates that the abnormal state is in progress, does not immediately make an emergency stop of the vehicle, but instead automatically drives the vehicle to a specific area recommended as an emergency evacuation location in an area where the sleep-permitted automatic driving is possible and then stops the vehicle. The vehicle device according to any one of claims 1 to 6 ,
a passenger state estimation unit (105b) capable of estimating whether a passenger other than the driver is in the abnormal state;
and a second evacuation instruction unit (112b) that causes the vehicle to at least automatically perform an evacuation action when it is estimated that multiple occupants are in the abnormal state based on the estimation results by the driver state estimation unit and the passenger state estimation unit. The vehicle device according to any one of claims 1 to 7 ,
a passenger state estimation unit (105b) capable of estimating whether a passenger other than the driver is in the abnormal state;
and a notification control unit (106c) that causes a notification device (21a) to notify at least the driver,
The notification control unit is a vehicle device that, when it is estimated that the passenger is in the abnormal state, causes the notification device to issue a notification to the driver suggesting that an emergency call be made. An estimation method for a vehicle that can be used in a vehicle that switches between sleep-permitted automated driving, which is an automated driving level at which a driver is permitted to sleep, and sleep-non-permitted driving, which is an automated driving level at which a driver is not permitted to sleep,
Executed by at least one processor,
a driver state estimation step capable of estimating whether the driver is in an abnormal state other than a sleeping state by using a plurality of types of sensors;
A driving identification step of identifying whether the vehicle is in the sleep-permitting automatic driving mode or the sleep-non-permitting automatic driving mode,
In the driver state estimation step, when it is determined in the driving identification step that the driver is in the sleep-permitted automatic driving state, a plurality of types of sensors are used to estimate whether or not the driver is in the abnormal state, whereas when it is determined in the driving identification step that the driver is in the sleep-permitted automatic driving state, the number of types of sensors used is reduced compared to when it is determined that the driver is in the sleep-permitted automatic driving state , and whether or not the driver is in the abnormal state is estimated;
In the driver state estimation process, it is possible to estimate whether or not the abnormal state exists using an imaging device that images the driver and a biosensor that measures bioinformation of the driver, and if the driving identification process identifies that the driver is in sleep-non-permitted driving, the imaging device and the biosensor are used to estimate whether or not the abnormal state exists, while if the driving identification process identifies that the driver is in sleep-permitted automatic driving, the imaging device but not the biosensor is used to estimate whether or not the abnormal state exists . An estimation method for a vehicle that can be used in a vehicle that switches between sleep-permitted automated driving, which is an automated driving level at which a driver is permitted to sleep, and sleep-non-permitted driving, which is an automated driving level at which a driver is not permitted to sleep,
Executed by at least one processor,
a driver state estimation step capable of estimating whether the driver is in an abnormal state other than a sleeping state by using a plurality of types of sensors;
A driving identification step of identifying whether the vehicle is in the sleep-permitting automatic driving mode or the sleep-non-permitting automatic driving mode,
In the driver state estimation step, when it is determined in the driving identification step that the driver is in the sleep-permitted automatic driving state, a plurality of types of sensors are used to estimate whether or not the driver is in the abnormal state, whereas when it is determined in the driving identification step that the driver is in the sleep-permitted automatic driving state, the number of types of sensors used is reduced compared to when it is determined that the driver is in the sleep-permitted automatic driving state , and whether or not the driver is in the abnormal state is estimated;
In the driver state estimation step, whether or not the abnormal state exists is estimated by using fewer types of sensors than when the driver determines that the vehicle is in sleep-permitted automatic driving, and if it is determined that the vehicle is in an abnormal state, even if the driver determines that the vehicle is in sleep-permitted automatic driving in the driving identification step, the vehicle estimation method re-estimates whether or not the abnormal state exists by using the same number of types of sensors as when the driver determines that the vehicle is in sleep-permitted automatic driving . An estimation method for a vehicle that can be used in a vehicle that switches between sleep-permitted automated driving, which is an automated driving level at which a driver is permitted to sleep, and sleep-non-permitted driving, which is an automated driving level at which a driver is not permitted to sleep,
Executed by at least one processor,
a driver state estimation step capable of estimating whether the driver is in an abnormal state other than a sleeping state by using a plurality of types of sensors;
A driving identification step of identifying whether the vehicle is in the sleep-permitting automatic driving mode or the sleep-non-permitting automatic driving mode,
In the driver state estimation step, when it is determined in the driving identification step that the driver is in the sleep-permitted automatic driving state, a plurality of types of sensors are used to estimate whether or not the driver is in the abnormal state, whereas when it is determined in the driving identification step that the driver is in the sleep-permitted automatic driving state, the number of types of sensors used is reduced compared to when it is determined that the driver is in the sleep-permitted automatic driving state , and whether or not the driver is in the abnormal state is estimated;
a seat control instruction step for controlling a reclining angle of an electric seat of the vehicle,
In the seat control instruction process, when the driver's state estimation process estimates that the abnormal state exists and the reclining angle of the electric seat of the driver's seat of the vehicle is a sleep angle in which the angle of the seat back relative to the floor surface of the vehicle is reclined less than a first specified angle, the reclining angle of the electric seat of the driver's seat is returned to a reference angle in which the angle of the seat back relative to the floor surface is raised to or above a second specified angle that is greater than the first specified angle . An estimation method for a vehicle that can be used in a vehicle that switches between sleep-permitted automated driving, which is an automated driving level at which a driver is permitted to sleep, and sleep-non-permitted driving, which is an automated driving level at which a driver is not permitted to sleep,
Executed by at least one processor,
a driver state estimation step capable of estimating whether the driver is in an abnormal state other than a sleeping state by using a plurality of types of sensors;
A driving identification step of identifying whether the vehicle is in the sleep-permitting automatic driving mode or the sleep-non-permitting automatic driving mode,
In the driver state estimation step, when it is determined in the driving identification step that the driver is in the sleep-permitted automatic driving state, a plurality of types of sensors are used to estimate whether or not the driver is in the abnormal state, whereas when it is determined in the driving identification step that the driver is in the sleep-permitted automatic driving state, the number of types of sensors used is reduced compared to when it is determined that the driver is in the sleep-permitted automatic driving state , and whether or not the driver is in the abnormal state is estimated;
The method includes a third evacuation instruction step of causing the vehicle to automatically take an evacuation action and make an emergency call to a center based on at least the driver state estimation step estimating that the driver is in an abnormal state,
In the third evacuation instruction step,
When a predetermined evacuation area reachable by the sleep-permitting autonomous driving exists, the evacuation action is implemented by driving the vehicle to the evacuation area by the sleep-permitting autonomous driving and then stopping the vehicle, whereas when the evacuation area reachable by the sleep-permitting autonomous driving does not exist, the evacuation action is implemented by making an emergency stop of the vehicle,
An estimation method for a vehicle , in which, when the vehicle is driven to the evacuation area using the sleep-permitted automatic driving mode and then stopped, the emergency call is made at a time when the vehicle is able to travel a predetermined distance or more without any plans for the vehicle to change lanes . An estimation method for a vehicle that can be used in a vehicle that switches between sleep-permitted automated driving, which is an automated driving level at which a driver is permitted to sleep, and sleep-non-permitted driving, which is an automated driving level at which a driver is not permitted to sleep,
Executed by at least one processor,
a driver state estimation step capable of estimating whether the driver is in an abnormal state other than a sleeping state by using a plurality of types of sensors;
A driving identification step of identifying whether the vehicle is in the sleep-permitting automatic driving mode or the sleep-non-permitting automatic driving mode,
In the driver state estimation step, when it is determined in the driving identification step that the driver is in the sleep-permitted automatic driving state, a plurality of types of sensors are used to estimate whether or not the driver is in the abnormal state, whereas when it is determined in the driving identification step that the driver is in the sleep-permitted automatic driving state, the number of types of sensors used is reduced compared to when it is determined that the driver is in the sleep-permitted automatic driving state , and whether or not the driver is in the abnormal state is estimated;
a passenger state estimation step capable of estimating whether a passenger other than the driver is in the abnormal state;
a second evacuation instruction step of causing the vehicle to at least automatically perform an evacuation action when it is estimated that a plurality of occupants are in the abnormal state based on the estimation results in the driver state estimation step and the passenger state estimation step,
In the second evacuation instruction process, when it is estimated that multiple occupants are in the abnormal state, the vehicle estimation method causes the occupants to take the evacuation action without confirming with the occupants whether or not they are in an abnormal state .

Images