JP7601659B2 - Driving posture determination device - Google Patents

Description

The present invention relates to a vehicle driver's driving posture determination device.

Various technologies have been proposed for controlling the posture of a vehicle driver. For example, Patent Document 1 proposes a driver posture control device that controls the driver's posture using seat position information calculated based on the driver's gender and physical information. In addition, Patent Document 2 proposes an occupant posture control device that appropriately controls the posture of an occupant depending on the vehicle's motion state, etc.

JP 2013-063761 A JP 2009-226980 A

Here, even if the driver himself adjusts the position of the driver's seat and steering wheel to set the driving position, the driver's driving posture in that set state is not necessarily optimal. Specifically, even if the driver himself sets the driving position, the driver's body may shake significantly while driving, which may unconsciously cause stress to the driver. The above-mentioned Patent Documents 1 and 2 control the driver's posture according to the driver's body and the driving state of the vehicle, but do not present an appropriate driving position from the perspective of stress for the driver.

The present invention was made in consideration of the above problems, and the object of the present invention is to provide a driving posture determination device that determines a driving position that can reduce the stress on the driver caused by driving a vehicle.

In order to solve the above problems, according to one aspect of the present invention, a driving posture determination device is provided that includes a stress estimation unit that estimates the stress state of a vehicle driver, a learning unit that associates driving position setting information, vehicle running state information, and driver stress state information and stores them in a memory unit, and an appropriate position determination unit that determines a driving position suitable for the driver based on the stored learning data.

The driving posture determination device may further include a control unit that controls a position adjustment device that adjusts the driving position, and the learning unit may store driving position setting information, vehicle driving state information, and driver stress state information in association with each other while changing the driving position.

The driving posture determination device may further include a posture determination unit that determines the deviation of the driver's actual posture from the driver's appropriate posture, and the learning unit may store the posture deviation information in the memory unit in association with the driving position setting information, the vehicle running state information, and the driver's stress state information.

In the driving posture determination device, the appropriate position determination unit may present a driving position suitable for the driver when starting or ending use of the vehicle.

In the driving posture determination device described above, when the vehicle's destination is set, the appropriate position determination unit may present the driver with a driving position suitable for the driver according to the planned driving route to the set destination.

As described above, the present invention makes it possible to determine a driving position that can reduce the driver's stress caused by driving a vehicle.

1 is a schematic diagram showing a configuration example of a driving posture determination device according to a first embodiment of the present invention; 2 is a block diagram showing a configuration example of a driving posture determination device according to the embodiment; FIG. FIG. 11 is an explanatory diagram showing deviations in the driver's posture. FIG. 2 is an explanatory diagram illustrating an example of a data set to be stored in a learning data storage unit. 4 is a flowchart of a learning data accumulation process performed by the driving posture determination device according to the embodiment. 4 is a flowchart of a recommended driving position presenting process performed by the driving posture determination device according to the embodiment. FIG. 5 is a block diagram showing a configuration example of a driving posture determination device according to a second embodiment of the present invention. 4 is a flowchart of a learning model generation process performed by the driving posture determination device according to the embodiment. FIG. 4 is an explanatory diagram showing an example of a learning process of a driving position determination model. 4 is a flowchart of a recommended driving position presenting process performed by the driving posture determination device according to the embodiment. FIG. 2 is an explanatory diagram showing a driving position determination model.

Below, a preferred embodiment of the present invention will be described in detail with reference to the attached drawings. Note that in this specification and drawings, components having substantially the same functional configuration are designated by the same reference numerals to avoid redundant description.

<<1. First embodiment>>
<1-1. Configuration example>
First, an example of the configuration of a driving posture determination device according to a first embodiment of the present invention will be described.
The driving posture determination device of the first embodiment is configured as a device that determines a driving position suitable for a driver based on the learning results of the driver's stress state while driving a vehicle, and presents the driving position suitable for the driver (recommended driving position) to the driver.

In this specification, the term "driver's driving posture" refers to the driver's own posture, and the term "driving position" refers to at least the longitudinal position of the driver's seat 5 of the vehicle and the angle of the backrest 5a. The term "driving position" may also include the setting of adjustable elements such as the height of the seat 5b of the driver's seat 5, the angle of the seat 5b, the recession degree of the seat 5b, the recession degree of the backrest 5a, or the position of the headrest 5c, and may also include the setting of the tilt angle or longitudinal position of the steering wheel 9. In the following embodiment, in order to facilitate understanding of the invention, an example will be described in which the longitudinal position of the driver's seat 5, the angle of the backrest 5a, the height of the seat 5b, and the longitudinal position of the steering wheel 9 are determined as the "driving position".

Figure 1 is a schematic diagram showing an example of the configuration of the driving posture determination device 1 according to this embodiment, and Figure 2 is a block diagram showing an example of the configuration of the driving posture determination device 1.

The driving posture determination device 1 includes a control device 50. The driving posture determination device 1 includes a driver monitoring device 21, a surrounding environment sensor 23, a vehicle running state sensor 25, a vehicle position detection unit 27, and an input unit 29 as devices that input signals to the control device 50. The driving posture determination device 1 includes an HMI (Human Machine Interface) 41, a power seat drive unit 43, and a steering position adjustment unit 45 as devices to which the control device 50 outputs signals. The driver monitoring device 21, the surrounding environment sensor 23, the vehicle running state sensor 25, the vehicle position detection unit 27, the input unit 29, the HMI 41, the power seat drive unit 43, and the steering position adjustment unit 45 are each connected to the control device 50 directly or via a communication means such as a CAN (Controller Area Network) or a LIN (Local Inter Net).

(1-1-1. Driver Monitoring Device)
The driver monitoring device 21 is installed so as to include at least the driver D within its imaging range. The driver monitoring device 21 includes, for example, an infrared camera. The driver monitoring device 21 includes an image processing device (not shown) and executes a process of detecting biological information such as the sweating state, body temperature, blood flow, and heart rate of the driver D based on the acquired image data.

For example, the driver monitoring device 21 can perform OCT (Optical Coherence Tomography) analysis based on image data generated by an infrared camera to detect the sweating state of the driver D. The stress estimation unit 63 can detect the body temperature and blood flow of the driver D based on the image data generated by the infrared camera. Furthermore, the heart rate can be measured from the blood flow. The driver monitoring device 21 transmits the generated image data to the control device 50.

The detected biometric information of driver D is not limited to the examples of sweating state, body temperature, blood flow, and heart rate, and may be other biometric information. Furthermore, the method of detecting driver D's biometric information is not limited to the above examples. For example, instead of or together with a camera installed in the vehicle, a wearable device equipped with a sensor for detecting biometric information may be used. In this case, the wearable device is connected to the control device 50, for example, via a short-range wireless communication means. The wearable device may be, for example, a wristwatch-type wearable device or a head-mounted wearable device.

In this embodiment, the driver monitoring device 21 further includes an optical camera equipped with an imaging element such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor). The driver monitoring device 21 includes an image processing device (not shown) and performs an object detection process based on the acquired image data to identify the posture of at least the upper body of the driver D. The driver monitoring device 21 transmits the image data that identifies the posture of the driver D to the control device 50.

(1-1-2. Ambient environment sensor)
The surrounding environment sensor 23 is a sensor that detects information about the surrounding environment of the vehicle. The surrounding environment sensor 23 includes, for example, one or more of an imaging camera, a high-frequency radar sensor, an ultrasonic sensor, and a LiDAR. The imaging camera is composed of one or more cameras equipped with an imaging element such as a CCD or a CMOS, similar to the driver monitoring device 21. The surrounding environment sensor 23 may be installed as a safety function of the vehicle. The surrounding environment sensor 23 transmits a sensor signal including detected data to the control device 50. In this embodiment, the surrounding environment sensor 23 is used to estimate at least the form of the road on which the vehicle is traveling. Specifically, the control device 50 determines whether the road is a winding road with successive left and right curves based on the signal transmitted from the surrounding environment sensor 23.

(1-1-3. Vehicle Running Condition Sensor)
The vehicle running condition sensor 25 is composed of at least one sensor that detects the operation amount and behavior of the vehicle. The vehicle running condition sensor 25 includes at least one of a vehicle speed sensor, an acceleration sensor, and an angular velocity sensor, and detects information on the behavior of the vehicle, such as the vehicle speed, longitudinal acceleration, lateral acceleration, yaw rate, and roll angle. The vehicle running condition sensor 25 also includes at least one of an accelerator position sensor, a brake stroke sensor, a brake pressure sensor, a steering angle sensor, and an engine rotation speed sensor, and detects information on the operation amount of the vehicle, such as the steering angle of the steering wheel or steering wheels, the accelerator opening, and the amount of brake operation.

(1-1-4. Vehicle position detection unit)
The vehicle position detection unit 27 detects the position information of the vehicle on the map data. For example, the vehicle position detection unit 27 may be a GPS antenna that receives satellite signals from GPS (Global Positioning System) satellites. The vehicle position detection unit 27 transmits the detected vehicle position information to the control device 50. Note that the vehicle position detection unit 27 may include an antenna that receives satellite signals from other satellite systems that identify the position of the vehicle, instead of or in addition to the GPS antenna.

(1-1-5. Input section)
The input unit 29 accepts the operation input of the driver D to the control device 50. The input unit 29 may be, for example, a touch panel display, a dial-type operation device, or a change-over switch. In this embodiment, the input unit 29 is configured to be able to accept an input operation for selecting at least the on/off of the driving position learning function. In addition, in this embodiment, the input unit 29 accepts an operation input of a power seat that adjusts the front-rear position of the driver's seat 5, the angle of the backrest 5a, and the height of the seat 5b. Furthermore, in this embodiment, the input unit 29 accepts an operation input of a steering position adjustment unit 45 that adjusts the front-rear position of the steering wheel 9. The input unit 29 transmits a signal including the input information to the control device 50.

(1-1-6.HMI)
The HMI 41 is driven by the control device 50 and presents various information to the driver D by means of image display, audio output, etc. The HMI 41 includes, for example, a display device and a speaker provided in an instrument panel. The display device may be a display device of a navigation system. The HMI 41 may also include a HUD (head-up display) that displays information on the front window.

(1-1-7. Power seat drive unit)
The power seat drive unit 43 constitutes a part of a position adjustment device that adjusts the driving position, and includes an actuator that adjusts the longitudinal position of the driver's seat 5 and the angle of the backrest 5a. In this embodiment, the power seat drive unit 43 includes a first motor 31, a second motor 33, and a third motor 35, each of which has a supply current controlled by an arithmetic processing unit 51. The first motor 31 is disposed, for example, inside the backrest 5a to change the angle of the backrest 5a. The second motor 33 is disposed, for example, inside the seat portion 5b to move the driver's seat 5 in the longitudinal direction. The third motor 35 is disposed, for example, inside the seat portion 5b to change the height of the seat portion 5b.

(1-1-8. Steering position adjustment unit)
The steering position adjustment unit 45 constitutes a part of a position adjustment device that adjusts the driving position, and includes an actuator that adjusts the longitudinal position of the steering wheel 9. The steering position adjustment unit 45 includes, for example, a rack-and-pinion mechanism and an actuator to which a supply current is controlled by the control device 50. The actuator may be, for example, a motor that is disposed inside the steering column and changes the steering wheel 9 in the longitudinal direction.

(1-1-9. Control Device)
The control device 50 learns the stress state of the driver D according to the driving state of the vehicle in the set driving position using information on the driving state of the vehicle and information on the stress state of the driver D as input data, and determines a driving position suitable for the driver D based on the learning result. In addition, in this embodiment, the control device 50 presents the determined driving position suitable for the driver D to the driver D. As a result, the driver D can accept the presented driving position and reset the position of the driver's seat 5, the angle of the backrest 5a, the height of the seat 5b, or the position of the steering wheel 9 to achieve a driving position that can reduce the stress of the driver D. Hereinafter, a configuration example of the control device 50 of the driving posture determination device 1 according to this embodiment will be specifically described.

<1-2. Functional configuration of the control device>
2, the control device 50 includes an arithmetic processing unit 51, a storage unit 53, and a learning data storage unit 55. The control device 50 is configured to include at least an arithmetic processing device such as a CPU (Central Processing Unit) or a GPU (Graphic Processing Unit). Note that a part or all of the control device 50 may be configured with updatable firmware or the like, or may be a program module or the like executed by instructions from the CPU or the like.

(1-2-1. Storage section)
Of these, the storage unit 53 is a storage element such as a random access memory (RAM) or a read only memory (ROM), or a hard disk drive (HDD), a compact disc (CD), a digital versatile disc (DVD), or an SSD (SSD). The storage unit 53 is configured with a storage medium such as a solid state drive, a USB (Universal Serial Bus) flash, a storage device, etc. The storage unit 53 stores software programs executed by the arithmetic processing unit, various parameters used in the arithmetic processing, acquired The calculated data, calculation results, etc. are stored.

(1-2-2. Learning Data Storage Unit)
The learning data memory unit 55 is composed of an updatable storage medium such as a RAM, HDD, CD, DVD, SSD, USB flash, storage device, etc., and stores learning data of the driving position judgment model obtained as a result of learning by the learning unit 67 of the calculation processing unit 51.

(1-2-3. Arithmetic Processing Unit)
The arithmetic processing unit 51 is configured to include an arithmetic processing device such as a CPU or an MPU, and an image processing device such as a GPU. The arithmetic processing device and the image processing device execute various arithmetic processing by executing programs stored in the storage unit 53. In this embodiment, the arithmetic processing unit 51 includes a control unit 61, a stress estimation unit 63, a posture determination unit 65, a learning unit 67, and an appropriate position determination unit 69. Some or all of these units are functions realized by the execution of a program by the arithmetic processing device or the image processing device.

[1-2-3-1. Control unit]
The control unit 61 controls the driving of the power seat driving unit 43 and the steering position adjustment unit 45 based on an operation input signal of the power seat and steering position adjustment unit 45 transmitted from the input unit 29. In this embodiment, the control unit 61 controls the driving of the power seat driving unit 43 and the steering position adjustment unit 45 based on a control command from the stress estimation unit 63 to search for a driving position suitable for the driver D with the learning function turned on, and adjusts the driving position.

[1-2-3-2. Stress Estimation Unit]
The stress estimation unit 63 estimates the stress state of the driver D. In this embodiment, the stress estimation unit 63 estimates the stress state of the driver D based on biological information of the driver D transmitted from the driver monitoring device 21. In this embodiment, the stress estimation unit 63 estimates the stress state of the driver D based on data on the sweating state, body temperature, blood flow, and heart rate detected by the driver monitoring device 21.

For example, it is known that when a person feels stress, the brain is stimulated and sweats. For this reason, the stress estimation unit 63 estimates that the driver D has begun to feel stressed when the degree of increase in the amount of sweating exceeds a preset threshold. Furthermore, the stress estimation unit 63 estimates that the driver D is feeling stressed during the period after the degree of increase in the amount of sweating exceeds the threshold until the amount of sweating returns to the value before the increase.

It is also known that when a person feels stress, the sympathetic nervous system becomes active and body temperature rises. For this reason, the stress estimation unit 63 estimates that driver D has begun to feel stressed when the degree of increase in body temperature exceeds a preset threshold. Furthermore, the stress estimation unit 63 estimates that driver D is feeling stressed after the degree of increase in body temperature exceeds the threshold until the body temperature returns to the value before the increase.

It is also known that when a person feels stress, the sympathetic nervous system becomes active, causing blood vessels to constrict, decreasing blood flow and increasing heart rate. For this reason, the stress estimation unit 63 may estimate that driver D is feeling stressed while blood flow is below a preset threshold. The stress estimation unit 63 may also estimate that driver D is feeling stressed while the heart rate exceeds a preset threshold.

The stress estimation unit 63 may estimate that the driver D is feeling stressed when at least one of the above examples applies, or may estimate that the driver D is feeling stressed when two or more of the above examples apply. The method of detecting the state in which the driver D is feeling stressed is not limited to the above examples. Furthermore, the stress estimation unit 63 may estimate the stress level of the driver D according to the value or degree of change of the sweating state, body temperature, blood flow state, or heart rate.

[1-2-3-3. Posture determination section]
The posture determination unit 65 determines the posture of the driver D while driving the vehicle. Specifically, the posture determination unit 65 determines the movement of the driver D from the appropriate posture based on the image data transmitted from the driver monitoring device 21. If the driving position is not appropriate, the driving posture of the driver D is likely to deviate from the appropriate position depending on the running state of the vehicle. For this reason, in this embodiment, in addition to the stress information of the driver D, By using information on the dynamic deviation of the driver D from the appropriate posture as input data, the accuracy of learning the appropriate driving position for the driver D is improved.

FIG. 3 is an explanatory diagram showing dynamic deviations in the driving posture of the driver D. In FIG.
3 shows the vibration (sway) of the upper body of the driver D when the vehicle repeatedly accelerates and decelerates suddenly, or turns right and left. The reference vibration in the center left of the figure represents a state in which the driver D is in a driving position suitable for him and the driver's upper body sways with a predetermined period and amplitude.

In contrast, if the driving position is not suitable for driver D, the vibration mode (vibration form) may shift, for example as shown in the upper left of the figure. When the vibration mode is shifted, the ratio of head to torso displacement and the ratio of head to torso sway angle are different compared to the reference vibration. In addition, as shown in the lower left of the figure, the amplitude of the sway may shift. When the amplitude is shifted, the vibration mode and the frequency of the sway are the same as those of the reference vibration, but the amplitude of the sway has changed. In addition, as shown on the right of the figure, the frequency of the sway may shift. When the frequency is shifted, the vibration mode and the amplitude are the same as those of the reference vibration, but the frequency of the sway has changed.

The posture determination unit 65 compares the image data that identifies the posture of the driver D in a time series and determines whether or not there is a deviation in the posture of the driver D. The posture determination unit 65 may also determine the manner in which the posture of the driver D is dynamically deviated.

[1-2-3-4. Learning section]
With the learning function turned on, the learning unit 67 associates and stores in the learning data storage unit 55 information on the driving position setting, information on the vehicle's running state, and information on the driver D's stress state. In this embodiment, the learning unit 67 associates and stores information on the vehicle's running position in order to learn the stress state in a running scene in which the driver D's posture becomes unstable while the vehicle is running. In this embodiment, the learning unit 67 also associates and stores information on the driver D's driving posture.

In this embodiment, the learning unit 67 acquires various data for multiple driving positions in driving scenes in which the driver D's posture becomes unstable while the vehicle is traveling, and stores the data in the learning data storage unit 55. Specifically, the learning unit 67, with the learning function turned on, determines driving scenes in which the driver D's posture becomes unstable based on the information on the vehicle's position on the map data transmitted from the vehicle position detection unit 27, and changes the driving position each time the vehicle travels through the driving scene. Driving scenes in which the driver D's posture becomes unstable are appropriately set in advance, such as a winding road with successive right and left curves, or a road with a highly uneven surface.

For example, when the vehicle position approaches the driving scene, the learning unit 67 drives one or more of the first motor 31, second motor 33, or third motor 35 of the power seat drive unit 43 or the actuators of the steering position adjustment unit 45 to change the driving position from the driving position when the learning function was turned on to an unlearned driving position. Also, when the learning unit 67 estimates that the driver D is feeling stressed in the set driving position, it drives one or more of the first motor 31, second motor 33, or third motor 35 of the power seat drive unit 43 or the actuators of the steering position adjustment unit 45 to search for a driving position that reduces stress.

More specifically, when driver D feels stressed in a certain driving position, the learning unit 67 drives one or more of the first motor 31, second motor 33, or third motor 35 of the power seat drive unit 43 or the actuator of the steering position adjustment unit 45. At this time, if driver D's stress is reduced, the driving position is further changed in the same direction. On the other hand, when stress increases, the driving position is changed in the opposite direction. In this way, the learning unit 67 searches for a driving position that reduces driver D's stress while changing the driving position.

The learning unit 67 may return the driving position to the original position after the vehicle has passed through the driving scene. The learning unit 67 may also determine the timing when the vehicle passes through a driving scene in which the driver D's posture becomes unstable based on information about the road in the vehicle's traveling direction detected by the surrounding environment sensor 23, instead of determining the timing based on the vehicle's position information and map data.

FIG. 4 shows an example of a data set stored in the learning data storage unit 55.
With the learning function turned on, the learning unit 67 acquires the following data when the vehicle travels through a driving scene in which the driver D's driving posture becomes unstable, and stores the data in the learning data storage unit 55. The learning unit 67 stores data on the control amount (rotation amount) of the actuators of the first motor 31, the second motor 33, and the third motor 35 of the power seat drive unit 43 driven by the control unit 61 and the steering position adjustment unit 45 as driving position information. The control amount of each motor or actuator corresponds to data indicating the front-rear position of the driver's seat 5, the angle of the backrest 5a, the height of the seat 5b, and the front-rear position of the steering wheel 9.

The learning unit 67 also stores data such as vehicle speed, longitudinal acceleration, lateral acceleration, yaw rate, and roll angle based on the sensor signal output from the vehicle driving state sensor 25 as information on the vehicle driving state. The learning unit 67 also stores vehicle position data transmitted from the vehicle position detection unit 27 as information on the vehicle driving position. The learning unit 67 may also store road condition data such as curves and road surface unevenness based on data transmitted from the surrounding environment sensor 23 as information on the vehicle driving position. The learning unit 67 also stores data on the deviation of the driving posture determined by the posture determination unit 65 as information on the driving posture of the driver D. The learning unit 67 also stores data on the stress state of the driver D estimated by the stress estimation unit 63 as information on the driver stress state.

[1-2-3-5. Appropriate position determination unit]
The appropriate position determination unit 69 determines a driving position suitable for the driver D based on the learning data stored in the learning data storage unit 55. For example, the appropriate position determination unit 69 determines a driving position where the driver D does not feel stress and where there is little deviation in the driving posture as a recommended driving position suitable for the driver D.

In this embodiment, the data set stored in the learning data storage unit 55 includes information on the vehicle's driving state and the vehicle's driving position. Therefore, it is possible to compare the stress state of the driver D due to differences in driving positions when the turning acceleration or longitudinal acceleration generated by the vehicle's behavior and driving line is the same. This makes it possible to improve the accuracy of the recommended driving position determined by the appropriate position determination unit 69. Furthermore, when the data set stored in the learning data storage unit 55 includes data on the dynamic deviation of the driver D's posture (vibration mode, amplitude, or frequency), it is possible to determine a recommended driving position that can reduce the deviation of the posture that increases the driver D's stress.

The information on the recommended driving position includes data on the recommended position of the driver's seat 5 in the fore-aft direction, the recommended angle of the backrest 5a, the recommended height of the seat 5b, and the recommended position of the steering wheel 9 in the fore-aft direction. When the stress estimation unit 63 estimates the stress level felt by the driver D, the appropriate position determination unit 69 may determine that the driving position with the lowest stress level and the smallest deviation in driving posture is the driving position suitable for the driver D. The appropriate position determination unit 69 may determine the driving position suitable for the driver D at all times, when the learning function is turned off, or when the vehicle begins or ends being used.

The appropriate position determination unit 69 may also present the driving position suitable for the driver D, determined based on the learning data, to the driver D as a recommended driving position. For example, the appropriate position determination unit 69 may drive the HMI 41 to present the recommended driving position to the driver D. Specifically, the appropriate position determination unit 69 may present an operation guide for changing the current driving position setting to the recommended driving position setting by at least one of audio and display means. For example, the appropriate position determination unit 69 may present to the driver D an operation guide for moving the position of the driver's seat 5 forward or backward, an operation guide for decreasing or increasing the angle of the backrest 5a, or an operation guide for increasing or decreasing the height of the seat 5b. Alternatively, the appropriate position determination unit 69 may present an operation guide for moving the position of the steering wheel 9 forward or backward.

In addition, if the vehicle is equipped with a function for storing the fore-aft position of the driver's seat 5, the angle of the backrest 5a, the height of the seat 5b, and the fore-aft position of the steering wheel 9, the appropriate position determination unit 69 may store the recommended driving position setting so that the driving position is automatically set the next time the same driver D uses the vehicle.

Furthermore, the appropriate position determination unit 69 may output a control command to the control unit 61 so that the driving position becomes the recommended driving position. When automatically adjusting the driving position to the recommended driving position, it is preferable to adjust the driving position while the vehicle is stopped so that the driver D does not feel uneasy or in danger.

<1-3. Operation example of driving posture determination device>
Next, a description will be given of an example of the operation of the driving posture determination device 1 according to this embodiment. As an example of the operation of the driving posture determination device 1, a learning data accumulation process and a recommended driving position presentation process will be described below.

(1-3-1. Learning data accumulation process)
FIG. 5 is a flowchart showing the learning data accumulation process.
First, the learning unit 67 determines whether the learning function is on or off (step S11). The learning function is set to on or off based on an operation input to the input unit 29 by the driver D. If the learning function is not on (S11/No), the learning unit 67 ends this routine and repeats the determination of step S11.

On the other hand, if the learning function is on (S11/Yes), the learning unit 67 acquires driver identification information (step S13). The driver identification information is information for identifying the driver D sitting in the driver's seat 5, and is acquired to identify the driver D to whom the recommended driving position is to be applied. The driver identification information is not particularly limited, but may be data set and registered by a user such as the driver D, or may be data assigned to an individual driver D identified by the driver monitoring device 21 through feature analysis of the face image of the driver D, etc.

Next, the learning unit 67 determines whether the driving scene of the vehicle is one in which the driver D's driving posture is likely to be unstable (step S15). For example, when the learning unit 67 determines that the vehicle is driving or is driving on a winding road based on the vehicle position information transmitted from the vehicle position detection unit 27 and the map data, it determines that the driving scene is one in which the driver D's driving posture is likely to be unstable. The learning unit 67 may also determine whether the driving scene of the vehicle is one in which the driver D's driving posture is likely to be unstable based on the information on the road conditions in the vehicle's traveling direction transmitted from the surrounding environment sensor 23.

If the vehicle driving situation is not determined to be one in which the driver D's driving posture is likely to be unstable (S15/No), the learning unit 67 ends this routine and returns to step S11. On the other hand, if the vehicle driving situation is determined to be one in which the driver D's driving posture is likely to be unstable (S15/Yes), the learning unit 67 sets a driving position that estimates the stress state (step S17). Specifically, the learning unit 67 adjusts the driving position by driving at least one of the first motor 31, second motor 33, and third motor 35 of the power seat drive unit 43 and the actuator of the steering position adjustment unit 45.

For example, if the data on the driving position that estimates the stress state is not stored in the learning data storage unit 55, the learning unit 67 appropriately changes at least one of the following from the driving position that was set when the vehicle started traveling: the fore-and-aft position of the driver's seat 5, the angle of the backrest 5a, the height of the seat 5b, or the fore-and-aft position of the steering wheel 9.

In addition, when data on driving positions that have previously estimated the stress state of the driver D is stored in the learning data storage unit 55, the learning unit 67 changes the driving position in a direction that is expected to reduce stress, based on a driving position with a low stress state. Specifically, the learning unit 67 refers to data on the stress state of the driver D when the driving position was changed up to the last time, and if the change in driving position reduces the stress of the driver D, it further changes the driving position in the same direction. On the other hand, if the stress increases, it changes the driving position in the opposite direction. At this time, information on the ideal stress state and posture deviation is set in advance, and the learning unit 67 may change the driving position in a direction that approaches the ideal stress state.

Next, the learning unit 67 acquires information on the vehicle's running state transmitted from the vehicle running state sensor 25 (step S19). For example, the learning unit 67 acquires vehicle behavior data such as longitudinal acceleration, lateral acceleration, yaw rate, and roll angle, and vehicle operation amount data such as accelerator opening, brake pressure, steering angle, and engine speed.

Next, the learning unit 67 acquires information on the vehicle's position (step S21). For example, the learning unit 67 acquires vehicle position data based on the vehicle position information transmitted from the vehicle position detection unit 27 and map data. The learning unit 67 may acquire data on road conditions, such as the radius of curvature of curves and the unevenness of the road surface, based on road information transmitted from the surrounding environment sensor 23, in addition to the vehicle position data.

Next, the stress estimation unit 63 estimates the stress state of the driver D based on the biological information of the driver D transmitted from the driver monitoring device 21 (step S23). Specifically, the stress estimation unit 63 estimates the stress state of the driver D based on the data of the sweating state, body temperature, blood flow, and heart rate detected by the driver monitoring device 21. The stress estimation unit 63 may estimate that the driver D is feeling stressed when at least one of the above examples applies, or may estimate that the driver D is feeling stressed when two or more of the above examples apply. The stress estimation unit 63 may also estimate the stress level of the driver D based on the data of the sweating state, body temperature, blood flow state, or heart rate.

Next, the posture determination unit 65 determines the dynamic deviation of the driver D from the correct posture based on the image data transmitted from the driver monitoring device 21 (step S25). For example, the posture determination unit 65 compares the image data that specifies the posture of the driver D in a time series and determines whether or not there is a deviation in the posture of the driver D. The posture determination unit 65 may determine the manner of the dynamic deviation of the posture of the driver D (deviation in vibration mode, deviation in amplitude, or deviation in frequency).

Next, the learning unit 67 associates the acquired driving position setting information, vehicle driving state information, vehicle position information, driver D's stress state information, and driver D's driving posture deviation information, and stores them in the learning data storage unit 55 (step S27). The learning unit 67 stores these data sets as time-series data in the learning data storage unit 55 while the vehicle is traveling in a driving scene where driver D's driving posture is likely to be unstable.

By repeatedly executing the above steps S11 to S27, the driving posture determination device 1 acquires data on the stress state and driving posture deviation felt by the driver D at each driving position while changing the driving position, and stores the data in the learning data storage unit 55.

(1-3-2. Recommended driving position presentation process)
FIG. 6 shows a flowchart of the recommended driving position presenting process.
First, the appropriate position determination unit 69 determines whether to start the process of presenting a recommended driving position (step S31). For example, the appropriate position determination unit 69 may determine to start the process of presenting a recommended driving position when the learning function is turned off, or when the vehicle is started or stopped being used. Alternatively, the appropriate position determination unit 69 may constantly execute the process of presenting a recommended driving position.

If it is not determined that the process of presenting a recommended driving position is to be started (S31/No), the appropriate position determination unit 69 ends this routine and repeats the determination in step S31. On the other hand, if it is determined that the process of presenting a recommended driving position is to be started (S31/Yes), the appropriate position determination unit 69 acquires driver identification information in the same procedure as in step S13 above (step S33).

Next, the appropriate position determination unit 69 determines a driving position (recommended driving position) suitable for driver D based on the learning data stored in the learning data storage unit 55 (step S35). For example, the appropriate position determination unit 69 determines a driving position in which driver D does not feel stress and in which there is little deviation in driving posture as a driving position suitable for driver D. When the stress estimation unit 63 estimates the stress level felt by driver D, the appropriate position determination unit 69 may determine a driving position in which there is the lowest stress level and little deviation in driving posture as a driving position suitable for driver D.

At that time, the appropriate position determination unit 69 may determine the recommended driving position by comparing the stress state of the driver D when the generated turning acceleration or longitudinal acceleration is the same, such as when the vehicle behavior and driving line are the same. Furthermore, the appropriate position determination unit 69 may determine a recommended driving position that can reduce dynamic deviations in posture (vibration mode, amplitude, or frequency) that increase the stress of the driver D. The information on the recommended driving position includes data on the recommended position of the driver's seat 5 in the longitudinal direction, the recommended angle of the backrest 5a, the recommended height of the seat 5b, and the recommended position of the steering wheel 9 in the longitudinal direction.

Next, the appropriate position determination unit 69 presents the recommended driving position determined to be suitable for the driver D to the driver D (step S37). For example, the appropriate position determination unit 69 may drive the HMI 41 to present an operation guide for changing the current driving position setting to the recommended driving position setting by at least one of audio and display means. Specifically, the appropriate position determination unit 69 may present the driver D with an operation guide for moving the position of the driver's seat 5 forward or backward, an operation guide for decreasing or increasing the angle of the backrest 5a, or an operation guide for increasing or decreasing the height of the seat 5b. Alternatively, the appropriate position determination unit 69 may present an operation guide for moving the position of the steering wheel 9 forward or backward.

When the vehicle is provided with a function for storing the longitudinal position of the driver's seat 5, the angle of the backrest 5a, the height of the seat 5b, and the longitudinal position of the steering wheel 9, the appropriate position determination unit 69 may store the recommended driving position setting so that the driving position will be automatically set the next time the same driver D uses the vehicle. Furthermore, the appropriate position determination unit 69 may output a control command to the control unit 61 so that the driving position becomes the recommended driving position. When automatically adjusting the driving position to the recommended driving position, it is preferable to adjust the driving position while the vehicle is stopped so that the driver D does not feel uneasy or in danger.

1-4. Effects of the First Embodiment
As described above, the driving posture determination device 1 according to the first embodiment stores driving position setting information, vehicle driving state information, and driver D's stress state information in the learning data storage unit 55 while the vehicle is traveling in association with each other, and determines a recommended driving position suitable for the driver D based on the stored learning data. Therefore, it is possible to determine a driving position that can reduce stress that the driver D himself is unlikely to notice.

In addition, the driving posture determination device 1 according to this embodiment estimates the stress state while changing the driving position each time the vehicle travels through a driving scene in which the driver D's driving posture is likely to be unstable, and stores the acquired data set in the learning data storage unit 55. This makes it possible to efficiently acquire data on the stress state of the driver D in a plurality of driving positions. In addition, when the vehicle travels through a driving scene in which the driver D's driving posture is likely to be unstable, the stress state is estimated and the acquired data set is stored in the learning data storage unit 55, so the load on the calculation processing unit 51 can be reduced.

In addition, the driving posture determination device 1 according to this embodiment further includes information on the deviation in the driver D's posture in the data set, and the recommended driving position is determined taking into account the information on the deviation in the driver D's posture. Therefore, it is possible to determine a recommended driving position that can not only reduce the stress felt by the driver D, but also reduce the deviation in the driver D's posture.

The driving posture determination device 1 according to this embodiment also presents the determined recommended driving position to the driver D. This allows the driver D to easily set the driving position to a less stressful one. Furthermore, when the recommended driving position is automatically set by the drive of the power seat drive unit 43 and the steering position adjustment unit 45, a less stressful driving position can be achieved even more easily.

<<2. Second embodiment>>
Next, a driving posture determining device according to a second embodiment of the present invention will be described.
The driving posture judgment device of the second embodiment is constructed as a device that uses machine learning to learn the relationship between the driving position, the vehicle's driving state, and the driver D's stress state to generate a driving position judgment model, uses the driving position judgment model to determine a recommended driving position that can reduce stress according to the planned route, and presents the recommended driving position.

Figure 7 is a block diagram showing an example of the configuration of the driving posture determination device 100 according to this embodiment. The basic configuration of the driving posture determination device 100 according to this embodiment is common to the example of the configuration of the driving posture determination device 1 according to the first embodiment, but the functions of the learning unit 66 and the appropriate position determination unit 68 are different from those in the first embodiment. The driving posture determination device 100 according to this embodiment will be described, focusing on the differences from the first embodiment.

The driving posture determination device 100 according to this embodiment includes a navigation system 30. The navigation system 30 is a known navigation system, and has a function of guiding the vehicle's driving route from the current position to a destination set by the driver D or the like, based on information on the vehicle's position detected by the vehicle position detection unit 27. The control device 50 acquires at least information on the planned driving route from the navigation system 30.

In addition, in this embodiment, with the learning function turned on, the learning unit 66 performs machine learning using the driving position setting information, information on the vehicle's running state, and information on the driver D's stress state as input data, and generates a driving position judgment model. In addition, in this embodiment, the learning unit 66 further uses information on the vehicle's running position as input data. Furthermore, the learning unit 66 uses data on the deviation of the driver D's driving posture as input data.

The functions of the learning unit 66 and the appropriate position determination unit 68 of the driving posture determination device 100 according to this embodiment will be explained below with reference to the flowchart.

FIG. 8 shows a flowchart of the learning model generation process.
The calculation processing unit 51 of the driving posture determination device 100 executes the processes of steps S11 to S25 in the same procedure as the learning data accumulation process in the first embodiment. Next, the learning unit 66 accumulates a data set consisting of the acquired driving position setting information, information on the vehicle's running state, information on the vehicle's running position, information on the deviation of the driver D's driving posture, and information on the driver D's stress state in the learning data storage unit 54, and executes the learning process using the data set as input data (step S28). The learning unit 66 generates a driving position determination model as a result of the learning, and stores the driving position determination model in the learning data storage unit 54.

FIG. 9 is an explanatory diagram showing an example of a learning process of the driving position determination model.
With the learning function turned on, the learning unit 66 acquires the following data when the vehicle travels through a driving scene in which the driver D's driving posture becomes unstable, and stores the data in the learning data storage unit 54. The learning unit 66 stores data on the control amount (rotation amount) of the actuators of the first motor 31, the second motor 33, and the third motor 35 of the power seat drive unit 43 driven by the control unit 61 and the steering position adjustment unit 45 as input data for the driving position. The control amount of each motor or actuator corresponds to data indicating the longitudinal position of the driver's seat 5, the angle of the backrest 5a, the height of the seat 5b, and the longitudinal position of the steering wheel 9.

The learning unit 66 also stores data such as vehicle speed, longitudinal acceleration, lateral acceleration, yaw rate, and roll angle based on the sensor signal output from the vehicle driving state sensor 25 as input data on the vehicle driving state. The learning unit 66 also stores vehicle position data transmitted from the vehicle position detection unit 27 as input data on the vehicle driving position. The learning unit 66 may also store road condition data such as curves and road surface unevenness based on data transmitted from the surrounding environment sensor 23 as input data on the vehicle driving position. The learning unit 66 also stores data on the deviation of the driving posture determined by the posture determination unit 65 as input data on the driving posture of the driver D. The learning unit 66 also stores data on the stress state of the driver D estimated by the stress estimation unit 63 as input data on the driver stress state.

The learning unit 66 generates a driving position judgment model by inputting these input data into a machine learning model. In this case, the learning unit 66 may perform supervised machine learning using the ideal stress state and ideal posture deviation set according to at least one of the data on the vehicle's running state or running position as teacher data, or may perform unsupervised machine learning. In the case of supervised machine learning, it is easier to obtain a recommended driving position that approaches the ideal stress state and ideal posture deviation. On the other hand, even in the case of unsupervised machine learning, it is easier to obtain a recommended driving position that reduces the stress state or posture deviation for each driver D.

The machine learning model may be, for example, a computational model using a neural network such as a support vector machine, a nearest neighbor method, or a deep learning or Bayesian network. The driving position determination model is generated for each driver identification data associated with the driver D and stored in the learning data storage unit 54.

FIG. 10 shows a flowchart of the recommended driving position presenting process.
First, the appropriate position determination unit 68 determines whether the presentation function of the recommended driving position is on (step S41). The on or off of the presentation function is set based on the operation input to the input unit 29 by the driver D. Alternatively, the presentation function may be set to the on state when the destination of the navigation system is set. If the presentation function is not on (S41/No), the appropriate position determination unit 68 ends this routine and repeats the determination of step S41. On the other hand, if the presentation function is on (S41/Yes), the appropriate position determination unit 68 acquires driver identification information in the same procedure as in step S13 above (step S43). As a result, a driving position determination model corresponding to the driver D is selected.

Next, the appropriate position determination unit 68 obtains planned driving route information based on data of the planned driving route from the current location to the destination set by the driver D (step S45). For example, the appropriate position determination unit 68 obtains driving route status data such as the number of curves on the planned driving route, the number of consecutive right and left curves, the legal speed limit, and the unevenness of the road surface from the data of the planned driving route from the current location to the destination set by the driver D. In addition, the appropriate position determination unit 68 sets expected driving state data such as the expected vehicle speed, expected longitudinal acceleration, expected lateral acceleration, and expected yaw rate while driving the planned driving route based on the obtained information of the planned driving route.

Next, the appropriate position determination unit 68 determines a recommended driving position according to the planned driving route based on the driving position determination model generated by the learning unit 67 (step S47). As shown in FIG. 11, the appropriate position determination unit 68 inputs the expected driving state data and the driving route situation data into the driving position determination model, and obtains the data of the recommended driving position to be output. For example, when the driving position determination model is generated by supervised machine learning, a recommended driving position that can minimize the difference from the ideal stress state or the ideal posture deviation on the entire planned driving route is output. Also, when the driving position determination model is generated by unsupervised machine learning, a recommended driving position that can minimize the stress state or posture deviation of the driver D on the entire planned driving route is output. The information on the recommended driving position includes data on the recommended position in the front-rear direction of the driver's seat 5, the recommended angle of the backrest 5a, the recommended height of the seat 5b, and the recommended position in the front-rear direction of the steering wheel 9.

Next, the appropriate position determination unit 68 presents the recommended driving position output from the driving position determination model to the driver D (step S49). The method of presenting the recommended driving position can be the same as that of the appropriate position determination unit 69 according to the first embodiment. In addition, the appropriate position determination unit 68 may output a control command to the control unit 61 so that the driving position becomes the recommended driving position.

As described above, the driving posture determination device 100 according to the second embodiment associates driving position setting information, vehicle driving state information, and driver D's stress state information while the vehicle is traveling, stores them in the learning data storage unit 55, and performs machine learning using these data sets as input data to generate a driving position determination model. In addition, the driving posture determination device 100 inputs expected driving state data and driving route situation data obtained based on data on the planned driving route from the current position to the destination into the driving position determination model, and presents the output recommended driving position to the driver D.

Therefore, the driving posture determination device 100 according to this embodiment can obtain the same effect as the driving posture determination device 1 according to the first embodiment, and the driver D can set the recommended driving position that can reduce the stress of the driver D according to the planned driving route. Furthermore, when the recommended driving position is automatically set by the drive of the power seat drive unit 43 and the steering position adjustment unit 45, a less stressful driving position can be realized even more easily.

The above describes in detail preferred embodiments of the present invention with reference to the attached drawings, but the present invention is not limited to such examples. It is clear that a person with ordinary knowledge in the technical field to which the present invention pertains can conceive of various modified or revised examples within the scope of the technical ideas described in the claims, and it is understood that these also naturally fall within the technical scope of the present invention.

For example, in the above embodiment, an example was described in which the driving position was adjusted by adjusting the front-rear position of the driver's seat 5, the angle of the backrest 5a, the height of the seat 5b, and the front-rear position of the steering wheel 9, but the present invention is not limited to such an example. The inclination of the seat 5b of the driver's seat 5, the degree of recession of the backrest 5a or the seat 5b, the position of the headrest 5c, the tilt angle of the steering wheel 9, etc. may be adjustable.

In the above embodiment, the driving position is adjustable using an actuator, but the present invention can also be applied to vehicles in which the posture of the driver's seat 5, the position of the steering wheel 9, etc. are manually adjusted. In this case, the posture of the driver's seat 5 and the position of the steering wheel 9 are detected by a sensor to learn the stress state, etc., and when learning or presenting a recommended driving position, the system is configured to instruct the driver D on the amount of adjustment, for example. Even when configured in this way, it is possible to learn the stress state and deviations in driving posture in multiple driving positions and determine the driving position suitable for the driver D.

Reference Signs List 1...driving posture determination device, 5...driver's seat, 5a...backrest, 5b...seat, 5c...headrest, 9 steering wheel, 21...driver monitoring device, 43...power seat drive unit, 45...steering position adjustment unit, 50...control device, 51...arithmetic processing unit, 53...storage unit, 55...learning data storage unit, 61...control unit, 63...stress estimation unit, 65...posture determination unit, 66, 67...learning unit, 68, 69...appropriate position determination unit

Claims (5)

a stress estimation unit for estimating a stress state of a driver of the vehicle;
a posture determining unit that determines a dynamic deviation of an actual posture of the driver from a proper posture of the driver based on a vibration of the upper body of the driver;
a learning unit that associates information on a driving position setting, information on a running state of the vehicle , information on a dynamic deviation of the driver's posture, and information on a stress state of the driver in a storage unit and stores the information in the memory unit;
an appropriate position determination unit that determines a driving position suitable for the driver that reduces a dynamic deviation of the posture that increases the stress state of the driver based on the stored learning data; and
A driving posture determination device comprising: A control unit for controlling a position adjustment device for adjusting the driving position is further provided.
2. The driving posture determination device according to claim 1, wherein the learning unit stores, in association with each other, setting information of the driving position, information on the vehicle's running state, information on dynamic deviations in the driver's posture , and information on the driver's stress state while changing the driving position. 3. The driving posture determination device according to claim 1, wherein the information on the dynamic deviation of the posture is information on deviation of at least one of a vibration mode, an amplitude, and a frequency of the vibration of the upper body of the driver . The driving posture determination device according to any one of claims 1 to 3, wherein the appropriate position determination unit presents a driving position suitable for the driver when starting or ending use of the vehicle. The driving posture determination device according to any one of claims 1 to 3, wherein the appropriate position determination unit, when a destination of the vehicle is set, presents a driving position suitable for the driver according to a planned driving route to the set destination.

Images