JP2022094829A - Driving support device, driving support method, and driving support program - Google Patents

Abstract

To provide a vehicle driving support device capable of enhancing adaptability of support processing to a driver of a vehicle.SOLUTION: A driving support device 1 for supporting driving of a vehicle by a driver comprises a traveling state discrimination part 100 for discriminating a driver's personal state during traveling of the vehicle into a plurality of levels; a traveling skill discrimination part 110 for discriminating driving skill of the driver during traveling into a plurality of levels; an aging state discrimination part 120 for discriminating aging change of the personal state into a plurality of levels; an aging skill discrimination part 130 for discriminating aging change of the driving skill into a plurality of levels; and a support processing control part 140 for controlling support processing to the driver in accordance with a correlation between each level of the personal state and the driving skill during driving, and each level of the personal state and the driving skill during aging change.SELECTED DRAWING: Figure 2

Description

The present disclosure relates to a driving assistance technique that assists a driver of a vehicle in driving.

In the technique disclosed in Patent Document 1, the content of driving support for the driver is determined according to the driving skill of the driver. On the other hand, in the technique disclosed in Patent Document 2, the control process of the vehicle is realized by updating the driver model according to the emotional state of the driver.

Japanese Unexamined Patent Publication No. 2017-220996 Japanese Unexamined Patent Publication No. 2018-18169706

However, in the case of the disclosed techniques of Patent Documents 1 and 2, depending on the correlation between the driver's driving skill and the emotional state, in the support process determined during driving according to either of the driving skill and the emotional state, There was a risk of incompatibility with the individual driver.

An object of the present disclosure is to provide a vehicle driving support device that enhances the suitability of support processing for a vehicle driver. Another object of the present disclosure is to provide a vehicle driving support method that enhances the suitability of the support process for the driver of the vehicle. Yet another subject of the present disclosure is to provide a vehicle driving assistance program that enhances the suitability of assistive processing for vehicle drivers.

Hereinafter, the technical means of the present disclosure for solving the problems will be described. The scope of claims and the reference numerals in parentheses described in this column indicate the correspondence with the specific means described in the embodiment described in detail later, and limit the technical scope of the present disclosure. It's not something to do.

The first aspect of the present disclosure is
It is a driving support device (1) that supports driving by the driver (6) of the vehicle (2).
A running state determination unit (100) that discriminates the individual state of the driver while the vehicle is running at a plurality of levels,
A driving skill discriminating unit (110) that discriminates the driving skill of the driver during driving into multiple levels, and
The secular variation unit (120), which discriminates the secular variation of the individual status at multiple levels,
The secular skill discrimination unit (130), which discriminates the secular variation of driving skills into multiple levels,
It is provided with a support processing control unit (140) that controls the support processing for the driver according to the correlation between each level of the individual state and the driving skill during driving and each level of the individual state and the secular variation of the driving skill.

The second aspect of the present disclosure is
It is a driving support method that supports driving by the driver (6) of the vehicle (2).
The running state determination step (S1) for discriminating the individual state of the driver while the vehicle is running at a plurality of levels, and
The driving skill discrimination process (S2) for discriminating the driving skill of the driver during driving into multiple levels, and
The secular variation step (S5), which discriminates the secular variation of the individual status to multiple levels, and
The secular skill discrimination process (S6), which discriminates the secular variation of driving skills into multiple levels,
The support process control step (S8) for controlling the support process for the driver according to the correlation between each level of the individual state and the driving skill during driving and each level of the individual state and the secular variation of the driving skill is included.

The third aspect of the present disclosure is
It is a driving support program including an instruction to be executed by the processor (12) in order to support the driving by the driver (6) of the vehicle (2).
The order is
The running state determination step (S1) for discriminating the individual state of the driver while the vehicle is running to a plurality of levels, and
The driving skill discrimination process (S2), which discriminates the driving skill of the driver during driving to multiple levels, and
The secular variation step (S5), which discriminates the secular variation of the individual status to multiple levels, and
The secular skill discrimination process (S6), which discriminates the secular variation of driving skills to multiple levels,
The support process control step (S8) for controlling the support process for the driver according to the correlation between each level of the individual state and the driving skill during driving and each level of the individual state and the secular variation of the driving skill is included.

According to these first to third aspects, the individual state of the driver while the vehicle is running and the driving skill of the driver while the vehicle is running are discriminated into a plurality of levels, respectively. Further, according to the first to third aspects, the secular variation of the driver's personal condition and driving skill is also determined for each of a plurality of levels. Therefore, in the first to third aspects, the support process for the driver is controlled according to the correlation between each level of the individual state and the driving skill during driving and each level of the individual state and the secular variation of the driving skill. According to this, the level correlation between the individual state and the driving skill can be subdivided from the two viewpoints of running and secular variation, and can be finely reflected in the support processing. Therefore, it is possible to improve the suitability of the assist processing for the driver.

It is a block diagram which shows the whole structure of the driving support device by one Embodiment. It is a block diagram which shows the detailed structure of the driving support apparatus by one Embodiment. It is a flowchart which shows the driving support flow of the driving support method by one Embodiment. It is a flowchart which shows the running state determination routine of FIG. It is a flowchart which shows the example of the selection flow of the state index in the running state determination routine of FIG. It is a flowchart which shows the state correlation discrimination subroutine of FIG. It is a flowchart which shows the running skill discrimination routine of FIG. It is a flowchart which shows the example of the selection flow of the skill index in the running skill discrimination routine of FIG. It is a flowchart which shows the skill correlation discrimination subroutine of FIG. It is a characteristic table which shows the correlation matrix in the driving support flow of FIG. It is a flowchart which shows the aging state determination routine of FIG. It is a flowchart which shows the aged skill discrimination routine of FIG. It is a flowchart which shows the support process control routine of FIG.

Hereinafter, one embodiment will be described with reference to the drawings.

The driving support device 1 of the embodiment shown in FIG. 1 supports the driving of the vehicle 2 by the driver 6. The vehicle 2 may be capable of autonomous driving constantly in the automatic driving mode or temporarily by switching between the manual driving mode and the automatic driving mode. Here, the automated driving mode may be realized by autonomous driving control in which the operating system performs all driving tasks, such as conditional driving automation, advanced driving automation, or complete driving automation. The automated driving control mode may be implemented in advanced driving assistance control in which the driver 6 performs some or all driving tasks, such as driving assistance or partial driving automation. The automatic driving mode may be realized by combining or switching between the autonomous driving control and the advanced driving support control.

The vehicle 2 is equipped with a sensor system 3, an information presentation system 4, and a map unit 5. The sensor system 3 acquires various information that can be used for operation control by the operation support device 1. As shown in FIG. 2, the sensor system 3 includes an outside world sensor 30 and an inside world sensor 32.

The outside world sensor 30 generates information on the outside world, which is the surrounding environment of the vehicle 2. The outside world sensor 30 may generate outside world information by detecting an object existing in the outside world of the vehicle 2. The object detection type external sensor 30 is, for example, at least one of a camera, a LiDAR (Light Detection and Ranging / Laser Imaging Detection and Ranging), a radar, a sonar, and the like. The outside world sensor 30 may generate outside world information by receiving a signal from a GNSS (Global Navigation Satellite System) artificial satellite existing in the outside world of the vehicle 2 or a roadside unit of ITS (Intelligent Transport Systems). The signal reception type external sensor 30 is at least one of, for example, a GNSS receiver, a telematics receiver, and the like.

The inner world sensor 32 generates information on the inner world, which is the internal environment of the vehicle 2. The internal world sensor 32 may generate internal world information by detecting a specific kinetic physical quantity in the internal world of the vehicle 2. The physical quantity detection type internal sensor 32 is at least one of, for example, a traveling speed sensor, an acceleration sensor, a gyro sensor, an in-vehicle temperature sensor, and the like. The inner world sensor 32 may generate inner world information by detecting a specific state regarding an occupant in the inner world of the vehicle 2. The occupant detection type internal sensor 32 is at least one of, for example, a driver status monitor, a biological sensor, a seating sensor, an actuator sensor, an in-vehicle device sensor, and the like.

Here, the driver status monitor is a state of the driver 6 who operates the vehicle 2 in manual driving among the occupants of the vehicle 2, for example, at least one of an eyeball state, an eyelid state, a head state, a facial expression, a posture, and the like. Is detected. The biosensor detects at least one of the vital signs of the driver 6, for example, pulse (that is, heartbeat), blood pressure, electrocardiogram, respiration, body temperature, fingerprint, and the like. The seating sensor detects the seated state of the driver 6 in the driver's seat of the vehicle 2. The actuator sensor has, as an instruction state from the driver 6 regarding the traveling actuator of the vehicle 2, for example, an accelerator pedal operation state, a brake pedal operation state, a steering wheel steering state, a start switch on / off state, a shift lever shift state, and the like. Of these, at least one type is detected. The in-vehicle device sensor is an operation state of the driver 6 or another occupant related to the in-vehicle device including the information presentation system 4, for example, a switch on / off state, a touch panel input state, a non-contact recognizable gesture state, and the like. Detect one type.

The information presentation system 4 presents various information to the occupants including the driver 6. The information presentation system 4 includes a visual presentation unit 40, an auditory presentation unit 42, and a skin sensation presentation unit 44.

The visual presentation unit 40 transmits the presentation target information by stimulating the vision of the driver 6. The visual presentation unit 40 is, for example, at least one of a HUD (Head-up Display), an MFD (Multi Function Display), a combination meter, a navigation unit, a light emitting unit, and the like. The auditory presentation unit 42 transmits information to be presented by stimulating the auditory sense of the driver 6. The auditory presentation unit 42 is at least one of, for example, a speaker, a buzzer, a vibration unit, and the like. The skin sensation presentation unit 44 transmits the presentation target information by stimulating the skin sensation of the driver 6. The skin sensation stimulated by the skin sensation presentation unit 44 includes at least one of, for example, a tactile sensation, a temperature sensation, and a wind sensation. The skin sensation presentation unit 44 is, for example, at least one of a vibration unit of the steering handle, a vibration unit of the driver's seat, a reaction force unit of the steering handle, a reaction force unit of the accelerator pedal, a reaction force unit of the brake pedal, an air conditioning unit, and the like. It is a kind.

The map unit 5 non-temporarily stores the map information that can be used for driving by the driving support device 1. The map unit 5 includes at least one type of non-transitory tangible storage medium, such as a semiconductor memory, a magnetic medium, and an optical medium. The map unit 5 may be a database of locators that estimate the amount of self-state including the self-position of the vehicle 2. The map unit 5 may be a database of navigation units for navigating the travel route of the vehicle 2. The map unit 5 may be configured by combining a plurality of types of these databases and the like.

The map unit 5 acquires and stores the latest map information, for example, by communicating with an external center. The map information is converted into two-dimensional or three-dimensional data as information representing the traveling environment of the vehicle 2. The map information may include road information representing at least one type of, for example, the position, shape, and road surface condition of the road itself. The map information may include marking information indicating at least one type of, for example, the position and shape of a sign and a lane marking attached to a road. The map information may include structure information representing at least one type of, for example, the position and shape of a building facing a road and a traffic light.

The driving support device 1 shown in FIG. 1 is connected to the sensor system 3, the information presentation system 4, and the map unit 5 via at least one of a LAN (Local Area Network), a wire harness, an internal bus, and the like. Ru. The driving support device 1 includes at least one dedicated computer. The dedicated computer constituting the driving support device 1 may be an integrated ECU (Electronic Control Unit) that integrates the driving control of the vehicle 2. The dedicated computer constituting the driving support device 1 may be a judgment ECU for determining a driving task in the driving control of the vehicle 2. The dedicated computer constituting the driving support device 1 may be a monitoring ECU that monitors the driving control of the vehicle 2. The dedicated computer constituting the driving support device 1 may be an actuator ECU that individually controls the traveling actuator of the vehicle 2. The dedicated computer constituting the driving support device 1 may be a locator ECU that estimates the self-state amount of the vehicle 2. The dedicated computer constituting the driving support device 1 may be a navigation ECU for navigating the traveling route of the vehicle 2. The dedicated computer constituting the driving support device 1 may be an HCU (HMI (Human Machine Interface) Control Unit) that controls the information presentation of the information presentation system 4. The dedicated computer constituting the driving support device 1 may be at least one external computer that constructs, for example, an external center or a mobile terminal capable of communicating with the vehicle 2.

The dedicated computer constituting the driving support device 1 has at least one memory 10 and one processor 12. The memory 10 is a non-transitional substantive storage medium of at least one kind among, for example, a semiconductor memory, a magnetic medium, an optical medium, and the like, which temporarily stores programs and data that can be read by a computer. The processor 12 includes, for example, at least one of a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a RISC (Reduced Instruction Set Computer) -CPU, and the like as a core.

The processor 12 executes a plurality of instructions included in the driving support program stored in the memory 10. As a result, the driving support device 1 constructs a plurality of functional blocks for supporting the driving of the vehicle 2. At this time, in the driving support device 1, a plurality of functional units (functional blocks) are constructed by causing the processor 12 to execute a plurality of instructions by the driving support program stored in the memory 10 in order to support the driving of the vehicle 2. To. As shown in FIG. 2, the plurality of functional blocks constructed by the driving support device 1 include a running state determination unit 100, a running skill determination unit 110, an aged state determination unit 120, an aged skill determination unit 130, and support processing. The control unit 140 is included.

Hereinafter, a driving support method for supporting the driving of the vehicle 2 jointly by the functional units 100, 110, 120, 130, and 140 will be described with reference to the drawings such as the driving support flow shown in FIGS. 3 to 11. In addition, each "S" in this flow means a plurality of steps executed by a plurality of instructions included in a driving support program.

In S1 of the driving support flow shown in FIG. 3, the traveling state determination unit 100 executes a traveling state determination routine in order to determine the individual state of the driver 6 while the vehicle 2 is traveling at a plurality of levels. In S10 of the running state determination routine shown in FIG. 4, the running state determination unit 100 selects a state index Ip for comparing the past and the present as a correlation of individual states during running.

Here, the state index Ip is an index for presumably discriminating, for example, a drowsiness state, an inattentive state, a fatigue state, a drowsiness state, and the like as the individual state of the driver 6 during traveling. The state index Ip includes, for example, eyeball movement including soccerd and line-of-sight direction, eyelid opening / closing movement including blinking, head movement including face orientation, facial expression, body posture, pulse (that is, heartbeat), and the like. Among blood pressure, electrocardiogram, respiration, body temperature and the like, at least a plurality of types based on the information of the sensor system 3 can be mentioned.

The selection of the state index Ip is executed according to at least one of the traveling condition of the vehicle 2 and the characteristic condition of the driver 6. The traveling conditions of the vehicle 2 include, for example, the type and shape of the traveling path, the traffic congestion and structural complexity of the surrounding environment, the behavior of the own vehicle 2 including the traveling speed, the relative relationship with other vehicles or traffic users, and the surroundings based on the behavior. It is set for at least one type based on the information of the sensor system 3 among the risk, the time and time zone of running, the weather, and the like. The characteristic conditions of the driver 6 are set for at least one of, for example, a driving score, an elapsed time from the start of driving, a determination accuracy of an individual state, and the like, based on past driving results.

FIG. 5 shows an example of a selection flow of the state index Ip. In S100 of the selection flow example, the traveling state determination unit 100 acquires necessary information from the sensor system 3. In the following S101, the traveling state determination unit 100 determines the type of the traveling path as the traveling condition of the vehicle 2. As a result, when the traveling environment is an automobile-only road, the traveling state determination unit 100 in S102 selects a state index Ip of a type that requires level determination of an individual condition while traveling on the automobile-only road. On the other hand, when the driving environment is a general road in a city center with a high degree of congestion, the traveling state determination unit 100 in S103 needs to determine the level of an individual state while traveling at the high degree of congestion. , Select. On the other hand, when the driving environment is a general road in the suburbs where the degree of congestion is low, the traveling state determination unit 100 in S104 needs to determine the level of the individual state while driving at the low degree of congestion. , Select.

In S11 of the running state determination routine shown in FIG. 4, the running state determination unit 100 sets baseline data Dpb with respect to the past state index Ip to be compared with the current state index Ip as a correlation of the individual state during running. .. Here, the baseline data Dpb is set to give the required distribution for the state index Ip selected by S10 in the past sampling data covering all the options of the state index Ip in S10.

In S12 of the running state determination routine shown in FIG. 4, the running state determination unit 100 sets a state threshold value Tp for discriminating the level of each past and present state index Ip to be compared as a correlation of individual states during running. Set. Here, the state threshold value Tp is set according to the past driving behavior such as during safe driving and during risk driving. The selection of the state threshold Tp is executed based on the distribution of the baseline data Dpb regarding the state index Ip in the past running set by S11. In this case, for example, an intermediate value, a valley value, a machine learning value, or the like between peaks during safe driving and risk driving in the distribution of baseline data Dpb is selected as the state threshold Tp with respect to the state index Ip.

In S13 of the running state determination routine shown in FIG. 4, the running state determination unit 100 discriminates the correlation of the individual state during the current running to a plurality of levels with respect to the distribution of the individual state during the past running. , Execute the state correlation discrimination subroutine. In the state correlation determination subroutine S130 shown in FIG. 6, the traveling state determination unit 100 uses the current traveling data Dpp of the state index Ip selected by S10 and the baseline data during the past traveling set by S11. The Dpb and the state threshold value Tp selected by S12 are acquired. In the following S131, the running state determination unit 100 uses the state threshold value Tp as a reference by correlation analysis in which the data Dpp of the state index Ip currently running is compared with the distribution of the baseline data Dpb in the past running. Determine the individual status of the vehicle currently running at multiple levels.

Here, in the correlation analysis, the Mahalanobis distance from the center of gravity in the distribution of the baseline data Dpb to the data Dpp of the state index Ip is calculated, and the level of the individual state is determined according to the magnitude relationship between the calculation result and the state threshold value Tp. May be good. In the correlation analysis, the correlation between the distribution of the baseline data Dpb and the data Dpp of the state index Ip may be calculated by, for example, a support vector machine or a k-nearest neighbor algorithm, and the level of the individual state may be determined according to the calculation result. In the correlation analysis, an accuracy matrix which is a fluctuation of the correlation between the distribution of the baseline data Dpb and the data Dpp of the state index Ip may be calculated by, for example, a graphical lasso, and the level of the individual state may be determined according to the calculation result. .. There are three types of individual condition levels determined by correlation analysis by any of the methods: normal level, worsening level of condition worse than normal, and abnormal level of worsening condition from worsening level.

For example, when the individual state level is determined to be a normal level because the Maharanovirus distance is equal to or less than the first state threshold value Tp, the state correlation determination subroutine shifts to S132. In S132, the traveling state determination unit 100 stores in the memory 10 the determination result of the normal level together with the time stamp indicating the current traveling time. On the other hand, when the individual state level is determined to be a deterioration level due to, for example, the Maharanovirus distance exceeding the first state threshold value Tp and becoming equal to or less than the second state threshold value, the state correlation determination subroutine shifts to S133. In S133, the traveling state determination unit 100 stores the determination result of the deterioration level in the memory 10 together with the time stamp. On the other hand, when the individual state level is determined to be an abnormal level due to, for example, the Maharanovirus distance exceeding the second state threshold value Tp, the state correlation determination subroutine shifts to S134. In S134, the traveling state determination unit 100 stores the determination result of the abnormality level in the memory 10 together with the time stamp. When at least a part of the memory 10 is composed of the external memory of the external computer, the determination result of the personal state level is output to the external memory by communication and stored.

In S2 of the driving support flow shown in FIG. 3, the traveling skill determination unit 110 executes a traveling skill determination routine in order to determine the driving skill of the driver 6 while the vehicle 2 is traveling at a plurality of levels. In S20 of the running skill discriminating routine shown in FIG. 7, the running skill discriminating unit 110 selects a skill index Id for comparing the past and the present as a correlation of driving skills during running.

Here, the skill index Id is an index for presumably discriminating, for example, a driving score or the like as the driving skill of the driver 6 during driving. The skill index Id includes, for example, acceleration, deceleration, lateral G, steering angle, operating amount or operating speed of the pedal or steering wheel related thereto, lateral position in the lane (during correction steering or lane change), and the like. Among them, at least a plurality of types based on the information of the sensor system 3 can be mentioned. The selection of the skill index Id is executed according to at least one of the traveling condition of the vehicle 2 and the characteristic condition of the driver 6. The traveling conditions of the vehicle 2 and the characteristic conditions of the driver 6 are set according to the case of the state index Ip.

FIG. 8 shows an example of the selection flow of the skill index Id. In S200 of the selection flow example, the running skill determination unit 110 acquires necessary information from the sensor system 3. In the following S201, the traveling skill determination unit 110 determines the type of the travel path as the travel condition of the vehicle 2. As a result, when the driving environment is a motorway, the driving skill determination unit 110 in S202 selects a skill index Id of a type that requires level discrimination of the driving skill while driving on the motorway. On the other hand, when the driving environment is a general road in a city center with a high degree of congestion, the driving skill determination unit 110 in S203 needs to determine the level of the driving skill while driving at the high degree of congestion. , Select. On the other hand, when the driving environment is a general road in the suburbs where the degree of congestion is low, the driving skill determination unit 110 in S204 needs to determine the level of the driving skill while driving at the low degree of congestion. , Select.

In the running skill discriminating routine S21 shown in FIG. 7, the running skill discriminating unit 110 sets baseline data Ddb with respect to the past skill index Id to be compared with the current skill index Id as the correlation of the driving skill during running. .. Here, the baseline data Ddb is set to give the required distribution for the skill index Id selected by S20 in the past sampling data covering all the options of the skill index Id in S20.

In S22 of the running skill discriminating routine shown in FIG. 7, the running skill discriminating unit 110 sets a skill threshold value Td for discriminating the level of each past and present skill index Id to be compared as a correlation of driving skills during running. Set. Here, the skill threshold value Td is set according to past driving results such as during safe driving and during risk driving. The setting of the skill threshold value Td is executed based on the distribution of the baseline data Ddb regarding the skill index Id in the past running set by S21. In this case, for example, an intermediate value, a valley value, a machine learning value, or the like between peaks during safe driving and risk driving in the distribution of baseline data Ddb is set as the skill threshold Td with respect to the skill index Id.

In S23 of the driving skill discrimination routine shown in FIG. 7, the driving skill discriminating unit 110 discriminates the correlation of the driving skill during the current driving to a plurality of levels with respect to the distribution of the driving skill during the past driving. , Execute the skill correlation discrimination subroutine. In the skill correlation discrimination subroutine S230 shown in FIG. 9, the running skill discriminating unit 110 uses the current running data Ddp of the skill index Id selected by S20 and the baseline data during past running set by S21. The Ddb and the skill threshold Td selected by S22 are acquired. In the following S231, the running skill determination unit 110 compares the distribution of the baseline data Ddb in the past running with the data Ddp of the skill index Id currently running, and uses the skill threshold Td as a reference. Discriminate the driving skill currently being driven to multiple levels. Here, in the correlation analysis, it is preferable that the level of driving skill is determined by any of the methods according to the case of the baseline data Dpb. There are three types of driving skill levels determined by correlation analysis by either method: normal level, rough level of driving rougher than normal, and risk level of rough driving further from rough level.

For example, when the driving skill level is determined to be a normal level because the Maharanovirus distance is equal to or less than the first skill threshold value Td, the skill correlation determination subroutine shifts to S232. In S232, the traveling skill determination unit 110 stores in the memory 10 the determination result from the normal level together with the time stamp indicating the current travel time. On the other hand, when the driving skill level is determined to be a rough level, for example, because the Maharanovirus distance exceeds the first skill threshold Td and becomes equal to or less than the second skill threshold Td, the skill correlation determination subroutine shifts to S233. In S233, the running skill determination unit 110 stores the determination result of the rough level in the memory 10 together with the time stamp. On the other hand, when the driving skill level is determined to be the risk level, for example, because the Maharanovirus distance exceeds the second skill threshold Td, the skill correlation determination subroutine shifts to S234. In S234, the running skill determination unit 110 stores the determination result of the risk level in the memory 10 together with the time stamp. When at least a part of the memory 10 is composed of an external memory of an external computer, the determination result of the driving skill level is output to the external memory by communication and stored.

In S3 of the driving support flow shown in FIG. 3, the driving state determination unit 100 and the driving skill determination unit 110 have the driving level of the individual state determined by S13 and the driving level of the driving skill determined by S23. The correlation is jointly extracted. In this correlation extraction, each currently running level of the individual state and the driving skill is set as a correlation pair, and the matrix value corresponding to the correlation pair in the correlation matrix shown in FIG. 10 is set to a predetermined extraction flag value Cn.

In S4 of the driving support flow shown in FIG. 3, the aged state determination unit 120 and the aged skill determination unit 130 jointly determine whether or not the elapsed time from the reference time is equal to or longer than the set time. Here, the reference time is set to, for example, the first use time after the completion or maintenance of the vehicle 2, the previous affirmative judgment time by S4, or the like. If an affirmative judgment is made because the elapsed time from the reference time is equal to or longer than the set time, the driving support flow sequentially shifts to S5 to S8. On the other hand, if a negative determination is made because the elapsed time from the reference time is less than the set time, the driving support flow skips S5 to S7 and shifts to S8.

In S5 of the driving support flow shown in FIG. 3, the aging state determination unit 120 executes an aging state determination routine in order to discriminate the secular variation of the individual state at a plurality of levels. In S50 of the aged state determination routine shown in FIG. 11, the aged state determination unit 120 determines the level of the individual state determined during the past running at the reference time and the current running after the set time or more has passed from the reference time. To get the level of personal condition. In the following S51, the aged state determination unit 120 further determines the degree of deviation in the correlation between the individual state level during the past run and the individual state level during the current run as the level of secular variation. The secular variation level, which is the degree of deviation of the individual condition level, is the improvement tendency level in which the individual condition level is improving, the steady-state tendency level in which the individual condition level is steady without change, and the individual condition level is in a deteriorating tendency. There are three types of deterioration trend levels.

In S6 of the driving support flow shown in FIG. 3, the secular skill discriminating unit 130 executes a secular skill discriminating routine in order to discriminate the secular variation of the driving skill at a plurality of levels. In S60 of the aged skill discrimination routine shown in FIG. 12, the aged skill discriminating unit 130 is discriminated between the level of the driving skill determined during the past driving at the reference time and the current driving after the set time or more has passed from the reference time. Acquire the level of driving skill. In the following S61, the aged skill determination unit 130 further determines the degree of deviation in the correlation between the driving skill level during the past driving and the driving skill level during the current driving as the level of secular variation. The secular variation level, which is the degree of deviation of the driving skill level, is the improvement tendency level where the driving skill level tends to improve, the steady tendency level where the driving skill level is steady without substantially changing, and the driving skill level tends to deteriorate. There are three types of deterioration trend levels.

In S7 of the driving support flow shown in FIG. 3, the secular state determination unit 120 and the secular skill determination unit 130 have the secular variation level of the individual state determined by S51 and the secular variation level of the driving skill determined by S61. Collaborative extraction of correlations. In this correlation extraction, each secular change level of the individual state and the driving skill is set as a correlation pair, and the matrix value corresponding to the correlation pair in the correlation matrix shown in FIG. 10 is set to a predetermined extraction flag value Ca.

Here, in S7 of the present embodiment, as shown in FIG. 10, even if the correlation between the secular variation level of the individual state determined by S51 and the running level of the driving skill determined by S23 is further extracted. It may or may not be extracted. Further, in S7 of the present embodiment, as shown in FIG. 10, the correlation between the running level of the individual state determined by S13 and the secular variation level of the driving skill determined by S61 may be further extracted. And it does not have to be extracted.

In S8 of the driving support flow shown in FIG. 3, the support processing control unit 140 performs support processing according to the correlation between each level of the individual state and the driving skill during driving and each level of the individual state and the secular variation of the driving skill. Execute a support processing control routine to control. The support processing control routine S80 shown in FIG. 13 skips S5 to S7 even when the elapsed time from the reference time is longer than the set time (via S5 to S7) but the elapsed time is less than the set time (S5 to S7 are skipped). In the case of), but it will be migrated. In S80, the support processing control unit 140 determines appropriate short-term support processing for the driver 6 in accordance with the extraction flag value Cn representing the correlation of the traveling level extracted by S3.

Here, in the short-term support process, the support application matching the matrix value in which the extraction flag value Cn is set is selectively started from the support applications registered for each correlation pair in the correlation matrix shown in FIG. To. For example, when the correlated pair currently running has a normal level of personal condition and a normal level of driving skill, a proposal for improving convenience and comfort by launching a suitable support application is proposed in the information presentation system 4 Is presented to the driver 6. On the other hand, for example, when the correlation pair currently being driven becomes a normal level personal state and a rough level driving skill, a proposal for assisting driving by starting a matching support application is proposed from the information presentation system 4 to the driver. Presented to 6. In this case, a support application for directly assisting the driving of the driver 6 by using the automatic operation mode may be started in place of or in addition to the support application of the assistance proposal. On the other hand, for example, when the correlation pair currently running becomes a deterioration level personal condition and a normal level driving skill, a proposal including a break promotion to restore concentration by launching a suitable support application is proposed. Is presented from the information presentation system 4 to the driver 6.

The support processing control routine S81 shown in FIG. 13 does not shift when the elapsed time from the reference time is less than the set time (when skipping S5 to S7), and when the elapsed time is equal to or longer than the set time (S5). -Move to only via S7). In S81, the support processing control unit 140 determines the appropriate long-term support processing for the driver 6 according to the extraction flag value Ca representing the correlation of the secular variation level extracted by S7.

Here, in the long-term support process, the support application matching the matrix value set with the extraction flag value Ca is selectively started from the support applications registered for each correlation pair in the correlation matrix shown in FIG. To. For example, when the correlation pair of secular variation becomes an individual condition at the deterioration tendency level and a driving skill at the steady tendency level, by launching a suitable support application, an early warning or a break promotion to be aware of the deterioration tendency is given. The including proposal is presented from the information presentation system 4 to the driver 6. On the other hand, for example, when the correlation pair of secular variation becomes a steady level individual state and a deterioration tendency level driving skill, a proposal for noticing the skill deterioration tendency by starting a suitable support application is an information presentation system. Presented from 4 to driver 6. In this case, a support application for early intervention in the operation of the driver 6 using the automatic driving mode may be started in place of or in addition to the support application of the noticed proposal. On the other hand, for example, when the correlation pair of secular variation becomes an individual condition at the deterioration tendency level and a driving skill at the deterioration tendency level, a proposal for inducing the return of the driver's license by launching a suitable support application is information. It is presented from the presentation system 4 to the driver 6.

The support application that realizes the above short-term support processing and long-term support processing may be installed before the first use of the vehicle 2, for example, at the time of factory shipment or maintenance of the vehicle 2, or the driver 6 registration operation after the first use. May be installed by. In particular, it is preferable that the installation by the registration operation of the support application can be executed for each correlation pair in the correlation matrix shown in FIG. However, when an existing support application is registered in association with a correlation pair for registering a new support application, the support application is added to the driver 6 based on the overlapping status of the usage rights of the units used in the information presentation system 4. It is recommended that the installation be executed after confirming the necessity of replacement.

From the explanation so far, in the present embodiment, S1 corresponds to the running state determination process, S2 corresponds to the running skill determination process, S5 corresponds to the aged state determination process, and S6 corresponds to the aged skill determination process. However, S8 corresponds to the support processing control process.

(Action effect)
The effects of the present embodiment described above will be described below.

According to the present embodiment, the individual state of the driver 6 while the vehicle 2 is running and the driving skill of the driver 6 during the running are discriminated into a plurality of levels, respectively. Further, according to the present embodiment, the secular variation of the individual state of the driver 6 and the driving skill is also determined for each of a plurality of levels. Therefore, in the present embodiment, the support process for the driver 6 is controlled according to the correlation between each level of the individual state and the driving skill during driving and each level of the individual state and the secular variation of the driving skill. According to this, the level correlation between the individual state and the driving skill can be subdivided from the two viewpoints of running and secular variation, and can be finely reflected in the support processing. Therefore, it is possible to improve the suitability of the support process for the driver 6.

According to the present embodiment, the correlation of the individual state during the current driving is discriminated at a plurality of levels with respect to the distribution of the individual state during the past driving. According to this, the individual state currently running can be appropriately determined based on the steady individual state represented by the past distribution. Therefore, the determination of the individual state with respect to such a past distribution is advantageous in enhancing the suitability of the support process.

According to the present embodiment, as the correlation of the individual state, the state index Ip for comparing the past and the present is selected according to at least one of the traveling condition of the vehicle 2 and the characteristic condition of the driver 6. According to this, with respect to the state index Ip that reflects the conditions that influence the individual state, the correlation between the individual state during past driving and the current driving is determined, so that the accuracy of the determination is improved. obtain. Therefore, the determination of the individual state using such a state index Ip is advantageous in enhancing the suitability of the support processing.

According to the present embodiment, the correlation of the driving skill in the current driving is determined to a plurality of levels with respect to the distribution of the driving skill in the past driving. According to this, the driving skill currently being driven can be appropriately determined based on the steady driving skill represented by the past distribution. Therefore, the determination of the driving skill with respect to such a past distribution is advantageous in enhancing the suitability of the support processing.

According to the present embodiment, as the correlation of driving skills, the skill index Id for comparing the past and the present is selected according to at least one of the driving condition of the vehicle 2 and the characteristic condition of the driver 6. According to this, regarding the skill index Id that reflects the conditions that influence the driving skill, the correlation of the driving skill between the past driving and the current driving is determined, so that the accuracy of the determination is improved. obtain. Therefore, the determination of the driving skill using such a skill index Id is advantageous in enhancing the suitability of the support process.

According to the present embodiment, the correlation between the level of the individual state determined during the current driving and the level of the individual state determined during the past driving is determined to be a plurality of levels as the secular variation of the individual state. According to this, the secular variation of the individual state can be appropriately determined from the degree of deviation of the correlation appearing in the individual state currently running based on the individual state of the past running. Therefore, the secular variation discrimination of the individual state based on the past discrimination results is advantageous in enhancing the suitability of the support processing.

According to the present embodiment, the correlation between the level of the driving skill determined during the current driving and the level of the driving skill determined during the past driving is discriminated into a plurality of levels as the secular variation of the driving skill. According to this, the secular variation of the driving skill can be appropriately determined from the degree of deviation of the correlation appearing in the driving skill currently being driven based on the driving skill during the past driving. Therefore, the secular variation discrimination of the driving skill based on the past discrimination result is advantageous in enhancing the suitability of the support processing.

(Other embodiments)
Although one embodiment has been described above, the present disclosure is not construed as being limited to the embodiment, and can be applied to various embodiments without departing from the gist of the present disclosure.

In the modified example, the dedicated computer constituting the driving support device 1 may include at least one of a digital circuit and an analog circuit as a processor. Here, the digital circuit is, for example, among ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array), SOC (System on a Chip), PGA (Programmable Gate Array), CPLD (Complex Programmable Logic Device) and the like. , At least one type. Further, such a digital circuit may have a memory for storing a program.

1: Driving support device, 2: Vehicle, 6: Driver, 100: Driving state determination unit, 110: Driving skill determination unit, 120: Aged state determination unit, 130: Aged skill determination unit, 140: Support processing control unit

Claims (15)

It is a driving support device (1) that supports driving by the driver (6) of the vehicle (2).
A traveling state determination unit (100) that determines the individual state of the driver while the vehicle is traveling at a plurality of levels,
A driving skill discriminating unit (110) that discriminates the driving skill of the driver during driving into a plurality of levels,
The secular variation unit (120), which discriminates the secular variation of the individual status into a plurality of levels,
The secular skill discriminating unit (130), which discriminates the secular variation of the driving skill into a plurality of levels,
A support processing control unit (140) that controls the support processing for the driver according to the correlation between each level of the individual state and the driving skill during the driving and each level of the individual state and the secular variation of the driving skill. ) And, a driving support device. The driving support device according to claim 1, wherein the traveling state determination unit determines a plurality of levels of the correlation of the individual state during the current traveling with respect to the distribution of the individual state during the traveling in the past. .. 2. The driving state determination unit selects a state index for comparing the past and the present as a correlation of the individual state according to at least one of the driving condition of the vehicle and the characteristic condition of the driver. The driving support device described in. Any one of claims 1 to 3 in which the running skill discriminating unit discriminates the correlation of the driving skill in the current running to a plurality of levels with respect to the distribution of the driving skill in the past running. The driving support device described in the section. 4. The driving skill discriminating unit selects a skill index for comparing the past and the present as a correlation of the driving skill according to at least one of the driving condition of the vehicle and the characteristic condition of the driver. The driving support device described in. The aging state determination unit uses the correlation between the level of the individual state determined during the current running and the level of the personal state determined during the past running as the secular variation of the personal state. The driving support device according to any one of claims 1 to 5, which discriminates into a plurality of levels. The aged skill discriminating unit has a plurality of correlations between the level of the driving skill determined during the current driving and the level of the driving skill determined during the past driving as the secular variation of the driving skill. The driving support device according to any one of claims 1 to 6, which is determined by level. It is a driving support method that supports driving by the driver (6) of the vehicle (2).
The running state determination step (S1) for discriminating the individual state of the driver while the vehicle is running at a plurality of levels,
The driving skill determination step (S2) for discriminating the driving skill of the driver during driving into a plurality of levels,
The secular state determination step (S5) for discriminating the secular variation of the individual state into a plurality of levels,
The secular skill discrimination process (S6) for discriminating the secular variation of the driving skill into a plurality of levels,
A support process control step (S8) for controlling the support process for the driver according to the correlation between each level of the individual state and the driving skill during the driving and each level of the individual state and the secular variation of the driving skill. ) And, including driving support methods. The driving support method according to claim 8, wherein the traveling state determination step determines the correlation of the individual state in the current traveling to a plurality of levels with respect to the distribution of the individual state in the traveling in the past. .. 9. The traveling state determination step selects a state index for comparing the past and the present as a correlation of the individual state according to at least one of the driving condition of the vehicle and the characteristic condition of the driver. The driving support method described in. The driving skill determination step is any one of claims 8 to 10 for determining the correlation of the driving skill in the current driving to a plurality of levels with respect to the distribution of the driving skill in the past driving. The driving support method described in the section. 11. The driving skill determination process selects a skill index for comparing the past and the present as a correlation of the driving skill according to at least one of the driving condition of the vehicle and the characteristic condition of the driver. The driving support method described in. In the aging state determination step, the correlation between the level of the personal state determined during the current running and the level of the personal state determined during the past running is defined as the secular variation of the personal state. The driving support method according to any one of claims 8 to 12, which distinguishes into a plurality of levels. In the aged skill determination process, a plurality of correlations between the level of the driving skill determined during the current driving and the level of the driving skill determined during the past driving are used as the secular variation of the driving skill. The driving support method according to any one of claims 8 to 13, which is determined by level. It is a driving support program including an instruction to be executed by the processor (12) in order to support the driving by the driver (6) of the vehicle (2).
The command is
The running state determination step (S1) for discriminating the individual state of the driver while the vehicle is running at a plurality of levels,
The driving skill determination step (S2) for discriminating the driving skill of the driver during driving to a plurality of levels,
The secular state determination step (S5) for discriminating the secular variation of the individual state to a plurality of levels,
The secular skill discrimination process (S6) for discriminating the secular variation of the driving skill to a plurality of levels,
A support process control step (S8) for controlling the support process for the driver according to the correlation between each level of the individual state and the driving skill during the driving and each level of the individual state and the secular variation of the driving skill. ) And, including driving support programs.

Images