JP7468329B2 - Driving assistance device, driving assistance method, and driving assistance program - Google Patents

Description

This disclosure relates to driving assistance technology that assists a vehicle driver in driving.

In the technology disclosed in Patent Document 1, the content of driving assistance for the driver is determined according to the driver's driving skill. On the other hand, in the technology disclosed in Patent Document 2, the driver model is updated according to the driver's emotional state, thereby realizing vehicle control processing.

JP 2017-220796 A JP 2018-18169706 A

However, in the case of the technologies disclosed in Patent Documents 1 and 2, depending on the correlation between the driver's driving skills and emotional state, there was a risk that the assistance processing determined while driving based on either the driving skills or the emotional state would not be suitable for the individual driver.

The object of the present disclosure is to provide a vehicle driving assistance device that improves the suitability of assistance processing for a vehicle driver. Another object of the present disclosure is to provide a vehicle driving assistance method that improves the suitability of assistance processing for a vehicle driver. Yet another object of the present disclosure is to provide a vehicle driving assistance program that improves the suitability of assistance processing for a vehicle driver.

The technical means of the present disclosure for solving the problems will be explained below. Note that the claims and the reference characters in parentheses in this section indicate the corresponding relationship with the specific means described in the embodiments described in detail later, and do not limit the technical scope of the present disclosure.

A first aspect of the present disclosure is
A driving assistance device (1) for assisting a driver (6) of a vehicle (2), comprising:
A driving state discrimination unit (100) for discriminating a driver's individual state into a plurality of levels while the vehicle is driving;
A driving skill discrimination unit (110) for discriminating a driver's driving skill into a plurality of levels while driving;
an aging condition discrimination unit (120) for discriminating aging changes in a personal condition into a plurality of levels;
An aging skill discrimination unit (130) for discriminating aging changes in driving skills into a plurality of levels;
an assistance processing control unit (140) for controlling assistance processing for a driver in accordance with a correlation between each level of a personal state and a driving skill during driving and each level of a change over time in the personal state and the driving skill ;
The driving condition discrimination unit discriminates the correlation of the individual condition during the current driving into a plurality of levels with respect to the distribution of the individual condition during the past driving, and selects a condition index for comparing the past and present as the correlation of the individual condition according to at least one of the vehicle driving conditions and the driver characteristic conditions .

A second aspect of the present disclosure is
A driving assistance method for assisting a driver (6) of a vehicle (2), comprising:
A driving condition discrimination process (S1) for discriminating a driver's personal condition while the vehicle is traveling into a plurality of levels;
A driving skill discrimination step (S2) of discriminating the driving skill of a driver while driving into a plurality of levels;
an aging condition discrimination step (S5) of discriminating the aging change of the individual condition into a plurality of levels;
An age-related skill discrimination step (S6) of discriminating age-related changes in driving skills into a plurality of levels;
and an assistance process control step (S8) of controlling assistance processes for a driver in accordance with a correlation between each level of a personal state and a driving skill during driving and each level of a change over time in the personal state and the driving skill ,
The driving condition discrimination process, which discriminates the correlation of the individual condition during the current driving to a plurality of levels with respect to the distribution of the individual condition during the past driving, selects a condition index for comparing the past and present as the correlation of the individual condition according to at least one of the vehicle driving conditions and the driver's characteristic conditions .

A third aspect of the present disclosure is
A driving assistance program including instructions to be executed by a processor (12) to assist a driver (6) of a vehicle (2) in driving the vehicle,
The command is,
A driving state discrimination process (S1) for discriminating a driver's individual state while the vehicle is traveling into a plurality of levels;
A driving skill discrimination process (S2) for discriminating the driving skill of a driver while driving into a plurality of levels;
an aging condition discrimination step (S5) of discriminating the aging change of the individual condition into a plurality of levels;
An age-related skill discrimination step (S6) of discriminating age-related changes in driving skills into a plurality of levels;
and an assistance process control step (S8) of controlling an assistance process for a driver in accordance with a correlation between each level of a personal state and a driving skill during driving and each level of a change over time in the personal state and the driving skill,
The driving condition discrimination process, which discriminates the correlation of the individual condition during the current driving period against the distribution of the individual condition during the past driving period into multiple levels, selects a condition index for comparing the past and present as the correlation of the individual condition according to at least one of the vehicle driving conditions and the driver's characteristic conditions .

According to the first to third aspects, the driver's personal state while the vehicle is traveling and the driver's driving skills while traveling are each determined into a plurality of levels. Furthermore, according to the first to third aspects, the aging changes of the driver's personal state and driving skills are also determined into a plurality of levels. Therefore, in the first to third aspects, the support processing for the driver is controlled according to the correlation between each level of the personal state and driving skills while traveling and each level of the aging changes of the personal state and driving skills. This allows the level correlation between the personal state and driving skills to be subdivided from two perspectives, that is, while traveling and aging changes, and can be precisely reflected in the support processing. Therefore, it is possible to improve the suitability of the support processing for the driver.

1 is a block diagram showing an overall configuration of a driving assistance device according to an embodiment; 1 is a block diagram showing a detailed configuration of a driving assistance device according to an embodiment; 4 is a flowchart showing a driving assistance flow of a driving assistance method according to one embodiment. 4 is a flowchart showing a running state determination routine of FIG. 3; 4 is a flowchart showing an example of a selection flow of a state index in the running state discrimination routine of FIG. 3 . 5 is a flowchart showing a state correlation determination subroutine of FIG. 4 . 4 is a flowchart showing a driving skill determination routine of FIG. 3. 4 is a flowchart showing an example of a selection flow of a skill index in the driving skill determination routine of FIG. 3 . 8 is a flowchart showing a skill correlation determination subroutine of FIG. 7; 4 is a characteristic table showing a correlation matrix in the driving assistance flow of FIG. 3 . 4 is a flowchart showing the aging condition determination routine of FIG. 3; 4 is a flowchart showing the aging skill determination routine of FIG. 3 . 4 is a flowchart showing the support process control routine of FIG. 3 .

One embodiment is described below with reference to the drawings.

The driving assistance device 1 of one embodiment shown in FIG. 1 assists the driver 6 of the vehicle 2 in driving. The vehicle 2 may be capable of automatic driving constantly in an automatic driving mode, or temporarily by switching between the automatic driving mode and the manual driving mode. Here, the automatic driving mode may be realized by autonomous driving control, such as conditional driving automation, advanced driving automation, or full driving automation, in which the system performs all driving tasks when activated. The automatic driving control mode may be realized in advanced driving assistance control, such as driving assistance or partial driving automation, in which the driver 6 performs some or all driving tasks. The automatic driving mode may be realized by combining or switching between the autonomous driving control and the advanced driving assistance 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 driving control by the driving assistance device 1. As shown in FIG. 2, the sensor system 3 includes an external sensor 30 and an internal sensor 32.

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

The internal sensor 32 generates information about the internal environment of the vehicle 2. The internal sensor 32 may generate the internal information by detecting a specific physical quantity of motion in the internal environment of the vehicle 2. The internal sensor 32 of the physical quantity detection type is at least one of a driving speed sensor, an acceleration sensor, a gyro sensor, and an in-vehicle temperature sensor, for example. The internal sensor 32 may generate the internal information by detecting a specific state related to an occupant in the internal environment of the vehicle 2. The internal sensor 32 of the occupant detection type is at least one of a driver status monitor, a biological sensor, a seating sensor, an actuator sensor, and an in-vehicle equipment sensor, for example.

Here, the driver status monitor detects at least one of the following conditions of the driver 6, who is one of the occupants of the vehicle 2 and who operates the vehicle 2 in manual driving: eyeball condition, eyelid condition, head condition, facial expression, posture, etc. The biosensor detects at least one of the following conditions as the driver 6's vital signs: pulse (i.e., heart rate), blood pressure, electrocardiogram, respiration, body temperature, and fingerprints. The seating sensor detects the seating state of the driver 6 in the driver's seat of the vehicle 2. The actuator sensor detects at least one of the following conditions as instructions from the driver 6 regarding the vehicle 2's driving actuators: accelerator pedal operation state, brake pedal operation state, steering wheel steering state, starter switch on/off state, and shift lever shift state. The in-vehicle device sensor detects at least one of the following conditions as the driver 6 or other occupants' operation of in-vehicle devices including the information presentation system 4: switch on/off state, touch panel input state, and non-contact recognizable gesture state.

The information presentation system 4 presents various information to the occupants, including the driver 6. The information presentation system 4 is composed of a visual presentation unit 40, an auditory presentation unit 42, and a cutaneous 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 at least one of a head-up display (HUD), a multi-function display (MFD), a combination meter, a navigation unit, and a light-emitting unit. The auditory presentation unit 42 transmits the presentation target information by stimulating the hearing of the driver 6. The auditory presentation unit 42 is at least one of a speaker, a buzzer, and a vibration unit. The cutaneous sensation presentation unit 44 transmits the presentation target information by stimulating the cutaneous sensation of the driver 6. The cutaneous sensation stimulated by the cutaneous sensation presentation unit 44 includes at least one of touch, temperature, and wind. The cutaneous sensation presentation unit 44 is at least one of a vibration unit of a steering wheel, a vibration unit of a driver's seat, a reaction unit of a steering wheel, a reaction unit of an accelerator pedal, a reaction unit of a brake pedal, and an air conditioning unit.

The map unit 5 non-temporarily stores map information that can be used for driving by the driving assistance 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, or an optical medium. The map unit 5 may be a database of a locator that estimates the vehicle's own state quantity including the vehicle's own position. The map unit 5 may be a database of a navigation unit that navigates the vehicle's travel route. The map unit 5 may be configured by combining multiple types of these databases.

The map unit 5 acquires and stores the latest map information, for example, by communicating with an external center. The map information is digitized in two or three dimensions as information representing the driving environment of the vehicle 2. The map information may include road information representing at least one of the following: the position, shape, and road surface condition of the road itself. The map information may include marking information representing at least one of the following: the positions and shapes of signs and dividing lines attached to the road. The map information may include structure information representing at least one of the positions and shapes of buildings and traffic lights facing the road.

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

The dedicated computer constituting the driving assistance device 1 has at least one memory 10 and one processor 12. The memory 10 is at least one type of non-transient tangible storage medium, such as a semiconductor memory, a magnetic medium, or an optical medium, that non-temporarily stores computer-readable programs and data. The processor 12 includes at least one type of core, such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or a RISC (Reduced Instruction Set Computer)-CPU.

The processor 12 executes a number of commands included in the driving assistance program stored in the memory 10. This causes the driving assistance device 1 to construct a number of functional blocks for assisting the driving of the vehicle 2. At this time, in the driving assistance device 1, the driving assistance program stored in the memory 10 for assisting the driving of the vehicle 2 causes the processor 12 to execute a number of commands, thereby constructing a number of functional units (functional blocks). The multiple functional blocks constructed by the driving assistance device 1 include a driving state discrimination unit 100, a driving skill discrimination unit 110, an aging state discrimination unit 120, an aging skill discrimination unit 130, and an assistance processing control unit 140, as shown in FIG. 2.

Below, the driving assistance method for assisting the driving of the vehicle 2 through cooperation between the functional units 100, 110, 120, 130, and 140 will be explained with reference to the driving assistance flow diagrams shown in Figures 3 to 11. Note that each "S" in this flow diagram represents multiple steps executed by multiple commands included in the driving assistance program.

In S1 of the driving assistance flow shown in FIG. 3, the driving state discrimination unit 100 executes a driving state discrimination routine to discriminate the personal state of the driver 6 while the vehicle 2 is driving into multiple levels. In S10 of the driving state discrimination routine shown in FIG. 4, the driving state discrimination unit 100 selects a state index Ip for comparing the past and present as a correlation of the personal state while driving.

The state index Ip is an index for predictively determining the individual state of the driver 6 while driving, such as drowsiness, inattentiveness, fatigue, and absentmindedness. The state index Ip may be at least a plurality of types based on information from the sensor system 3, such as eye movement including saccades and gaze direction, eyelid opening and closing movement including blinking, head movement including facial direction, facial expression, body posture, pulse (i.e., heart rate), blood pressure, electrocardiogram, respiration, and body temperature.

The state index Ip is selected according to at least one of the driving conditions of the vehicle 2 and the characteristic conditions of the driver 6. The driving conditions of the vehicle 2 are set for at least one of the following based on information from the sensor system 3: the type and shape of the road, the degree of traffic congestion and structural complexity of the surrounding environment, the behavior of the vehicle 2 including the driving speed, the relative relationship with other vehicles or traffic users and the surrounding risks based thereon, the time and time period of the drive, and the weather. The characteristic conditions of the driver 6 are set for at least one of the following based on past driving results: the driving score, the time elapsed since the start of driving, and the accuracy of determining the individual state.

Figure 5 shows an example of a flow for selecting a state index Ip. In S100 of the selection flow example, the driving state discrimination unit 100 acquires necessary information from the sensor system 3. In the following S101, the driving state discrimination unit 100 discriminates the type of road as a driving condition of the vehicle 2. As a result, when the driving environment is a motorway, the driving state discrimination unit 100 selects a type of state index Ip that requires a level discrimination of the personal state while driving on the motorway in S102. On the other hand, when the driving environment is a general road in a city center with a high degree of congestion, the driving state discrimination unit 100 selects a type of state index Ip that requires a level discrimination of the personal state while driving at the high degree of congestion in S103. On the other hand, when the driving environment is a general road in a suburban area with a low degree of congestion, the driving state discrimination unit 100 selects a type of state index Ip that requires a level discrimination of the personal state while driving at the low degree of congestion in S104.

In S11 of the driving condition discrimination routine shown in FIG. 4, the driving condition discrimination unit 100 sets baseline data Dpb for past condition index Ip to be compared with the current condition index Ip as a correlation of the individual condition while driving. Here, the baseline data Dpb is set so as to give the required distribution for the condition index Ip selected by S10 among the past sampling data covering all options of the condition index Ip in S10.

In S12 of the driving state discrimination routine shown in FIG. 4, the driving state discrimination unit 100 sets a state threshold Tp for discriminating the level of each past and present state index Ip to be compared as a correlation of the personal state while driving. Here, the state threshold Tp is set according to past driving behavior such as safe driving and risky driving. The state threshold Tp is selected based on the distribution of the baseline data Dpb related to the state index Ip during past driving set in S11. In this case, for example, the intermediate value, valley value, or machine learning value between the peaks during safe driving and risky driving in the distribution of the baseline data Dpb is selected as the state threshold Tp for the state index Ip.

In S13 of the driving state discrimination routine shown in FIG. 4, the driving state discrimination unit 100 executes a state correlation discrimination subroutine to discriminate the correlation of the individual state during the current driving into multiple levels with respect to the distribution of the individual state during the past driving. In S130 of the state correlation discrimination subroutine shown in FIG. 6, the driving state discrimination unit 100 acquires the data Dpp of the state index Ip selected in S10 during the current driving, the baseline data Dpb during the past driving set in S11, and the state threshold value Tp selected in S12. In the following S131, the driving state discrimination unit 100 discriminates the individual state during the current driving into multiple levels based on the state threshold value Tp by correlation analysis that compares the data Dpp of the state index Ip during the current driving with the distribution of the baseline data Dpb during the past driving.

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

For example, if the individual condition level is determined to be a normal level because the Mahalanovillas distance is equal to or less than the first condition threshold Tp, the state correlation discrimination subroutine proceeds to S132. In S132, the running state discrimination unit 100 stores the result of discrimination from the normal level in the memory 10 together with a timestamp indicating the current running time. On the other hand, if the individual condition level is determined to be a worsening level because, for example, the Mahalanovillas distance exceeds the first condition threshold Tp and is equal to or less than the second condition threshold Tp, the state correlation discrimination subroutine proceeds to S133. In S133, the running state discrimination unit 100 stores the result of discrimination from the worsening level in the memory 10 together with a timestamp. On the other hand, if the individual condition level is determined to be an abnormal level because, for example, the Mahalanovillas distance exceeds the second condition threshold Tp, the state correlation discrimination subroutine proceeds to S134. In S134, the running state discrimination unit 100 stores the result of discrimination from the abnormal level in the memory 10 together with a timestamp. Furthermore, if at least a portion of memory 10 is configured as an external memory of an external computer, the results of the personal condition level determination are output to the external memory via communication and stored therein.

In S2 of the driving assistance flow shown in FIG. 3, the driving skill discrimination unit 110 executes a driving skill discrimination routine to discriminate the driving skill of the driver 6 while the vehicle 2 is traveling into multiple levels. In S20 of the driving skill discrimination routine shown in FIG. 7, the driving skill discrimination unit 110 selects a skill index Id for comparing the past and present as a correlation of driving skills while traveling.

The skill index Id is an index for predictively determining, for example, a driving score as the driving skill of the driver 6 while driving. The skill index Id may be at least a plurality of types based on information from the sensor system 3, such as acceleration, deceleration, lateral G, steering angle and the pedal or steering wheel operation amount or operation speed related thereto, and the lateral position within the lane (when correcting steering or changing lanes). The skill index Id is selected according to at least one of the driving conditions of the vehicle 2 and the characteristic conditions of the driver 6. The driving conditions of the vehicle 2 and the characteristic conditions of the driver 6 are set in accordance with the state index Ip.

Figure 8 shows an example of a selection flow of skill index Id. In S200 of the selection flow example, the driving skill discrimination unit 110 acquires necessary information from the sensor system 3. In the following S201, the driving skill discrimination unit 110 discriminates the type of road as a driving condition of the vehicle 2. As a result, if the driving environment is a motorway, the driving skill discrimination unit 110 selects a type of skill index Id that requires a level discrimination of driving skill while driving on the motorway in S202. On the other hand, if the driving environment is a general road in a city center with a high degree of congestion, the driving skill discrimination unit 110 selects a type of skill index Id that requires a level discrimination of driving skill while driving at the high degree of congestion in S203. On the other hand, if the driving environment is a general road in a suburban area with a low degree of congestion, the driving skill discrimination unit 110 selects a type of skill index Id that requires a level discrimination of driving skill while driving at the low degree of congestion in S204.

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

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

In S23 of the driving skill discrimination routine shown in FIG. 7, the driving skill discrimination unit 110 executes a skill correlation discrimination subroutine to discriminate the correlation of the driving skill during the current driving into multiple levels with respect to the distribution of the driving skill during the past driving. In S230 of the skill correlation discrimination subroutine shown in FIG. 9, the driving skill discrimination unit 110 acquires the data Ddp of the skill index Id selected in S20 during the current driving, the baseline data Ddb during the past driving set in S21, and the skill threshold Td selected in S22. In the following S231, the driving skill discrimination unit 110 discriminates the driving skill during the current driving into multiple levels based on the skill threshold Td by a correlation analysis that compares the data Ddp of the skill index Id during the current driving with the distribution of the baseline data Ddb during the past driving. Here, the correlation analysis may be performed by any of the methods similar to the case of the baseline data Dpb to discriminate the level of the driving skill. The driving skill levels determined by correlation analysis using either method are three types: normal level, rough level, which is rougher than normal, and risk level, which is rougher than the rough level.

For example, if the driving skill level is determined to be normal because the Mahalanovillas distance is equal to or less than the first skill threshold Td, the skill correlation determination subroutine proceeds to S232. In S232, the driving skill determination unit 110 stores the result of the determination from the normal level in the memory 10 together with a timestamp indicating the current driving time. On the other hand, if the driving skill level is determined to be rough because, for example, the Mahalanovillas distance exceeds the first skill threshold Td and is equal to or less than the second skill threshold Td, the skill correlation determination subroutine proceeds to S233. In S233, the driving skill determination unit 110 stores the result of the determination from the rough level in the memory 10 together with a timestamp. On the other hand, if the driving skill level is determined to be risky because, for example, the Mahalanovillas distance exceeds the second skill threshold Td, the skill correlation determination subroutine proceeds to S234. In S234, the driving skill determination unit 110 stores the result of the determination from the risk level in the memory 10 together with a timestamp. Furthermore, if at least a portion of memory 10 is configured as an external memory of an external computer, the results of the driving skill level determination are output to the external memory via communication and stored therein.

In S3 of the driving assistance flow shown in FIG. 3, the driving state discrimination unit 100 and the driving skill discrimination unit 110 jointly extract the correlation between the driving level of the personal state discriminated in S13 and the driving level of the driving skill discriminated in S23. In this correlation extraction, the current driving levels of the personal state and the driving skill are 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 assistance flow shown in FIG. 3, the aging state determination unit 120 and the aging skill determination unit 130 cooperate to determine whether the time elapsed since the reference time is equal to or greater than a set time. Here, the reference time is set, for example, to the time of first use after completion or maintenance of the vehicle 2, or the time of the previous positive determination by S4. If a positive determination is made because the time elapsed since the reference time is equal to or greater than the set time, the driving assistance flow proceeds sequentially to S5 to S8. On the other hand, if a negative determination is made because the time elapsed since the reference time is less than the set time, the driving assistance flow skips S5 to S7 and proceeds to S8.

In S5 of the driving assistance flow shown in FIG. 3, the aging state determination unit 120 executes an aging state determination routine to determine the aging change of the individual state into multiple levels. In S50 of the aging state determination routine shown in FIG. 11, the aging state determination unit 120 acquires the level of the individual state determined during the past driving at the reference time and the level of the individual state determined during the current driving that has elapsed a set time or more since the reference time. In the following S51, the aging state determination unit 120 further determines the degree of deviation in the correlation between the individual state level during the past driving and the individual state level during the current driving as the level of aging change. There are three types of aging change levels that are the degree of deviation of the individual state level: an improvement trend level where the individual state level is improving, a steady trend level where the individual state level is steady without any change, and a deterioration trend level where the individual state level is worsening.

In S6 of the driving assistance flow shown in FIG. 3, the aging skill determination unit 130 executes an aging skill determination routine to determine the change in driving skill over time into multiple levels. In S60 of the aging skill determination routine shown in FIG. 12, the aging skill determination unit 130 acquires the driving skill level determined during past driving at a reference time and the driving skill level determined during current driving that has elapsed a set time or more since the reference time. In the following S61, the aging skill determination unit 130 further determines the deviation in the correlation between the driving skill level during past driving and the driving skill level during current driving as the level of change over time. There are three types of change over time levels that are the deviation of the driving skill level: an improvement trend level where the driving skill level is improving, a steady trend level where the driving skill level is substantially unchanged and steady, and a deterioration trend level where the driving skill level is deteriorating.

In S7 of the driving assistance flow shown in FIG. 3, the aging condition determination unit 120 and the aging skill determination unit 130 jointly extract the correlation between the aging change level of the personal condition determined in S51 and the aging change level of the driving skill determined in S61. In this correlation extraction, the aging change levels of the personal condition and the driving skill are treated 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 this embodiment, as shown in FIG. 10, a correlation may or may not be extracted between the level of change over time of the personal condition determined by S51 and the driving level of the driving skill determined by S23. Also, in S7 of this embodiment, as shown in FIG. 10, a correlation may or may not be extracted between the driving level of the personal condition determined by S13 and the level of change over time of the driving skill determined by S61.

In S8 of the driving assistance flow shown in FIG. 3, the assistance processing control unit 140 executes an assistance processing control routine to control assistance processing according to the correlation between each level of the personal state and driving skill while driving and each level of the personal state and driving skill in the change over time. S80 of the assistance processing control routine shown in FIG. 13 is entered whether the elapsed time from the reference time is equal to or greater than the set time (if S5 to S7 are passed) or if the elapsed time is less than the set time (if S5 to S7 are skipped). In S80, the assistance processing control unit 140 determines the appropriate short-term assistance processing for the driver 6 according to the extraction flag value Cn that indicates the correlation of the driving level extracted by S3.

Here, in the short-term support process, from among the support applications registered for each correlation pair in the correlation matrix shown in FIG. 10, a support application that matches the matrix value set by the extraction flag value Cn is selectively launched. For example, when the correlation pair currently traveling is a normal level of personal condition and a normal level of driving skill, a proposal to improve convenience and comfort is presented to the driver 6 from the information presentation system 4 by launching a suitable support application. On the other hand, for example, when the correlation pair currently traveling is a normal level of personal condition and a rough level of driving skill, a proposal to assist driving is presented to the driver 6 from the information presentation system 4 by launching a suitable support application. In this case, a support application for directly assisting the driver 6 in driving using the automatic driving mode may be launched instead of or in addition to the support application of the support proposal. On the other hand, for example, when the correlation pair currently traveling is a worsening level of personal condition and a normal level of driving skill, a proposal including encouraging rest to restore concentration is presented to the driver 6 from the information presentation system 4 by launching a suitable support application.

The assistance process control routine shown in FIG. 13 does not proceed to S81 if the time elapsed since the reference time is less than the set time (if S5 to S7 are skipped), but proceeds only if the time elapsed is equal to or greater than the set time (if S5 to S7 are passed through). In S81, the assistance process control unit 140 determines an appropriate long-term assistance process for the driver 6 according to the extraction flag value Ca, which indicates the correlation of the aging level extracted by S7.

Here, in the long-term support process, from among the support applications registered for each correlation pair in the correlation matrix shown in FIG. 10, a support application that matches the matrix value set by the extraction flag value Ca is selectively launched. For example, when the correlation pair of aging changes is a personal condition with a worsening tendency level and a driving skill with a steady tendency level, a proposal including an early warning or rest promotion to give notice of the worsening tendency of the condition is presented to the driver 6 from the information presentation system 4 by launching a suitable support application. On the other hand, when the correlation pair of aging changes is a personal condition with a steady level and a driving skill with a worsening tendency level, a proposal to give notice of the skill deterioration tendency is presented to the driver 6 from the information presentation system 4 by launching a suitable support application. In this case, a support application for early intervention in the driving of the driver 6 using the automatic driving mode may be launched instead of or in addition to the support application for the awareness proposal. On the other hand, when the correlation pair of aging changes is a personal condition with a worsening tendency level and a driving skill with a worsening tendency level, a proposal to induce the driver to give up his/her driver's license is presented to the driver 6 from the information presentation system 4 by launching a suitable support application.

The assistance applications that respectively realize the above short-term assistance processing and long-term assistance processing may be installed before the first use, for example, when the vehicle 2 is shipped from the factory or during maintenance, or may be installed by the driver 6 through a registration operation after the first use. In particular, installation through the registration operation of the assistance application may be executable for each correlation pair in the correlation matrix shown in FIG. 10. However, if an existing assistance application is registered in association with the correlation pair to which a new assistance application is to be registered, the driver 6 may confirm whether or not the assistance application needs to be replaced, taking into account the overlapping status of usage rights for units used in the information presentation system 4, before installation is performed.

From the explanation so far, in this embodiment, S1 corresponds to the driving condition determination process, S2 corresponds to the driving skill determination process, S5 corresponds to the aging condition determination process, S6 corresponds to the aging skill determination process, and S8 corresponds to the assistance processing control process.

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

According to this embodiment, the personal state of the driver 6 while the vehicle 2 is traveling and the driving skills of the driver 6 while traveling are each determined into a plurality of levels. Furthermore, according to this embodiment, the aging changes of the personal state and driving skills of the driver 6 are also determined into a plurality of levels. Therefore, in this embodiment, the support processing for the driver 6 is controlled according to the correlation between each level of the personal state and driving skills while traveling and each level of the aging changes of the personal state and driving skills. According to this, the level correlation between the personal state and driving skills can be subdivided from two perspectives, that is, while traveling and aging changes, and can be precisely reflected in the support processing. Therefore, it is possible to improve the suitability of the support processing for the driver 6.

According to this embodiment, the correlation of the individual state during the current drive with the distribution of the individual state during past drives is determined at multiple levels. This allows the individual state during the current drive to be appropriately determined based on the steady individual state represented by the past distribution. Therefore, determining the individual state with respect to such a past distribution is advantageous in improving the suitability of the assistance process.

According to this 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 driving conditions of the vehicle 2 and the characteristic conditions of the driver 6. As a result, the correlation of the individual state during past driving and the current driving is determined with respect to the state index Ip that reflects the conditions that affect the individual state, so the accuracy of the determination can be improved. Therefore, determining the individual state using such a state index Ip is advantageous in improving the compatibility of the assistance process.

According to this embodiment, the correlation between the driving skill during the current drive and the distribution of driving skills during past drives is determined into multiple levels. This allows the driving skill during the current drive to be appropriately determined based on the steady driving skill represented by the past distribution. Therefore, determining the driving skill based on such a past distribution is advantageous in improving the suitability of the assistance process.

According to this embodiment, as a correlation of driving skills, a skill index Id for comparing the past and the present is selected according to at least one of the driving conditions of the vehicle 2 and the characteristic conditions of the driver 6. As a result, the correlation of driving skills during past driving and current driving is determined with respect to the skill index Id that reflects the conditions that affect the driving skills, so the accuracy of the determination can be improved. Therefore, determining driving skills using such a skill index Id is advantageous in improving the compatibility of the assistance process.

According to this embodiment, the correlation between the level of the personal condition determined during the current drive and the level of the personal condition determined during past drives is determined into multiple levels as changes in the personal condition over time. This allows the changes in the personal condition over time to be properly determined from the degree of deviation in correlation that appears in the personal condition during the current drive, based on the personal condition during past drives. Therefore, determining changes in the personal condition over time based on such past determination results is advantageous in improving the suitability of the assistance process.

According to this embodiment, the correlation between the level of driving skill determined during the current drive and the level of driving skill determined during past drives is determined into multiple levels as changes in driving skill over time. As a result, changes in driving skill over time can be properly determined from the degree of deviation in correlation that appears in driving skill during current drive based on driving skill during past drives. Therefore, determining changes in driving skill over time based on past determination results is advantageous in improving the suitability of the assistance process.

Other Embodiments
Although one embodiment has been described above, the present disclosure should not be construed as being limited to this embodiment, and can be applied to various embodiments within the scope not departing from the gist of the present disclosure.

In a modified example, the dedicated computer constituting the driving assistance device 1 may include at least one of a digital circuit and an analog circuit as a processor. Here, the digital circuit is at least one of the following: ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array), SOC (System on a Chip), PGA (Programmable Gate Array), and CPLD (Complex Programmable Logic Device). Such a digital circuit may also have a memory that stores a program.

1: Driving assistance device, 2: Vehicle, 6: Driver, 100: Driving state discrimination unit, 110: Driving skill discrimination unit, 120: Aging state discrimination unit, 130: Aging skill discrimination unit, 140: Assistance processing control unit

Claims (11)

A driving assistance device (1) for assisting a driver (6) of a vehicle (2), comprising:
a driving state discrimination unit (100) for discriminating the individual state of the driver while the vehicle is driving into a plurality of levels;
a driving skill discrimination unit (110) for discriminating the driving skill of the driver while driving into a plurality of levels;
an aging condition discrimination unit (120) for discriminating the aging change of the personal condition into a plurality of levels;
an aging skill discrimination unit (130) for discriminating the aging change of the driving skill into a plurality of levels;
an assistance processing control unit (140) that controls assistance processing for the driver in accordance with a correlation between each level of the personal state and the driving skill during the driving and each level of the personal state and the driving skill in the aging change ;
The driving assistance device, wherein the driving state discrimination unit discriminates the correlation of the individual state during the current driving period into a plurality of levels with respect to the distribution of the individual state during the past driving period, and selects a state index for comparing the past and present as the correlation of the individual state in accordance with at least one of the driving conditions of the vehicle and the characteristic conditions of the driver . The driving support device according to claim 1 , wherein the driving skill determination unit determines a correlation of the driving skill during the current driving state with respect to a distribution of the driving skill during the past driving state into a plurality of levels. The driving assistance device according to claim 2, wherein the driving skill discrimination unit selects a skill index for comparing the past and the present as a correlation of the driving skill in accordance with at least one of the driving conditions of the vehicle and the characteristic conditions of the driver. The driving assistance device according to any one of claims 1 to 3, wherein the aging condition determination unit determines a correlation between a level of the personal condition determined during the current driving and a level of the personal condition determined during the past driving into a plurality of levels as the aging change of the personal condition. The driving assistance device according to any one of claims 1 to 4, wherein the aging skill discrimination unit discriminates the correlation between the level of the driving skill discriminated during the current driving and the level of the driving skill discriminated during the past driving into a plurality of levels as an aging change of the driving skill. A driving assistance method for assisting a driver (6) of a vehicle (2), comprising:
A driving state discrimination process (S1) of discriminating the personal state of the driver while the vehicle is traveling into a plurality of levels;
A driving skill discrimination step (S2) of discriminating the driving skill of the driver while driving into a plurality of levels;
an aging condition discrimination step (S5) of discriminating the aging change of the personal condition into a plurality of levels;
An age-related skill discrimination step (S6) of discriminating the age-related change in the driving skill into a plurality of levels;
and an assistance processing control step (S8) of controlling an assistance processing for the driver in accordance with a correlation between each level of the personal state and the driving skill during the driving and each level of the personal state and the driving skill in the aging change ,
The driving assistance method includes a driving condition discrimination process for discriminating, into a plurality of levels, the correlation of the individual condition during the current driving with respect to the distribution of the individual condition during the past driving, and selecting a condition index for comparing the past and present as the correlation of the individual condition in accordance with at least one of the driving conditions of the vehicle and the characteristic conditions of the driver . The driving assistance method according to claim 6 , wherein the driving skill determination step determines a correlation between the driving skill during the current driving state and a distribution of the driving skill during the past driving state into a plurality of levels. The driving assistance method according to claim 7 , wherein the driving skill discrimination step selects a skill index for comparing the past and the present as a correlation of the driving skill in accordance with at least one of the driving conditions of the vehicle and characteristic conditions of the driver. The driving assistance method according to any one of claims 6 to 8, wherein the aging condition determination step determines a correlation between a level of the personal condition determined during the current driving and a level of the personal condition determined during the past driving into a plurality of levels as the aging change of the personal condition. The driving assistance method according to any one of claims 6 to 9, wherein the aging skill discrimination process discriminates a correlation between the level of the driving skill discriminated during the current driving and the level of the driving skill discriminated during the past driving into a plurality of levels as an aging change of the driving skill. A driving assistance program including instructions to be executed by a processor (12) to assist a driver (6) of a vehicle (2) in driving the vehicle,
The instruction:
A driving state discrimination process (S1) for discriminating the individual state of the driver while the vehicle is traveling into a plurality of levels;
A driving skill discrimination step (S2) for discriminating the driving skill of the driver during the driving into a plurality of levels;
an aging condition discrimination step (S5) of discriminating the aging change of the personal condition into a plurality of levels;
An age-related skill discrimination step (S6) for discriminating the age-related change in the driving skill into a plurality of levels;
and an assistance process control step (S8) for controlling an assistance process for the driver in accordance with a correlation between each level of the personal state and the driving skill during the driving and each level of the personal state and the driving skill in the aging change ,
The driving condition discrimination process discriminates the correlation of the individual condition during the current driving period into a plurality of levels with respect to the distribution of the individual condition during the past driving period, and selects a condition index for comparing the past and present as the correlation of the individual condition in accordance with at least one of the driving conditions of the vehicle and the characteristic conditions of the driver .

Images