JP5643142B2 - Driving ability determination device and driving ability determination method - Google Patents

Description

  The present invention relates to a driving capability determination device and a driving capability determination method for determining a driving capability of a driver.

  Drivers' driving ability tends to decline with age, and in recent years, casualty accidents of elderly drivers have become a social problem. Elderly drivers are known to have a high rate of accidents due to a variety of causes, including misstepping of the brake and accelerator pedals, carelessness to other vehicles and pedestrians, signals, and oversight of signs. Along with this, the Road Traffic Law was revised, and older drivers (70 years old and older) were obliged to take senior training courses, but there was almost no effect. The fact is that it has not decreased at all.

  The main causes of accidents caused by elderly drivers are a decline in judgment of elderly people (including blurring due to dementia) and a decline in exercise ability of elderly people. Decreased judgment is associated with brain aging. Older people have problems that it takes a long time to respond to a certain stimulus and it is impossible to select an appropriate action. In addition, a decrease in athletic ability is caused by, for example, a decrease in visual function such as narrowing of the visual field or a decrease in dynamic visual acuity, a decrease in hearing function such as narrowing of the audible band or a decrease in hearing level, aging of muscles and nerves This is a general decline in motor function.

  For this reason, it is important to determine whether or not the elderly driver can safely drive the vehicle.

  Further, not only elderly drivers but also non-elderly drivers may be in a state where the vehicle cannot be safely driven depending on the physical condition. For example, if you are tired from continuous driving, there may be a drowsy driving or a random driving, and it is possible to determine whether it is safe to drive the vehicle even for non-elderly drivers. is important.

  In Patent Document 1 below, in order for the elderly driver to be aware of the decline in driving skills, the driver's handle operation is focused on the steering operation specific to the elderly driver (smooth steering at the corner of the road). There is disclosed a technique for issuing a warning (or determining a driving age of a driver) when a measurement value related to (operation of the steering wheel) exceeds a predetermined threshold value that separates a young person and an elderly person.

  Patent Document 2 listed below is a technique for monitoring a driving operation, and detects a deviation amount between an operation amount related to a driver's operation and a normal reference (an operation amount when the operation is smoothly performed). Thus, a technique for monitoring the driving operation of the driver is disclosed. In Patent Document 2, monitoring of the steering wheel operation (steering angle) is mainly described, but it is also described that the depression angle of the pedal may be used as the operation amount of the accelerator pedal or the brake pedal.

  In the technique described in Patent Document 1, it is a driving by an elderly driver by determining whether or not the steering wheel operation is smoothly performed at a corner (whether or not the vehicle is traveling on an appropriate track at a corner) (or The driving age of the driver). Specifically, according to the technique described in Patent Document 1, the steering angle of the steering wheel within the period from the entry point to the exit point of the turning angle is detected, and whether or not the driver can turn smoothly is determined. (Whether or not “awkwardness” appears in the handle operation) is determined. Note that the technique described in Patent Document 2 discloses a technique for numerically calculating the state of steering operation at a corner, and the technique described in Patent Document 1 is an application of this calculation technique. It can be said.

JP 2008-250406 A (summary) JP 2001-253266 (Abstract, paragraph [0049])

  However, the technique described in Patent Document 1 merely determines whether or not the driver can smoothly turn the corner. Although it is possible to determine the driving capability of the driver by this determination, the driving capability cannot be determined with high accuracy. For example, according to the technique described in Patent Document 1, it is possible to determine that the driving capability of the driver has decreased, but it is impossible to detect a sign that the driving capability of the driver will decrease. is there. That is, in the technique described in Patent Document 1, it can be detected that the driver is not driving the vehicle safely, but the driver can drive the vehicle safely (the judgment power and exercise ability of the driver are deteriorated). ) Is difficult to detect.

  In order to solve the above problem, an object of the present invention is to provide a driving ability determination device and a driving ability determination method that can determine the driving ability of a driver with higher accuracy.

In order to achieve the above object, the driving capability determination device of the present invention is a driving capability determination device that determines the driving capability of a driver who drives a vehicle,
Based on sensing information supplied from a driver operation detection sensor that detects a driving operation amount of the driver and a vehicle sensor that detects a driving state of the vehicle, a driving feature amount indicating a driving characteristic of the driver is calculated. A driving feature observation unit;
A driving capability determination unit that determines the driving capability of the driver from the driving feature amount of the driver calculated by the driving feature amount observation unit;
Have
When the driving ability determination unit calculates a Lyapunov index indicating divergence from the driving feature quantity of the driver using a calculation technology of a chaotic dynamical system, and the calculated Lyapunov index is lower than the normal index value The driving capability of the driver is determined to be deteriorated.

In order to achieve the above object, the driving capability determination method of the present invention is a driving capability determination method executed by a driving capability determination device that determines the driving capability of a driver who drives a vehicle.
Based on sensing information supplied from a driver operation detection sensor that detects a driving operation amount of the driver and a vehicle sensor that detects a driving state of the vehicle, a driving feature amount indicating a driving characteristic of the driver is calculated. Driving feature observation step;
A driving ability determination step for determining the driving ability of the driver from the driving feature quantity of the driver calculated in the driving feature quantity observation step,
Have
In the driving ability determination step, when the Lyapunov index indicating the divergence is calculated from the driving feature amount of the driver using a calculation technique of a chaotic dynamical system, and the calculated Lyapunov index is lower than the normal index value It is determined that the driving ability of the driver is deteriorated.

  The present invention has the above-described configuration or processing, and has an effect that the driving ability of the driver can be determined with higher accuracy.

It is a block diagram which shows an example of a structure of the driving capability determination apparatus in embodiment of this invention. It is a flowchart which shows an example of the measurement process of the driving | operation feature-value in embodiment of this invention. It is a flowchart which shows an example of the determination process of the athletic ability in embodiment of this invention. It is a flowchart which shows an example of the fluctuation | variation analysis process in embodiment of this invention. It is a flowchart which shows an example of the alerting process in embodiment of this invention. It is a flowchart which shows an example of the alerting process in embodiment of this invention. It is a figure which shows a specific example of the fluctuation | variation analysis process in embodiment of this invention. It is a block diagram which shows an example of a structure of the driving capability determination apparatus in another embodiment of this invention.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

  The present invention observes the driver's driving feature amount based on the amount of operation of the brake pedal, accelerator pedal, steering wheel, etc., in order to prevent a driver who falls into a casual driving, or a decrease in cognitive ability and response speed by an elderly driver, Based on the driving characteristics, it is determined whether the driving ability of the driver is a normal person level or a cognitively impaired person level (a driver who falls into a random driving or an elderly driver who falls into a cognitive disorder). . In addition, by alerting the driver whose driving ability is low (deteriorated), the cognitive ability is activated and the driver's operating ability is improved and returned to perform safe driving. is there.

  The present invention utilizes brain science. It is the attention function part of the frontal lobe that is targeted for alerting. The attention function part of the frontal lobe is a part that can be strengthened and recovered even in an aging or fatigued brain, for example. The attention time in the attention function unit is stimulated, so that matters to be noted in advance can be considered, and the reaction time for a certain stimulus is shortened by providing a margin for reaction preparation. In addition, by simultaneously stimulating the predictive power and optimizing the procedure and force adjustment until the operation is completed, the time until the optimal operation is realized is shortened.

  In addition, the present invention is configured to be realized even in a low-priced car (small car, light car), and the driver's consciousness level is measured and measured while minimizing the replacement or installation of the in-vehicle device. It realizes driving ability judgment and alerting based on consciousness level.

  First, the configuration of the driving ability determination device in the embodiment of the present invention will be described. FIG. 1 is a block diagram showing an example of the configuration of the driving ability determination device according to the embodiment of the present invention. The driving capability determination device 100 illustrated in FIG. 1 includes a driving feature amount observation unit 110, a driving capability determination unit 120, an allowable level information storage unit 130, an alarm unit 140, and a diagnostic checklist creation unit 150. In FIG. 1, each function is illustrated as a block, but each of these functions can be realized by hardware and / or (a program that can be executed by a computer).

  The driving feature amount observation unit 110 has a function of measuring a feature amount of a driver's driving operation amount (hereinafter referred to as a driving feature amount) from various information such as a driver's operation and a vehicle state. The driving feature amount observation unit 110 can calculate the driving feature amount of the driver based on sensing information from the driver operation detection sensor 191 and the vehicle sensor 192, for example. In addition, the driving feature amount observation unit 110 can convert the driving feature amount of the driver into an attractor (for example, perform the processing of FIG. 2 described later) when using a dynamical technology.

  The driver operation detection sensor 191 includes, for example, a sensor that detects an accelerator pedal depression amount (depression angle, depressing force, etc.), a sensor that detects a brake pedal depressing amount (depression angle, depressing force, etc.), It is possible to use a sensor or the like that detects an operation distance of the handle (a steering distance of the handle (for example, a steering amount that can be grasped from a rotation angle of the handle) or a torque). The vehicle sensor 192 can use, for example, a vehicle speed sensor that measures the speed of the vehicle or an acceleration sensor that determines the acceleration of the vehicle.

  The driving capability determination unit 120 has a function of determining the driving capability of the driver based on the driving feature amount of the driver measured by the driving feature amount observation unit 110. For example, the driving capability determination unit 120 compares the driving feature amount of the driver with the driving model information stored in the allowable level information storage unit 130 to determine whether the driving feature amount of the driver exceeds a certain reference. Or, it is possible to specify whether or not it is similar to a certain standard.

  In addition, the tolerance level information storage unit 130 has a function of storing in advance driving model information that is referred to when the driving capability determination unit 120 determines. As driving model information, for example, a driving model of a normal healthy person (information that can be recognized as a general healthy driver), a driving model of a cognitive person with a disability (a standard that can be recognized as an elderly driver or a driver who is in a state of random driving) Or the like) can be used.

  In addition, when the driving capability determination unit 120 determines that the driver cannot perform safe driving, the alarm unit 140 issues a warning alert to the driver from the monitor / speaker 193, for example. It has a function to notify. Note that any information such as visual screen display information and auditory audio information can be used as the warning notified from the alarm unit 140. Further, for example, when the driver issues a warning during driving, the notification may be performed in a manner that does not surprise the driver (for example, voice information with a tone that asks questions).

  The diagnostic checklist creation unit 150 accumulates information determined by the driving ability determination unit 120 as being in a state where the driver cannot perform safe driving, and processes the accumulated information to diagnose checklist information. (Medical chart) is created, and this diagnostic checklist information (medical chart) is transmitted to a specific distribution destination (distribution destination address) via the communication unit 194, for example.

  Next, processing according to the present invention will be described based on the configuration of the driving ability determination device 100 illustrated in FIG.

  FIG. 2 is a flowchart showing an example of a driving feature amount measurement process according to the embodiment of the present invention. The driving feature amount measurement process illustrated in FIG. 2 is a process executed by the driving feature amount observation unit 110 illustrated in FIG. 1 on the order of milliseconds (millisecond units).

  In FIG. 2, the driving feature amount observation unit 110 acquires the depression amount of the brake pedal (step S201), acquires the depression amount of the accelerator pedal (step S202), and acquires the steering wheel rotation distance and torque (step S203). . Each of the sensing information in steps S201 to S203 is supplied from the driver operation detection sensor 191 to the driving feature amount observation unit 110 in units of milliseconds, for example. In addition, the driving feature amount observation unit 110 acquires XYZ (a value of acceleration in a three-dimensional space) of the acceleration sensor (step S204). The sensing information in step S204 is supplied from the vehicle sensor 192 to the driving feature amount observation unit 110 in units of milliseconds, for example. In addition, each process of step S201-S204 is a parallel process.

  Here, the driving feature quantity observation unit 110 determines whether the vehicle is moving forward or backward from X (acceleration in the forward / reverse direction of the vehicle) (step S205). When the acceleration value X is forward, the driving feature amount observation unit 110 measures the driving feature amount at the time of forward travel, and converts the measured value into an attractor. For example, the driving feature amount observation unit 110 measures the driving feature amount of braking at the time of forward movement to make an attractor (step S206), measures the driving feature amount of acceleration at the time of forward movement, and converts it to an attractor (step S207). The driving feature amount of the steering speed (steering distance / millisecond) is measured and converted into an attractor (step S208).

  On the other hand, when the acceleration value X is backward, the driving feature amount observation unit 110 measures the driving feature amount during backward travel and converts the measured value into an attractor. For example, the driving feature amount observation unit 110 measures the driving feature amount of braking at the time of reverse travel and converts it into an attractor (step S209), measures the driving feature amount of acceleration at the time of reverse travel and converts it into an attractor (step S210), and moves backward The driving feature quantity at the steering speed (steering distance / millisecond) is measured and converted into an attractor (step S211).

  As described above, the driving feature quantity observation unit 110 can measure the driving feature quantity of the driver and make it an attractor in the millisecond order.

  FIG. 3A is a flowchart showing an example of determination processing of athletic ability in the embodiment of the present invention. In addition, the determination process of athletic ability illustrated in FIG. 3A is a process executed by the driving ability determination unit 120 illustrated in FIG. 1 on the order of several seconds to one minute (units of several seconds to one minute).

  In FIG. 3A, the driving ability determination unit 120 acquires the driving feature amount of the latest driver from the driving feature amount observation unit 110 (step S310). Note that the driving feature amount of the driver acquired in step S310 is a result calculated by steps S206 to S211 illustrated in FIG. 1 (each driving feature amount is attracted). Next, the driving ability determination unit 120 performs a fluctuation analysis process of the acquired driving feature amount of the driver (step S330). In the fluctuation analysis process in step S330, the driving ability determination unit 120 performs a process of calculating a Lyapunov exponent from each driving feature amount, for example. Details of the fluctuation analysis processing in step S330 will be described later with reference to FIG. 3B. Then, the driving ability determination unit 120 accumulates (logs) the transition of the processing result of the fluctuation analysis process (specifically, the calculated Lyapunov exponent) in step S330 as a log (step S350).

  FIG. 3B is a flowchart illustrating an example of a fluctuation analysis process according to the embodiment of the present invention. Note that the fluctuation analysis process illustrated in FIG. 3B explains the details of the fluctuation analysis process in step S330 of FIG. 3A as described above.

  In FIG. 3A, the driving ability determination unit 120 acquires the attractor group (attractor matrix) for forward braking (step S3311), calculates the Lyapunov exponent for forward braking (step S3312), and the past attractor group. Thus, the stability tendency of the Lyapunov exponent is analyzed (step S3313).

  Further, the driving ability determination unit 120 acquires the attractor group (attractor matrix) for reverse braking (step S3321), calculates the Lyapunov index for reverse braking (step S3322), and determines the Lyapunov from the past attractor group. The stability tendency of the index is analyzed (step S3323).

  Further, the driving ability determination unit 120 acquires an attractor group (attractor matrix) for acceleration at the time of forward travel (step S3331), calculates a Lyapunov exponent of the steering speed at the time of forward travel (step S3332), and calculates from the past attractor group. The stability tendency of the Lyapunov exponent is analyzed (step S3333).

  Further, the driving ability determination unit 120 acquires the attractor group (attractor matrix) for the reverse travel acceleration (step S3341), calculates the Lyapunov exponent for the reverse travel acceleration (step S3342), and determines the Lyapunov from the past attractor group. The stability tendency of the index is analyzed (step S3343).

  Further, the driving ability determination unit 120 acquires the attractor group (attractor matrix) of the steering speed at the time of forward travel (step S3351), calculates the Lyapunov exponent of the steering speed at the time of forward travel (step S3352), and the past attractor group. Thus, the stability tendency of the Lyapunov exponent is analyzed (step S3353).

  Further, the driving ability determination unit 120 acquires the attractor group (attractor matrix) of the steering speed during reverse travel (step S3361), calculates the Lyapunov exponent of the steering speed during reverse travel (step S3362), and the past attractor group Thus, the stability tendency of the Lyapunov exponent is analyzed (step S3363).

  Note that the specific calculation of the fluctuation analysis process according to the embodiment of the present invention can be executed, for example, as illustrated in FIG. FIG. 6 is a diagram illustrating an example of a specific calculation method of the fluctuation analysis processing according to the embodiment of the present invention. Note that the calculation method of the fluctuation analysis process is not limited to that shown in FIG. Various studies have been conducted on analysis methods of complex systems, and any analysis method established now and in the future can be applied to the present invention (for example, complex system analysis tools that have come here, {HYPERLINK See "http://www.ieice.org/cs/csbn/program/papers/04_1_miao.pdf", http: //www.ieice.org/cs/csbn/program/papers/04_1_miao.pdf} ).

  In the embodiment of the present invention, for example, the amount of depression of the brake pedal (detects the brake pedal torque, the depression angle, etc.), the amount of depression of the accelerator pedal (detects the torque of the accelerator pedal, the depression angle, etc.), the steering wheel rotation distance ( Alternatively, the steering wheel steering angle), the torque, the acceleration that can be detected by the acceleration sensor, the speed that can be detected by the speed sensor, and the like are acquired (steps S201 to S204 in FIG. 2). Such sensing data is acquired as a curve that fluctuates with respect to the time axis as shown in FIG. 6A, for example, and can be handled as a driving feature amount that represents a driving feature of the driver. .

  Here, for example, by acquiring the attractor (trajectory) of the local trend of the motion feature amount (local trend) in the minute window while shifting the range of the predetermined minute window (time width τ), the motion feature amount Are obtained (S3311, S3321, S3331, S3341, S3351, S3361, FIG. 6B in FIG. 3B), and the Lyapunov exponent is obtained from the thus obtained attractor group (attractor matrix). It is possible to calculate (S3312, S3322, S3332, S3342, S3352, S3362 in FIG. 3B, FIG. 6C). At this time, only one Lyapunov exponent is calculated, but by shifting a window (metawindow) including a plurality of predetermined minute windows (time width τ), time series data (temporal) of the Lyapunov exponent is calculated. A plurality of different Lyapunov exponents).

  Although it is possible to determine whether or not the driving ability of the driver is deteriorated from data of several Lyapunov exponents that are different in time, there are various determination methods in this case. In general, the higher the Lyapunov exponent, the more active the brain function, the lower the brain function calms down.For example, when the Lyapunov exponent simply falls below a predetermined value, the driving ability deteriorates. You may determine that you are doing. Further, by predicting future fluctuations of the Lyapunov exponent from the time-series data of the Lyapunov exponent, it may be determined that the driving ability may be deteriorated thereafter. Further, for example, by analyzing the pattern of the attractor group (attractor matrix), it may be determined that the driving ability is deteriorated when the pattern is similar to a model of night driving or random driving for the elderly. .

  FIG. 4 is a flowchart showing an example of the alerting process in the embodiment of the present invention. Note that the alerting process illustrated in FIG. 4 is obtained by the driving ability determination unit 120 and the alarm unit 140 illustrated in FIG. 1 as the analysis result of the fluctuation analysis process (the processing result of step S330 in FIG. 3A). It is executed whenever it is done.

  In FIG. 4, the driving ability determination unit 120 obtains driving tolerance level comparison data (step S <b> 401) and obtains a deterioration state of the driving ability (e.g., represented by a Lyapunov exponent based on a driving feature amount) ( Step S402). Note that the driving permissible level comparison data acquired in step S401 is driving model information (such as a driving model for a normal healthy person and a driving model for a cognitive person) stored in the permissible level information storage unit 130. Moreover, the deterioration state of the driving ability acquired in step S402 is an analysis result of the fluctuation analysis process in step S330 in FIG. 3A (a process result in step S330 in FIG. 3A), and specifically, an attractor for each driving feature amount. This is the Lyapunov exponent calculated from the group and each motion feature.

  The driving ability determination unit 120 determines whether or not the driving ability of the driver has entered the deteriorated state based on the comparison data of the allowable driving level and the deteriorated state of the driving ability (step S403). Specifically, the driving ability determination unit 120 determines whether the driving feature amount of the driver belongs to a driving model of a normal healthy person or a driving model of a cognitive person, and the driving feature amount of the driver is that of the cognitive person. When it is determined that it belongs to the driving model (when the driving feature value of the driver is greatly deviated from the driving model of the normal healthy person, or when the driving feature value of the driver is similar to the driving model of the cognitive person) Then, it is determined that the driving ability of the driver has entered a deteriorated state. In determining whether or not the driver's driving ability has entered a deteriorated state, as described above, for example, by comparing with the driving allowable level (threshold level) using the Lyapunov exponent (or considering its variation). It may be performed, and it may be determined whether the pattern is similar to a normal healthy person or a cognitively impaired person by pattern analysis of determination of the attractor group.

  The driving ability determination unit 120 may determine that the driving ability of the driver has entered a deteriorated state when the operation by the driver is rough.

  When it is determined that the driving ability of the driver has entered the deteriorated state, the driving ability determination unit 120 instructs the alarm unit 140 to call attention, and the warning unit 140 notifies the warning (step S404). . Further, the driving ability determination unit 120 accumulates (logs) items (deterioration items) that are determined that the driving ability of the driver has entered a deteriorated state (step S405). At this time, the alerting content (warning content) notified from the alarm unit 140 may be stored together with the degradation item. On the other hand, when it is not determined that the driving ability of the driver has entered the deteriorated state, the processes of steps S404 and S405 are not performed.

  Note that the timing of warning by the alarm unit 140 may be, for example, when it is determined that the driving ability of the driver has entered a deteriorated state (that is, immediately after it is determined that the driving ability of the driver has entered a deteriorated state). However, any other timing may be used. For example, when the driving capability determination unit 120 detects that the sensing information by the driver operation detection sensor 191 or the vehicle sensor 192 has approached the state in which the previous warning has been performed, the driving capability determination unit 120 displays the previous warning through the warning unit 140. You may decide to alert | report, or you may decide to alert | report the alert performed last time via the alarm part 140 just before passing the point (associating with path | route information) which performed the alert last time. . Further, if the driver has a recognition function, a warning may be recalled at the start of the operation by alerting the content of the warning that was notified during the previous driving of the driver. .

  FIG. 5 is a flowchart showing an example of a chart distribution process according to the embodiment of the present invention. Note that the medical chart distribution process shown in FIG. 5 is executed by the diagnostic checklist creation unit 150 shown in FIG. 1 every time a trip (or one day) is completed, for example.

  In FIG. 5, the diagnostic checklist creation unit 150 acquires distribution destination information (distribution destination address) (step S501) and also acquires unreported degradation items (step S502). The distribution destination information (distribution destination address) is, for example, a mail address addressed to a driver's guardian or a server address of a service provider. Further, the unreported deterioration items acquired in step S502 are items that have not yet been processed by the chart distribution process shown in FIG. 5 among the deterioration items logged in step S405 of FIG. .

  Then, the diagnostic checklist creation unit 150 creates a diagnostic checklist (chart) that lists unreported degradation items (step S503), and the distribution destination information (cartography) acquired in step S501 (step S503). Delivery to (delivery destination address) (step S504). The diagnostic checklist (the medical record) may include notifying deterioration information (warning details) notified from the alarm unit 140 together with unreported deterioration items. For example, when the driver's guardian confirms this diagnostic checklist (the medical record), the driver's guardian knows the driving ability of the driver, and instructs the driver to drive or when the driver drives. It is possible to perform device control settings.

  Next, another embodiment of the present invention will be described. According to this embodiment, the driver's driving ability deterioration state is determined in more detail by reflecting the age (age) of the driver estimated using DFA (Detrended Fluctuation Analysis) analysis. become able to.

  FIG. 7 is a block diagram showing an example of the configuration of the driving ability determination device according to another embodiment of the present invention. The driving capability determination device 100 illustrated in FIG. 7 includes a driving feature amount observation unit 110, a driving capability determination unit 120, an allowable level information storage unit 130, an alarm unit 140, a diagnostic checklist creation unit 150, and a DFA analysis unit 160. Have. In FIG. 7, each function is illustrated by a block, but each of these functions can be realized by hardware and / or (a program that can be executed by a computer).

  The driving ability determination device 100 illustrated in FIG. 7 further includes a DFA analysis unit 160 as compared with the configuration illustrated in FIG. In addition, a function is added to the driving capability determination unit 120, and further, driving model information that enables more detailed determination is stored in the tolerance level information storage unit 130. Hereinafter, functions and operations characteristic of another embodiment of the present invention will be mainly described.

The DFA analysis unit 160 performs DFA analysis based on various types of information such as driver operations and vehicle states (for example, sensing information from the driver operation detection sensor 191 and the vehicle sensor 192), and the DFA analysis result (scaling index α ) Is output. Note that DFA analysis is a technique for analyzing long-term correlation characteristics of non-stationary time-series data, and since it is a widely known technique, detailed description thereof is omitted here. New time series data created by integrating the input data is divided into boxes of length n, and the local trend is calculated by calculating an approximate straight line by the least square method in each box, and the trend is removed from the signal. A value (F (n)) obtained by averaging the variances is calculated. F (n) determined by this DFA analysis can be represented by F (n) ∝n ^α and is characterized by a scaling index α.

  The inventor of the present invention uses the scaling index obtained by the DFA analysis to estimate the age (age) of the driver, and determines the driving ability of the driver based on the estimated age (age) of the driver. I found it useful. Specifically, for example, it is possible to divide the age by α ≧ 0.8 and α <0.8 with α = 0.8 as a threshold value. Hereinafter, a case where α ≧ 0.8 is calculated is referred to as a young group, and a case where α <0.8 is calculated as an old group. Here, as an example, the age is divided into two by one threshold (for example, α = 0.8) (classified into two categories of young and old), but the value set as the threshold or The number of threshold values and the number of categories to be classified can be set as appropriate.

  The DFA analysis result by the DFA analysis unit 160 is supplied to the driving ability determination unit 120. The driving capability determination unit 120 has a function of determining the driving capability of the driver based on the driving feature amount of the driver measured by the driving feature amount observation unit 110. For example, the driving capability determination unit 120 By comparing with the driving model information stored in the level information storage unit 130, it is possible to specify whether or not the driving feature amount of the driver exceeds a certain reference or is similar to a certain reference. Is possible.

  In the present embodiment, the driving ability determination unit 120 further has a function of selecting driving model information stored in the allowable level information storage unit 130 based on the DFA analysis result of the DFA analysis unit 160. The driving capability determination unit 120, for example, based on the value of the scaling index α supplied from the DFA analysis unit 160, the value of the scaling index α from the plurality of driving model information stored in the allowable level information storage unit 130. By selecting the driving model information corresponding to, and comparing the driving feature quantity of the driver with the selected driving model information, whether the driving feature quantity of the driver exceeds a certain standard or similar to a certain standard Determine whether or not.

  In addition, in the tolerance level information storage unit 130, two driving model information for young people and old people are stored. For example, when the Lyapunov exponent value is compared with a predetermined value for determining the deterioration of driving ability, the predetermined value for young people and the predetermined value for the elderly are stored, and the deterioration determination of driving ability is determined. When the similarity of the pattern of the attractor group is determined, the attractor group for young people and the attractor group for elderly people are stored. As shown in the above-described example, when the scaling index α supplied from the DFA analysis unit 160 is 0.8 or more, the driving ability determination unit 120 determines the predetermined value for the young group or the young group. By selecting an attractor group as driving model information and comparing it with the selected driving model information, it is determined whether the driving feature of the driver exceeds a certain standard or is similar to a certain standard Then, the deterioration state of the driving ability is determined. Similarly, when the scaling index α supplied from the DFA analysis unit 160 is less than 0.8, the driving ability determination unit 120 selects a predetermined value for the elderly group or an attractor group for the elderly group as the driving model information. Then, by comparing with the selected driving model information, it is determined whether the driving feature quantity of the driver exceeds a certain standard or whether it is similar to a certain standard. judge. Regarding the predetermined value to be compared with the Lyapunov exponent in the determination of the deterioration of driving ability, it is desirable that the predetermined value for the younger group is set higher than the predetermined value for the older group.

  As described above, according to the present embodiment, the age (age) of the driver is estimated based on the DFA analysis result by the DFA analysis unit 160, and the driving model information corresponding to the estimated age (age) of the driver is obtained. It is possible to select and determine the deterioration state of the driving ability of the driver based on the selected driving model information.

  The present invention has an effect that the driving ability of the driver can be determined with higher accuracy, and can be applied to a driving ability determination technique for determining the driving ability of the driver.

DESCRIPTION OF SYMBOLS 100 Driving capability determination apparatus 110 Driving feature amount observation unit 120 Driving capability determination unit 130 Allowable level information storage unit 140 Alarm unit 150 Diagnostic checklist creation unit 191 Driver operation detection sensor 192 Vehicle sensor 193 Speaker / monitor 194 Communication unit

Claims (18)

A driving capability determination device that determines the driving capability of a driver who drives a vehicle,
Based on sensing information supplied from a driver operation detection sensor that detects a driving operation amount of the driver and a vehicle sensor that detects a driving state of the vehicle, a driving feature amount indicating a driving characteristic of the driver is calculated. A driving feature observation unit;
A driving capability determination unit that determines the driving capability of the driver from the driving feature amount of the driver calculated by the driving feature amount observation unit;
Have
When the driving ability determination unit calculates a Lyapunov index indicating divergence from the driving feature quantity of the driver using a calculation technology of a chaotic dynamical system, and the calculated Lyapunov index is lower than the normal index value The driving ability determination device configured to determine that the driving ability of the driver is deteriorated.   The said driving capability determination part observes the time-sequential rise and fall of the said Lyapunov exponent, and when it exists in the stable tendency, it is comprised so that the timing at which the driving capability of the said driver is determined to be deteriorated is estimated. Driving ability judgment device.   The driving capability determination device according to claim 1, further comprising: an alarm unit that notifies the driver of a warning warning when the driving capability determination unit determines that the driving capability of the driver is deteriorated.   The driving capability according to claim 3, wherein the alarm unit is configured to notify the driver of a warning warning immediately after the driving capability determination unit determines that the driving capability of the driver is deteriorated. Judgment device.   When it is determined by the driving capability determination unit that the driving capability of the driver is deteriorated, when sensing information at that time is stored and similar sensing information is detected next time, when the same point is passed next time The driving capability determination device according to claim 3, wherein the alarm unit is configured to notify the driver of a warning to alert at any timing when starting the next driving.   A history information transmission unit that accumulates history information when the driving capability determination unit determines that the driving capability of the driver is deteriorated, and transmits the history information to a predetermined distribution destination via a communication unit. The driving ability determination device according to claim 1, further comprising:   History information when the driving capability determination unit determines that the driving capability of the driver is deteriorated is accumulated, and the history information and the driving capability of the driver are stored in a predetermined distribution destination via a communication unit. The driving ability determination device according to claim 3, further comprising a history information transmission unit configured to transmit a content of a warning performed by the warning unit when it is determined that the deterioration has occurred. The driving operation amount, depression amount of the accelerator pedal by the driver, stepping amount of the brake pedal by the driver, the driving behavior determining apparatus as set forth in claim 1 Ru der either steering amount of the steering wheel by the driver. Based on the sensing information, a trend removal fluctuation analysis unit that calculates a scaling index by analysis using a trend removal fluctuation analysis method,
The driving ability determination unit selects a normal exponent value corresponding to the scaling exponent calculated by the trend removal fluctuation analysis unit, and uses the selected normal exponent value to determine the driving capability of the driver. The driving ability determination device according to claim 1, which is configured to determine. A driving capability determination method executed by a driving capability determination device that determines the driving capability of a driver who drives a vehicle,
Based on sensing information supplied from a driver operation detection sensor that detects a driving operation amount of the driver and a vehicle sensor that detects a driving state of the vehicle, a driving feature amount indicating a driving characteristic of the driver is calculated. Driving feature observation step;
A driving ability determination step for determining the driving ability of the driver from the driving feature quantity of the driver calculated in the driving feature quantity observation step,
Have
In the driving ability determination step, when the Lyapunov index indicating the divergence is calculated from the driving feature amount of the driver using a calculation technique of a chaotic dynamical system, and the calculated Lyapunov index is lower than the normal index value The driving ability determination method for determining that the driving ability of the driver is deteriorated.   11. The driving capability determination method according to claim 10, wherein, in the driving capability determination step, a time-series increase / decrease in the Lyapunov exponent is observed, and when there is a stable tendency, a timing at which the driving capability of the driver is determined to be deteriorated is predicted. .   The driving capability determination method according to claim 10, further comprising: an alarm step of notifying the driver of a warning for warning when it is determined that the driving capability of the driver is deteriorated in the driving capability determination step.   The driving ability determination method according to claim 12, wherein immediately after it is determined that the driving ability of the driver is deteriorated in the driving ability determination step, the warning step notifies the driver of a warning to call attention.   When it is determined in the driving capability determination step that the driving capability of the driver is deteriorated, when sensing information at that time is stored and similar sensing information is detected next time, when the same point is passed next time The driving ability determination method according to claim 12, wherein a warning for warning is notified to the driver in the warning step at any timing when starting the next driving.   History information transmission that accumulates history information when it is determined in the driving capability determination step that the driving capability of the driver is deteriorated, and transmits the history information to a predetermined distribution destination via a predetermined communication unit. The driving ability determination method according to claim 10, further comprising a step.   History information when the driving capability of the driver is determined to be deteriorated in the driving capability determination step is accumulated, and the history information and the driving of the driver are stored in a predetermined distribution destination via a predetermined communication unit. The driving capability determination method according to claim 12, further comprising a history information transmission step of transmitting the content of the warning performed in the alarm step when it is determined that the capability is deteriorated. The driving operation amount, depression amount of the accelerator pedal by the driver, stepping amount of the brake pedal by the driver, the driving behavior determination method according to claim 10 Ru der either steering amount of the steering wheel by the driver. Based on the sensing information, a trend removal fluctuation analysis unit that calculates a scaling index by analysis using a trend removal fluctuation analysis method,
The driving ability determination unit selects a normal exponent value corresponding to the scaling exponent calculated by the trend removal fluctuation analysis unit, and uses the selected normal exponent value to determine the driving capability of the driver. The driving ability determination method according to claim 10 for determination.

Images