JP2004329956A - Driver monitoring device and safety device using the same - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To monitor the mental and physical state such as the fatigue degree, vigilance or the degree of skill of a driver. <P>SOLUTION: This driver monitoring device is provided with a monitoring means 8 for monitoring the state of driving a driven object by the driver 1; a biological signal detecting means 3 for detecting biological signals of the driver 1; a computing means 4 for quantifying information included in the biological signals detected by the biological signal detecting means 3; and a determining means 5 for determining the driver's degree of skill from driving information from the monitoring means 8 and the change of biological signal information from the start of driving from the computing means 4. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

  The present invention relates to a technique for monitoring a mental and physical condition such as a degree of fatigue, arousal, or skill of a driver.

  Monitoring a driver in a vehicle is a very important technology in terms of preventing a traffic accident caused by a decrease in concentration due to falling asleep or fatigue. As a driver monitoring method, various biological information detection technologies have been devised so far. As a detection target when directly using a biological signal, a detection target related to circulatory system information such as electrocardiogram information and a pulse (for example, see Patent Document 1), and a detection target related to eye movement such as blinking and opening / closing of an eyelid (for example, Reference 2), related to the steering state of the steering (for example, see Patent Document 3), and related to the driving posture (for example, see Patent Document 4). Other examples include a change in inter-vehicle distance with a vehicle in front (for example, see Patent Literature 5) and an estimation based on the elapsed time from the start of driving (for example, see Patent Literature 6). Among them, circulatory system information such as electrocardiographic information will be effective for more accurately estimating the mental and physical state of the driver as an index reflecting the function of the autonomic nerve.

  For example, Patent Literature 1 discloses a technique for detecting an electrocardiogram from a steering wheel. In FIG. 4, a pair of electrodes 21a and 21b are arranged on the steering wheel 20 in a state where they are separated from each other. The signal of the electrode 21 is amplified by an amplifier 22, converted into a digital signal by an A / D converter 23, and then sent to a CPU 24. The CPU 24 is connected to a ROM 25, a RAM 26, and an interface 28 for an output device 27 via a bus.

  In the above configuration, when the driver operates the steering wheel 20, the driver comes into contact with the electrodes 21a and 21b, so that an electrocardiographic signal is detected. The electrocardiographic signal is amplified to an appropriate level by the amplifier 22. Subsequently, the data is A / D converted by the A / D converter 23 and sent to the CPU 24. The transmitted data is temporarily held on the RAM 26. The CPU 24 performs processing according to a program stored in the ROM 25. That is, the interval of the R wave which is the wave having the highest heak than the electrocardiogram signal is obtained, and the moving average and the variation are calculated. A judgment criterion is provided because the arousal level has a correlation with these values, and when a drowsiness is detected based on the criterion, a warning is given to the driver from the output device.

  In detecting dozing, a pulse wave may be used instead of an electrocardiogram (for example, see Patent Document 7). In addition, as a processing method of the calculation part, there is a method of estimating the arousal degree from power from a specific frequency band by performing frequency analysis by Fourier transform in addition to the average and the variation (for example, see Patent Document 8).

On the other hand, non-linear processing methods using chaos theory for data processing at RR intervals have recently attracted attention. For example, there is disclosed a technique for diagnosing a health condition based on whether or not a pulse wave and a heartbeat signal satisfy a condition that they are chaos. This is based on the knowledge that pulse waves and heartbeat signals obtained from healthy living bodies have chaos. In order for certain data to be chaotic, conditions such as having a non-integer fractal dimension and a positive maximum Lyapunov number are generally used (for example, see Patent Document 9).
JP-A-4-183439 Japanese Utility Model Publication No. 1-125003 JP-B-62-34214 JP-A-3-157598 JP-A-5-162562 Japanese Utility Model Publication No. 63-27232 JP-A-2-6231 JP-A-1-131648 JP-A-4-208136

  There are several problems in detecting the dozing in the conventional in-vehicle driver monitoring technology.

  First, regarding the method of detecting the movement of the eyes, when the driver wears sunglasses or the like, the eyelids may not be detected in some cases. To avoid this, the driver must wear special glasses.

  In addition, what is estimated from the steering state can be said to be effective during high-speed driving. However, during a traffic jam, it is difficult to detect dozing because there are times when steering is hardly performed. Actually, during these times, the degree of alertness decreases, and small contact accidents and the like tend to occur.

  In the method of checking the posture during driving, it is presumed that the state is already extremely dangerous when a posture change related to dozing occurs. For the purpose of preventing accidents, it is necessary to detect the condition before a clear symptom such as a change in posture occurs.

  From these issues, it can be said that a method using an index such as electrocardiographic information or a pulse is a method suitable for estimating a so-called psychosomatic state including an awake state before the driver falls asleep. However, this method also has some problems in the related art.

  First, it is difficult to cope with individual differences in a method in which a threshold value is provided for an integrated value of power based on heart rate or frequency analysis to make a determination. Although the heart rate does fluctuate depending on the arousal level, the range of fluctuation may be quite small depending on the person, and a correct estimation may not be obtained. Similarly, the same problem arises when a target frequency band is fixed when integrating power.

  Second, the circadian rhythm is not taken into account. A human has a circadian rhythm of about 24 hours, and the interval between R waves of the heartbeat (RR interval) fluctuates throughout the day under the control of this rhythm. Therefore, although the baseline of the heart rate variability differs depending on the driving time zone, the prior art does not recognize a determination algorithm that takes this change into account.

  Third, the skill level of the driver is not considered. Beginners can easily expect that heart rate variability is greatly affected by external factors such as road conditions and running conditions of other vehicles, as compared to skilled drivers. Therefore, when monitoring heart rate variability, it is necessary to take into account the skill level of the driver, but such considerations are not found in the prior art.

  An object of the present invention is to solve the above-described problem and to estimate the skill level of a driver by using information related to a driving operation, and to determine a mental and physical state according to the estimated skill level.

  In order to achieve the above object, the present invention provides a monitoring means for monitoring a driving state of a driving object by a driver, a biological signal detecting means for detecting a biological signal of the driver, and a living body detected by the biological signal detecting means. A computing means for quantifying the information contained in the signal, and a judging means for judging the skill of the driver from the driving information by the monitoring means and a change in the biological signal information from the start of driving by the computing means.

  In this way, the monitoring means determines and monitors what kind of driving the driver is performing, for example, the degree of skill in how to accelerate, how to speed, how to turn the steering wheel, and the like.

  The driver monitor device of the present invention can determine the driver's skill level by monitoring the driving operation status and using the result together with the driver's biological signal index.

  According to a first aspect of the present invention, there is provided a monitoring means for monitoring a driving state of a driving object by a driver, a biological signal detecting means for detecting a biological signal of the driver, and information included in the biological signal detected by the biological signal detecting means. And a determining means for determining the skill level of the driver based on the driving information from the monitoring means and a change in the biological signal information from the start of driving by the calculating means.

  Thereby, the monitoring means monitors what kind of driving the driver is performing, for example, how to accelerate, how fast, how to turn the steering wheel, and the like. The determination means can determine the skill level of the driver by capturing the change in the biological signal information together with the driving method from the start of driving.

  A second invention is characterized in that the biological signal detecting means detects a vibration on the surface of the living body accompanying the pulsation of the heart.

  Thus, the mental and physical condition of the driver and the skill level are determined based on the cardiac diagram detected by the biological signal detecting means.

  The third invention is configured to include a notifying unit that notifies the driver of information on the mental and physical condition of the driver from the driver monitoring device.

  Thus, the information about the mental and physical condition of the driver from the driver monitoring device is fed back to the driver by the notifying means, so that the driver can be aware of his / her state and perform safe driving.

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

  FIG. 1 is a block diagram showing the configuration of the first embodiment of the present invention. The driver 1 is sitting on the driver's seat 2. A biological signal detecting means 3 is provided inside the driver's seat 2. The output of the biological signal detecting means 3 is connected to the calculating means 4, and further connected from the calculating means 4 to the determining means 5.

  In the above configuration, the biological signal detecting means 3 detects the cardiogram of the driver 1 from the buttocks of the driver 1. The cardiogram is a vibration of the body surface accompanying the pulsation of the heart, and can be easily sensed by using a high-sensitivity pressure sensor such as polyvinylidene fluoride processed in a thin film. By obtaining the interval between peaks from the obtained cardiogram, it is possible to obtain sequence data substantially corresponding to the heartbeat.

  It is known that when this data is complemented with a spline curve or the like and treated as time-series data and subjected to frequency analysis, a 1 / f-like fluctuation is recognized. This suggests that the heartbeat interval data includes a non-linear component. The calculating means 4 obtains an index based on the chaos theory for the data detected by the biological signal detecting means 3, and quantifies the fluctuation of the data. Examples of the chaos index include a correlation dimension (fractal dimension) and a Lyapunov exponent. Here, the Lyapunov exponent will be described as an example.

  In the calculating means 2, the heartbeat interval data is divided into units of 5 minutes. A Lyapunov exponent is obtained for the cut-out heartbeat interval series in units of 5 minutes. The five minutes here are not absolute.

The procedure for obtaining the Lyapunov exponent is shown below. The Lyapunov exponent is an index indicating how far adjacent points on an attractor are separated over time, and indicates how difficult it is to predict the underlying data in the future. This is closely related to the initial value dependence, which is one of the characteristics of chaos. An attractor also represents an orbit of a system in an n-dimensional space. For one-dimensional data series such as heartbeat intervals,
X (t1), X (t2), ..., X (ti), ...
In order to embed the data of N points in the n-dimensional phase space, the following data set is prepared.

{X (t1), X (t1 + τ), ..., X (t1 + (n-1) τ)}
{X (t2), X (t2 + τ), ..., X (t2 + (n-1) τ)}
・ ・ ・ ・ ・
{X (ti), X (ti + τ), ..., X (ti + (n-1) τ)}
・ ・ ・ ・ ・
{X (tN), X (tN + τ), ..., X (tN + (n-1) τ)}
Where i-th point is
Xin = {X (ti), X (ti + τ), ..., X (ti + (n-1) τ)}
Can be expressed as

  With reference to a certain point X (0) on the attractor obtained in this way, the next point X (1) on the trajectory is orthogonal to the vector X (0) X (1) and is equal to the unit distance. The distant point is defined as Y0 (0). The points when τ time has elapsed for X (0) and Y0 (0) are defined as X (τ) and Y0 (τ). The distance between X (0) and Y0 (0) is d0 (0), and the distance between X (τ) and Y0 (τ) is d0 (τ). At this time, the enlargement (reduction) rate of the distance between the two points after elapse of τ time can be obtained by dividing d0 (τ) by d0 (0).

  Next, a point separated by a unit distance in the same direction as X (τ) and Y0 (τ) is defined as Y1 (0). Points at which τ time has elapsed for X (τ) and Y1 (0) are defined as X (2τ) and Y1 (τ). The distance between X (τ) and Y1 (0) is d1 (0), and the distance between X (2τ) and Y1 (τ) is d1 (τ). At this time, the enlargement (reduction) rate of the distance between the two points after elapse of τ time can be obtained by dividing d1 (τ) by d1 (0).

  This step is repeated, and the average of the enlargement (reduction) rate of the distance obtained in each step is the Lyapunov exponent. This can be generalized as follows.

  If the embedding dimension is, for example, three, a total of three Lyapunov exponents are obtained for each dimension, and the largest one is particularly called the maximum Lyapunov exponent.

  FIG. 2 shows the change of the maximum Lyapunov exponent in units of 15 minutes for the heartbeat interval of a healthy man. The horizontal axis is the elapsed time and the unit is minute. It can be seen that the rhythm that the Lyapunov index decreases with the start of driving and rises again after taking a break is repeated. The drop is remarkable immediately after the start of operation and at the time of the first traffic jam. The heart rate is similarly plotted. There is a negative correlation between Lyapunov index and heart rate. However, it can be seen that there is a large difference in resolution between the two indices with respect to the rate of change. For example, when driving is resumed after the second break, the maximum Lyapunov number is greatly reduced, but the heart rate is only slightly increased (the units differ between the two indices). However, since the scale of each axis is taken at the same ratio, there is no problem in comparing the visual form as it is). From the above, the superiority of the present invention using the chaos index over the prior art will be clear.

  Next, the determination means 5 determines the mental and physical state of the driver 1 using the chaos index obtained by the calculation means 4. The determination of the physical and mental state here means the degree of the influence of stress caused by fatigue due to long-time driving or traffic congestion. Heartbeat fluctuations are dominated by the autonomic nervous system, which is subject to dual control of the sympathetic and parasympathetic nervous systems. When the sympathetic nervous system is activated, the heart rate rises and the living body becomes suitable for activity. When the parasympathetic nervous system is activated, the heart rate falls. In the living body, each nervous system does not act independently, but acts with mutual afferent. This antagonistic dominance with the feedback function causes the heartbeat to behave chaotically. Therefore, when either one of the nervous systems protrudes, the chaos index becomes smaller. Such a situation is caused by a stress load caused by driving.

  The judging means 5 obtains a differential value of the change of the chaos index and uses this as a criterion for the judgment. That is, when the Lyapunov exponent has decreased (the differential value is negative) for a certain period of time or more, it is determined that the driver is under a stress load to such an extent that a break is required. The time at this time may be, for example, about 15 minutes, but may be set to an arbitrary time according to the driver.

  Various criteria can be used as a criterion other than the time during which the negative differential value continues. For example, a comparison with a chaos index at the start of operation, an absolute value of a differential value, or the like may be considered as a reference. In the present invention, there is no restriction on these criteria.

  As described above, according to the first embodiment, since the chaos index is used to determine the state of the driver, there is an effect that the determination can be performed with higher accuracy.

  Next, a second embodiment of the present invention will be described. In FIG. 1, a clock unit 6 outputs a current time. The time information is configured to be transmitted to the determination means 5. In addition, the storage unit 7 stores criteria for determining the mental and physical state of the driver at each time. The determination unit 5 is configured to be able to access the storage unit 7.

  In the above configuration, the judgment means 5 uses the time information from the time measurement means 6 in addition to the chaos index output from the calculation means 4. The living body has a biological rhythm called circadian variation, and shows a characteristic change at each time. FIG. 3 shows the maximum Lyapunov exponent and the daily change in heart rate. The horizontal axis represents time. At this time, the subject wakes up at around 7:20 am, but the Lyapunov exponent is significantly reduced before and after that. There are two peaks in the morning and afternoon. It is said that the mountains seen in the afternoon may disappear with aging. Note that the heart rate also has a negative correlation with the Lyapunov exponent here, but it can be seen that the ratio of the fluctuation range is considerably smaller than that of the Lyapunov exponent.

  By taking into account that the baseline of the chaos index fluctuates greatly during one day, more accurate determination can be made. In other words, in the time zone immediately after waking up, the baseline (the time during which the negative differential value continues) for determining that a break is necessary because the baseline originally tends to drop sharply is slightly relaxed, and the evening is relatively stable. In the time zone, it is necessary to tighten the criteria for judgment. The storage means 7 stores references corresponding to each time zone.

  In addition, it is expected that the life rhythm will vary depending on the driver, such as a night shift driver, but in such a case, an input means for inputting the wake-up time is provided, and the timekeeping means is replaced with the elapsed time from the wake-up time. Information may be used.

  As described above, according to the second embodiment, since the mental and physical state of the driver is determined based on the time information, there is an effect that the determination can be made in consideration of the biological rhythm.

  Next, a third embodiment of the present invention will be described. In FIG. 1, a monitoring means 8 monitors the operation state of the steering wheel 9 and the accelerator 10 by the driver 1. The monitored result is configured to be sent to the determination means 5.

  In the above configuration, the monitoring means 8 has a role relating to the way the driver 1 drives. For example, you can tell how much acceleration you are accelerating or how fast you have turned a curve by monitoring steering and accelerator operations.

  The judging means 5 judges the skill level of the driver from the information on the driving content from the monitoring means 8 and the result of indexing the biological signal from the calculating means 4. For example, if the driver is constantly driving at a low speed and sees an increase in heart rate, the driver is expected to be quite nervous and probably a beginner. Conversely, a driver who drives with a very high driving technique and hardly changes the index of the vital sign is judged to be a skilled person. For the determination of the driving state at the time of the determination, a standardized threshold value may be obtained using many drivers, and the obtained threshold value may be employed.

  As described above, according to the third embodiment, the driver's skill level can be determined by monitoring the driving content and detecting the biological signal in combination.

  Next, a fourth embodiment of the present invention will be described. In FIG. 1, the signal from the driver monitor device 11 is configured to be notified to the driver 1 by the notification means 12.

  In the above configuration, the driver monitoring device 11 outputs a determination result indicating the mental and physical state of the driver, for example, a result of classifying the state into five stages based on the chaos index, and a signal indicating that a break is necessary. You. The notification means 12 visually or audibly transmits the signal output by the driver monitoring device 11 to the driver. For example, when it is determined that a break is necessary, the driver is notified by a warning sound.

  As described above, according to the fourth embodiment, it is possible to feed back information about the mental and physical condition of the driver to the driver, so that there is an effect that safe driving can be supported.

  Next, a fifth embodiment of the present invention will be described. In FIG. 1, the control means 13 is connected to the driver monitor device 11 so as to adjust the hardness of the suspension.

  In the above configuration, when the information on the driver's skill level is output from the driver monitor device 11, the control unit 13 adjusts the suspension 14 so that the suspension 14 has a hardness corresponding to the driver's skill level. For example, when the driver is determined to be a beginner, the suspension 14 is set to be soft, and when it is determined to be an expert, the suspension 14 is adjusted to be hard.

  Of course, the vehicle settings are not limited to suspension. In the present invention, all parameters to be changed according to the driver's skill level are to be controlled.

  As described above, according to the fifth embodiment, since the mental and physical condition and the skill level of the driver are transmitted to the control means 13, there is an effect that the vehicle can be set optimally for the driver.

  Next, a sixth embodiment of the present invention will be described. In FIG. 1, the control means 13 is connected to the driver monitor device 11 so as to be able to turn on a hazard lamp 15 which is a device of an automobile as an object to be driven.

  In the above configuration, when it is determined from the driver monitoring device 11 that the driver's fatigue is accumulated in relation to the mental and physical condition of the driver, the control means 13 turns on the hazard lamp 15 and turns on the following vehicle. Inform the driver that the vehicle will decelerate or stop after a while. Of course, not only the hazard lamp 15 but also the brake mechanism and the engine may be controlled to forcibly decelerate. By performing such control, it is possible to prevent the occurrence of an accident due to a decrease in the driver's attention.

  As described above, according to the sixth embodiment, since the mental and physical condition and the skill level of the driver are transmitted to the control means 13, there is an effect that the vehicle can be set optimally for the driver.

Configuration diagram of an embodiment of the present invention Graph showing change in chaos index during driving Graph showing daily fluctuation of chaos index Configuration diagram of conventional technology

Explanation of reference numerals

Reference Signs List 3 biological signal detecting means 4 calculating means 5 determining means 6 clocking means 7 storage means 8 monitoring means 12 notification means 13 control means 15 equipment

Claims (3)

Monitoring means for monitoring the driving state of the driving object by the driver, biological signal detecting means for detecting a biological signal of the driver, and calculating means for quantifying information contained in the biological signal detected by the biological signal detecting means And a determining means for determining the skill level of the driver from a change in the biological signal information from the start of the driving by the calculating means and the driving information by the monitoring means. 2. The driver monitoring apparatus according to claim 1, wherein the biological signal detecting means detects a vibration of a living body surface accompanying a pulsation of the heart. A safety device comprising an informing means for informing the driver of information on the mental and physical condition of the driver from the driver monitoring device according to claim 1 or 2.

Images